Training in progress, step 310000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db51f55bf1a16f0aa27746b583a094e054e9a9dfc4763b285a75a463ec28ba4e
+oid sha256:c9b24e15aaa4e24fe327e8a8cce89f20e5c9f2d77bf1d531b089aac8a736f1ed
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf63bd5c42184ed6348a862f43229e825f00ce4dfcc6c106b3192d2a71460f8
+oid sha256:4758b3d99119d3a14a23fd0aec29ffaa12fdc4ff244891bef5326c956e766005
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
+oid sha256:7d41d8b5030d0b0c384b52902b63df577c91ad4b52f45f72ce22b77b0fec1a92
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7914b9f1e3709b1198ec189eb9bb9105cd6b88dedbcbbdd4128934a703cf33e3
+oid sha256:9b8c10dab6d3ee824fc8fe4628d3bf3ceea806ce0d2fbe513f32af4d508ab89e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.691648822269808,
-  "global_step": 300000,
+  "epoch": 6.9147037830121345,
+  "global_step": 310000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6006,11 +6006,211 @@
       "eval_samples_per_second": 1167.773,
       "eval_steps_per_second": 18.302,
       "step": 300000
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 0.00011893996636109606,
+      "loss": 0.2728,
+      "step": 300500
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 0.00011847572270435852,
+      "loss": 0.2726,
+      "step": 301000
+    },
+    {
+      "epoch": 6.71,
+      "eval_loss": 0.2552023231983185,
+      "eval_runtime": 5.3426,
+      "eval_samples_per_second": 429.941,
+      "eval_steps_per_second": 6.738,
+      "step": 301000
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 0.00011801187847126579,
+      "loss": 0.2696,
+      "step": 301500
+    },
+    {
+      "epoch": 6.74,
+      "learning_rate": 0.00011754843873434411,
+      "loss": 0.2691,
+      "step": 302000
+    },
+    {
+      "epoch": 6.74,
+      "eval_loss": 0.25297147035598755,
+      "eval_runtime": 1.9927,
+      "eval_samples_per_second": 1152.684,
+      "eval_steps_per_second": 18.066,
+      "step": 302000
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 0.00011708540856169612,
+      "loss": 0.2702,
+      "step": 302500
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 0.00011662279301694567,
+      "loss": 0.2698,
+      "step": 303000
+    },
+    {
+      "epoch": 6.76,
+      "eval_loss": 0.253802090883255,
+      "eval_runtime": 1.9502,
+      "eval_samples_per_second": 1177.813,
+      "eval_steps_per_second": 18.459,
+      "step": 303000
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 0.0001161605971591822,
+      "loss": 0.2697,
+      "step": 303500
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 0.00011569882604290559,
+      "loss": 0.2706,
+      "step": 304000
+    },
+    {
+      "epoch": 6.78,
+      "eval_loss": 0.252233624458313,
+      "eval_runtime": 2.0068,
+      "eval_samples_per_second": 1144.633,
+      "eval_steps_per_second": 17.939,
+      "step": 304000
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 0.00011523748471797075,
+      "loss": 0.2704,
+      "step": 304500
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 0.00011477657822953255,
+      "loss": 0.2705,
+      "step": 305000
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 0.25286948680877686,
+      "eval_runtime": 2.0237,
+      "eval_samples_per_second": 1135.028,
+      "eval_steps_per_second": 17.789,
+      "step": 305000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 0.00011431611161799043,
+      "loss": 0.2732,
+      "step": 305500
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 0.0001138560899189335,
+      "loss": 0.2707,
+      "step": 306000
+    },
+    {
+      "epoch": 6.83,
+      "eval_loss": 0.2536955773830414,
+      "eval_runtime": 2.005,
+      "eval_samples_per_second": 1145.645,
+      "eval_steps_per_second": 17.955,
+      "step": 306000
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 0.00011339651816308543,
+      "loss": 0.271,
+      "step": 306500
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 0.00011293740137624925,
+      "loss": 0.2713,
+      "step": 307000
+    },
+    {
+      "epoch": 6.85,
+      "eval_loss": 0.25167515873908997,
+      "eval_runtime": 1.9694,
+      "eval_samples_per_second": 1166.352,
+      "eval_steps_per_second": 18.28,
+      "step": 307000
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 0.00011247874457925261,
+      "loss": 0.2716,
+      "step": 307500
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 0.0001120205527878927,
+      "loss": 0.2696,
+      "step": 308000
+    },
+    {
+      "epoch": 6.87,
+      "eval_loss": 0.25594934821128845,
+      "eval_runtime": 1.9543,
+      "eval_samples_per_second": 1175.377,
+      "eval_steps_per_second": 18.421,
+      "step": 308000
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 0.00011156283101288165,
+      "loss": 0.2701,
+      "step": 308500
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 0.00011110558425979132,
+      "loss": 0.2702,
+      "step": 309000
+    },
+    {
+      "epoch": 6.89,
+      "eval_loss": 0.2543644607067108,
+      "eval_runtime": 1.9412,
+      "eval_samples_per_second": 1183.27,
+      "eval_steps_per_second": 18.545,
+      "step": 309000
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 0.00011064881752899906,
+      "loss": 0.2698,
+      "step": 309500
+    },
+    {
+      "epoch": 6.91,
+      "learning_rate": 0.00011019253581563262,
+      "loss": 0.2695,
+      "step": 310000
+    },
+    {
+      "epoch": 6.91,
+      "eval_loss": 0.2494657188653946,
+      "eval_runtime": 2.0069,
+      "eval_samples_per_second": 1144.556,
+      "eval_steps_per_second": 17.938,
+      "step": 310000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 9.584443437666508e+21,
+  "total_flos": 9.903930576441008e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf63bd5c42184ed6348a862f43229e825f00ce4dfcc6c106b3192d2a71460f8
+oid sha256:4758b3d99119d3a14a23fd0aec29ffaa12fdc4ff244891bef5326c956e766005
 size 102501541