Training in progress, step 20000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ac9ebeb8dac5b552a8ccdae781ab5530a4491505556af0c9010fb8f32e60c3
+oid sha256:173452dfa9502e73bf5ce8ef586e58da95df2151c37d5e318b90455200ecfb7b
 size 3141646744

runs/Apr25_13-44-28_ip-26-0-167-177/events.out.tfevents.1714052716.ip-26-0-167-177.156194.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f7f1750e79c17ed233ddec97d5a18467e60f4657fc9fc54778c0d6a0117e50
-size 89835
+oid sha256:4ffc80484fd2bc093371ccee6de7cb1b267e4812f00da1bd11c1ed67ecb5ec20
+size 175722

wandb/run-20240425_134518-etajcxpg/files/config.yaml

@@ -32,6 +32,7 @@ _wandb:
       3:
       - 7
       - 23
+      - 62
       4: 3.11.9
       5: 0.16.6
       6: 4.40.1

wandb/run-20240425_134518-etajcxpg/files/output.log

@@ -9480,3 +9480,9346 @@
 
 
 
+
+
+
+
+
+
+
+
+
+ 50%|█████     | 10050/20000 [5:03:05<4:55:14,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 50%|█████     | 10075/20000 [5:03:49<4:54:47,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 50%|█████     | 10100/20000 [5:04:34<4:54:17,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 51%|█████     | 10125/20000 [5:05:19<4:53:32,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 51%|█████     | 10149/20000 [5:06:01<4:52:21,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 51%|█████     | 10175/20000 [5:06:48<4:52:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 51%|█████     | 10200/20000 [5:07:32<4:51:54,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 51%|█████     | 10225/20000 [5:08:17<4:51:23,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 51%|█████▏    | 10250/20000 [5:09:01<4:50:03,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 51%|█████▏    | 10275/20000 [5:09:46<4:50:07,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10300/20000 [5:10:31<4:48:49,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10325/20000 [5:11:15<4:49:35,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10350/20000 [5:12:00<4:46:21,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10375/20000 [5:12:45<4:45:45,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10399/20000 [5:13:27<4:44:59,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10425/20000 [5:14:14<4:44:36,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10450/20000 [5:14:59<4:43:39,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▏    | 10474/20000 [5:15:41<4:44:47,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 52%|█████▎    | 10500/20000 [5:16:28<4:42:54,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 53%|█████▎    | 10525/20000 [5:17:12<4:41:46,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 53%|█████▎    | 10550/20000 [5:17:57<4:41:40,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 53%|█████▎    | 10575/20000 [5:18:42<4:42:00,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 53%|█████▎    | 10600/20000 [5:19:26<4:38:57,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 53%|█████▎    | 10625/20000 [5:20:11<4:38:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 53%|█████▎    | 10650/20000 [5:20:56<4:38:21,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 53%|█████▎    | 10675/20000 [5:21:40<4:37:35,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▎    | 10700/20000 [5:22:25<4:37:18,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▎    | 10725/20000 [5:23:09<4:35:39,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▍    | 10750/20000 [5:23:54<4:34:28,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▍    | 10775/20000 [5:24:39<4:33:30,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▍    | 10799/20000 [5:25:22<4:33:48,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▍    | 10825/20000 [5:26:08<4:31:46,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▍    | 10850/20000 [5:26:53<4:32:01,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 54%|█████▍    | 10875/20000 [5:27:37<4:32:20,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▍    | 10900/20000 [5:28:22<4:29:34,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▍    | 10925/20000 [5:29:06<4:29:13,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▍    | 10950/20000 [5:29:51<4:29:22,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▍    | 10975/20000 [5:30:35<4:28:33,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▌    | 11000/20000 [5:31:20<4:28:05,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▌    | 11025/20000 [5:32:04<4:26:43,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▌    | 11050/20000 [5:32:49<4:26:15,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 55%|█████▌    | 11075/20000 [5:33:34<4:25:13,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▌    | 11100/20000 [5:34:18<4:24:44,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▌    | 11125/20000 [5:35:03<4:23:25,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▌    | 11150/20000 [5:35:47<4:23:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▌    | 11175/20000 [5:36:32<4:22:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▌    | 11200/20000 [5:37:17<4:21:43,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▌    | 11225/20000 [5:38:01<4:20:32,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▋    | 11250/20000 [5:38:46<4:19:28,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▋    | 11275/20000 [5:39:31<4:19:09,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 56%|█████▋    | 11300/20000 [5:40:15<4:19:04,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▋    | 11324/20000 [5:40:58<4:17:35,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▋    | 11350/20000 [5:41:44<4:16:17,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▋    | 11375/20000 [5:42:29<4:16:23,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▋    | 11400/20000 [5:43:13<4:15:31,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▋    | 11425/20000 [5:43:58<4:15:00,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▋    | 11450/20000 [5:44:43<4:14:22,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▋    | 11475/20000 [5:45:27<4:14:23,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 57%|█████▊    | 11500/20000 [5:46:12<4:13:34,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11525/20000 [5:46:56<4:11:57,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11550/20000 [5:47:41<4:10:10,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11575/20000 [5:48:25<4:11:06,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11600/20000 [5:49:10<4:09:24,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11624/20000 [5:49:53<4:08:59,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11649/20000 [5:50:37<4:08:10,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11674/20000 [5:51:22<4:07:57,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 58%|█████▊    | 11699/20000 [5:52:07<4:07:22,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▊    | 11724/20000 [5:52:51<4:05:09,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▊    | 11749/20000 [5:53:36<4:04:41,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▉    | 11774/20000 [5:54:21<4:04:12,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▉    | 11799/20000 [5:55:05<4:03:48,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▉    | 11823/20000 [5:55:48<4:02:46,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▉    | 11849/20000 [5:56:35<4:02:03,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▉    | 11874/20000 [5:57:19<4:01:11,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 59%|█████▉    | 11899/20000 [5:58:04<4:00:48,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|█████▉    | 11924/20000 [5:58:48<3:59:58,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|█████▉    | 11949/20000 [5:59:33<3:58:47,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|█████▉    | 11974/20000 [6:00:18<3:58:09,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|█████▉    | 11999/20000 [6:01:02<3:57:02,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|██████    | 12024/20000 [6:01:47<3:57:28,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|██████    | 12049/20000 [6:02:31<3:56:12,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|██████    | 12074/20000 [6:03:16<3:55:13,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 60%|██████    | 12099/20000 [6:04:00<3:54:56,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████    | 12124/20000 [6:04:45<3:53:49,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████    | 12149/20000 [6:05:29<3:52:01,  1.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████    | 12174/20000 [6:06:14<3:52:12,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████    | 12199/20000 [6:06:59<3:51:42,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████    | 12224/20000 [6:07:43<3:50:55,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████    | 12249/20000 [6:08:28<3:49:50,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████▏   | 12274/20000 [6:09:12<3:49:16,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|██████▏   | 12299/20000 [6:09:57<3:48:57,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12324/20000 [6:10:41<3:46:59,  1.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12349/20000 [6:11:26<3:47:40,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12374/20000 [6:12:11<3:47:26,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12399/20000 [6:12:55<3:48:13,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12424/20000 [6:13:40<3:48:45,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12449/20000 [6:14:26<3:53:17,  1.85s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12474/20000 [6:15:16<4:08:53,  1.98s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████▏   | 12499/20000 [6:16:04<4:00:05,  1.92s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12524/20000 [6:16:52<3:56:05,  1.89s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12549/20000 [6:17:39<3:53:11,  1.88s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12574/20000 [6:18:26<3:52:18,  1.88s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12599/20000 [6:19:13<3:48:07,  1.85s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12624/20000 [6:19:59<3:47:57,  1.85s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12649/20000 [6:20:45<3:46:55,  1.85s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12674/20000 [6:21:32<3:46:43,  1.86s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|██████▎   | 12699/20000 [6:22:18<3:43:26,  1.84s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▎   | 12724/20000 [6:23:03<3:42:34,  1.84s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▎   | 12749/20000 [6:23:49<3:41:04,  1.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▍   | 12774/20000 [6:24:35<3:40:53,  1.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▍   | 12799/20000 [6:25:21<3:37:52,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▍   | 12823/20000 [6:26:04<3:39:02,  1.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▍   | 12849/20000 [6:26:52<3:36:57,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▍   | 12874/20000 [6:27:37<3:35:40,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|██████▍   | 12899/20000 [6:28:23<3:34:54,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▍   | 12924/20000 [6:29:08<3:33:50,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▍   | 12949/20000 [6:29:54<3:33:00,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▍   | 12974/20000 [6:30:39<3:32:11,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▍   | 12999/20000 [6:31:24<3:31:04,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▌   | 13024/20000 [6:32:10<3:30:16,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▌   | 13049/20000 [6:32:55<3:30:00,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▌   | 13074/20000 [6:33:40<3:29:27,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|██████▌   | 13099/20000 [6:34:26<3:28:59,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▌   | 13124/20000 [6:35:11<3:28:58,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▌   | 13149/20000 [6:35:57<3:28:22,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▌   | 13174/20000 [6:36:42<3:27:22,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▌   | 13199/20000 [6:37:28<3:26:17,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▌   | 13224/20000 [6:38:13<3:25:19,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▌   | 13249/20000 [6:38:59<3:25:19,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▋   | 13275/20000 [6:39:46<3:24:18,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|██████▋   | 13299/20000 [6:40:30<3:23:39,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13324/20000 [6:41:15<3:23:51,  1.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13349/20000 [6:42:01<3:23:34,  1.84s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13374/20000 [6:42:47<3:21:38,  1.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13400/20000 [6:43:34<3:20:26,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13424/20000 [6:44:18<3:18:49,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13449/20000 [6:45:03<3:17:33,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13475/20000 [6:45:50<3:17:01,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████▋   | 13499/20000 [6:46:34<3:17:34,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13524/20000 [6:47:19<3:15:43,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13550/20000 [6:48:06<3:14:30,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13574/20000 [6:48:50<3:13:59,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13599/20000 [6:49:35<3:12:31,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13625/20000 [6:50:22<3:11:59,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13649/20000 [6:51:05<3:11:42,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13675/20000 [6:51:52<3:11:35,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████▊   | 13699/20000 [6:52:36<3:09:28,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▊   | 13725/20000 [6:53:23<3:08:22,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▊   | 13749/20000 [6:54:06<3:08:00,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▉   | 13774/20000 [6:54:51<3:07:47,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▉   | 13800/20000 [6:55:38<3:06:43,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▉   | 13824/20000 [6:56:21<3:05:24,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▉   | 13850/20000 [6:57:08<3:05:01,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▉   | 13874/20000 [6:57:52<3:04:17,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|██████▉   | 13896/20000 [6:58:31<3:03:21,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|██████▉   | 13924/20000 [6:59:22<3:02:56,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|██████▉   | 13949/20000 [7:00:07<3:02:20,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|██████▉   | 13975/20000 [7:00:54<3:00:46,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|██████▉   | 13999/20000 [7:01:37<2:59:53,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|███████   | 14025/20000 [7:02:24<2:58:57,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|███████   | 14049/20000 [7:03:07<2:58:57,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|███████   | 14075/20000 [7:03:54<2:58:04,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|███████   | 14099/20000 [7:04:38<2:57:21,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████   | 14125/20000 [7:05:24<2:56:25,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████   | 14149/20000 [7:06:08<2:55:36,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████   | 14175/20000 [7:06:55<2:54:38,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████   | 14199/20000 [7:07:38<2:54:32,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████   | 14225/20000 [7:08:25<2:54:51,  1.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████   | 14249/20000 [7:09:08<2:52:59,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████▏  | 14275/20000 [7:09:55<2:51:55,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|███████▏  | 14299/20000 [7:10:38<2:51:47,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▏  | 14325/20000 [7:11:25<2:50:44,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▏  | 14349/20000 [7:12:08<2:48:51,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▏  | 14375/20000 [7:12:55<2:49:02,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▏  | 14399/20000 [7:13:38<2:47:52,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▏  | 14424/20000 [7:14:23<2:46:51,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▏  | 14449/20000 [7:15:08<2:46:29,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▏  | 14474/20000 [7:15:53<2:46:27,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|███████▎  | 14500/20000 [7:16:40<2:45:36,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14524/20000 [7:17:23<2:43:52,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14550/20000 [7:18:10<2:44:04,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14574/20000 [7:18:53<2:42:37,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14600/20000 [7:19:40<2:41:41,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14625/20000 [7:20:25<2:41:40,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14649/20000 [7:21:08<2:39:54,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14675/20000 [7:21:55<2:39:42,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|███████▎  | 14699/20000 [7:22:38<2:38:49,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▎  | 14725/20000 [7:23:25<2:38:02,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▎  | 14749/20000 [7:24:08<2:37:40,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▍  | 14775/20000 [7:24:55<2:36:38,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▍  | 14799/20000 [7:25:38<2:35:41,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▍  | 14825/20000 [7:26:25<2:35:21,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▍  | 14849/20000 [7:27:08<2:34:52,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▍  | 14875/20000 [7:27:55<2:33:24,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|███████▍  | 14899/20000 [7:28:38<2:32:57,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|███████▍  | 14925/20000 [7:29:25<2:32:16,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|███████▍  | 14949/20000 [7:30:08<2:31:26,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|███████▍  | 14975/20000 [7:30:55<2:30:26,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|███████▍  | 14999/20000 [7:31:38<2:30:07,  1.80s/it]
+ 75%|███████▌  | 15000/20000 [7:31:40<2:30:03,  1.80s/it][INFO|trainer.py:3614] 2024-04-25 21:17:02,950 >> ***** Running Evaluation *****
+[INFO|trainer.py:3616] 2024-04-25 21:17:02,950 >>   Num examples = 639
+[INFO|trainer.py:3619] 2024-04-25 21:17:02,950 >>   Batch size = 32
+100%|██████████| 3/3 [00:00<00:00,  2.97it/s]
+[INFO|configuration_utils.py:471] 2024-04-25 21:17:04,502 >> Configuration saved in ./checkpoint-15000/config.json
+[INFO|configuration_utils.py:697] 2024-04-25 21:17:04,505 >> Configuration saved in ./checkpoint-15000/generation_config.json
+[INFO|modeling_utils.py:2590] 2024-04-25 21:17:08,476 >> Model weights saved in ./checkpoint-15000/model.safetensors
+[INFO|tokenization_utils_base.py:2488] 2024-04-25 21:17:08,493 >> tokenizer config file saved in ./checkpoint-15000/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-25 21:17:08,495 >> Special tokens file saved in ./checkpoint-15000/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2488] 2024-04-25 21:17:18,331 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-25 21:17:18,333 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|trainer.py:3397] 2024-04-25 21:17:18,359 >> Deleting older checkpoint [checkpoint-10000] due to args.save_total_limit
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|███████▌  | 15024/20000 [7:32:38<2:28:58,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|███████▌  | 15050/20000 [7:33:25<2:28:25,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|███████▌  | 15074/20000 [7:34:08<2:27:41,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▌  | 15100/20000 [7:34:55<2:27:17,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▌  | 15124/20000 [7:35:38<2:26:30,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▌  | 15150/20000 [7:36:25<2:25:21,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▌  | 15174/20000 [7:37:08<2:24:54,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▌  | 15200/20000 [7:37:55<2:23:58,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▌  | 15224/20000 [7:38:38<2:22:34,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▋  | 15250/20000 [7:39:25<2:22:07,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▋  | 15274/20000 [7:40:08<2:21:43,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|███████▋  | 15300/20000 [7:40:55<2:20:45,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████▋  | 15324/20000 [7:41:38<2:20:03,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████▋  | 15350/20000 [7:42:25<2:19:39,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████▋  | 15374/20000 [7:43:08<2:18:35,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████▋  | 15400/20000 [7:43:55<2:17:58,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████▋  | 15424/20000 [7:44:38<2:17:32,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████▋  | 15450/20000 [7:45:25<2:16:01,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████▋  | 15474/20000 [7:46:08<2:15:09,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15500/20000 [7:46:55<2:14:27,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15525/20000 [7:47:39<2:13:51,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15549/20000 [7:48:23<2:12:55,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15575/20000 [7:49:09<2:12:36,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15599/20000 [7:49:52<2:11:43,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15625/20000 [7:50:39<2:10:45,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15649/20000 [7:51:22<2:10:35,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15675/20000 [7:52:09<2:09:54,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|███████▊  | 15699/20000 [7:52:52<2:08:33,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|███████▊  | 15725/20000 [7:53:39<2:07:32,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|███████▉  | 15750/20000 [7:54:24<2:07:22,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|███████▉  | 15774/20000 [7:55:07<2:06:15,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|███████▉  | 15800/20000 [7:55:53<2:05:55,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|███████▉  | 15824/20000 [7:56:36<2:04:54,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|███████▉  | 15850/20000 [7:57:23<2:03:50,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|███████▉  | 15875/20000 [7:58:08<2:04:29,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|███████▉  | 15900/20000 [7:58:53<2:02:15,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|███████▉  | 15925/20000 [7:59:38<2:01:33,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|███████▉  | 15949/20000 [8:00:21<2:00:45,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|███████▉  | 15975/20000 [8:01:07<2:00:07,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|███████▉  | 15999/20000 [8:01:51<1:59:45,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|████████  | 16025/20000 [8:02:37<1:59:14,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|████████  | 16050/20000 [8:03:22<1:58:57,  1.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|████████  | 16075/20000 [8:04:07<1:57:31,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|████████  | 16100/20000 [8:04:52<1:56:21,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████  | 16125/20000 [8:05:37<1:55:52,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████  | 16150/20000 [8:06:21<1:54:47,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████  | 16175/20000 [8:07:06<1:54:45,  1.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████  | 16200/20000 [8:07:51<1:52:08,  1.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████  | 16225/20000 [8:08:35<1:52:47,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████▏ | 16250/20000 [8:09:20<1:51:12,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████▏ | 16275/20000 [8:10:04<1:50:13,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16300/20000 [8:10:49<1:49:31,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16325/20000 [8:11:33<1:49:12,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16350/20000 [8:12:18<1:48:17,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16375/20000 [8:13:02<1:47:12,  1.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16399/20000 [8:13:45<1:47:04,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16425/20000 [8:14:31<1:46:18,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16450/20000 [8:15:16<1:44:56,  1.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16475/20000 [8:16:00<1:44:20,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 16499/20000 [8:16:43<1:44:01,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 16525/20000 [8:17:29<1:43:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 16550/20000 [8:18:14<1:42:31,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 16575/20000 [8:18:58<1:42:11,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 16600/20000 [8:19:43<1:41:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 16625/20000 [8:20:28<1:40:07,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 16650/20000 [8:21:12<1:39:29,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 16675/20000 [8:21:57<1:38:54,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▎ | 16700/20000 [8:22:42<1:37:57,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▎ | 16725/20000 [8:23:26<1:37:29,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 16750/20000 [8:24:11<1:36:56,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 16775/20000 [8:24:56<1:35:59,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 16800/20000 [8:25:40<1:35:34,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 16824/20000 [8:26:23<1:34:03,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 16850/20000 [8:27:09<1:33:30,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 16875/20000 [8:27:54<1:33:08,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 16900/20000 [8:28:39<1:32:10,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▍ | 16925/20000 [8:29:23<1:31:22,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▍ | 16950/20000 [8:30:08<1:30:48,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▍ | 16975/20000 [8:30:53<1:29:53,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▌ | 17000/20000 [8:31:37<1:29:01,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▌ | 17025/20000 [8:32:22<1:28:19,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▌ | 17050/20000 [8:33:06<1:28:02,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▌ | 17075/20000 [8:33:51<1:26:51,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 17100/20000 [8:34:36<1:26:06,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 17125/20000 [8:35:20<1:25:20,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 17151/20000 [8:36:07<1:24:41,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 17175/20000 [8:36:50<1:23:45,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 17200/20000 [8:37:34<1:23:01,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 17224/20000 [8:38:17<1:22:48,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▋ | 17250/20000 [8:39:03<1:21:51,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▋ | 17275/20000 [8:39:48<1:20:47,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▋ | 17300/20000 [8:40:33<1:20:12,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 17325/20000 [8:41:17<1:19:36,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 17350/20000 [8:42:02<1:18:35,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 17375/20000 [8:42:46<1:18:02,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 17401/20000 [8:43:33<1:17:36,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 17425/20000 [8:44:16<1:16:14,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 17450/20000 [8:45:00<1:16:10,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 17475/20000 [8:45:45<1:14:59,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17500/20000 [8:46:29<1:14:07,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17525/20000 [8:47:14<1:13:31,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17550/20000 [8:47:59<1:13:09,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17575/20000 [8:48:43<1:12:28,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17600/20000 [8:49:28<1:11:20,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17625/20000 [8:50:12<1:10:27,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17651/20000 [8:50:59<1:09:54,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17675/20000 [8:51:42<1:09:05,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 17700/20000 [8:52:26<1:08:09,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▊ | 17726/20000 [8:53:13<1:07:41,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 17750/20000 [8:53:56<1:07:12,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 17775/20000 [8:54:40<1:05:59,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 17801/20000 [8:55:27<1:05:19,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 17825/20000 [8:56:10<1:04:35,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 17850/20000 [8:56:54<1:03:48,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 17875/20000 [8:57:39<1:03:02,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|████████▉ | 17900/20000 [8:58:23<1:02:11,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|████████▉ | 17925/20000 [8:59:08<1:01:44,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|████████▉ | 17950/20000 [8:59:53<1:00:52,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|████████▉ | 17976/20000 [9:00:39<1:00:13,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████ | 18000/20000 [9:01:22<59:27,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████ | 18025/20000 [9:02:07<58:41,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████ | 18051/20000 [9:02:53<57:53,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████ | 18075/20000 [9:03:36<57:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████ | 18100/20000 [9:04:20<56:25,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████ | 18125/20000 [9:05:05<55:43,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████ | 18150/20000 [9:05:50<54:58,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████ | 18175/20000 [9:06:34<54:06,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████ | 18200/20000 [9:07:19<53:22,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████ | 18226/20000 [9:08:05<52:42,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████▏| 18250/20000 [9:08:48<51:58,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████▏| 18275/20000 [9:09:32<51:05,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 18300/20000 [9:10:17<50:28,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 18326/20000 [9:11:03<49:49,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 18350/20000 [9:11:46<48:51,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|███████��█▏| 18375/20000 [9:12:31<48:16,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 18400/20000 [9:13:15<47:27,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 18425/20000 [9:14:00<46:46,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 18450/20000 [9:14:44<45:59,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 18475/20000 [9:15:29<45:13,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18501/20000 [9:16:15<44:30,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18525/20000 [9:16:58<43:57,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18550/20000 [9:17:42<42:58,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18575/20000 [9:18:27<42:17,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18601/20000 [9:19:13<41:40,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18625/20000 [9:19:56<41:01,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18650/20000 [9:20:41<40:08,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 18675/20000 [9:21:25<39:16,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▎| 18700/20000 [9:22:10<38:38,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▎| 18725/20000 [9:22:54<37:58,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▎| 18749/20000 [9:23:37<37:05,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 18774/20000 [9:24:22<36:26,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 18799/20000 [9:25:06<35:43,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 18824/20000 [9:25:51<34:59,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 18850/20000 [9:26:37<34:07,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 18874/20000 [9:27:20<33:26,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 18899/20000 [9:28:05<32:39,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▍| 18924/20000 [9:28:49<31:54,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▍| 18950/20000 [9:29:36<31:09,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▍| 18974/20000 [9:30:18<30:32,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▍| 18999/20000 [9:31:03<29:41,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▌| 19024/20000 [9:31:47<28:59,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▌| 19050/20000 [9:32:34<28:10,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▌| 19074/20000 [9:33:16<27:27,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▌| 19099/20000 [9:34:01<26:49,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▌| 19124/20000 [9:34:46<25:58,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▌| 19149/20000 [9:35:30<25:10,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▌| 19174/20000 [9:36:15<24:30,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▌| 19199/20000 [9:36:59<23:44,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▌| 19224/20000 [9:37:44<23:04,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▌| 19249/20000 [9:38:28<22:19,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▋| 19274/20000 [9:39:13<21:34,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▋| 19299/20000 [9:39:57<20:46,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19325/20000 [9:40:44<20:03,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19349/20000 [9:41:26<19:14,  1.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19374/20000 [9:42:11<18:36,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19399/20000 [9:42:55<17:49,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19425/20000 [9:43:42<17:07,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19449/20000 [9:44:24<16:24,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19474/20000 [9:45:09<15:38,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 19499/20000 [9:45:54<14:52,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19525/20000 [9:46:40<14:03,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19549/20000 [9:47:23<13:23,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19574/20000 [9:48:07<12:37,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19599/20000 [9:48:52<11:58,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19624/20000 [9:49:36<11:10,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19649/20000 [9:50:21<10:23,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19674/20000 [9:51:05<09:40,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 19700/20000 [9:51:52<08:54,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▊| 19724/20000 [9:52:34<08:10,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▊| 19749/20000 [9:53:19<07:25,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▉| 19774/20000 [9:54:03<06:42,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▉| 19800/20000 [9:54:50<05:56,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▉| 19824/20000 [9:55:33<05:14,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▉| 19849/20000 [9:56:17<04:29,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▉| 19874/20000 [9:57:02<03:44,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████▉| 19900/20000 [9:57:48<02:57,  1.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████▉| 19924/20000 [9:58:31<02:15,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████▉| 19949/20000 [9:59:15<01:30,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████▉| 19974/20000 [10:00:00<00:46,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|██████████| 20000/20000 [10:00:46<00:00,  1.78s/it]
+{'loss': 0.8191, 'grad_norm': 0.6796875, 'learning_rate': 0.0, 'epoch': 4.94}
+100%|██████████| 20000/20000 [10:00:46<00:00,  1.78s/it][INFO|trainer.py:3614] 2024-04-25 23:46:09,359 >> ***** Running Evaluation *****
+[INFO|trainer.py:3616] 2024-04-25 23:46:09,359 >>   Num examples = 639
+[INFO|trainer.py:3619] 2024-04-25 23:46:09,360 >>   Batch size = 32
+100%|██████████| 20000/20000 [10:00:48<00:00,[INFO|trainer.py:3305] 2024-04-25 23:46:10,900 >> Saving model checkpoint to ./checkpoint-20000
+[INFO|configuration_utils.py:471] 2024-04-25 23:46:10,904 >> Configuration saved in ./checkpoint-20000/config.json
+[INFO|configuration_utils.py:697] 2024-04-25 23:46:10,907 >> Configuration saved in ./checkpoint-20000/generation_config.json
+[INFO|modeling_utils.py:2590] 2024-04-25 23:46:14,897 >> Model weights saved in ./checkpoint-20000/model.safetensors
+[INFO|tokenization_utils_base.py:2488] 2024-04-25 23:46:14,913 >> tokenizer config file saved in ./checkpoint-20000/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-25 23:46:14,914 >> Special tokens file saved in ./checkpoint-20000/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2488] 2024-04-25 23:46:24,829 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-25 23:46:24,831 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|trainer.py:3397] 2024-04-25 23:46:24,858 >> Deleting older checkpoint [checkpoint-15000] due to args.save_total_limit
+[INFO|trainer.py:2316] 2024-04-25 23:46:24,966 >>
+Training completed. Do not forget to share your model on huggingface.co/models =)
+100%|██████████| 20000/20000 [10:01:02<00:00,  1.80s/it]
+[INFO|trainer.py:4035] 2024-04-25 23:46:24,979 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.

wandb/run-20240425_134518-etajcxpg/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.9694, "train/grad_norm": 0.765625, "train/learning_rate": 5.115384615384615e-05, "train/epoch": 2.478368355995056, "train/global_step": 10025, "_timestamp": 1714070863.3109484, "_runtime": 18145.071139335632, "_step": 403, "eval/loss": 1.0057789087295532, "eval/runtime": 1.5251, "eval/samples_per_second": 418.982, "eval/steps_per_second": 1.967}
+{"train/loss": 0.8191, "train/grad_norm": 0.6796875, "train/learning_rate": 0.0, "train/epoch": 4.944375772558715, "train/global_step": 20000, "_timestamp": 1714088784.9765599, "_runtime": 36066.73675084114, "_step": 805, "eval/loss": 1.0042184591293335, "eval/runtime": 1.5308, "eval/samples_per_second": 417.441, "eval/steps_per_second": 1.96, "train_runtime": 36068.0493, "train_samples_per_second": 141.954, "train_steps_per_second": 0.555, "total_flos": 9.058112140235663e+19, "train_loss": 1.0958750234603882}

wandb/run-20240425_134518-etajcxpg/run-etajcxpg.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5c84a6349f083978b30c5d2558db9c712d66ea8f5e0264543ed8cac8646be3
-size 4787581
+oid sha256:5c6bcbd1336c1cd3ce20a2143fd84ab170d80ecdfd34b10c8b8012857a9b75b9
+size 9669284