Training in progress, step 42500

nohup.out

@@ -23350,3 +23350,275 @@ Configuration saved in ./checkpoint-42000/config.json
 Model weights saved in ./checkpoint-42000/pytorch_model.bin
 Configuration saved in ./checkpoint-42000/preprocessor_config.json
 Configuration saved in ./preprocessor_config.json
+Deleting older checkpoint [checkpoint-40500] due to args.save_total_limit
+
 62%|██████▏   | 42001/67700 [25:16:23<436:10:34, 61.10s/it]
 62%|██████▏   | 42002/67700 [25:16:25<308:57:10, 43.28s/it]
 62%|██████▏   | 42003/67700 [25:16:27<220:08:20, 30.84s/it]
 62%|██████▏   | 42004/67700 [25:16:28<157:41:24, 22.09s/it]
 62%|██████▏   | 42005/67700 [25:16:30<114:00:17, 15.97s/it]
 62%|██████▏   | 42006/67700 [25:16:32<83:17:55, 11.67s/it] 
 62%|██████▏   | 42007/67700 [25:16:33<61:48:07,  8.66s/it]
 62%|██████▏   | 42008/67700 [25:16:35<46:39:37,  6.54s/it]
 62%|██████▏   | 42009/67700 [25:16:37<36:01:31,  5.05s/it]
 62%|██████▏   | 42010/67700 [25:16:38<28:31:35,  4.00s/it]
 62%|██████▏   | 42011/67700 [25:16:40<23:10:41,  3.25s/it]
 62%|██████▏   | 42012/67700 [25:16:41<19:21:03,  2.71s/it]
 62%|██████▏   | 42013/67700 [25:16:43<16:40:55,  2.34s/it]
 62%|██████▏   | 42014/67700 [25:16:44<14:56:03,  2.09s/it]
 62%|██████▏   | 42015/67700 [25:16:45<13:26:43,  1.88s/it]
 62%|██████▏   | 42016/67700 [25:16:47<12:22:11,  1.73s/it]
 62%|██████▏   | 42017/67700 [25:16:48<11:27:13,  1.61s/it]
 62%|██████▏   | 42018/67700 [25:16:49<10:45:40,  1.51s/it]
 62%|██████▏   | 42019/67700 [25:16:51<10:18:40,  1.45s/it]
 62%|██████▏   | 42020/67700 [25:16:52<9:51:00,  1.38s/it] 
 62%|██████▏   | 42021/67700 [25:16:53<9:30:07,  1.33s/it]
 62%|██████▏   | 42022/67700 [25:16:54<9:06:06,  1.28s/it]
 62%|██████▏   | 42023/67700 [25:16:55<8:40:35,  1.22s/it]
 62%|██████▏   | 42024/67700 [25:16:56<8:12:27,  1.15s/it]
 62%|██████▏   | 42025/67700 [25:16:59<11:14:45,  1.58s/it]
 62%|██████▏   | 42026/67700 [25:17:02<13:31:14,  1.90s/it]
 62%|██████▏   | 42027/67700 [25:17:04<14:48:35,  2.08s/it]
 62%|██████▏   | 42028/67700 [25:17:07<15:51:23,  2.22s/it]
 62%|██████▏   | 42029/67700 [25:17:09<16:21:42,  2.29s/it]
 62%|██████▏   | 42030/67700 [25:17:11<16:21:16,  2.29s/it]
 62%|██████▏   | 42031/67700 [25:17:14<16:18:26,  2.29s/it]
 62%|██████▏   | 42032/67700 [25:17:16<16:07:21,  2.26s/it]
 62%|██████▏   | 42033/67700 [25:17:18<16:02:46,  2.25s/it]
 62%|██████▏   | 42034/67700 [25:17:20<15:44:22,  2.21s/it]
 62%|██████▏   | 42035/67700 [25:17:22<15:34:24,  2.18s/it]
 62%|██████▏   | 42036/67700 [25:17:24<15:25:34,  2.16s/it]
 62%|██████▏   | 42037/67700 [25:17:27<15:19:01,  2.15s/it]
 62%|██████▏   | 42038/67700 [25:17:29<15:09:08,  2.13s/it]
 62%|██████▏   | 42039/67700 [25:17:31<15:02:06,  2.11s/it]
 62%|██████▏   | 42040/67700 [25:17:33<14:50:19,  2.08s/it]
 62%|██████▏   | 42041/67700 [25:17:35<14:44:31,  2.07s/it]
 62%|██████▏   | 42042/67700 [25:17:37<14:31:44,  2.04s/it]
 62%|██████▏   | 42043/67700 [25:17:39<14:16:05,  2.00s/it]
 62%|██████▏   | 42044/67700 [25:17:41<13:59:23,  1.96s/it]
 62%|██████▏   | 42045/67700 [25:17:42<13:46:57,  1.93s/it]
 62%|██████▏   | 42046/67700 [25:17:44<13:36:49,  1.91s/it]
 62%|██████▏   | 42047/67700 [25:17:46<13:22:12,  1.88s/it]
 62%|██████▏   | 42048/67700 [25:17:48<13:15:17,  1.86s/it]
 62%|██████▏   | 42049/67700 [25:17:50<13:04:12,  1.83s/it]
 62%|██████▏   | 42050/67700 [25:17:51<12:52:44,  1.81s/it]
 62%|██████▏   | 42051/67700 [25:17:53<12:36:03,  1.77s/it]
 62%|██████▏   | 42052/67700 [25:17:55<12:25:34,  1.74s/it]
 62%|██████▏   | 42053/67700 [25:17:56<12:14:01,  1.72s/it]
 62%|██████▏   | 42054/67700 [25:17:58<12:06:51,  1.70s/it]
 62%|██████▏   | 42055/67700 [25:18:00<11:56:17,  1.68s/it]
 62%|██████▏   | 42056/67700 [25:18:01<11:47:39,  1.66s/it]
 62%|██████▏   | 42057/67700 [25:18:03<11:37:03,  1.63s/it]
 62%|██████▏   | 42058/67700 [25:18:04<11:27:16,  1.61s/it]
 62%|██████▏   | 42059/67700 [25:18:06<11:17:07,  1.58s/it]
 62%|██████▏   | 42060/67700 [25:18:07<11:08:42,  1.56s/it]
 62%|██████▏   | 42061/67700 [25:18:09<10:55:44,  1.53s/it]
 62%|██████▏   | 42062/67700 [25:18:10<10:42:47,  1.50s/it]
 62%|██████▏   | 42063/67700 [25:18:12<10:26:48,  1.47s/it]
 62%|██████▏   | 42064/67700 [25:18:13<10:14:38,  1.44s/it]
 62%|██████▏   | 42065/67700 [25:18:14<10:05:04,  1.42s/it]
 62%|██████▏   | 42066/67700 [25:18:16<9:48:43,  1.38s/it] 
 62%|██████▏   | 42067/67700 [25:18:17<9:37:30,  1.35s/it]
 62%|██████▏   | 42068/67700 [25:18:18<9:21:29,  1.31s/it]
 62%|██████▏   | 42069/67700 [25:18:20<9:08:22,  1.28s/it]
 62%|██████▏   | 42070/67700 [25:18:21<8:53:20,  1.25s/it]
 62%|██████▏   | 42071/67700 [25:18:22<8:48:18,  1.24s/it]
 62%|██████▏   | 42072/67700 [25:18:23<8:27:55,  1.19s/it]
 62%|██████▏   | 42073/67700 [25:18:24<8:01:01,  1.13s/it]
 62%|██████▏   | 42074/67700 [25:18:25<7:37:34,  1.07s/it]
 62%|██████▏   | 42075/67700 [25:18:27<10:53:23,  1.53s/it]
 62%|██████▏   | 42076/67700 [25:18:30<13:08:59,  1.85s/it]
 62%|██████▏   | 42077/67700 [25:18:33<14:36:24,  2.05s/it]
 62%|██████▏   | 42078/67700 [25:18:35<15:32:09,  2.18s/it]
 62%|██████▏   | 42079/67700 [25:18:38<16:06:28,  2.26s/it]
 62%|██████▏   | 42080/67700 [25:18:40<16:14:02,  2.28s/it]
 62%|██████▏   | 42081/67700 [25:18:42<16:11:28,  2.28s/it]
 62%|██████▏   | 42082/67700 [25:18:44<16:07:23,  2.27s/it]
 62%|██████▏   | 42083/67700 [25:18:47<15:56:10,  2.24s/it]
 62%|██████▏   | 42084/67700 [25:18:49<15:51:14,  2.23s/it]
 62%|██████▏   | 42085/67700 [25:18:51<15:39:04,  2.20s/it]
 62%|██████▏   | 42086/67700 [25:18:53<15:35:31,  2.19s/it]
 62%|██████▏   | 42087/67700 [25:18:55<15:24:49,  2.17s/it]
 62%|██████▏   | 42088/67700 [25:18:57<15:16:35,  2.15s/it]
 62%|██████▏   | 42089/67700 [25:18:59<15:05:38,  2.12s/it]
 62%|██████▏   | 42090/67700 [25:19:01<14:47:29,  2.08s/it]
 62%|██████▏   | 42091/67700 [25:19:03<14:37:06,  2.06s/it]
 62%|██████▏   | 42092/67700 [25:19:05<14:27:39,  2.03s/it]
 62%|██████▏   | 42093/67700 [25:19:07<14:14:53,  2.00s/it]
 62%|██████▏   | 42094/67700 [25:19:09<14:01:04,  1.97s/it]
 62%|██████▏   | 42095/67700 [25:19:11<13:48:04,  1.94s/it]
 62%|██████▏   | 42096/67700 [25:19:13<13:37:07,  1.91s/it]
 62%|██████▏   | 42097/67700 [25:19:15<13:25:45,  1.89s/it]
 62%|██████▏   | 42098/67700 [25:19:16<13:13:30,  1.86s/it]
 62%|██████▏   | 42099/67700 [25:19:18<13:03:10,  1.84s/it]
 62%|██████▏   | 42100/67700 [25:19:20<12:52:16,  1.81s/it]
                                                           
 62%|██████▏   | 42100/67700 [25:19:20<12:52:16,  1.81s/it]
 62%|██████▏   | 42101/67700 [25:19:22<12:41:37,  1.79s/it]
 62%|██████▏   | 42102/67700 [25:19:23<12:30:22,  1.76s/it]
 62%|██████▏   | 42103/67700 [25:19:25<12:23:15,  1.74s/it]
 62%|██████▏   | 42104/67700 [25:19:27<12:14:47,  1.72s/it]
 62%|██████▏   | 42105/67700 [25:19:28<12:02:27,  1.69s/it]
 62%|██████▏   | 42106/67700 [25:19:30<11:54:21,  1.67s/it]
 62%|██████▏   | 42107/67700 [25:19:32<11:44:51,  1.65s/it]
 62%|██████▏   | 42108/67700 [25:19:33<11:29:34,  1.62s/it]
 62%|██████▏   | 42109/67700 [25:19:35<11:15:16,  1.58s/it]
 62%|██████▏   | 42110/67700 [25:19:36<11:01:02,  1.55s/it]
 62%|██████▏   | 42111/67700 [25:19:38<10:51:08,  1.53s/it]
 62%|██████▏   | 42112/67700 [25:19:39<10:40:32,  1.50s/it]
 62%|██████▏   | 42113/67700 [25:19:40<10:29:12,  1.48s/it]
 62%|██████▏   | 42114/67700 [25:19:42<10:13:58,  1.44s/it]
 62%|██████▏   | 42115/67700 [25:19:43<9:56:24,  1.40s/it] 
 62%|██████▏   | 42116/67700 [25:19:44<9:39:35,  1.36s/it]
 62%|██████▏   | 42117/67700 [25:19:46<9:23:21,  1.32s/it]
 62%|██████▏   | 42118/67700 [25:19:47<9:11:16,  1.29s/it]
 62%|██████▏   | 42119/67700 [25:19:48<8:56:17,  1.26s/it]
 62%|██████▏   | 42120/67700 [25:19:49<8:41:47,  1.22s/it]
 62%|██████▏   | 42121/67700 [25:19:50<8:35:00,  1.21s/it]
 62%|██████▏   | 42122/67700 [25:19:51<8:15:40,  1.16s/it]
 62%|██████▏   | 42123/67700 [25:19:52<7:58:50,  1.12s/it]
 62%|██████▏   | 42124/67700 [25:19:53<7:40:29,  1.08s/it]
 62%|██████▏   | 42125/67700 [25:19:56<10:49:18,  1.52s/it]
 62%|██████▏   | 42126/67700 [25:19:59<12:59:33,  1.83s/it]
 62%|██████▏   | 42127/67700 [25:20:01<14:26:02,  2.03s/it]
 62%|██████▏   | 42128/67700 [25:20:04<15:22:47,  2.17s/it]
 62%|██████▏   | 42129/67700 [25:20:06<15:53:51,  2.24s/it]
 62%|██████▏   | 42130/67700 [25:20:08<16:04:12,  2.26s/it]
 62%|██████▏   | 42131/67700 [25:20:10<15:59:58,  2.25s/it]
 62%|██████▏   | 42132/67700 [25:20:13<15:51:45,  2.23s/it]
 62%|███���██▏   | 42133/67700 [25:20:15<15:44:27,  2.22s/it]
 62%|██████▏   | 42134/67700 [25:20:17<15:46:25,  2.22s/it]
 62%|██████▏   | 42135/67700 [25:20:19<15:37:41,  2.20s/it]
 62%|██████▏   | 42136/67700 [25:20:21<15:30:28,  2.18s/it]
 62%|██████▏   | 42137/67700 [25:20:23<15:16:58,  2.15s/it]
 62%|██████▏   | 42138/67700 [25:20:26<15:06:20,  2.13s/it]
 62%|██████▏   | 42139/67700 [25:20:28<14:55:51,  2.10s/it]
 62%|██████▏   | 42140/67700 [25:20:30<14:48:11,  2.08s/it]
 62%|██████▏   | 42141/67700 [25:20:32<14:37:23,  2.06s/it]
 62%|██████▏   | 42142/67700 [25:20:34<14:27:45,  2.04s/it]
 62%|██████▏   | 42143/67700 [25:20:36<14:16:57,  2.01s/it]
 62%|██████▏   | 42144/67700 [25:20:37<14:03:27,  1.98s/it]
 62%|██████▏   | 42145/67700 [25:20:39<13:49:03,  1.95s/it]
 62%|██████▏   | 42146/67700 [25:20:41<13:37:26,  1.92s/it]
 62%|██████▏   | 42147/67700 [25:20:43<13:27:33,  1.90s/it]
 62%|██████▏   | 42148/67700 [25:20:45<13:14:26,  1.87s/it]
 62%|██████▏   | 42149/67700 [25:20:47<12:58:11,  1.83s/it]
 62%|██████▏   | 42150/67700 [25:20:48<12:51:39,  1.81s/it]
 62%|██████▏   | 42151/67700 [25:20:50<12:41:58,  1.79s/it]
 62%|██████▏   | 42152/67700 [25:20:52<12:32:33,  1.77s/it]
 62%|██████▏   | 42153/67700 [25:20:53<12:17:25,  1.73s/it]
 62%|██████▏   | 42154/67700 [25:20:55<12:08:57,  1.71s/it]
 62%|██████▏   | 42155/67700 [25:20:57<12:00:48,  1.69s/it]
 62%|██████▏   | 42156/67700 [25:20:58<11:53:23,  1.68s/it]
 62%|██████▏   | 42157/67700 [25:21:00<11:41:11,  1.65s/it]
 62%|██████▏   | 42158/67700 [25:21:02<11:33:06,  1.63s/it]
 62%|██████▏   | 42159/67700 [25:21:03<11:23:20,  1.61s/it]
 62%|██████▏   | 42160/67700 [25:21:05<11:10:56,  1.58s/it]
 62%|██████▏   | 42161/67700 [25:21:06<10:59:22,  1.55s/it]
 62%|██████▏   | 42162/67700 [25:21:08<10:50:15,  1.53s/it]
 62%|██████▏   | 42163/67700 [25:21:09<10:39:14,  1.50s/it]
 62%|██████▏   | 42164/67700 [25:21:10<10:27:14,  1.47s/it]
 62%|██████▏   | 42165/67700 [25:21:12<10:21:24,  1.46s/it]
 62%|██████▏   | 42166/67700 [25:21:13<10:11:46,  1.44s/it]
 62%|██████▏   | 42167/67700 [25:21:15<9:58:11,  1.41s/it] 
 62%|██████▏   | 42168/67700 [25:21:16<9:36:55,  1.36s/it]
 62%|██████▏   | 42169/67700 [25:21:17<9:23:12,  1.32s/it]
 62%|██████▏   | 42170/67700 [25:21:18<9:11:34,  1.30s/it]
 62%|██████▏   | 42171/67700 [25:21:19<8:52:52,  1.25s/it]
 62%|██████▏   | 42172/67700 [25:21:21<8:40:20,  1.22s/it]
 62%|██████▏   | 42173/67700 [25:21:22<8:21:03,  1.18s/it]
 62%|██████▏   | 42174/67700 [25:21:23<7:54:03,  1.11s/it]
 62%|██████▏   | 42175/67700 [25:21:25<11:05:40,  1.56s/it]
 62%|██████▏   | 42176/67700 [25:21:28<13:13:06,  1.86s/it]
 62%|██████▏   | 42177/67700 [25:21:30<14:39:55,  2.07s/it]
 62%|██████▏   | 42178/67700 [25:21:33<15:33:07,  2.19s/it]
 62%|██████▏   | 42179/67700 [25:21:35<16:08:46,  2.28s/it]
 62%|██████▏   | 42180/67700 [25:21:38<16:14:32,  2.29s/it]
 62%|██████▏   | 42181/67700 [25:21:40<16:14:38,  2.29s/it]
 62%|██████▏   | 42182/67700 [25:21:42<16:07:29,  2.27s/it]
 62%|██████▏   | 42183/67700 [25:21:44<16:03:27,  2.27s/it]
 62%|██████▏   | 42184/67700 [25:21:47<15:53:44,  2.24s/it]
 62%|██████▏   | 42185/67700 [25:21:49<15:47:45,  2.23s/it]
 62%|██████▏   | 42186/67700 [25:21:51<15:31:38,  2.19s/it]
 62%|██████▏   | 42187/67700 [25:21:53<15:23:19,  2.17s/it]
 62%|██████▏   | 42188/67700 [25:21:55<15:10:54,  2.14s/it]
 62%|██████▏   | 42189/67700 [25:21:57<15:01:06,  2.12s/it]
 62%|██████▏   | 42190/67700 [25:21:59<15:01:25,  2.12s/it]
 62%|██████▏   | 42191/67700 [25:22:01<14:51:03,  2.10s/it]
 62%|██████▏   | 42192/67700 [25:22:03<14:47:08,  2.09s/it]
 62%|██████▏   | 42193/67700 [25:22:05<14:34:16,  2.06s/it]
 62%|██████▏   | 42194/67700 [25:22:07<14:31:21,  2.05s/it]
 62%|██████▏   | 42195/67700 [25:22:09<14:15:43,  2.01s/it]
 62%|██████▏   | 42196/67700 [25:22:11<14:01:43,  1.98s/it]
 62%|██████▏   | 42197/67700 [25:22:13<13:46:06,  1.94s/it]
 62%|██████▏   | 42198/67700 [25:22:15<13:31:14,  1.91s/it]
 62%|██████▏   | 42199/67700 [25:22:17<13:14:44,  1.87s/it]
 62%|██████▏   | 42200/67700 [25:22:18<13:03:45,  1.84s/it]
                                                           
 62%|██████▏   | 42200/67700 [25:22:18<13:03:45,  1.84s/it]
 62%|██████▏   | 42201/67700 [25:22:20<12:57:35,  1.83s/it]
 62%|██████▏   | 42202/67700 [25:22:22<12:44:37,  1.80s/it]
 62%|██████▏   | 42203/67700 [25:22:24<12:35:49,  1.78s/it]
 62%|██████▏   | 42204/67700 [25:22:25<12:21:08,  1.74s/it]
 62%|██████▏   | 42205/67700 [25:22:27<12:08:10,  1.71s/it]
 62%|██████▏   | 42206/67700 [25:22:29<11:53:56,  1.68s/it]
 62%|██████▏   | 42207/67700 [25:22:30<11:43:14,  1.66s/it]
 62%|██████▏   | 42208/67700 [25:22:32<11:32:55,  1.63s/it]
 62%|██████▏   | 42209/67700 [25:22:33<11:17:46,  1.60s/it]
 62%|██████▏   | 42210/67700 [25:22:35<11:06:52,  1.57s/it]
 62%|██████▏   | 42211/67700 [25:22:36<10:56:45,  1.55s/it]
 62%|██████▏   | 42212/67700 [25:22:38<10:52:19,  1.54s/it]
 62%|██████▏   | 42213/67700 [25:22:39<10:41:53,  1.51s/it]
 62%|██████▏   | 42214/67700 [25:22:41<10:28:18,  1.48s/it]
 62%|██████▏   | 42215/67700 [25:22:42<10:17:07,  1.45s/it]
 62%|██████▏   | 42216/67700 [25:22:43<10:05:33,  1.43s/it]
 62%|██████▏   | 42217/67700 [25:22:45<9:51:56,  1.39s/it] 
 62%|██████▏   | 42218/67700 [25:22:46<9:36:04,  1.36s/it]
 62%|██████▏   | 42219/67700 [25:22:47<9:22:41,  1.32s/it]
 62%|██████▏   | 42220/67700 [25:22:48<9:06:25,  1.29s/it]
 62%|██████▏   | 42221/67700 [25:22:50<8:51:32,  1.25s/it]
 62%|██████▏   | 42222/67700 [25:22:51<8:36:02,  1.22s/it]
 62%|██████▏   | 42223/67700 [25:22:52<8:14:53,  1.17s/it]
 62%|██████▏   | 42224/67700 [25:22:53<7:51:38,  1.11s/it]
 62%|██████▏   | 42225/67700 [25:22:55<10:58:45,  1.55s/it]
 62%|██████▏   | 42226/67700 [25:22:58<13:11:02,  1.86s/it]
 62%|██████▏   | 42227/67700 [25:23:01<14:35:55,  2.06s/it]
 62%|██████▏   | 42228/67700 [25:23:03<15:28:19,  2.19s/it]
 62%|██████▏   | 42229/67700 [25:23:05<16:05:14,  2.27s/it]
 62%|██████▏   | 42230/67700 [25:23:08<16:11:17,  2.29s/it]
 62%|██████▏   | 42231/67700 [25:23:10<16:10:16,  2.29s/it]
 62%|██████▏   | 42232/67700 [25:23:12<15:59:12,  2.26s/it]
 62%|██████▏   | 42233/67700 [25:23:14<15:52:51,  2.24s/it]
 62%|██████▏   | 42234/67700 [25:23:17<15:44:00,  2.22s/it]
 62%|██████▏   | 42235/67700 [25:23:19<15:32:02,  2.20s/it]
 62%|██████▏   | 42236/67700 [25:23:21<15:24:47,  2.18s/it]
 62%|██████▏   | 42237/67700 [25:23:23<15:19:13,  2.17s/it]
 62%|██████▏   | 42238/67700 [25:23:25<15:09:15,  2.14s/it]
 62%|██████▏   | 42239/67700 [25:23:27<15:03:30,  2.13s/it]
 62%|██████▏   | 42240/67700 [25:23:29<14:48:42,  2.09s/it]
 62%|██████▏   | 42241/67700 [25:23:31<14:35:22,  2.06s/it]
 62%|██████▏   | 42242/67700 [25:23:33<14:26:53,  2.04s/it]
 62%|██████▏   | 42243/67700 [25:23:35<14:12:56,  2.01s/it]
 62%|██████▏   | 42244/67700 [25:23:37<13:52:51,  1.96s/it]
 62%|██████▏   | 42245/67700 [25:23:39<13:35:28,  1.92s/it]
 62%|██████▏   | 42246/67700 [25:23:41<13:19:47,  1.89s/it]
 62%|██████▏   | 42247/67700 [25:23:42<13:04:55,  1.85s/it]
 62%|██████▏   | 42248/67700 [25:23:44<12:58:56,  1.84s/it]
 62%|██████▏   | 42249/67700 [25:23:46<12:53:45,  1.82s/it]
 62%|██████▏   | 42250/67700 [25:23:48<12:44:47,  1.80s/it]
 62%|██████▏   | 42251/67700 [25:23:50<12:38:46,  1.79s/it]
 62%|██████▏   | 42252/67700 [25:23:51<12:30:25,  1.77s/it]
 62%|██████▏   | 42253/67700 [25:23:53<12:23:56,  1.75s/it]
 62%|██████▏   | 42254/67700 [25:23:55<12:14:34,  1.73s/it]
 62%|██████▏   | 42255/67700 [25:23:56<12:06:00,  1.71s/it]
 62%|██████▏   | 42256/67700 [25:23:58<11:57:50,  1.69s/it]
 62%|██████▏   | 42257/67700 [25:24:00<11:47:31,  1.67s/it]
 62%|██████▏   | 42258/67700 [25:24:01<11:34:08,  1.64s/it]
 62%|██████▏   | 42259/67700 [25:24:03<11:24:14,  1.61s/it]
 62%|██████▏   | 42260/67700 [25:24:04<11:12:15,  1.59s/it]
 62%|██████▏   | 42261/67700 [25:24:06<11:00:41,  1.56s/it]
 62%|██████▏   | 42262/67700 [25:24:07<10:50:11,  1.53s/it]
 62%|██████▏   | 42263/67700 [25:24:09<10:38:59,  1.51s/it]
 62%|██████▏   | 42264/67700 [25:24:10<10:28:04,  1.48s/it]
 62%|██████▏   | 42265/67700 [25:24:11<10:15:29,  1.45s/it]
 62%|██████▏   | 42266/67700 [25:24:13<10:06:05,  1.43s/it]
 62%|██████▏   | 42267/67700 [25:24:14<9:46:47,  1.38s/it] 
 62%|██████▏   | 42268/67700 [25:24:15<9:27:26,  1.34s/it]
 62%|██████▏   | 42269/67700 [25:24:17<9:11:59,  1.30s/it]
 62%|██████▏   | 42270/67700 [25:24:18<8:59:24,  1.27s/it]
 62%|██████▏   | 42271/67700 [25:24:19<8:45:05,  1.24s/it]
 62%|██████▏   | 42272/67700 [25:24:20<8:30:00,  1.20s/it]
 62%|██████▏   | 42273/67700 [25:24:21<8:10:10,  1.16s/it]
 62%|██████▏   | 42274/67700 [25:24:22<7:45:11,  1.10s/it]
 62%|██████▏   | 42275/67700 [25:24:25<10:51:25,  1.54s/it]
 62%|██████▏   | 42276/67700 [25:24:27<12:57:18,  1.83s/it]
 62%|██████▏   | 42277/67700 [25:24:30<14:21:55,  2.03s/it]
 62%|██████▏   | 42278/67700 [25:24:32<15:15:18,  2.16s/it]
 62%|██████▏   | 42279/67700 [25:24:34<15:39:18,  2.22s/it]
 62%|██████▏   | 42280/67700 [25:24:37<15:48:16,  2.24s/it]
 62%|██████▏   | 42281/67700 [25:24:39<15:51:19,  2.25s/it]
 62%|██████▏   | 42282/67700 [25:24:41<15:51:42,  2.25s/it]
 62%|██████▏   | 42283/67700 [25:24:43<15:48:14,  2.24s/it]
 62%|██████▏   | 42284/67700 [25:24:46<15:38:41,  2.22s/it]
 62%|██████▏   | 42285/67700 [25:24:48<15:30:46,  2.20s/it]
 62%|██████▏   | 42286/67700 [25:24:50<15:33:37,  2.20s/it]
 62%|██████▏   | 42287/67700 [25:24:52<15:21:05,  2.17s/it]
 62%|██████▏   | 42288/67700 [25:24:54<15:05:59,  2.14s/it]
 62%|██████▏   | 42289/67700 [25:24:56<14:54:37,  2.11s/it]
 62%|██████▏   | 42290/67700 [25:24:58<14:40:51,  2.08s/it]
 62%|██████▏   | 42291/67700 [25:25:00<14:33:55,  2.06s/it]
 62%|██████▏   | 42292/67700 [25:25:02<14:21:30,  2.03s/it]
 62%|██████▏   | 42293/67700 [25:25:04<14:09:56,  2.01s/it]
 62%|██████▏   | 42294/67700 [25:25:06<14:02:14,  1.99s/it]
 62%|██████▏   | 42295/67700 [25:25:08<13:49:36,  1.96s/it]
 62%|██████▏   | 42296/67700 [25:25:10<13:37:16,  1.93s/it]
 62%|██████▏   | 42297/67700 [25:25:12<13:24:34,  1.90s/it]
 62%|██████▏   | 42298/67700 [25:25:14<13:16:12,  1.88s/it]
 62%|██████▏   | 42299/67700 [25:25:15<13:07:38,  1.86s/it]
 62%|██████▏   | 42300/67700 [25:25:17<12:53:33,  1.83s/it]
                                                           
 62%|██████▏   | 42300/67700 [25:25:17<12:53:33,  1.83s/it]
 62%|██████▏   | 42301/67700 [25:25:19<12:43:37,  1.80s/it]
 62%|██████▏   | 42302/67700 [25:25:21<12:32:33,  1.78s/it]
 62%|██████▏   | 42303/67700 [25:25:22<12:24:06,  1.76s/it]
 62%|██████▏   | 42304/67700 [25:25:24<12:09:47,  1.72s/it]
 62%|██████▏   | 42305/67700 [25:25:26<12:00:41,  1.70s/it]
 62%|██████▏   | 42306/67700 [25:25:27<11:50:09,  1.68s/it]
 62%|██████▏   | 42307/67700 [25:25:29<11:40:33,  1.66s/it]
 62%|██████▏   | 42308/67700 [25:25:30<11:26:20,  1.62s/it]
 62%|██████▏   | 42309/67700 [25:25:32<11:17:32,  1.60s/it]
 62%|██████▏   | 42310/67700 [25:25:33<11:05:47,  1.57s/it]
 62%|██████▏   | 42311/67700 [25:25:35<10:50:58,  1.54s/it]
 62%|██████▏   | 42312/67700 [25:25:36<10:38:27,  1.51s/it]
 63%|██████▎   | 42313/67700 [25:25:38<10:28:17,  1.48s/it]
 63%|██████▎   | 42314/67700 [25:25:39<10:17:35,  1.46s/it]
 63%|██████▎   | 42315/67700 [25:25:40<10:08:22,  1.44s/it]
 63%|██████▎   | 42316/67700 [25:25:42<9:59:52,  1.42s/it] 
 63%|██████▎   | 42317/67700 [25:25:43<9:44:01,  1.38s/it]
 63%|██████▎   | 42318/67700 [25:25:44<9:25:48,  1.34s/it]
 63%|██████▎   | 42319/67700 [25:25:46<9:07:55,  1.30s/it]
 63%|██████▎   | 42320/67700 [25:25:47<8:53:02,  1.26s/it]
 63%|██████▎   | 42321/67700 [25:25:48<8:42:01,  1.23s/it]
 63%|██████▎   | 42322/67700 [25:25:49<8:33:40,  1.21s/it]
 63%|██████▎   | 42323/67700 [25:25:50<8:09:35,  1.16s/it]
 63%|██████▎   | 42324/67700 [25:25:51<7:45:03,  1.10s/it]
 63%|██████▎   | 42325/67700 [25:25:54<10:52:39,  1.54s/it]
 63%|██████▎   | 42326/67700 [25:25:56<12:57:44,  1.84s/it]
 63%|██████▎   | 42327/67700 [25:25:59<14:21:22,  2.04s/it]
 63%|██████▎   | 42328/67700 [25:26:01<15:17:07,  2.17s/it]
 63%|██████▎   | 42329/67700 [25:26:04<15:39:44,  2.22s/it]
 63%|██████▎   | 42330/67700 [25:26:06<15:48:48,  2.24s/it]
 63%|██████▎   | 42331/67700 [25:26:08<15:51:51,  2.25s/it]
 63%|██████▎   | 42332/67700 [25:26:10<15:49:47,  2.25s/it]
 63%|██████▎   | 42333/67700 [25:26:13<15:47:20,  2.24s/it]
 63%|██████▎   | 42334/67700 [25:26:15<15:51:29,  2.25s/it]
 63%|██████▎   | 42335/67700 [25:26:17<15:38:20,  2.22s/it]
 63%|██████▎   | 42336/67700 [25:26:19<15:25:38,  2.19s/it]
 63%|██████▎   | 42337/67700 [25:26:21<15:19:18,  2.17s/it]
 63%|██████▎   | 42338/67700 [25:26:23<15:02:35,  2.14s/it]
 63%|██████▎   | 42339/67700 [25:26:25<14:50:11,  2.11s/it]
 63%|██████▎   | 42340/67700 [25:26:27<14:33:57,  2.07s/it]
 63%|██████▎   | 42341/67700 [25:26:29<14:24:37,  2.05s/it]
 63%|██████▎   | 42342/67700 [25:26:31<14:09:27,  2.01s/it]
 63%|██████▎   | 42343/67700 [25:26:33<13:56:05,  1.98s/it]
 63%|██████▎   | 42344/67700 [25:26:35<13:42:16,  1.95s/it]
 63%|██████▎   | 42345/67700 [25:26:37<13:35:46,  1.93s/it]
 63%|██████▎   | 42346/67700 [25:26:39<13:25:12,  1.91s/it]
 63%|██████▎   | 42347/67700 [25:26:41<13:17:47,  1.89s/it]
 63%|██████▎   | 42348/67700 [25:26:42<13:07:29,  1.86s/it]
 63%|██████▎   | 42349/67700 [25:26:44<12:55:17,  1.83s/it]
 63%|██████▎   | 42350/67700 [25:26:46<12:43:26,  1.81s/it]
 63%|██████▎   | 42351/67700 [25:26:48<12:33:43,  1.78s/it]
 63%|██████▎   | 42352/67700 [25:26:49<12:23:07,  1.76s/it]
 63%|██████▎   | 42353/67700 [25:26:51<12:11:19,  1.73s/it]
 63%|██████▎   | 42354/67700 [25:26:53<11:56:42,  1.70s/it]
 63%|██████▎   | 42355/67700 [25:26:54<11:48:27,  1.68s/it]
 63%|██████▎   | 42356/67700 [25:26:56<11:37:39,  1.65s/it]
 63%|██████▎   | 42357/67700 [25:26:57<11:24:51,  1.62s/it]
 63%|██████▎   | 42358/67700 [25:26:59<11:12:35,  1.59s/it]
 63%|██████▎   | 42359/67700 [25:27:00<11:01:26,  1.57s/it]
 63%|██████▎   | 42360/67700 [25:27:02<10:50:41,  1.54s/it]
 63%|██████▎   | 42361/67700 [25:27:03<10:40:22,  1.52s/it]
 63%|██████▎   | 42362/67700 [25:27:05<10:30:55,  1.49s/it]
 63%|██████▎   | 42363/67700 [25:27:06<10:24:32,  1.48s/it]
 63%|██████▎   | 42364/67700 [25:27:08<10:12:03,  1.45s/it]
 63%|██████▎   | 42365/67700 [25:27:09<10:01:13,  1.42s/it]
 63%|██████▎   | 42366/67700 [25:27:10<9:45:29,  1.39s/it] 
 63%|██████▎   | 42367/67700 [25:27:12<9:30:05,  1.35s/it]
 63%|██████▎   | 42368/67700 [25:27:13<9:17:28,  1.32s/it]
 63%|██████▎   | 42369/67700 [25:27:14<9:05:46,  1.29s/it]
 63%|██████▎   | 42370/67700 [25:27:15<8:50:20,  1.26s/it]
 63%|██████▎   | 42371/67700 [25:27:16<8:37:01,  1.22s/it]
 63%|██████▎   | 42372/67700 [25:27:17<8:23:33,  1.19s/it]
 63%|██████▎   | 42373/67700 [25:27:18<8:00:39,  1.14s/it]
 63%|██████▎   | 42374/67700 [25:27:19<7:36:22,  1.08s/it]
 63%|██████▎   | 42375/67700 [25:27:22<10:55:03,  1.55s/it]
 63%|██████▎   | 42376/67700 [25:27:25<13:10:03,  1.87s/it]
 63%|██████▎   | 42377/67700 [25:27:27<14:38:27,  2.08s/it]
 63%|██████▎   | 42378/67700 [25:27:30<15:32:35,  2.21s/it]
 63%|██████▎   | 42379/67700 [25:27:32<16:04:43,  2.29s/it]
 63%|██████▎   | 42380/67700 [25:27:35<16:11:19,  2.30s/it]
 63%|██████▎   | 42381/67700 [25:27:37<16:11:59,  2.30s/it]
 63%|██████▎   | 42382/67700 [25:27:39<16:10:58,  2.30s/it]
 63%|██████▎   | 42383/67700 [25:27:41<16:07:42,  2.29s/it]
 63%|██████▎   | 42384/67700 [25:27:44<15:50:53,  2.25s/it]
 63%|██████▎   | 42385/67700 [25:27:46<15:52:44,  2.26s/it]
 63%|██████▎   | 42386/67700 [25:27:48<15:37:57,  2.22s/it]
 63%|██████▎   | 42387/67700 [25:27:50<15:22:09,  2.19s/it]
 63%|██████▎   | 42388/67700 [25:27:52<15:06:55,  2.15s/it]
 63%|██████▎   | 42389/67700 [25:27:54<14:48:22,  2.11s/it]
 63%|██████▎   | 42390/67700 [25:27:56<14:35:34,  2.08s/it]
 63%|██████▎   | 42391/67700 [25:27:58<14:24:10,  2.05s/it]
 63%|██████▎   | 42392/67700 [25:28:00<14:09:12,  2.01s/it]
 63%|██████▎   | 42393/67700 [25:28:02<13:55:30,  1.98s/it]
 63%|██████▎   | 42394/67700 [25:28:04<13:42:28,  1.95s/it]
 63%|██████▎   | 42395/67700 [25:28:06<13:37:08,  1.94s/it]
 63%|██████▎   | 42396/67700 [25:28:08<13:18:55,  1.89s/it]
 63%|██████▎   | 42397/67700 [25:28:09<13:12:12,  1.88s/it]
 63%|██████▎   | 42398/67700 [25:28:11<12:58:56,  1.85s/it]
 63%|██████▎   | 42399/67700 [25:28:13<12:47:53,  1.82s/it]
 63%|██████▎   | 42400/67700 [25:28:15<12:38:32,  1.80s/it]
                                                           
 63%|██████▎   | 42400/67700 [25:28:15<12:38:32,  1.80s/it]
 63%|██████▎   | 42401/67700 [25:28:16<12:27:32,  1.77s/it]
 63%|██████▎   | 42402/67700 [25:28:18<12:18:20,  1.75s/it]
 63%|██████▎   | 42403/67700 [25:28:20<12:08:08,  1.73s/it]
 63%|██████▎   | 42404/67700 [25:28:21<12:01:45,  1.71s/it]
 63%|██████▎   | 42405/67700 [25:28:23<11:50:19,  1.68s/it]
 63%|██████▎   | 42406/67700 [25:28:25<11:41:23,  1.66s/it]
 63%|██████▎   | 42407/67700 [25:28:26<11:30:54,  1.64s/it]
 63%|██████▎   | 42408/67700 [25:28:28<11:23:17,  1.62s/it]
 63%|██████▎   | 42409/67700 [25:28:29<11:10:54,  1.59s/it]
 63%|██████▎   | 42410/67700 [25:28:31<11:03:25,  1.57s/it]
 63%|██████▎   | 42411/67700 [25:28:32<10:51:16,  1.55s/it]
 63%|██████▎   | 42412/67700 [25:28:34<10:43:13,  1.53s/it]
 63%|██████▎   | 42413/67700 [25:28:35<10:32:17,  1.50s/it]
 63%|██████▎   | 42414/67700 [25:28:37<10:22:46,  1.48s/it]
 63%|██████▎   | 42415/67700 [25:28:38<10:08:34,  1.44s/it]
 63%|██████▎   | 42416/67700 [25:28:39<9:57:05,  1.42s/it] 
 63%|██████▎   | 42417/67700 [25:28:41<9:40:41,  1.38s/it]
 63%|██████▎   | 42418/67700 [25:28:42<9:30:38,  1.35s/it]
 63%|██████▎   | 42419/67700 [25:28:43<9:18:20,  1.33s/it]
 63%|██████▎   | 42420/67700 [25:28:45<9:05:18,  1.29s/it]
 63%|██████▎   | 42421/67700 [25:28:46<8:51:10,  1.26s/it]
 63%|██████▎   | 42422/67700 [25:28:47<8:34:58,  1.22s/it]
 63%|██████▎   | 42423/67700 [25:28:48<8:11:58,  1.17s/it]
 63%|██████▎   | 42424/67700 [25:28:49<7:46:06,  1.11s/it]
 63%|██████▎   | 42425/67700 [25:28:51<10:51:26,  1.55s/it]
 63%|██████▎   | 42426/67700 [25:28:54<13:01:22,  1.85s/it]
 63%|██████▎   | 42427/67700 [25:28:57<14:32:08,  2.07s/it]
 63%|██████▎   | 42428/67700 [25:28:59<15:19:09,  2.18s/it]
 63%|██████▎   | 42429/67700 [25:29:01<15:36:57,  2.22s/it]
 63%|██████▎   | 42430/67700 [25:29:04<15:43:48,  2.24s/it]
 63%|██████▎   | 42431/67700 [25:29:06<15:48:57,  2.25s/it]
 63%|██████▎   | 42432/67700 [25:29:08<15:47:35,  2.25s/it]
 63%|██████▎   | 42433/67700 [25:29:10<15:42:14,  2.24s/it]
 63%|██████▎   | 42434/67700 [25:29:13<15:39:40,  2.23s/it]
 63%|██████▎   | 42435/67700 [25:29:15<15:30:38,  2.21s/it]
 63%|██████▎   | 42436/67700 [25:29:17<15:21:46,  2.19s/it]
 63%|██████▎   | 42437/67700 [25:29:19<15:11:57,  2.17s/it]
 63%|██████▎   | 42438/67700 [25:29:21<15:04:10,  2.15s/it]
 63%|██████▎   | 42439/67700 [25:29:23<14:49:38,  2.11s/it]
 63%|██████▎   | 42440/67700 [25:29:25<14:41:29,  2.09s/it]
 63%|██████▎   | 42441/67700 [25:29:27<14:28:25,  2.06s/it]
 63%|██████▎   | 42442/67700 [25:29:29<14:23:34,  2.05s/it]
 63%|██████▎   | 42443/67700 [25:29:31<14:10:46,  2.02s/it]
 63%|██████▎   | 42444/67700 [25:29:33<14:02:31,  2.00s/it]
 63%|██████▎   | 42445/67700 [25:29:35<13:44:22,  1.96s/it]
 63%|██████▎   | 42446/67700 [25:29:37<13:31:12,  1.93s/it]
 63%|██████▎   | 42447/67700 [25:29:39<13:14:02,  1.89s/it]
 63%|██████▎   | 42448/67700 [25:29:40<13:02:01,  1.86s/it]
 63%|██████▎   | 42449/67700 [25:29:42<12:48:51,  1.83s/it]
 63%|██████▎   | 42450/67700 [25:29:44<12:39:05,  1.80s/it]
 63%|██████▎   | 42451/67700 [25:29:46<12:30:33,  1.78s/it]
 63%|██████▎   | 42452/67700 [25:29:47<12:26:25,  1.77s/it]
 63%|██████▎   | 42453/67700 [25:29:49<12:14:53,  1.75s/it]
 63%|██████▎   | 42454/67700 [25:29:51<12:05:59,  1.73s/it]
 63%|██████▎   | 42455/67700 [25:29:52<11:54:21,  1.70s/it]
 63%|██████▎   | 42456/67700 [25:29:54<11:48:02,  1.68s/it]
 63%|██████▎   | 42457/67700 [25:29:56<11:32:43,  1.65s/it]
 63%|██████▎   | 42458/67700 [25:29:57<11:19:50,  1.62s/it]
 63%|██████▎   | 42459/67700 [25:29:59<11:11:03,  1.60s/it]
 63%|██████▎   | 42460/67700 [25:30:00<11:03:17,  1.58s/it]
 63%|██████▎   | 42461/67700 [25:30:02<10:53:57,  1.55s/it]
 63%|██████▎   | 42462/67700 [25:30:03<10:43:05,  1.53s/it]
 63%|██████▎   | 42463/67700 [25:30:05<10:30:58,  1.50s/it]
 63%|██████▎   | 42464/67700 [25:30:06<10:18:04,  1.47s/it]
 63%|██████▎   | 42465/67700 [25:30:07<10:11:06,  1.45s/it]
 63%|██████▎   | 42466/67700 [25:30:09<9:57:45,  1.42s/it] 
 63%|██████▎   | 42467/67700 [25:30:10<9:42:15,  1.38s/it]
 63%|██████▎   | 42468/67700 [25:30:11<9:26:59,  1.35s/it]
 63%|██████▎   | 42469/67700 [25:30:13<9:12:59,  1.32s/it]
 63%|██████▎   | 42470/67700 [25:30:14<8:56:45,  1.28s/it]
 63%|██████▎   | 42471/67700 [25:30:15<8:39:59,  1.24s/it]
 63%|██████▎   | 42472/67700 [25:30:16<8:20:01,  1.19s/it]
 63%|██████▎   | 42473/67700 [25:30:17<7:59:08,  1.14s/it]
 63%|██████▎   | 42474/67700 [25:30:18<7:35:32,  1.08s/it]
 63%|██████▎   | 42475/67700 [25:30:21<10:52:35,  1.55s/it]
 63%|██████▎   | 42476/67700 [25:30:23<12:55:55,  1.85s/it]
 63%|██████▎   | 42477/67700 [25:30:26<14:19:42,  2.05s/it]
 63%|██████▎   | 42478/67700 [25:30:28<15:12:17,  2.17s/it]
 63%|██████▎   | 42479/67700 [25:30:30<15:30:38,  2.21s/it]
 63%|██████▎   | 42480/67700 [25:30:33<15:37:56,  2.23s/it]
 63%|██████▎   | 42481/67700 [25:30:35<15:42:29,  2.24s/it]
 63%|██████▎   | 42482/67700 [25:30:37<15:37:11,  2.23s/it]
 63%|██████▎   | 42483/67700 [25:30:39<15:32:40,  2.22s/it]
 63%|██████▎   | 42484/67700 [25:30:42<15:27:21,  2.21s/it]
 63%|██████▎   | 42485/67700 [25:30:44<15:23:52,  2.20s/it]
 63%|██████▎   | 42486/67700 [25:30:46<15:07:06,  2.16s/it]
 63%|██████▎   | 42487/67700 [25:30:48<14:57:41,  2.14s/it]
 63%|██████▎   | 42488/67700 [25:30:50<14:38:51,  2.09s/it]
 63%|██████▎   | 42489/67700 [25:30:52<14:30:23,  2.07s/it]
 63%|██████▎   | 42490/67700 [25:30:54<14:17:54,  2.04s/it]
 63%|██████▎   | 42491/67700 [25:30:56<14:12:26,  2.03s/it]
 63%|██████▎   | 42492/67700 [25:30:58<13:58:14,  2.00s/it]
 63%|██████▎   | 42493/67700 [25:31:00<13:51:41,  1.98s/it]
 63%|██████▎   | 42494/67700 [25:31:02<13:41:12,  1.95s/it]
 63%|██████▎   | 42495/67700 [25:31:03<13:27:59,  1.92s/it]
 63%|██████▎   | 42496/67700 [25:31:05<13:18:32,  1.90s/it]
 63%|██████▎   | 42497/67700 [25:31:07<13:13:26,  1.89s/it]
 63%|██████▎   | 42498/67700 [25:31:09<13:04:01,  1.87s/it]
 63%|██████▎   | 42499/67700 [25:31:11<12:50:22,  1.83s/it]
 63%|██████▎   | 42500/67700 [25:31:13<12:45:46,  1.82s/it]
                                                           
 63%|██████▎   | 42500/67700 [25:31:13<12:45:46,  1.82s/it]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+***** Running Evaluation *****
+  Num examples = 2021
+  Batch size = 8
+{'eval_loss': 0.8499256372451782, 'eval_wer': 0.8743196437407225, 'eval_cer': 0.22421200562136118, 'eval_runtime': 115.1721, 'eval_samples_per_second': 17.548, 'eval_steps_per_second': 2.197, 'epoch': 62.04}
+{'loss': 1.5818, 'learning_rate': 2.9247716894977165e-05, 'epoch': 62.19}
+{'loss': 1.5852, 'learning_rate': 2.9133561643835613e-05, 'epoch': 62.33}
+{'loss': 1.6057, 'learning_rate': 2.901940639269406e-05, 'epoch': 62.48}
+{'loss': 1.5922, 'learning_rate': 2.8905251141552506e-05, 'epoch': 62.63}
+{'loss': 1.6275, 'learning_rate': 2.8791095890410954e-05, 'epoch': 62.78}
+
+
  0%|          | 0/253 [00:00<?, ?it/s]
+
  1%|          | 2/253 [00:00<00:42,  5.95it/s]
+
  1%|          | 3/253 [00:00<00:58,  4.28it/s]
+
  2%|▏         | 4/253 [00:00<01:03,  3.92it/s]
+
  2%|▏         | 5/253 [00:01<01:10,  3.52it/s]
+
  2%|▏         | 6/253 [00:01<01:12,  3.41it/s]
+
  3%|▎         | 7/253 [00:01<01:17,  3.19it/s]
+
  3%|▎         | 8/253 [00:02<01:19,  3.10it/s]
+
  4%|▎         | 9/253 [00:02<01:20,  3.05it/s]
+
  4%|▍         | 10/253 [00:02<01:20,  3.00it/s]
+
  4%|▍         | 11/253 [00:03<01:21,  2.96it/s]
+
  5%|▍         | 12/253 [00:03<01:19,  3.02it/s]
+
  5%|▌         | 13/253 [00:04<01:21,  2.95it/s]
+
  6%|▌         | 14/253 [00:04<01:17,  3.09it/s]
+
  6%|▌         | 15/253 [00:04<01:20,  2.96it/s]
+
  6%|▋         | 16/253 [00:04<01:18,  3.03it/s]
+
  7%|▋         | 17/253 [00:05<01:20,  2.93it/s]
+
  7%|▋         | 18/253 [00:05<01:18,  2.99it/s]
+
  8%|▊         | 19/253 [00:05<01:16,  3.07it/s]
+
  8%|▊         | 20/253 [00:06<01:13,  3.16it/s]
+
  8%|▊         | 21/253 [00:06<01:15,  3.07it/s]
+
  9%|▊         | 22/253 [00:06<01:16,  3.02it/s]
+
  9%|▉         | 23/253 [00:07<01:18,  2.95it/s]
+
  9%|▉         | 24/253 [00:07<01:16,  2.98it/s]
+
 10%|▉         | 25/253 [00:07<01:16,  2.97it/s]
+
 10%|█         | 26/253 [00:08<01:16,  2.98it/s]
+
 11%|█         | 27/253 [00:08<01:17,  2.93it/s]
+
 11%|█         | 28/253 [00:08<01:14,  3.00it/s]
+
 11%|█▏        | 29/253 [00:09<01:15,  2.96it/s]
+
 12%|█▏        | 30/253 [00:09<01:17,  2.88it/s]
+
 12%|█▏        | 31/253 [00:10<01:15,  2.92it/s]
+
 13%|█▎        | 32/253 [00:10<01:17,  2.85it/s]
+
 13%|█▎        | 33/253 [00:10<01:16,  2.89it/s]
+
 13%|█▎        | 34/253 [00:11<01:16,  2.87it/s]
+
 14%|█▍        | 35/253 [00:11<01:14,  2.92it/s]
+
 14%|█▍        | 36/253 [00:11<01:11,  3.04it/s]
+
 15%|█▍        | 37/253 [00:12<01:10,  3.06it/s]
+
 15%|█▌        | 38/253 [00:12<01:12,  2.95it/s]
+
 15%|█▌        | 39/253 [00:12<01:11,  3.00it/s]
+
 16%|█▌        | 40/253 [00:13<01:08,  3.11it/s]
+
 16%|█▌        | 41/253 [00:13<01:09,  3.06it/s]
+
 17%|█▋        | 42/253 [00:13<01:09,  3.05it/s]
+
 17%|█▋        | 43/253 [00:13<01:06,  3.17it/s]
+
 17%|█▋        | 44/253 [00:14<01:07,  3.09it/s]
+
 18%|█▊        | 45/253 [00:14<01:07,  3.07it/s]
+
 18%|█▊        | 46/253 [00:14<01:04,  3.20it/s]
+
 19%|█▊        | 47/253 [00:15<01:06,  3.11it/s]
+
 19%|█▉        | 48/253 [00:15<01:06,  3.09it/s]
+
 19%|█▉        | 49/253 [00:15<01:05,  3.13it/s]
+
 20%|█▉        | 50/253 [00:16<01:05,  3.12it/s]
+
 20%|██        | 51/253 [00:16<01:06,  3.02it/s]
+
 21%|██        | 52/253 [00:16<01:06,  3.00it/s]
+
 21%|██        | 53/253 [00:17<01:06,  3.02it/s]
+
 21%|██▏       | 54/253 [00:17<01:06,  3.01it/s]
+
 22%|██▏       | 55/253 [00:17<01:03,  3.13it/s]
+
 22%|██▏       | 56/253 [00:18<01:03,  3.09it/s]
+
 23%|██▎       | 57/253 [00:18<01:01,  3.20it/s]
+
 23%|██▎       | 58/253 [00:18<01:01,  3.17it/s]
+
 23%|██▎       | 59/253 [00:19<01:02,  3.12it/s]
+
 24%|██▎       | 60/253 [00:19<01:00,  3.18it/s]
+
 24%|██▍       | 61/253 [00:19<01:01,  3.10it/s]
+
 25%|██▍       | 62/253 [00:20<01:00,  3.18it/s]
+
 25%|██▍       | 63/253 [00:20<01:00,  3.13it/s]
+
 25%|██▌       | 64/253 [00:20<01:00,  3.13it/s]
+
 26%|██▌       | 65/253 [00:21<01:00,  3.09it/s]
+
 26%|██▌       | 66/253 [00:21<01:01,  3.02it/s]
+
 26%|██▋       | 67/253 [00:21<01:03,  2.93it/s]
+
 27%|██▋       | 68/253 [00:22<01:01,  3.03it/s]
+
 27%|██▋       | 69/253 [00:22<00:58,  3.13it/s]
+
 28%|██▊       | 70/253 [00:22<00:56,  3.23it/s]
+
 28%|██▊       | 71/253 [00:23<00:59,  3.07it/s]
+
 28%|██▊       | 72/253 [00:23<00:56,  3.19it/s]
+
 29%|██▉       | 73/253 [00:23<00:55,  3.24it/s]
+
 29%|██▉       | 74/253 [00:23<00:58,  3.07it/s]
+
 30%|██▉       | 75/253 [00:24<00:58,  3.03it/s]
+
 30%|███       | 76/253 [00:24<00:58,  3.02it/s]
+
 30%|███       | 77/253 [00:24<00:57,  3.05it/s]
+
 31%|███       | 78/253 [00:25<00:58,  2.99it/s]
+
 31%|███       | 79/253 [00:25<00:58,  2.95it/s]
+
 32%|███▏      | 80/253 [00:26<00:59,  2.91it/s]
+
 32%|███▏      | 81/253 [00:26<00:58,  2.93it/s]
+
 32%|███▏      | 82/253 [00:26<00:54,  3.12it/s]
+
 33%|███▎      | 83/253 [00:26<00:53,  3.17it/s]
+
 33%|███▎      | 84/253 [00:27<00:55,  3.07it/s]
+
 34%|███▎      | 85/253 [00:27<00:55,  3.01it/s]
+
 34%|███▍      | 86/253 [00:27<00:53,  3.13it/s]
+
 34%|███▍      | 87/253 [00:28<00:53,  3.10it/s]
+
 35%|███▍      | 88/253 [00:28<00:50,  3.24it/s]
+
 35%|███▌      | 89/253 [00:28<00:53,  3.09it/s]
+
 36%|███▌      | 90/253 [00:29<00:52,  3.08it/s]
+
 36%|███▌      | 91/253 [00:29<00:51,  3.13it/s]
+
 36%|███▋      | 92/253 [00:29<00:52,  3.08it/s]
+
 37%|███▋      | 93/253 [00:30<00:53,  3.01it/s]
+
 37%|███▋      | 94/253 [00:30<00:51,  3.06it/s]
+
 38%|███▊      | 95/253 [00:30<00:50,  3.14it/s]
+
 38%|███▊      | 96/253 [00:31<00:49,  3.15it/s]
+
 38%|███▊      | 97/253 [00:31<00:51,  3.05it/s]
+
 39%|███▊      | 98/253 [00:31<00:50,  3.07it/s]
+
 39%|███▉      | 99/253 [00:32<00:51,  2.98it/s]
+
 40%|███▉      | 100/253 [00:32<00:50,  3.05it/s]
+
 40%|███▉      | 101/253 [00:32<00:48,  3.12it/s]
+
 40%|████      | 102/253 [00:33<00:48,  3.12it/s]
+
 41%|████      | 103/253 [00:33<00:49,  3.03it/s]
+
 41%|████      | 104/253 [00:33<00:48,  3.07it/s]
+
 42%|████▏     | 105/253 [00:34<00:48,  3.06it/s]
+
 42%|████▏     | 106/253 [00:34<00:46,  3.17it/s]
+
 42%|████▏     | 107/253 [00:34<00:42,  3.41it/s]
+
 43%|████▎     | 108/253 [00:34<00:44,  3.24it/s]
+
 43%|████▎     | 109/253 [00:35<00:42,  3.36it/s]
+
 43%|████▎     | 110/253 [00:35<00:43,  3.32it/s]
+
 44%|████▍     | 111/253 [00:35<00:43,  3.23it/s]
+
 44%|████▍     | 112/253 [00:36<00:43,  3.22it/s]
+
 45%|████▍     | 113/253 [00:36<00:43,  3.20it/s]
+
 45%|████▌     | 114/253 [00:36<00:45,  3.08it/s]
+
 45%|████▌     | 115/253 [00:37<00:43,  3.15it/s]
+
 46%|████▌     | 116/253 [00:37<00:44,  3.07it/s]
+
 46%|████▌     | 117/253 [00:37<00:44,  3.08it/s]
+
 47%|████▋     | 118/253 [00:38<00:42,  3.19it/s]
+
 47%|████▋     | 119/253 [00:38<00:41,  3.21it/s]
+
 47%|████▋     | 120/253 [00:38<00:43,  3.07it/s]
+
 48%|████▊     | 121/253 [00:39<00:43,  3.07it/s]
+
 48%|████▊     | 122/253 [00:39<00:40,  3.26it/s]
+
 49%|████▊     | 123/253 [00:39<00:40,  3.21it/s]
+
 49%|████▉     | 124/253 [00:40<00:41,  3.12it/s]
+
 49%|████▉     | 125/253 [00:40<00:41,  3.08it/s]
+
 50%|████▉     | 126/253 [00:40<00:41,  3.06it/s]
+
 50%|█████     | 127/253 [00:41<00:42,  3.00it/s]
+
 51%|█████     | 128/253 [00:41<00:41,  3.03it/s]
+
 51%|█████     | 129/253 [00:41<00:42,  2.92it/s]
+
 51%|█████▏    | 130/253 [00:42<00:42,  2.89it/s]
+
 52%|█████▏    | 131/253 [00:42<00:41,  2.96it/s]
+
 52%|█████▏    | 132/253 [00:42<00:39,  3.07it/s]
+
 53%|█████▎    | 133/253 [00:43<00:39,  3.06it/s]
+
 53%|█████▎    | 134/253 [00:43<00:38,  3.08it/s]
+
 53%|█████▎    | 135/253 [00:43<00:38,  3.06it/s]
+
 54%|█████▍    | 136/253 [00:44<00:37,  3.10it/s]
+
 54%|█████▍    | 137/253 [00:44<00:37,  3.06it/s]
+
 55%|█████▍    | 138/253 [00:44<00:37,  3.06it/s]
+
 55%|█████▍    | 139/253 [00:45<00:37,  3.04it/s]
+
 55%|█████▌    | 140/253 [00:45<00:36,  3.09it/s]
+
 56%|█████▌    | 141/253 [00:45<00:36,  3.06it/s]
+
 56%|█████▌    | 142/253 [00:45<00:35,  3.15it/s]
+
 57%|█████▋    | 143/253 [00:46<00:36,  3.02it/s]
+
 57%|█████▋    | 144/253 [00:46<00:35,  3.11it/s]
+
 57%|█████▋    | 145/253 [00:46<00:34,  3.10it/s]
+
 58%|█████▊    | 146/253 [00:47<00:34,  3.10it/s]
+
 58%|█████▊    | 147/253 [00:47<00:34,  3.04it/s]
+
 58%|█████▊    | 148/253 [00:47<00:33,  3.10it/s]
+
 59%|█████▉    | 149/253 [00:48<00:34,  3.03it/s]
+
 59%|█████▉    | 150/253 [00:48<00:33,  3.11it/s]
+
 60%|█████▉    | 151/253 [00:48<00:32,  3.16it/s]
+
 60%|██████    | 152/253 [00:49<00:32,  3.08it/s]
+
 60%|██████    | 153/253 [00:49<00:33,  3.00it/s]
+
 61%|██████    | 154/253 [00:49<00:32,  3.06it/s]
+
 61%|██████▏   | 155/253 [00:50<00:32,  3.06it/s]
+
 62%|██████▏   | 156/253 [00:50<00:31,  3.06it/s]
+
 62%|██████▏   | 157/253 [00:50<00:30,  3.15it/s]
+
 62%|██████▏   | 158/253 [00:51<00:30,  3.10it/s]
+
 63%|██████▎   | 159/253 [00:51<00:29,  3.24it/s]
+
 63%|██████▎   | 160/253 [00:51<00:28,  3.22it/s]
+
 64%|██████▎   | 161/253 [00:52<00:29,  3.09it/s]
+
 64%|██████▍   | 162/253 [00:52<00:29,  3.13it/s]
+
 64%|██████▍   | 163/253 [00:52<00:28,  3.16it/s]
+
 65%|██████▍   | 164/253 [00:53<00:27,  3.18it/s]
+
 65%|██████▌   | 165/253 [00:53<00:27,  3.15it/s]
+
 66%|██████▌   | 166/253 [00:53<00:27,  3.15it/s]
+
 66%|██████▌   | 167/253 [00:54<00:27,  3.07it/s]
+
 66%|██████▋   | 168/253 [00:54<00:26,  3.17it/s]
+
 67%|██████▋   | 169/253 [00:54<00:26,  3.21it/s]
+
 67%|██████▋   | 170/253 [00:54<00:26,  3.12it/s]
+
 68%|██████▊   | 171/253 [00:55<00:25,  3.22it/s]
+
 68%|██████▊   | 172/253 [00:55<00:24,  3.26it/s]
+
 68%|██████▊   | 173/253 [00:55<00:24,  3.33it/s]
+
 69%|██████▉   | 174/253 [00:56<00:27,  2.90it/s]
+
 69%|██████▉   | 175/253 [00:56<00:25,  3.06it/s]
+
 70%|██████▉   | 176/253 [00:56<00:23,  3.21it/s]
+
 70%|██████▉   | 177/253 [00:57<00:24,  3.12it/s]
+
 70%|███████   | 178/253 [00:57<00:23,  3.15it/s]
+
 71%|███████   | 179/253 [00:57<00:24,  3.07it/s]
+
 71%|███████   | 180/253 [00:58<00:24,  3.03it/s]
+
 72%|███████▏  | 181/253 [00:58<00:23,  3.07it/s]
+
 72%|███████▏  | 182/253 [00:58<00:23,  2.98it/s]
+
 72%|███████▏  | 183/253 [00:59<00:23,  3.02it/s]
+
 73%|███████▎  | 184/253 [00:59<00:23,  2.91it/s]
+
 73%|███████▎  | 185/253 [00:59<00:23,  2.91it/s]
+
 74%|███████▎  | 186/253 [01:00<00:23,  2.90it/s]
+
 74%|███████▍  | 187/253 [01:00<00:22,  2.94it/s]
+
 74%|███████▍  | 188/253 [01:00<00:21,  2.99it/s]
+
 75%|███████▍  | 189/253 [01:01<00:20,  3.12it/s]
+
 75%|███████▌  | 190/253 [01:01<00:20,  3.05it/s]
+
 75%|███████▌  | 191/253 [01:01<00:20,  2.97it/s]
+
 76%|███████▌  | 192/253 [01:02<00:20,  3.02it/s]
+
 76%|███████▋  | 193/253 [01:02<00:18,  3.16it/s]
+
 77%|███████▋  | 194/253 [01:02<00:18,  3.13it/s]
+
 77%|███████▋  | 195/253 [01:03<00:18,  3.16it/s]
+
 77%|███████▋  | 196/253 [01:03<00:18,  3.10it/s]
+
 78%|███████▊  | 197/253 [01:03<00:17,  3.20it/s]
+
 78%|███████▊  | 198/253 [01:04<00:17,  3.12it/s]
+
 79%|███████▊  | 199/253 [01:04<00:17,  3.01it/s]
+
 79%|███████▉  | 200/253 [01:04<00:18,  2.94it/s]
+
 79%|███████▉  | 201/253 [01:05<00:17,  2.98it/s]
+
 80%|███████▉  | 202/253 [01:05<00:17,  2.98it/s]
+
 80%|████████  | 203/253 [01:05<00:16,  3.04it/s]
+
 81%|████████  | 204/253 [01:06<00:16,  2.96it/s]
+
 81%|████████  | 205/253 [01:06<00:16,  2.95it/s]
+
 81%|████████▏ | 206/253 [01:06<00:16,  2.90it/s]
+
 82%|████████▏ | 207/253 [01:07<00:15,  2.92it/s]
+
 82%|████████▏ | 208/253 [01:07<00:15,  2.91it/s]
+
 83%|████████▎ | 209/253 [01:07<00:15,  2.92it/s]
+
 83%|████████▎ | 210/253 [01:08<00:14,  3.02it/s]
+
 83%|████████▎ | 211/253 [01:08<00:14,  2.94it/s]
+
 84%|████████▍ | 212/253 [01:08<00:14,  2.85it/s]
+
 84%|████████▍ | 213/253 [01:09<00:14,  2.85it/s]
+
 85%|████████▍ | 214/253 [01:09<00:13,  2.82it/s]
+
 85%|████████▍ | 215/253 [01:09<00:13,  2.87it/s]
+
 85%|████████▌ | 216/253 [01:10<00:12,  2.90it/s]
+
 86%|████████▌ | 217/253 [01:10<00:11,  3.00it/s]
+
 86%|████████▌ | 218/253 [01:10<00:11,  3.06it/s]
+
 87%|████████▋ | 219/253 [01:11<00:11,  3.03it/s]
+
 87%|████████▋ | 220/253 [01:11<00:11,  2.92it/s]
+
 87%|████████▋ | 221/253 [01:11<00:11,  2.90it/s]
+
 88%|████████▊ | 222/253 [01:12<00:10,  2.91it/s]
+
 88%|████████▊ | 223/253 [01:12<00:10,  2.93it/s]
+
 89%|████████▊ | 224/253 [01:12<00:09,  3.00it/s]
+
 89%|████████▉ | 225/253 [01:13<00:09,  2.95it/s]
+
 89%|████████▉ | 226/253 [01:13<00:09,  2.99it/s]
+
 90%|████████▉ | 227/253 [01:13<00:08,  3.10it/s]
+
 90%|█████████ | 228/253 [01:14<00:08,  3.08it/s]
+
 91%|█████████ | 229/253 [01:14<00:07,  3.06it/s]
+
 91%|█████████ | 230/253 [01:14<00:07,  3.04it/s]
+
 91%|█████████▏| 231/253 [01:15<00:07,  3.00it/s]
+
 92%|█████████▏| 232/253 [01:15<00:06,  3.05it/s]
+
 92%|█████████▏| 233/253 [01:15<00:06,  3.02it/s]
+
 92%|█████████▏| 234/253 [01:16<00:06,  3.06it/s]
+
 93%|█████████▎| 235/253 [01:16<00:05,  3.20it/s]
+
 93%|█████████▎| 236/253 [01:16<00:05,  3.22it/s]
+
 94%|█████████▎| 237/253 [01:17<00:04,  3.21it/s]
+
 94%|█████████▍| 238/253 [01:17<00:05,  2.87it/s]
+
 94%|█████████▍| 239/253 [01:17<00:04,  2.96it/s]
+
 95%|█████████▍| 240/253 [01:18<00:04,  2.93it/s]
+
 95%|█████████▌| 241/253 [01:18<00:04,  2.91it/s]
+
 96%|█████████▌| 242/253 [01:18<00:03,  2.84it/s]
+
 96%|█████████▌| 243/253 [01:19<00:03,  2.81it/s]
+
 96%|█████████▋| 244/253 [01:19<00:03,  2.81it/s]
+
 97%|█████████▋| 245/253 [01:19<00:02,  2.91it/s]
+
 97%|█████████▋| 246/253 [01:20<00:02,  2.90it/s]
+
 98%|█████████▊| 247/253 [01:20<00:02,  2.91it/s]
+
 98%|█████████▊| 248/253 [01:21<00:01,  2.81it/s]
+
 98%|█████████▊| 249/253 [01:21<00:01,  2.86it/s]
+
 99%|█████████▉| 250/253 [01:21<00:01,  2.89it/s]
+
 99%|█████████▉| 251/253 [01:22<00:00,  2.96it/s]
+
+
                                                           
+
                                                 
 63%|██████▎   | 42500/67700 [25:33:07<12:45:46,  1.82s/it]
+
+
                                                 Saving model checkpoint to ./checkpoint-42500
+Configuration saved in ./checkpoint-42500/config.json
+Model weights saved in ./checkpoint-42500/pytorch_model.bin
+Configuration saved in ./checkpoint-42500/preprocessor_config.json
+Configuration saved in ./preprocessor_config.json

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c4b4457161e710e85c6ca0ef7f056bdbd11e403308492c9fc2e250b6c659397
+oid sha256:58af4e71f693a4f9c9a3d43bea6a3403f2f1649c959b33b1f5f004d51eb2c159
 size 1280898545

runs/Feb06_10-51-19_job-aa543290-d6de-4d4d-8a32-2149b1b8e7e3/events.out.tfevents.1644145311.job-aa543290-d6de-4d4d-8a32-2149b1b8e7e3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931f18ff52bbebd3f154382012d53d27d73992af3f403b77addb03bc627ec2bf
-size 102047
+oid sha256:ac25066664d7f044f40a864d70b03487afd2354d75c0607fb352c5273d6bcae2
+size 103219