Training in progress, step 43000

nohup.out

@@ -23622,3 +23622,275 @@ 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
+Deleting older checkpoint [checkpoint-41000] due to args.save_total_limit
+
 63%|██████▎   | 42501/67700 [25:34:30<424:27:59, 60.64s/it]
 63%|██████▎   | 42502/67700 [25:34:32<300:44:30, 42.97s/it]
 63%|██████▎   | 42503/67700 [25:34:34<214:07:43, 30.59s/it]
 63%|██████▎   | 42504/67700 [25:34:36<153:20:15, 21.91s/it]
 63%|██████▎   | 42505/67700 [25:34:37<110:46:00, 15.83s/it]
 63%|██████▎   | 42506/67700 [25:34:39<80:55:19, 11.56s/it] 
 63%|██████▎   | 42507/67700 [25:34:40<59:57:39,  8.57s/it]
 63%|██████▎   | 42508/67700 [25:34:42<45:17:01,  6.47s/it]
 63%|██████▎   | 42509/67700 [25:34:43<34:52:59,  4.99s/it]
 63%|██████▎   | 42510/67700 [25:34:45<27:38:34,  3.95s/it]
 63%|██████▎   | 42511/67700 [25:34:46<22:26:48,  3.21s/it]
 63%|██████▎   | 42512/67700 [25:34:48<18:50:43,  2.69s/it]
 63%|██████▎   | 42513/67700 [25:34:49<16:10:49,  2.31s/it]
 63%|██████▎   | 42514/67700 [25:34:51<14:36:32,  2.09s/it]
 63%|██████▎   | 42515/67700 [25:34:52<13:11:05,  1.88s/it]
 63%|██████▎   | 42516/67700 [25:34:54<12:06:16,  1.73s/it]
 63%|██████▎   | 42517/67700 [25:34:55<11:08:28,  1.59s/it]
 63%|██████▎   | 42518/67700 [25:34:56<10:22:50,  1.48s/it]
 63%|██████▎   | 42519/67700 [25:34:57<9:50:38,  1.41s/it] 
 63%|██████▎   | 42520/67700 [25:34:59<9:23:42,  1.34s/it]
 63%|██████▎   | 42521/67700 [25:35:00<9:01:07,  1.29s/it]
 63%|██████▎   | 42522/67700 [25:35:01<8:42:10,  1.24s/it]
 63%|██████▎   | 42523/67700 [25:35:02<8:24:17,  1.20s/it]
 63%|██████▎   | 42524/67700 [25:35:03<7:59:01,  1.14s/it]
 63%|██████▎   | 42525/67700 [25:35:06<11:15:28,  1.61s/it]
 63%|██████▎   | 42526/67700 [25:35:08<13:15:32,  1.90s/it]
 63%|██████▎   | 42527/67700 [25:35:11<14:26:59,  2.07s/it]
 63%|██████▎   | 42528/67700 [25:35:13<15:27:12,  2.21s/it]
 63%|██████▎   | 42529/67700 [25:35:16<15:54:40,  2.28s/it]
 63%|██████▎   | 42530/67700 [25:35:18<16:04:31,  2.30s/it]
 63%|██████▎   | 42531/67700 [25:35:20<16:01:49,  2.29s/it]
 63%|██████▎   | 42532/67700 [25:35:23<15:54:01,  2.27s/it]
 63%|██████▎   | 42533/67700 [25:35:25<15:46:32,  2.26s/it]
 63%|██████▎   | 42534/67700 [25:35:27<15:33:53,  2.23s/it]
 63%|██████▎   | 42535/67700 [25:35:29<15:33:45,  2.23s/it]
 63%|██████▎   | 42536/67700 [25:35:31<15:19:23,  2.19s/it]
 63%|██████▎   | 42537/67700 [25:35:34<15:16:51,  2.19s/it]
 63%|██████▎   | 42538/67700 [25:35:36<15:02:17,  2.15s/it]
 63%|██████▎   | 42539/67700 [25:35:38<14:49:40,  2.12s/it]
 63%|██████▎   | 42540/67700 [25:35:40<14:37:33,  2.09s/it]
 63%|██████▎   | 42541/67700 [25:35:42<14:29:08,  2.07s/it]
 63%|██████▎   | 42542/67700 [25:35:44<14:18:17,  2.05s/it]
 63%|██████▎   | 42543/67700 [25:35:46<14:05:04,  2.02s/it]
 63%|██████▎   | 42544/67700 [25:35:48<13:52:30,  1.99s/it]
 63%|██████▎   | 42545/67700 [25:35:49<13:37:25,  1.95s/it]
 63%|██████▎   | 42546/67700 [25:35:51<13:25:15,  1.92s/it]
 63%|██████▎   | 42547/67700 [25:35:53<13:09:25,  1.88s/it]
 63%|██████▎   | 42548/67700 [25:35:55<12:55:43,  1.85s/it]
 63%|██████▎   | 42549/67700 [25:35:57<12:42:10,  1.82s/it]
 63%|██████▎   | 42550/67700 [25:35:58<12:35:48,  1.80s/it]
 63%|██████▎   | 42551/67700 [25:36:00<12:23:53,  1.77s/it]
 63%|██████▎   | 42552/67700 [25:36:02<12:17:39,  1.76s/it]
 63%|██████▎   | 42553/67700 [25:36:03<12:05:59,  1.73s/it]
 63%|██████▎   | 42554/67700 [25:36:05<11:56:02,  1.71s/it]
 63%|██████▎   | 42555/67700 [25:36:07<11:47:48,  1.69s/it]
 63%|██████▎   | 42556/67700 [25:36:08<11:42:04,  1.68s/it]
 63%|██████▎   | 42557/67700 [25:36:10<11:28:17,  1.64s/it]
 63%|██████▎   | 42558/67700 [25:36:12<11:20:04,  1.62s/it]
 63%|██████▎   | 42559/67700 [25:36:13<11:11:17,  1.60s/it]
 63%|██████▎   | 42560/67700 [25:36:15<10:57:04,  1.57s/it]
 63%|██████▎   | 42561/67700 [25:36:16<10:49:07,  1.55s/it]
 63%|██████▎   | 42562/67700 [25:36:18<10:42:24,  1.53s/it]
 63%|██████▎   | 42563/67700 [25:36:19<10:33:15,  1.51s/it]
 63%|██████▎   | 42564/67700 [25:36:20<10:21:38,  1.48s/it]
 63%|██████▎   | 42565/67700 [25:36:22<10:07:59,  1.45s/it]
 63%|██████▎   | 42566/67700 [25:36:23<9:52:20,  1.41s/it] 
 63%|██████▎   | 42567/67700 [25:36:24<9:34:29,  1.37s/it]
 63%|██████▎   | 42568/67700 [25:36:26<9:17:58,  1.33s/it]
 63%|██████▎   | 42569/67700 [25:36:27<9:05:37,  1.30s/it]
 63%|██████▎   | 42570/67700 [25:36:28<8:51:39,  1.27s/it]
 63%|██████▎   | 42571/67700 [25:36:29<8:38:53,  1.24s/it]
 63%|██████▎   | 42572/67700 [25:36:30<8:20:22,  1.19s/it]
 63%|██████▎   | 42573/67700 [25:36:31<8:00:01,  1.15s/it]
 63%|██████▎   | 42574/67700 [25:36:32<7:41:12,  1.10s/it]
 63%|██████▎   | 42575/67700 [25:36:35<10:50:17,  1.55s/it]
 63%|██████▎   | 42576/67700 [25:36:38<12:59:06,  1.86s/it]
 63%|██████▎   | 42577/67700 [25:36:40<14:19:55,  2.05s/it]
 63%|██████▎   | 42578/67700 [25:36:43<15:11:30,  2.18s/it]
 63%|██████▎   | 42579/67700 [25:36:45<15:43:35,  2.25s/it]
 63%|██████▎   | 42580/67700 [25:36:47<15:52:06,  2.27s/it]
 63%|██████▎   | 42581/67700 [25:36:50<15:47:18,  2.26s/it]
 63%|██████▎   | 42582/67700 [25:36:52<15:44:26,  2.26s/it]
 63%|██████▎   | 42583/67700 [25:36:54<15:49:00,  2.27s/it]
 63%|██████▎   | 42584/67700 [25:36:56<15:37:10,  2.24s/it]
 63%|██████▎   | 42585/67700 [25:36:58<15:26:27,  2.21s/it]
 63%|██████▎   | 42586/67700 [25:37:00<15:11:35,  2.18s/it]
 63%|██████▎   | 42587/67700 [25:37:03<14:57:58,  2.15s/it]
 63%|██████▎   | 42588/67700 [25:37:05<14:49:32,  2.13s/it]
 63%|██████▎   | 42589/67700 [25:37:07<14:41:04,  2.11s/it]
 63%|██████▎   | 42590/67700 [25:37:09<14:29:45,  2.08s/it]
 63%|██████▎   | 42591/67700 [25:37:11<14:22:31,  2.06s/it]
 63%|██████▎   | 42592/67700 [25:37:13<14:16:57,  2.05s/it]
 63%|██████▎   | 42593/67700 [25:37:15<14:08:42,  2.03s/it]
 63%|██████▎   | 42594/67700 [25:37:17<13:49:15,  1.98s/it]
 63%|██████▎   | 42595/67700 [25:37:18<13:36:50,  1.95s/it]
 63%|██████▎   | 42596/67700 [25:37:20<13:23:20,  1.92s/it]
 63%|██████▎   | 42597/67700 [25:37:22<13:09:30,  1.89s/it]
 63%|██████▎   | 42598/67700 [25:37:24<12:59:56,  1.86s/it]
 63%|██████▎   | 42599/67700 [25:37:26<12:47:37,  1.83s/it]
 63%|██████▎   | 42600/67700 [25:37:27<12:40:02,  1.82s/it]
                                                           
 63%|██████▎   | 42600/67700 [25:37:27<12:40:02,  1.82s/it]
 63%|██████▎   | 42601/67700 [25:37:29<12:30:28,  1.79s/it]
 63%|██████▎   | 42602/67700 [25:37:31<12:17:14,  1.76s/it]
 63%|██████▎   | 42603/67700 [25:37:33<12:06:19,  1.74s/it]
 63%|██████▎   | 42604/67700 [25:37:34<11:57:17,  1.71s/it]
 63%|██████▎   | 42605/67700 [25:37:36<11:46:42,  1.69s/it]
 63%|██████▎   | 42606/67700 [25:37:37<11:37:40,  1.67s/it]
 63%|██████▎   | 42607/67700 [25:37:39<11:30:45,  1.65s/it]
 63%|██████▎   | 42608/67700 [25:37:41<11:20:43,  1.63s/it]
 63%|██████▎   | 42609/67700 [25:37:42<11:17:43,  1.62s/it]
 63%|██████▎   | 42610/67700 [25:37:44<11:03:03,  1.59s/it]
 63%|██████▎   | 42611/67700 [25:37:45<10:44:05,  1.54s/it]
 63%|██████▎   | 42612/67700 [25:37:47<10:34:13,  1.52s/it]
 63%|██████▎   | 42613/67700 [25:37:48<10:21:07,  1.49s/it]
 63%|██████▎   | 42614/67700 [25:37:50<10:12:07,  1.46s/it]
 63%|██████▎   | 42615/67700 [25:37:51<10:01:03,  1.44s/it]
 63%|██████▎   | 42616/67700 [25:37:52<9:51:25,  1.41s/it] 
 63%|██████▎   | 42617/67700 [25:37:54<9:39:00,  1.39s/it]
 63%|██████▎   | 42618/67700 [25:37:55<9:24:41,  1.35s/it]
 63%|██████▎   | 42619/67700 [25:37:56<9:09:23,  1.31s/it]
 63%|██████▎   | 42620/67700 [25:37:57<8:56:38,  1.28s/it]
 63%|██████▎   | 42621/67700 [25:37:58<8:40:43,  1.25s/it]
 63%|██████▎   | 42622/67700 [25:38:00<8:22:06,  1.20s/it]
 63%|██████▎   | 42623/67700 [25:38:01<8:04:15,  1.16s/it]
 63%|██████▎   | 42624/67700 [25:38:02<7:41:24,  1.10s/it]
 63%|██████▎   | 42625/67700 [25:38:04<10:46:21,  1.55s/it]
 63%|██████▎   | 42626/67700 [25:38:07<12:39:17,  1.82s/it]
 63%|██████▎   | 42627/67700 [25:38:09<13:45:45,  1.98s/it]
 63%|██████▎   | 42628/67700 [25:38:11<14:24:23,  2.07s/it]
 63%|██████▎   | 42629/67700 [25:38:13<14:43:46,  2.12s/it]
 63%|██████▎   | 42630/67700 [25:38:16<14:57:30,  2.15s/it]
 63%|██████▎   | 42631/67700 [25:38:18<14:53:40,  2.14s/it]
 63%|██████▎   | 42632/67700 [25:38:20<14:43:25,  2.11s/it]
 63%|███���██▎   | 42633/67700 [25:38:22<14:36:24,  2.10s/it]
 63%|██████▎   | 42634/67700 [25:38:24<14:22:25,  2.06s/it]
 63%|██████▎   | 42635/67700 [25:38:26<14:06:33,  2.03s/it]
 63%|██████▎   | 42636/67700 [25:38:28<13:47:20,  1.98s/it]
 63%|██████▎   | 42637/67700 [25:38:29<13:21:35,  1.92s/it]
 63%|██████▎   | 42638/67700 [25:38:31<13:07:31,  1.89s/it]
 63%|██████▎   | 42639/67700 [25:38:33<12:55:48,  1.86s/it]
 63%|██████▎   | 42640/67700 [25:38:35<12:41:51,  1.82s/it]
 63%|██████▎   | 42641/67700 [25:38:36<12:21:32,  1.78s/it]
 63%|██████▎   | 42642/67700 [25:38:38<12:04:10,  1.73s/it]
 63%|██████▎   | 42643/67700 [25:38:40<11:41:46,  1.68s/it]
 63%|██████▎   | 42644/67700 [25:38:41<11:21:45,  1.63s/it]
 63%|██████▎   | 42645/67700 [25:38:43<11:09:07,  1.60s/it]
 63%|██████▎   | 42646/67700 [25:38:44<10:48:18,  1.55s/it]
 63%|██████▎   | 42647/67700 [25:38:46<10:26:07,  1.50s/it]
 63%|██████▎   | 42648/67700 [25:38:47<10:06:01,  1.45s/it]
 63%|██████▎   | 42649/67700 [25:38:48<9:41:21,  1.39s/it] 
 63%|██████▎   | 42650/67700 [25:38:49<9:12:32,  1.32s/it]
 63%|██████▎   | 42651/67700 [25:38:50<8:38:52,  1.24s/it]
 63%|██████▎   | 42652/67700 [25:38:53<12:01:11,  1.73s/it]
 63%|██████▎   | 42653/67700 [25:38:56<13:48:43,  1.99s/it]
 63%|██████▎   | 42654/67700 [25:38:58<15:01:59,  2.16s/it]
 63%|██████▎   | 42655/67700 [25:39:01<15:38:39,  2.25s/it]
 63%|██████▎   | 42656/67700 [25:39:03<16:05:55,  2.31s/it]
 63%|██████▎   | 42657/67700 [25:39:06<16:00:38,  2.30s/it]
 63%|██████▎   | 42658/67700 [25:39:08<15:54:41,  2.29s/it]
 63%|██████▎   | 42659/67700 [25:39:10<15:48:51,  2.27s/it]
 63%|██████▎   | 42660/67700 [25:39:12<15:39:42,  2.25s/it]
 63%|██████▎   | 42661/67700 [25:39:14<15:31:35,  2.23s/it]
 63%|██████▎   | 42662/67700 [25:39:17<15:20:49,  2.21s/it]
 63%|██████▎   | 42663/67700 [25:39:19<15:11:09,  2.18s/it]
 63%|██████▎   | 42664/67700 [25:39:21<15:05:58,  2.17s/it]
 63%|██████▎   | 42665/67700 [25:39:23<14:55:05,  2.15s/it]
 63%|██████▎   | 42666/67700 [25:39:25<14:51:10,  2.14s/it]
 63%|██████▎   | 42667/67700 [25:39:27<14:40:34,  2.11s/it]
 63%|██████▎   | 42668/67700 [25:39:29<14:30:51,  2.09s/it]
 63%|██████▎   | 42669/67700 [25:39:31<14:24:01,  2.07s/it]
 63%|██████▎   | 42670/67700 [25:39:33<14:19:56,  2.06s/it]
 63%|██████▎   | 42671/67700 [25:39:35<14:05:47,  2.03s/it]
 63%|██████▎   | 42672/67700 [25:39:37<13:47:43,  1.98s/it]
 63%|██████▎   | 42673/67700 [25:39:39<13:33:30,  1.95s/it]
 63%|██████▎   | 42674/67700 [25:39:41<13:22:45,  1.92s/it]
 63%|██████▎   | 42675/67700 [25:39:43<13:06:05,  1.88s/it]
 63%|██████▎   | 42676/67700 [25:39:44<12:54:58,  1.86s/it]
 63%|██████▎   | 42677/67700 [25:39:46<12:45:49,  1.84s/it]
 63%|██████▎   | 42678/67700 [25:39:48<12:33:58,  1.81s/it]
 63%|██████▎   | 42679/67700 [25:39:50<12:24:22,  1.78s/it]
 63%|██████▎   | 42680/67700 [25:39:51<12:24:23,  1.79s/it]
 63%|██████▎   | 42681/67700 [25:39:53<12:12:05,  1.76s/it]
 63%|██████▎   | 42682/67700 [25:39:55<12:02:03,  1.73s/it]
 63%|██████▎   | 42683/67700 [25:39:56<11:49:37,  1.70s/it]
 63%|██████▎   | 42684/67700 [25:39:58<11:40:27,  1.68s/it]
 63%|██████▎   | 42685/67700 [25:40:00<11:28:27,  1.65s/it]
 63%|██████▎   | 42686/67700 [25:40:01<11:17:50,  1.63s/it]
 63%|██████▎   | 42687/67700 [25:40:03<11:17:24,  1.62s/it]
 63%|██████▎   | 42688/67700 [25:40:04<11:04:38,  1.59s/it]
 63%|██████▎   | 42689/67700 [25:40:06<10:52:55,  1.57s/it]
 63%|██████▎   | 42690/67700 [25:40:07<10:40:08,  1.54s/it]
 63%|██████▎   | 42691/67700 [25:40:09<10:24:17,  1.50s/it]
 63%|██████▎   | 42692/67700 [25:40:10<10:15:31,  1.48s/it]
 63%|██████▎   | 42693/67700 [25:40:11<9:56:22,  1.43s/it] 
 63%|██████▎   | 42694/67700 [25:40:13<9:37:53,  1.39s/it]
 63%|██████▎   | 42695/67700 [25:40:14<9:22:19,  1.35s/it]
 63%|██████▎   | 42696/67700 [25:40:15<9:08:39,  1.32s/it]
 63%|██████▎   | 42697/67700 [25:40:16<8:55:44,  1.29s/it]
 63%|██████▎   | 42698/67700 [25:40:18<8:41:46,  1.25s/it]
 63%|██████▎   | 42699/67700 [25:40:19<8:28:17,  1.22s/it]
 63%|██████▎   | 42700/67700 [25:40:20<8:08:10,  1.17s/it]
                                                          
 63%|██████▎   | 42700/67700 [25:40:20<8:08:10,  1.17s/it]
 63%|██████▎   | 42701/67700 [25:40:21<7:44:26,  1.11s/it]
 63%|██████▎   | 42702/67700 [25:40:23<10:50:20,  1.56s/it]
 63%|██████▎   | 42703/67700 [25:40:26<12:56:00,  1.86s/it]
 63%|██████▎   | 42704/67700 [25:40:28<14:13:10,  2.05s/it]
 63%|██████▎   | 42705/67700 [25:40:31<15:06:25,  2.18s/it]
 63%|██████▎   | 42706/67700 [25:40:33<15:25:57,  2.22s/it]
 63%|██████▎   | 42707/67700 [25:40:36<15:35:48,  2.25s/it]
 63%|██████▎   | 42708/67700 [25:40:38<15:41:22,  2.26s/it]
 63%|██████▎   | 42709/67700 [25:40:40<15:55:05,  2.29s/it]
 63%|██████▎   | 42710/67700 [25:40:42<15:41:26,  2.26s/it]
 63%|██████▎   | 42711/67700 [25:40:45<15:30:52,  2.24s/it]
 63%|██████▎   | 42712/67700 [25:40:47<15:17:42,  2.20s/it]
 63%|██████▎   | 42713/67700 [25:40:49<15:08:27,  2.18s/it]
 63%|██████▎   | 42714/67700 [25:40:51<14:59:29,  2.16s/it]
 63%|██████▎   | 42715/67700 [25:40:53<14:48:45,  2.13s/it]
 63%|██████▎   | 42716/67700 [25:40:55<14:32:05,  2.09s/it]
 63%|██████▎   | 42717/67700 [25:40:57<14:17:15,  2.06s/it]
 63%|██████▎   | 42718/67700 [25:40:59<14:08:56,  2.04s/it]
 63%|██████▎   | 42719/67700 [25:41:01<13:52:39,  2.00s/it]
 63%|██████▎   | 42720/67700 [25:41:03<13:36:48,  1.96s/it]
 63%|██████▎   | 42721/67700 [25:41:05<13:22:27,  1.93s/it]
 63%|██████▎   | 42722/67700 [25:41:06<13:13:20,  1.91s/it]
 63%|██████▎   | 42723/67700 [25:41:08<13:00:57,  1.88s/it]
 63%|██████▎   | 42724/67700 [25:41:10<12:47:36,  1.84s/it]
 63%|██████▎   | 42725/67700 [25:41:12<12:37:32,  1.82s/it]
 63%|██████▎   | 42726/67700 [25:41:14<12:26:52,  1.79s/it]
 63%|██████▎   | 42727/67700 [25:41:15<12:13:37,  1.76s/it]
 63%|██████▎   | 42728/67700 [25:41:17<12:05:44,  1.74s/it]
 63%|██████▎   | 42729/67700 [25:41:19<11:59:48,  1.73s/it]
 63%|██████▎   | 42730/67700 [25:41:20<11:51:51,  1.71s/it]
 63%|██████▎   | 42731/67700 [25:41:22<11:41:23,  1.69s/it]
 63%|██████▎   | 42732/67700 [25:41:24<11:33:40,  1.67s/it]
 63%|██████▎   | 42733/67700 [25:41:25<11:21:57,  1.64s/it]
 63%|██████▎   | 42734/67700 [25:41:27<11:14:17,  1.62s/it]
 63%|██████▎   | 42735/67700 [25:41:28<11:02:56,  1.59s/it]
 63%|██████▎   | 42736/67700 [25:41:30<10:54:49,  1.57s/it]
 63%|██████▎   | 42737/67700 [25:41:31<10:43:26,  1.55s/it]
 63%|██████▎   | 42738/67700 [25:41:33<10:33:31,  1.52s/it]
 63%|██████▎   | 42739/67700 [25:41:34<10:24:52,  1.50s/it]
 63%|██████▎   | 42740/67700 [25:41:36<10:16:58,  1.48s/it]
 63%|██████▎   | 42741/67700 [25:41:37<10:08:12,  1.46s/it]
 63%|██████▎   | 42742/67700 [25:41:38<9:57:43,  1.44s/it] 
 63%|██████▎   | 42743/67700 [25:41:40<9:44:46,  1.41s/it]
 63%|██████▎   | 42744/67700 [25:41:41<9:27:00,  1.36s/it]
 63%|██████▎   | 42745/67700 [25:41:42<9:12:29,  1.33s/it]
 63%|██████▎   | 42746/67700 [25:41:44<9:01:37,  1.30s/it]
 63%|██████▎   | 42747/67700 [25:41:45<8:45:46,  1.26s/it]
 63%|██████▎   | 42748/67700 [25:41:46<8:31:51,  1.23s/it]
 63%|██████▎   | 42749/67700 [25:41:47<8:12:14,  1.18s/it]
 63%|██████▎   | 42750/67700 [25:41:48<7:48:30,  1.13s/it]
 63%|██████▎   | 42751/67700 [25:41:49<7:29:55,  1.08s/it]
 63%|██████▎   | 42752/67700 [25:41:51<10:34:06,  1.53s/it]
 63%|██████▎   | 42753/67700 [25:41:54<12:38:22,  1.82s/it]
 63%|██████▎   | 42754/67700 [25:41:56<14:02:50,  2.03s/it]
 63%|██████▎   | 42755/67700 [25:41:59<14:57:12,  2.16s/it]
 63%|██████▎   | 42756/67700 [25:42:01<15:37:47,  2.26s/it]
 63%|██████▎   | 42757/67700 [25:42:04<15:40:36,  2.26s/it]
 63%|██████▎   | 42758/67700 [25:42:06<15:40:26,  2.26s/it]
 63%|██████▎   | 42759/67700 [25:42:08<15:38:57,  2.26s/it]
 63%|██████▎   | 42760/67700 [25:42:10<15:28:53,  2.23s/it]
 63%|██████▎   | 42761/67700 [25:42:13<15:24:38,  2.22s/it]
 63%|██████▎   | 42762/67700 [25:42:15<15:17:05,  2.21s/it]
 63%|██████▎   | 42763/67700 [25:42:17<15:02:21,  2.17s/it]
 63%|██████▎   | 42764/67700 [25:42:19<14:54:00,  2.15s/it]
 63%|██████▎   | 42765/67700 [25:42:21<14:43:39,  2.13s/it]
 63%|██████▎   | 42766/67700 [25:42:23<14:31:58,  2.10s/it]
 63%|██████▎   | 42767/67700 [25:42:25<14:18:05,  2.06s/it]
 63%|██████▎   | 42768/67700 [25:42:27<14:10:28,  2.05s/it]
 63%|██████▎   | 42769/67700 [25:42:29<13:57:06,  2.01s/it]
 63%|██████▎   | 42770/67700 [25:42:31<13:56:49,  2.01s/it]
 63%|██████▎   | 42771/67700 [25:42:33<13:44:47,  1.99s/it]
 63%|██████▎   | 42772/67700 [25:42:35<13:30:54,  1.95s/it]
 63%|██████▎   | 42773/67700 [25:42:37<13:23:07,  1.93s/it]
 63%|██████▎   | 42774/67700 [25:42:39<13:13:12,  1.91s/it]
 63%|██████▎   | 42775/67700 [25:42:40<12:59:07,  1.88s/it]
 63%|██████▎   | 42776/67700 [25:42:42<12:45:41,  1.84s/it]
 63%|██████▎   | 42777/67700 [25:42:44<12:36:11,  1.82s/it]
 63%|██████▎   | 42778/67700 [25:42:46<12:24:38,  1.79s/it]
 63%|██████▎   | 42779/67700 [25:42:47<12:14:42,  1.77s/it]
 63%|██████▎   | 42780/67700 [25:42:49<12:03:08,  1.74s/it]
 63%|██████▎   | 42781/67700 [25:42:51<11:52:35,  1.72s/it]
 63%|██████▎   | 42782/67700 [25:42:52<11:46:08,  1.70s/it]
 63%|██████▎   | 42783/67700 [25:42:54<11:33:47,  1.67s/it]
 63%|██████▎   | 42784/67700 [25:42:55<11:22:29,  1.64s/it]
 63%|██████▎   | 42785/67700 [25:42:57<11:13:57,  1.62s/it]
 63%|██████▎   | 42786/67700 [25:42:59<11:00:22,  1.59s/it]
 63%|██████▎   | 42787/67700 [25:43:00<10:46:26,  1.56s/it]
 63%|██████▎   | 42788/67700 [25:43:02<10:36:40,  1.53s/it]
 63%|██████▎   | 42789/67700 [25:43:03<10:25:22,  1.51s/it]
 63%|██████▎   | 42790/67700 [25:43:04<10:14:48,  1.48s/it]
 63%|██████▎   | 42791/67700 [25:43:06<10:10:22,  1.47s/it]
 63%|██████▎   | 42792/67700 [25:43:07<9:59:02,  1.44s/it] 
 63%|██████▎   | 42793/67700 [25:43:09<9:44:34,  1.41s/it]
 63%|██████▎   | 42794/67700 [25:43:10<9:26:32,  1.36s/it]
 63%|██████▎   | 42795/67700 [25:43:11<9:10:27,  1.33s/it]
 63%|██████▎   | 42796/67700 [25:43:12<8:56:32,  1.29s/it]
 63%|██████▎   | 42797/67700 [25:43:13<8:42:33,  1.26s/it]
 63%|██████▎   | 42798/67700 [25:43:15<8:29:03,  1.23s/it]
 63%|██████▎   | 42799/67700 [25:43:16<8:11:54,  1.19s/it]
 63%|██████▎   | 42800/67700 [25:43:17<8:02:25,  1.16s/it]
                                                          
 63%|██████▎   | 42800/67700 [25:43:17<8:02:25,  1.16s/it]
 63%|██████▎   | 42801/67700 [25:43:18<7:38:27,  1.10s/it]
 63%|██████▎   | 42802/67700 [25:43:20<10:48:06,  1.56s/it]
 63%|██████▎   | 42803/67700 [25:43:23<12:51:20,  1.86s/it]
 63%|██████▎   | 42804/67700 [25:43:25<14:10:01,  2.05s/it]
 63%|██████▎   | 42805/67700 [25:43:28<15:04:48,  2.18s/it]
 63%|██████▎   | 42806/67700 [25:43:30<15:33:58,  2.25s/it]
 63%|██████▎   | 42807/67700 [25:43:33<15:50:33,  2.29s/it]
 63%|██████▎   | 42808/67700 [25:43:35<15:52:26,  2.30s/it]
 63%|██████▎   | 42809/67700 [25:43:37<15:53:07,  2.30s/it]
 63%|██████▎   | 42810/67700 [25:43:40<15:45:11,  2.28s/it]
 63%|██████▎   | 42811/67700 [25:43:42<15:39:09,  2.26s/it]
 63%|██████▎   | 42812/67700 [25:43:44<15:38:13,  2.26s/it]
 63%|██████▎   | 42813/67700 [25:43:46<15:22:34,  2.22s/it]
 63%|██████▎   | 42814/67700 [25:43:48<15:11:46,  2.20s/it]
 63%|██████▎   | 42815/67700 [25:43:50<15:02:08,  2.18s/it]
 63%|██████▎   | 42816/67700 [25:43:53<15:01:34,  2.17s/it]
 63%|██████▎   | 42817/67700 [25:43:55<14:43:11,  2.13s/it]
 63%|██████▎   | 42818/67700 [25:43:57<14:32:05,  2.10s/it]
 63%|██████▎   | 42819/67700 [25:43:59<14:15:34,  2.06s/it]
 63%|██████▎   | 42820/67700 [25:44:01<14:06:59,  2.04s/it]
 63%|██████▎   | 42821/67700 [25:44:03<13:51:27,  2.01s/it]
 63%|██████▎   | 42822/67700 [25:44:04<13:44:29,  1.99s/it]
 63%|██████▎   | 42823/67700 [25:44:06<13:32:05,  1.96s/it]
 63%|██████▎   | 42824/67700 [25:44:08<13:19:47,  1.93s/it]
 63%|██████▎   | 42825/67700 [25:44:10<13:02:25,  1.89s/it]
 63%|██████▎   | 42826/67700 [25:44:12<13:01:19,  1.88s/it]
 63%|██████▎   | 42827/67700 [25:44:14<12:47:36,  1.85s/it]
 63%|██████▎   | 42828/67700 [25:44:15<12:36:17,  1.82s/it]
 63%|██████▎   | 42829/67700 [25:44:17<12:29:49,  1.81s/it]
 63%|██████▎   | 42830/67700 [25:44:19<12:19:01,  1.78s/it]
 63%|██████▎   | 42831/67700 [25:44:21<12:07:18,  1.75s/it]
 63%|██████▎   | 42832/67700 [25:44:22<11:58:25,  1.73s/it]
 63%|██████▎   | 42833/67700 [25:44:24<11:49:22,  1.71s/it]
 63%|██████▎   | 42834/67700 [25:44:26<11:33:40,  1.67s/it]
 63%|██████▎   | 42835/67700 [25:44:27<11:20:45,  1.64s/it]
 63%|██████▎   | 42836/67700 [25:44:29<11:09:50,  1.62s/it]
 63%|██████▎   | 42837/67700 [25:44:30<10:56:15,  1.58s/it]
 63%|██████▎   | 42838/67700 [25:44:32<10:44:37,  1.56s/it]
 63%|██████▎   | 42839/67700 [25:44:33<10:34:23,  1.53s/it]
 63%|██████▎   | 42840/67700 [25:44:35<10:24:33,  1.51s/it]
 63%|██████▎   | 42841/67700 [25:44:36<10:20:13,  1.50s/it]
 63%|██████▎   | 42842/67700 [25:44:37<10:06:17,  1.46s/it]
 63%|██████▎   | 42843/67700 [25:44:39<9:58:09,  1.44s/it] 
 63%|██████▎   | 42844/67700 [25:44:40<9:40:09,  1.40s/it]
 63%|██████▎   | 42845/67700 [25:44:41<9:27:09,  1.37s/it]
 63%|██████▎   | 42846/67700 [25:44:43<9:13:14,  1.34s/it]
 63%|██████▎   | 42847/67700 [25:44:44<8:58:00,  1.30s/it]
 63%|██████▎   | 42848/67700 [25:44:45<8:41:30,  1.26s/it]
 63%|██████▎   | 42849/67700 [25:44:46<8:29:09,  1.23s/it]
 63%|██████▎   | 42850/67700 [25:44:47<8:08:46,  1.18s/it]
 63%|██████▎   | 42851/67700 [25:44:48<7:43:49,  1.12s/it]
 63%|██████▎   | 42852/67700 [25:44:51<10:45:53,  1.56s/it]
 63%|██████▎   | 42853/67700 [25:44:53<12:44:59,  1.85s/it]
 63%|██████▎   | 42854/67700 [25:44:56<13:59:55,  2.03s/it]
 63%|██████▎   | 42855/67700 [25:44:58<14:55:03,  2.16s/it]
 63%|██████▎   | 42856/67700 [25:45:01<15:31:12,  2.25s/it]
 63%|██████▎   | 42857/67700 [25:45:03<15:44:08,  2.28s/it]
 63%|██████▎   | 42858/67700 [25:45:05<15:44:50,  2.28s/it]
 63%|██████▎   | 42859/67700 [25:45:08<15:40:16,  2.27s/it]
 63%|██████▎   | 42860/67700 [25:45:10<15:34:58,  2.26s/it]
 63%|██████▎   | 42861/67700 [25:45:12<15:24:53,  2.23s/it]
 63%|██████▎   | 42862/67700 [25:45:14<15:19:28,  2.22s/it]
 63%|██████▎   | 42863/67700 [25:45:16<15:09:51,  2.20s/it]
 63%|██████▎   | 42864/67700 [25:45:19<14:56:24,  2.17s/it]
 63%|██████▎   | 42865/67700 [25:45:21<14:46:39,  2.14s/it]
 63%|██████▎   | 42866/67700 [25:45:23<14:42:13,  2.13s/it]
 63%|██████▎   | 42867/67700 [25:45:25<14:28:48,  2.10s/it]
 63%|██████▎   | 42868/67700 [25:45:27<14:18:41,  2.07s/it]
 63%|██████▎   | 42869/67700 [25:45:29<14:08:10,  2.05s/it]
 63%|██████▎   | 42870/67700 [25:45:31<13:58:44,  2.03s/it]
 63%|██████▎   | 42871/67700 [25:45:33<13:42:06,  1.99s/it]
 63%|██████▎   | 42872/67700 [25:45:34<13:28:29,  1.95s/it]
 63%|██████▎   | 42873/67700 [25:45:36<13:16:33,  1.93s/it]
 63%|██████▎   | 42874/67700 [25:45:38<13:05:46,  1.90s/it]
 63%|██████▎   | 42875/67700 [25:45:40<12:53:54,  1.87s/it]
 63%|██████▎   | 42876/67700 [25:45:42<12:41:39,  1.84s/it]
 63%|██████▎   | 42877/67700 [25:45:44<12:30:49,  1.81s/it]
 63%|██████▎   | 42878/67700 [25:45:45<12:17:37,  1.78s/it]
 63%|██████▎   | 42879/67700 [25:45:47<12:09:03,  1.76s/it]
 63%|██████▎   | 42880/67700 [25:45:49<11:54:47,  1.73s/it]
 63%|██████▎   | 42881/67700 [25:45:50<11:44:52,  1.70s/it]
 63%|██████▎   | 42882/67700 [25:45:52<11:33:13,  1.68s/it]
 63%|██████▎   | 42883/67700 [25:45:53<11:25:00,  1.66s/it]
 63%|██████▎   | 42884/67700 [25:45:55<11:14:40,  1.63s/it]
 63%|██████▎   | 42885/67700 [25:45:57<11:08:28,  1.62s/it]
 63%|██████▎   | 42886/67700 [25:45:58<10:57:33,  1.59s/it]
 63%|██████▎   | 42887/67700 [25:46:00<10:48:31,  1.57s/it]
 63%|██████▎   | 42888/67700 [25:46:01<10:36:01,  1.54s/it]
 63%|██████▎   | 42889/67700 [25:46:03<10:29:32,  1.52s/it]
 63%|██████▎   | 42890/67700 [25:46:04<10:14:53,  1.49s/it]
 63%|██████▎   | 42891/67700 [25:46:05<10:04:07,  1.46s/it]
 63%|██████▎   | 42892/67700 [25:46:07<9:55:04,  1.44s/it] 
 63%|██████▎   | 42893/67700 [25:46:08<9:44:59,  1.41s/it]
 63%|██████▎   | 42894/67700 [25:46:09<9:27:41,  1.37s/it]
 63%|██████▎   | 42895/67700 [25:46:11<9:11:02,  1.33s/it]
 63%|██████▎   | 42896/67700 [25:46:12<8:58:14,  1.30s/it]
 63%|██████▎   | 42897/67700 [25:46:13<8:43:43,  1.27s/it]
 63%|██████▎   | 42898/67700 [25:46:14<8:29:44,  1.23s/it]
 63%|██████▎   | 42899/67700 [25:46:15<8:16:54,  1.20s/it]
 63%|██████▎   | 42900/67700 [25:46:16<8:01:10,  1.16s/it]
                                                          
 63%|██████▎   | 42900/67700 [25:46:16<8:01:10,  1.16s/it]
 63%|██████▎   | 42901/67700 [25:46:17<7:32:31,  1.09s/it]
 63%|██████▎   | 42902/67700 [25:46:20<10:35:39,  1.54s/it]
 63%|██████▎   | 42903/67700 [25:46:23<12:42:59,  1.85s/it]
 63%|██████▎   | 42904/67700 [25:46:25<14:00:59,  2.03s/it]
 63%|██��███▎   | 42905/67700 [25:46:27<14:46:45,  2.15s/it]
 63%|██████▎   | 42906/67700 [25:46:30<15:12:13,  2.21s/it]
 63%|██████▎   | 42907/67700 [25:46:32<15:19:35,  2.23s/it]
 63%|██████▎   | 42908/67700 [25:46:34<15:17:57,  2.22s/it]
 63%|██████▎   | 42909/67700 [25:46:36<15:10:39,  2.20s/it]
 63%|██████▎   | 42910/67700 [25:46:39<15:17:27,  2.22s/it]
 63%|██████▎   | 42911/67700 [25:46:41<15:13:38,  2.21s/it]
 63%|██████▎   | 42912/67700 [25:46:43<15:15:02,  2.21s/it]
 63%|██████▎   | 42913/67700 [25:46:45<15:06:40,  2.19s/it]
 63%|██████▎   | 42914/67700 [25:46:47<14:58:35,  2.18s/it]
 63%|██████▎   | 42915/67700 [25:46:49<14:47:59,  2.15s/it]
 63%|██████▎   | 42916/67700 [25:46:52<14:41:53,  2.13s/it]
 63%|██████▎   | 42917/67700 [25:46:54<14:30:15,  2.11s/it]
 63%|██████▎   | 42918/67700 [25:46:56<14:19:18,  2.08s/it]
 63%|██████▎   | 42919/67700 [25:46:58<14:09:07,  2.06s/it]
 63%|██████▎   | 42920/67700 [25:47:00<13:54:26,  2.02s/it]
 63%|██████▎   | 42921/67700 [25:47:01<13:40:43,  1.99s/it]
 63%|██████▎   | 42922/67700 [25:47:03<13:29:03,  1.96s/it]
 63%|██████▎   | 42923/67700 [25:47:05<13:17:17,  1.93s/it]
 63%|██████▎   | 42924/67700 [25:47:07<13:00:22,  1.89s/it]
 63%|██████▎   | 42925/67700 [25:47:09<12:47:51,  1.86s/it]
 63%|██████▎   | 42926/67700 [25:47:11<12:35:06,  1.83s/it]
 63%|██████▎   | 42927/67700 [25:47:12<12:26:26,  1.81s/it]
 63%|██████▎   | 42928/67700 [25:47:14<12:16:42,  1.78s/it]
 63%|██████▎   | 42929/67700 [25:47:16<12:05:38,  1.76s/it]
 63%|██████▎   | 42930/67700 [25:47:17<11:55:35,  1.73s/it]
 63%|██████▎   | 42931/67700 [25:47:19<11:45:31,  1.71s/it]
 63%|██████▎   | 42932/67700 [25:47:21<11:35:12,  1.68s/it]
 63%|██████▎   | 42933/67700 [25:47:22<11:26:48,  1.66s/it]
 63%|██████▎   | 42934/67700 [25:47:24<11:18:23,  1.64s/it]
 63%|██████▎   | 42935/67700 [25:47:25<11:09:03,  1.62s/it]
 63%|██████▎   | 42936/67700 [25:47:27<11:01:26,  1.60s/it]
 63%|██████▎   | 42937/67700 [25:47:28<10:44:43,  1.56s/it]
 63%|██████▎   | 42938/67700 [25:47:30<10:25:46,  1.52s/it]
 63%|██████▎   | 42939/67700 [25:47:31<10:09:43,  1.48s/it]
 63%|██████▎   | 42940/67700 [25:47:33<9:54:39,  1.44s/it] 
 63%|██████▎   | 42941/67700 [25:47:34<9:43:25,  1.41s/it]
 63%|██████▎   | 42942/67700 [25:47:35<9:29:44,  1.38s/it]
 63%|██████▎   | 42943/67700 [25:47:37<9:17:55,  1.35s/it]
 63%|██████▎   | 42944/67700 [25:47:38<9:09:30,  1.33s/it]
 63%|██████▎   | 42945/67700 [25:47:39<8:50:27,  1.29s/it]
 63%|██████▎   | 42946/67700 [25:47:40<8:32:45,  1.24s/it]
 63%|██████▎   | 42947/67700 [25:47:41<8:16:05,  1.20s/it]
 63%|██████▎   | 42948/67700 [25:47:42<7:59:58,  1.16s/it]
 63%|██████▎   | 42949/67700 [25:47:43<7:44:07,  1.13s/it]
 63%|██████▎   | 42950/67700 [25:47:44<7:33:01,  1.10s/it]
 63%|██████▎   | 42951/67700 [25:47:45<7:17:53,  1.06s/it]
 63%|██████▎   | 42952/67700 [25:47:48<10:25:57,  1.52s/it]
 63%|██████▎   | 42953/67700 [25:47:51<12:34:55,  1.83s/it]
 63%|██████▎   | 42954/67700 [25:47:53<13:54:54,  2.02s/it]
 63%|██████▎   | 42955/67700 [25:47:55<14:46:37,  2.15s/it]
 63%|██████▎   | 42956/67700 [25:47:58<15:22:46,  2.24s/it]
 63%|██████▎   | 42957/67700 [25:48:00<15:36:26,  2.27s/it]
 63%|██████▎   | 42958/67700 [25:48:02<15:32:23,  2.26s/it]
 63%|██████▎   | 42959/67700 [25:48:05<15:28:57,  2.25s/it]
 63%|██████▎   | 42960/67700 [25:48:07<15:24:15,  2.24s/it]
 63%|██████▎   | 42961/67700 [25:48:09<15:13:38,  2.22s/it]
 63%|██████▎   | 42962/67700 [25:48:11<15:05:35,  2.20s/it]
 63%|██████▎   | 42963/67700 [25:48:13<14:55:24,  2.17s/it]
 63%|██████▎   | 42964/67700 [25:48:15<14:46:06,  2.15s/it]
 63%|██████▎   | 42965/67700 [25:48:18<14:44:59,  2.15s/it]
 63%|██████▎   | 42966/67700 [25:48:20<14:40:46,  2.14s/it]
 63%|██████▎   | 42967/67700 [25:48:22<14:28:43,  2.11s/it]
 63%|██████▎   | 42968/67700 [25:48:24<14:14:57,  2.07s/it]
 63%|██████▎   | 42969/67700 [25:48:26<14:03:55,  2.05s/it]
 63%|██████▎   | 42970/67700 [25:48:28<13:50:56,  2.02s/it]
 63%|██████▎   | 42971/67700 [25:48:30<13:36:14,  1.98s/it]
 63%|██████▎   | 42972/67700 [25:48:31<13:23:53,  1.95s/it]
 63%|██████▎   | 42973/67700 [25:48:33<13:11:19,  1.92s/it]
 63%|██████▎   | 42974/67700 [25:48:35<13:01:00,  1.90s/it]
 63%|██████▎   | 42975/67700 [25:48:37<12:46:09,  1.86s/it]
 63%|██████▎   | 42976/67700 [25:48:39<12:38:26,  1.84s/it]
 63%|██████▎   | 42977/67700 [25:48:40<12:27:34,  1.81s/it]
 63%|██████▎   | 42978/67700 [25:48:42<12:13:30,  1.78s/it]
 63%|██████▎   | 42979/67700 [25:48:44<12:04:00,  1.76s/it]
 63%|██████▎   | 42980/67700 [25:48:46<11:55:14,  1.74s/it]
 63%|██████▎   | 42981/67700 [25:48:47<11:46:10,  1.71s/it]
 63%|██████▎   | 42982/67700 [25:48:49<11:35:08,  1.69s/it]
 63%|██████▎   | 42983/67700 [25:48:50<11:27:19,  1.67s/it]
 63%|██████▎   | 42984/67700 [25:48:52<11:19:29,  1.65s/it]
 63%|██████▎   | 42985/67700 [25:48:54<11:10:54,  1.63s/it]
 63%|██████▎   | 42986/67700 [25:48:55<10:58:48,  1.60s/it]
 63%|██████▎   | 42987/67700 [25:48:57<10:48:27,  1.57s/it]
 63%|██████▎   | 42988/67700 [25:48:58<10:42:59,  1.56s/it]
 63%|██████▎   | 42989/67700 [25:49:00<10:33:49,  1.54s/it]
 64%|██████▎   | 42990/67700 [25:49:01<10:23:18,  1.51s/it]
 64%|██████▎   | 42991/67700 [25:49:03<10:16:55,  1.50s/it]
 64%|██████▎   | 42992/67700 [25:49:04<10:04:07,  1.47s/it]
 64%|██████▎   | 42993/67700 [25:49:05<9:51:02,  1.44s/it] 
 64%|██████▎   | 42994/67700 [25:49:07<9:34:29,  1.40s/it]
 64%|██████▎   | 42995/67700 [25:49:08<9:20:34,  1.36s/it]
 64%|██████▎   | 42996/67700 [25:49:09<9:10:19,  1.34s/it]
 64%|██████▎   | 42997/67700 [25:49:10<8:53:50,  1.30s/it]
 64%|██████▎   | 42998/67700 [25:49:12<8:40:51,  1.27s/it]
 64%|██████▎   | 42999/67700 [25:49:13<8:26:24,  1.23s/it]
 64%|██████▎   | 43000/67700 [25:49:14<8:03:36,  1.17s/it]
                                                          
 64%|██████▎   | 43000/67700 [25:49:14<8:03:36,  1.17s/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': 0.8418570756912231, 'eval_wer': 0.875804057397328, 'eval_cer': 0.22160208793414976, 'eval_runtime': 114.0321, 'eval_samples_per_second': 17.723, 'eval_steps_per_second': 2.219, 'epoch': 62.78}
+{'loss': 1.5781, 'learning_rate': 2.8676940639269402e-05, 'epoch': 62.92}
+{'loss': 1.5754, 'learning_rate': 2.856278538812785e-05, 'epoch': 63.07}
+{'loss': 1.5775, 'learning_rate': 2.8449771689497715e-05, 'epoch': 63.22}
+{'loss': 1.568, 'learning_rate': 2.8335616438356163e-05, 'epoch': 63.37}
+{'loss': 1.5697, 'learning_rate': 2.822146118721461e-05, 'epoch': 63.52}
+
+
  0%|          | 0/253 [00:00<?, ?it/s]
+
  1%|          | 2/253 [00:00<00:41,  6.05it/s]
+
  1%|          | 3/253 [00:00<00:58,  4.26it/s]
+
  2%|▏         | 4/253 [00:00<01:04,  3.89it/s]
+
  2%|▏         | 5/253 [00:01<01:10,  3.52it/s]
+
  2%|▏         | 6/253 [00:01<01:11,  3.45it/s]
+
  3%|▎         | 7/253 [00:01<01:15,  3.24it/s]
+
  3%|▎         | 8/253 [00:02<01:17,  3.16it/s]
+
  4%|▎         | 9/253 [00:02<01:19,  3.09it/s]
+
  4%|▍         | 10/253 [00:02<01:20,  3.01it/s]
+
  4%|▍         | 11/253 [00:03<01:21,  2.99it/s]
+
  5%|▍         | 12/253 [00:03<01:19,  3.04it/s]
+
  5%|▌         | 13/253 [00:03<01:20,  2.98it/s]
+
  6%|▌         | 14/253 [00:04<01:16,  3.12it/s]
+
  6%|▌         | 15/253 [00:04<01:18,  3.04it/s]
+
  6%|▋         | 16/253 [00:04<01:16,  3.08it/s]
+
  7%|▋         | 17/253 [00:05<01:19,  2.95it/s]
+
  7%|▋         | 18/253 [00:05<01:18,  3.00it/s]
+
  8%|▊         | 19/253 [00:05<01:15,  3.08it/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<01:17,  3.00it/s]
+
  9%|▉         | 23/253 [00:07<01:18,  2.92it/s]
+
  9%|▉         | 24/253 [00:07<01:17,  2.97it/s]
+
 10%|▉         | 25/253 [00:07<01:17,  2.94it/s]
+
 10%|█         | 26/253 [00:08<01:17,  2.91it/s]
+
 11%|█         | 27/253 [00:08<01:18,  2.88it/s]
+
 11%|█         | 28/253 [00:08<01:15,  2.96it/s]
+
 11%|█▏        | 29/253 [00:09<01:16,  2.92it/s]
+
 12%|█▏        | 30/253 [00:09<01:16,  2.90it/s]
+
 12%|█▏        | 31/253 [00:10<01:15,  2.94it/s]
+
 13%|█▎        | 32/253 [00:10<01:16,  2.89it/s]
+
 13%|█▎        | 33/253 [00:10<01:15,  2.92it/s]
+
 13%|█▎        | 34/253 [00:11<01:15,  2.91it/s]
+
 14%|█▍        | 35/253 [00:11<01:13,  2.95it/s]
+
 14%|█▍        | 36/253 [00:11<01:11,  3.05it/s]
+
 15%|█▍        | 37/253 [00:11<01:09,  3.10it/s]
+
 15%|█▌        | 38/253 [00:12<01:11,  3.01it/s]
+
 15%|█▌        | 39/253 [00:12<01:10,  3.05it/s]
+
 16%|█▌        | 40/253 [00:12<01:07,  3.13it/s]
+
 16%|█▌        | 41/253 [00:13<01:08,  3.09it/s]
+
 17%|█▋        | 42/253 [00:13<01:08,  3.07it/s]
+
 17%|█▋        | 43/253 [00:13<01:06,  3.18it/s]
+
 17%|█▋        | 44/253 [00:14<01:07,  3.10it/s]
+
 18%|█▊        | 45/253 [00:14<01:08,  3.06it/s]
+
 18%|█▊        | 46/253 [00:14<01:05,  3.16it/s]
+
 19%|█▊        | 47/253 [00:15<01:06,  3.11it/s]
+
 19%|█▉        | 48/253 [00:15<01:06,  3.10it/s]
+
 19%|█▉        | 49/253 [00:15<01:05,  3.14it/s]
+
 20%|█▉        | 50/253 [00:16<01:04,  3.16it/s]
+
 20%|██        | 51/253 [00:16<01:05,  3.08it/s]
+
 21%|██        | 52/253 [00:16<01:06,  3.03it/s]
+
 21%|██        | 53/253 [00:17<01:05,  3.07it/s]
+
 21%|██▏       | 54/253 [00:17<01:06,  3.01it/s]
+
 22%|██▏       | 55/253 [00:17<01:04,  3.07it/s]
+
 22%|██▏       | 56/253 [00:18<01:04,  3.06it/s]
+
 23%|██▎       | 57/253 [00:18<01:01,  3.17it/s]
+
 23%|██▎       | 58/253 [00:18<01:01,  3.16it/s]
+
 23%|██▎       | 59/253 [00:19<01:01,  3.14it/s]
+
 24%|██▎       | 60/253 [00:19<01:00,  3.20it/s]
+
 24%|██▍       | 61/253 [00:19<01:01,  3.11it/s]
+
 25%|██▍       | 62/253 [00:20<00:59,  3.22it/s]
+
 25%|██▍       | 63/253 [00:20<01:00,  3.16it/s]
+
 25%|██▌       | 64/253 [00:20<01:00,  3.13it/s]
+
 26%|██▌       | 65/253 [00:20<01:00,  3.11it/s]
+
 26%|██▌       | 66/253 [00:21<01:01,  3.05it/s]
+
 26%|██▋       | 67/253 [00:21<01:03,  2.94it/s]
+
 27%|██▋       | 68/253 [00:22<01:00,  3.04it/s]
+
 27%|██▋       | 69/253 [00:22<00:58,  3.14it/s]
+
 28%|██▊       | 70/253 [00:22<00:56,  3.24it/s]
+
 28%|██▊       | 71/253 [00:22<00:59,  3.07it/s]
+
 28%|██▊       | 72/253 [00:23<00:57,  3.16it/s]
+
 29%|██▉       | 73/253 [00:23<00:56,  3.19it/s]
+
 29%|██▉       | 74/253 [00:23<00:57,  3.10it/s]
+
 30%|██▉       | 75/253 [00:24<00:57,  3.08it/s]
+
 30%|███       | 76/253 [00:24<00:58,  3.04it/s]
+
 30%|███       | 77/253 [00:24<00:57,  3.05it/s]
+
 31%|███       | 78/253 [00:25<00:58,  3.00it/s]
+
 31%|███       | 79/253 [00:25<00:59,  2.94it/s]
+
 32%|███▏      | 80/253 [00:25<00:59,  2.91it/s]
+
 32%|███▏      | 81/253 [00:26<00:58,  2.96it/s]
+
 32%|███▏      | 82/253 [00:26<00:54,  3.15it/s]
+
 33%|███▎      | 83/253 [00:26<00:53,  3.20it/s]
+
 33%|███▎      | 84/253 [00:27<00:54,  3.10it/s]
+
 34%|███▎      | 85/253 [00:27<00:55,  3.03it/s]
+
 34%|███▍      | 86/253 [00:27<00:53,  3.13it/s]
+
 34%|███▍      | 87/253 [00:28<00:53,  3.09it/s]
+
 35%|███▍      | 88/253 [00:28<00:50,  3.24it/s]
+
 35%|███▌      | 89/253 [00:28<00:52,  3.14it/s]
+
 36%|███▌      | 90/253 [00:29<00:52,  3.11it/s]
+
 36%|███▌      | 91/253 [00:29<00:51,  3.15it/s]
+
 36%|███▋      | 92/253 [00:29<00:51,  3.11it/s]
+
 37%|███▋      | 93/253 [00:30<00:53,  2.97it/s]
+
 37%|███▋      | 94/253 [00:30<00:52,  3.05it/s]
+
 38%|███▊      | 95/253 [00:30<00:50,  3.13it/s]
+
 38%|███▊      | 96/253 [00:31<00:49,  3.16it/s]
+
 38%|███▊      | 97/253 [00:31<00:50,  3.10it/s]
+
 39%|███▊      | 98/253 [00:31<00:49,  3.12it/s]
+
 39%|███▉      | 99/253 [00:32<00:50,  3.03it/s]
+
 40%|███▉      | 100/253 [00:32<00:49,  3.10it/s]
+
 40%|███▉      | 101/253 [00:32<00:48,  3.16it/s]
+
 40%|████      | 102/253 [00:32<00:47,  3.18it/s]
+
 41%|████      | 103/253 [00:33<00:48,  3.08it/s]
+
 41%|████      | 104/253 [00:33<00:47,  3.13it/s]
+
 42%|████▏     | 105/253 [00:33<00:48,  3.07it/s]
+
 42%|████▏     | 106/253 [00:34<00:46,  3.18it/s]
+
 42%|████▏     | 107/253 [00:34<00:42,  3.40it/s]
+
 43%|████▎     | 108/253 [00:34<00:44,  3.24it/s]
+
 43%|████▎     | 109/253 [00:35<00:42,  3.41it/s]
+
 43%|████▎     | 110/253 [00:35<00:43,  3.31it/s]
+
 44%|████▍     | 111/253 [00:35<00:44,  3.19it/s]
+
 44%|████▍     | 112/253 [00:36<00:44,  3.19it/s]
+
 45%|████▍     | 113/253 [00:36<00:45,  3.07it/s]
+
 45%|████▌     | 114/253 [00:36<00:46,  3.01it/s]
+
 45%|████▌     | 115/253 [00:37<00:44,  3.09it/s]
+
 46%|████▌     | 116/253 [00:37<00:44,  3.05it/s]
+
 46%|████▌     | 117/253 [00:37<00:44,  3.05it/s]
+
 47%|████▋     | 118/253 [00:38<00:42,  3.19it/s]
+
 47%|████▋     | 119/253 [00:38<00:42,  3.17it/s]
+
 47%|████▋     | 120/253 [00:38<00:43,  3.03it/s]
+
 48%|████▊     | 121/253 [00:39<00:43,  3.02it/s]
+
 48%|████▊     | 122/253 [00:39<00:40,  3.20it/s]
+
 49%|████▊     | 123/253 [00:39<00:41,  3.15it/s]
+
 49%|��███▉     | 124/253 [00:39<00:41,  3.11it/s]
+
 49%|████▉     | 125/253 [00:40<00:41,  3.07it/s]
+
 50%|████▉     | 126/253 [00:40<00:41,  3.07it/s]
+
 50%|█████     | 127/253 [00:40<00:41,  3.00it/s]
+
 51%|█████     | 128/253 [00:41<00:41,  3.04it/s]
+
 51%|█████     | 129/253 [00:41<00:42,  2.95it/s]
+
 51%|█████▏    | 130/253 [00:42<00:42,  2.90it/s]
+
 52%|█████▏    | 131/253 [00:42<00:41,  2.97it/s]
+
 52%|█████▏    | 132/253 [00:42<00:39,  3.08it/s]
+
 53%|█████▎    | 133/253 [00:42<00:38,  3.09it/s]
+
 53%|█████▎    | 134/253 [00:43<00:38,  3.11it/s]
+
 53%|█████▎    | 135/253 [00:43<00:38,  3.09it/s]
+
 54%|█████▍    | 136/253 [00:43<00:37,  3.16it/s]
+
 54%|█████▍    | 137/253 [00:44<00:37,  3.12it/s]
+
 55%|█████▍    | 138/253 [00:44<00:36,  3.12it/s]
+
 55%|█████▍    | 139/253 [00:44<00:36,  3.10it/s]
+
 55%|█████▌    | 140/253 [00:45<00:36,  3.12it/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,  3.00it/s]
+
 57%|█████▋    | 144/253 [00:46<00:35,  3.08it/s]
+
 57%|█████▋    | 145/253 [00:46<00:35,  3.08it/s]
+
 58%|█████▊    | 146/253 [00:47<00:34,  3.07it/s]
+
 58%|█████▊    | 147/253 [00:47<00:35,  3.02it/s]
+
 58%|█████▊    | 148/253 [00:47<00:34,  3.08it/s]
+
 59%|█████▉    | 149/253 [00:48<00:34,  3.03it/s]
+
 59%|█████▉    | 150/253 [00:48<00:33,  3.12it/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,  3.01it/s]
+
 61%|██████    | 154/253 [00:49<00:32,  3.09it/s]
+
 61%|██████▏   | 155/253 [00:50<00:31,  3.08it/s]
+
 62%|██████▏   | 156/253 [00:50<00:31,  3.06it/s]
+
 62%|██████▏   | 157/253 [00:50<00:30,  3.14it/s]
+
 62%|██████▏   | 158/253 [00:51<00:30,  3.10it/s]
+
 63%|██████▎   | 159/253 [00:51<00:29,  3.20it/s]
+
 63%|██████▎   | 160/253 [00:51<00:29,  3.19it/s]
+
 64%|██████▎   | 161/253 [00:51<00:29,  3.12it/s]
+
 64%|██████▍   | 162/253 [00:52<00:28,  3.16it/s]
+
 64%|██████▍   | 163/253 [00:52<00:28,  3.18it/s]
+
 65%|██████▍   | 164/253 [00:52<00:27,  3.20it/s]
+
 65%|██████▌   | 165/253 [00:53<00:28,  3.12it/s]
+
 66%|██████▌   | 166/253 [00:53<00:28,  3.05it/s]
+
 66%|██████▌   | 167/253 [00:53<00:28,  2.98it/s]
+
 66%|██████▋   | 168/253 [00:54<00:27,  3.11it/s]
+
 67%|██████▋   | 169/253 [00:54<00:26,  3.14it/s]
+
 67%|██████▋   | 170/253 [00:54<00:27,  3.07it/s]
+
 68%|██████▊   | 171/253 [00:55<00:25,  3.19it/s]
+
 68%|██████▊   | 172/253 [00:55<00:24,  3.25it/s]
+
 68%|██████▊   | 173/253 [00:55<00:24,  3.31it/s]
+
 69%|██████▉   | 174/253 [00:56<00:25,  3.07it/s]
+
 69%|██████▉   | 175/253 [00:56<00:24,  3.20it/s]
+
 70%|██████▉   | 176/253 [00:56<00:23,  3.30it/s]
+
 70%|██████▉   | 177/253 [00:57<00:23,  3.19it/s]
+
 70%|███████   | 178/253 [00:57<00:23,  3.20it/s]
+
 71%|███████   | 179/253 [00:57<00:23,  3.12it/s]
+
 71%|███████   | 180/253 [00:58<00:23,  3.09it/s]
+
 72%|███████▏  | 181/253 [00:58<00:23,  3.12it/s]
+
 72%|███████▏  | 182/253 [00:58<00:23,  3.04it/s]
+
 72%|███████▏  | 183/253 [00:58<00:22,  3.10it/s]
+
 73%|███████▎  | 184/253 [00:59<00:23,  2.98it/s]
+
 73%|███████▎  | 185/253 [00:59<00:22,  3.00it/s]
+
 74%|███████▎  | 186/253 [01:00<00:22,  3.03it/s]
+
 74%|███████▍  | 187/253 [01:00<00:21,  3.04it/s]
+
 74%|███████▍  | 188/253 [01:00<00:21,  3.05it/s]
+
 75%|███████▍  | 189/253 [01:00<00:20,  3.15it/s]
+
 75%|███████▌  | 190/253 [01:01<00:20,  3.07it/s]
+
 75%|███████▌  | 191/253 [01:01<00:20,  2.96it/s]
+
 76%|███████▌  | 192/253 [01:01<00:20,  3.01it/s]
+
 76%|███████▋  | 193/253 [01:02<00:18,  3.16it/s]
+
 77%|███████▋  | 194/253 [01:02<00:18,  3.12it/s]
+
 77%|███████▋  | 195/253 [01:02<00:18,  3.16it/s]
+
 77%|███████▋  | 196/253 [01:03<00:18,  3.09it/s]
+
 78%|███████▊  | 197/253 [01:03<00:17,  3.20it/s]
+
 78%|███████▊  | 198/253 [01:03<00:17,  3.14it/s]
+
 79%|███████▊  | 199/253 [01:04<00:17,  3.04it/s]
+
 79%|███████▉  | 200/253 [01:04<00:17,  2.96it/s]
+
 79%|███████▉  | 201/253 [01:04<00:17,  3.00it/s]
+
 80%|███████▉  | 202/253 [01:05<00:16,  3.00it/s]
+
 80%|████████  | 203/253 [01:05<00:16,  3.03it/s]
+
 81%|████████  | 204/253 [01:05<00:16,  2.92it/s]
+
 81%|████████  | 205/253 [01:06<00:16,  2.90it/s]
+
 81%|████████▏ | 206/253 [01:06<00:16,  2.83it/s]
+
 82%|████████▏ | 207/253 [01:06<00:16,  2.85it/s]
+
 82%|████████▏ | 208/253 [01:07<00:16,  2.80it/s]
+
 83%|████████▎ | 209/253 [01:07<00:15,  2.79it/s]
+
 83%|████████▎ | 210/253 [01:08<00:14,  2.90it/s]
+
 83%|████████▎ | 211/253 [01:08<00:14,  2.87it/s]
+
 84%|████████▍ | 212/253 [01:08<00:14,  2.83it/s]
+
 84%|████████▍ | 213/253 [01:09<00:13,  2.87it/s]
+
 85%|████████▍ | 214/253 [01:09<00:13,  2.87it/s]
+
 85%|████████▍ | 215/253 [01:09<00:13,  2.92it/s]
+
 85%|████████▌ | 216/253 [01:10<00:12,  2.96it/s]
+
 86%|████████▌ | 217/253 [01:10<00:11,  3.05it/s]
+
 86%|████████▌ | 218/253 [01:10<00:11,  3.08it/s]
+
 87%|████████▋ | 219/253 [01:11<00:11,  3.04it/s]
+
 87%|████████▋ | 220/253 [01:11<00:11,  2.94it/s]
+
 87%|████████▋ | 221/253 [01:11<00:11,  2.91it/s]
+
 88%|████████▊ | 222/253 [01:12<00:10,  2.92it/s]
+
 88%|████████▊ | 223/253 [01:12<00:10,  2.83it/s]
+
 89%|████████▊ | 224/253 [01:12<00:09,  2.94it/s]
+
 89%|████████▉ | 225/253 [01:13<00:09,  2.90it/s]
+
 89%|████████▉ | 226/253 [01:13<00:09,  2.96it/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,  3.02it/s]
+
 91%|█████████▏| 231/253 [01:15<00:07,  2.99it/s]
+
 92%|█████████▏| 232/253 [01:15<00:06,  3.02it/s]
+
 92%|█████████▏| 233/253 [01:15<00:06,  3.02it/s]
+
 92%|█████████▏| 234/253 [01:16<00:06,  2.98it/s]
+
 93%|█████████▎| 235/253 [01:16<00:05,  3.10it/s]
+
 93%|█████████▎| 236/253 [01:16<00:05,  3.06it/s]
+
 94%|█████████▎| 237/253 [01:17<00:05,  3.10it/s]
+
 94%|█████████▍| 238/253 [01:17<00:05,  2.95it/s]
+
 94%|█████████▍| 239/253 [01:17<00:04,  2.99it/s]
+
 95%|█████████▍| 240/253 [01:18<00:04,  2.94it/s]
+
 95%|█████████▌| 241/253 [01:18<00:04,  2.90it/s]
+
 96%|█████████▌| 242/253 [01:18<00:03,  2.80it/s]
+
 96%|█████████▌| 243/253 [01:19<00:03,  2.76it/s]
+
 96%|█████████▋| 244/253 [01:19<00:03,  2.76it/s]
+
 97%|█████████▋| 245/253 [01:19<00:02,  2.87it/s]
+
 97%|█████████▋| 246/253 [01:20<00:02,  2.83it/s]
+
 98%|█████████▊| 247/253 [01:20<00:02,  2.83it/s]
+
 98%|█████████▊| 248/253 [01:21<00:01,  2.75it/s]
+
 98%|█████████▊| 249/253 [01:21<00:01,  2.81it/s]
+
 99%|█████████▉| 250/253 [01:21<00:01,  2.84it/s]
+
 99%|█████████▉| 251/253 [01:22<00:00,  2.91it/s]
+
+
                                                          
+
                                                 
 64%|██████▎   | 43000/67700 [25:51:08<8:03:36,  1.17s/it]
+
+
                                                 Saving model checkpoint to ./checkpoint-43000
+Configuration saved in ./checkpoint-43000/config.json
+Model weights saved in ./checkpoint-43000/pytorch_model.bin
+Configuration saved in ./checkpoint-43000/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 sha256:58af4e71f693a4f9c9a3d43bea6a3403f2f1649c959b33b1f5f004d51eb2c159
+oid sha256:7d408ac0d2495eb0d2472fb35433aa5faaae2d7c01b2b8412abb20f64d4ca6da
 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:ac25066664d7f044f40a864d70b03487afd2354d75c0607fb352c5273d6bcae2
-size 103219
+oid sha256:a759d632dbf96d46ac99e3ffb7f94deeb791a62f36e81f41dbdb05d69ffb92be
+size 104391