Training in progress, step 44000

nohup.out

@@ -24166,3 +24166,275 @@ Configuration saved in ./checkpoint-43500/config.json
 Model weights saved in ./checkpoint-43500/pytorch_model.bin
 Configuration saved in ./checkpoint-43500/preprocessor_config.json
 Configuration saved in ./preprocessor_config.json
+Deleting older checkpoint [checkpoint-42000] due to args.save_total_limit
+
 64%|██████▍   | 43501/67700 [26:10:50<407:43:51, 60.66s/it]
 64%|██████▍   | 43502/67700 [26:10:51<288:58:51, 42.99s/it]
 64%|██████▍   | 43503/67700 [26:10:53<205:56:33, 30.64s/it]
 64%|██████▍   | 43504/67700 [26:10:55<147:39:13, 21.97s/it]
 64%|██████▍   | 43505/67700 [26:10:57<106:48:12, 15.89s/it]
 64%|██████▍   | 43506/67700 [26:10:58<78:11:07, 11.63s/it] 
 64%|██████▍   | 43507/67700 [26:11:00<58:04:50,  8.64s/it]
 64%|██████▍   | 43508/67700 [26:11:02<44:04:40,  6.56s/it]
 64%|██████▍   | 43509/67700 [26:11:03<34:03:32,  5.07s/it]
 64%|██████▍   | 43510/67700 [26:11:05<27:06:02,  4.03s/it]
 64%|██████▍   | 43511/67700 [26:11:07<22:10:40,  3.30s/it]
 64%|██████▍   | 43512/67700 [26:11:08<18:43:36,  2.79s/it]
 64%|██████▍   | 43513/67700 [26:11:10<16:12:25,  2.41s/it]
 64%|██████▍   | 43514/67700 [26:11:11<14:26:47,  2.15s/it]
 64%|██████▍   | 43515/67700 [26:11:13<13:04:14,  1.95s/it]
 64%|██████▍   | 43516/67700 [26:11:14<12:04:28,  1.80s/it]
 64%|██████▍   | 43517/67700 [26:11:16<11:18:03,  1.68s/it]
 64%|██████▍   | 43518/67700 [26:11:17<10:50:44,  1.61s/it]
 64%|██████▍   | 43519/67700 [26:11:18<10:19:15,  1.54s/it]
 64%|██████▍   | 43520/67700 [26:11:20<9:48:36,  1.46s/it] 
 64%|██████▍   | 43521/67700 [26:11:21<9:29:13,  1.41s/it]
 64%|██████▍   | 43522/67700 [26:11:22<9:24:33,  1.40s/it]
 64%|██████▍   | 43523/67700 [26:11:24<8:58:57,  1.34s/it]
 64%|██████▍   | 43524/67700 [26:11:25<8:39:07,  1.29s/it]
 64%|██████▍   | 43525/67700 [26:11:26<8:22:02,  1.25s/it]
 64%|██████▍   | 43526/67700 [26:11:27<8:13:45,  1.23s/it]
 64%|██████▍   | 43527/67700 [26:11:28<7:52:24,  1.17s/it]
 64%|██████▍   | 43528/67700 [26:11:29<7:26:09,  1.11s/it]
 64%|██████▍   | 43529/67700 [26:11:32<10:34:37,  1.58s/it]
 64%|██████▍   | 43530/67700 [26:11:34<12:27:44,  1.86s/it]
 64%|██████▍   | 43531/67700 [26:11:37<13:45:54,  2.05s/it]
 64%|██████▍   | 43532/67700 [26:11:39<14:36:19,  2.18s/it]
 64%|██████▍   | 43533/67700 [26:11:42<15:04:41,  2.25s/it]
 64%|██████▍   | 43534/67700 [26:11:44<15:13:32,  2.27s/it]
 64%|██████▍   | 43535/67700 [26:11:46<15:15:52,  2.27s/it]
 64%|██████▍   | 43536/67700 [26:11:48<15:11:03,  2.26s/it]
 64%|██████▍   | 43537/67700 [26:11:51<15:00:30,  2.24s/it]
 64%|██████▍   | 43538/67700 [26:11:53<14:51:20,  2.21s/it]
 64%|██████▍   | 43539/67700 [26:11:55<14:38:50,  2.18s/it]
 64%|██████▍   | 43540/67700 [26:11:57<14:27:33,  2.15s/it]
 64%|██████▍   | 43541/67700 [26:11:59<14:24:57,  2.15s/it]
 64%|██████▍   | 43542/67700 [26:12:01<14:15:41,  2.13s/it]
 64%|██████▍   | 43543/67700 [26:12:03<14:08:30,  2.11s/it]
 64%|██████▍   | 43544/67700 [26:12:05<14:04:50,  2.10s/it]
 64%|██████▍   | 43545/67700 [26:12:07<13:53:25,  2.07s/it]
 64%|██████▍   | 43546/67700 [26:12:09<13:47:57,  2.06s/it]
 64%|██████▍   | 43547/67700 [26:12:11<13:39:40,  2.04s/it]
 64%|██████▍   | 43548/67700 [26:12:13<13:28:27,  2.01s/it]
 64%|██████▍   | 43549/67700 [26:12:15<13:13:11,  1.97s/it]
 64%|██████▍   | 43550/67700 [26:12:17<12:59:00,  1.94s/it]
 64%|██████▍   | 43551/67700 [26:12:19<12:43:27,  1.90s/it]
 64%|██████▍   | 43552/67700 [26:12:21<12:29:48,  1.86s/it]
 64%|██████▍   | 43553/67700 [26:12:22<12:18:44,  1.84s/it]
 64%|██████▍   | 43554/67700 [26:12:24<12:11:07,  1.82s/it]
 64%|██████▍   | 43555/67700 [26:12:26<11:59:55,  1.79s/it]
 64%|██████▍   | 43556/67700 [26:12:28<11:49:11,  1.76s/it]
 64%|██████▍   | 43557/67700 [26:12:29<11:43:03,  1.75s/it]
 64%|██████▍   | 43558/67700 [26:12:31<11:36:46,  1.73s/it]
 64%|██████▍   | 43559/67700 [26:12:33<11:23:41,  1.70s/it]
 64%|██████▍   | 43560/67700 [26:12:34<11:20:58,  1.69s/it]
 64%|██████▍   | 43561/67700 [26:12:36<11:10:48,  1.67s/it]
 64%|██████▍   | 43562/67700 [26:12:37<10:59:03,  1.64s/it]
 64%|██████▍   | 43563/67700 [26:12:39<10:49:10,  1.61s/it]
 64%|██████▍   | 43564/67700 [26:12:41<10:38:17,  1.59s/it]
 64%|██████▍   | 43565/67700 [26:12:42<10:21:29,  1.55s/it]
 64%|██████▍   | 43566/67700 [26:12:43<10:12:28,  1.52s/it]
 64%|██████▍   | 43567/67700 [26:12:45<10:00:53,  1.49s/it]
 64%|██████▍   | 43568/67700 [26:12:46<9:52:07,  1.47s/it] 
 64%|██████▍   | 43569/67700 [26:12:48<9:40:52,  1.44s/it]
 64%|██████▍   | 43570/67700 [26:12:49<9:30:39,  1.42s/it]
 64%|██████▍   | 43571/67700 [26:12:50<9:18:43,  1.39s/it]
 64%|██████▍   | 43572/67700 [26:12:52<9:05:52,  1.36s/it]
 64%|██████▍   | 43573/67700 [26:12:53<8:50:21,  1.32s/it]
 64%|██████▍   | 43574/67700 [26:12:54<8:36:11,  1.28s/it]
 64%|██████▍   | 43575/67700 [26:12:55<8:22:03,  1.25s/it]
 64%|██████▍   | 43576/67700 [26:12:56<8:09:41,  1.22s/it]
 64%|██████▍   | 43577/67700 [26:12:58<7:56:03,  1.18s/it]
 64%|██████▍   | 43578/67700 [26:12:58<7:16:43,  1.09s/it]
 64%|██████▍   | 43579/67700 [26:13:01<10:10:20,  1.52s/it]
 64%|██████▍   | 43580/67700 [26:13:03<12:08:22,  1.81s/it]
 64%|██████▍   | 43581/67700 [26:13:06<13:38:12,  2.04s/it]
 64%|██████▍   | 43582/67700 [26:13:08<14:31:50,  2.17s/it]
 64%|██████▍   | 43583/67700 [26:13:11<15:00:38,  2.24s/it]
 64%|██████▍   | 43584/67700 [26:13:13<15:08:22,  2.26s/it]
 64%|██████▍   | 43585/67700 [26:13:15<15:05:50,  2.25s/it]
 64%|██████▍   | 43586/67700 [26:13:18<14:59:47,  2.24s/it]
 64%|██████▍   | 43587/67700 [26:13:20<14:57:38,  2.23s/it]
 64%|██████▍   | 43588/67700 [26:13:22<14:51:27,  2.22s/it]
 64%|██████▍   | 43589/67700 [26:13:24<14:45:11,  2.20s/it]
 64%|██████▍   | 43590/67700 [26:13:26<14:39:05,  2.19s/it]
 64%|██████▍   | 43591/67700 [26:13:28<14:35:40,  2.18s/it]
 64%|██████▍   | 43592/67700 [26:13:31<14:27:15,  2.16s/it]
 64%|██████▍   | 43593/67700 [26:13:33<14:19:47,  2.14s/it]
 64%|██████▍   | 43594/67700 [26:13:35<14:05:24,  2.10s/it]
 64%|██████▍   | 43595/67700 [26:13:37<13:56:15,  2.08s/it]
 64%|██████▍   | 43596/67700 [26:13:39<13:50:07,  2.07s/it]
 64%|██████▍   | 43597/67700 [26:13:41<13:34:29,  2.03s/it]
 64%|██████▍   | 43598/67700 [26:13:43<13:19:07,  1.99s/it]
 64%|██████▍   | 43599/67700 [26:13:44<13:07:32,  1.96s/it]
 64%|██████▍   | 43600/67700 [26:13:46<12:55:55,  1.93s/it]
                                                           
 64%|██████▍   | 43600/67700 [26:13:46<12:55:55,  1.93s/it]
 64%|██████▍   | 43601/67700 [26:13:48<12:44:33,  1.90s/it]
 64%|██████▍   | 43602/67700 [26:13:50<12:27:12,  1.86s/it]
 64%|██████▍   | 43603/67700 [26:13:52<12:15:32,  1.83s/it]
 64%|██████▍   | 43604/67700 [26:13:53<12:05:18,  1.81s/it]
 64%|██████▍   | 43605/67700 [26:13:55<11:54:05,  1.78s/it]
 64%|██████▍   | 43606/67700 [26:13:57<11:44:38,  1.75s/it]
 64%|██████▍   | 43607/67700 [26:13:59<11:32:06,  1.72s/it]
 64%|██████▍   | 43608/67700 [26:14:00<11:21:11,  1.70s/it]
 64%|██████▍   | 43609/67700 [26:14:02<11:11:56,  1.67s/it]
 64%|██████▍   | 43610/67700 [26:14:03<11:04:28,  1.65s/it]
 64%|██████▍   | 43611/67700 [26:14:05<10:57:53,  1.64s/it]
 64%|██████▍   | 43612/67700 [26:14:07<10:47:07,  1.61s/it]
 64%|██████▍   | 43613/67700 [26:14:08<10:34:05,  1.58s/it]
 64%|██████▍   | 43614/67700 [26:14:10<10:22:24,  1.55s/it]
 64%|██████▍   | 43615/67700 [26:14:11<10:15:15,  1.53s/it]
 64%|██████▍   | 43616/67700 [26:14:12<10:01:08,  1.50s/it]
 64%|██████▍   | 43617/67700 [26:14:14<9:52:04,  1.48s/it] 
 64%|██████▍   | 43618/67700 [26:14:15<9:41:59,  1.45s/it]
 64%|██████▍   | 43619/67700 [26:14:17<9:34:52,  1.43s/it]
 64%|██████▍   | 43620/67700 [26:14:18<9:23:04,  1.40s/it]
 64%|██████▍   | 43621/67700 [26:14:19<9:04:28,  1.36s/it]
 64%|██████▍   | 43622/67700 [26:14:20<8:54:12,  1.33s/it]
 64%|██████▍   | 43623/67700 [26:14:22<8:40:24,  1.30s/it]
 64%|██████▍   | 43624/67700 [26:14:23<8:25:35,  1.26s/it]
 64%|██████▍   | 43625/67700 [26:14:24<8:18:52,  1.24s/it]
 64%|██████▍   | 43626/67700 [26:14:25<8:02:31,  1.20s/it]
 64%|██████▍   | 43627/67700 [26:14:26<7:42:42,  1.15s/it]
 64%|██████▍   | 43628/67700 [26:14:27<7:24:37,  1.11s/it]
 64%|██████▍   | 43629/67700 [26:14:30<10:27:25,  1.56s/it]
 64%|██████▍   | 43630/67700 [26:14:32<12:26:55,  1.86s/it]
 64%|██████▍   | 43631/67700 [26:14:35<13:51:31,  2.07s/it]
 64%|██████▍   | 43632/67700 [26:14:37<14:38:19,  2.19s/it]
 64%|██████▍   | 43633/67700 [26:14:40<15:09:56,  2.27s/it]
 64%|██████▍   | 43634/67700 [26:14:42<15:16:28,  2.28s/it]
 64%|██████▍   | 43635/67700 [26:14:45<15:19:19,  2.29s/it]
 64%|██████▍   | 43636/67700 [26:14:47<15:13:23,  2.28s/it]
 64%|██████▍   | 43637/67700 [26:14:49<15:09:57,  2.27s/it]
 64%|██████▍   | 43638/67700 [26:14:51<14:57:39,  2.24s/it]
 64%|██████▍   | 43639/67700 [26:14:53<14:48:04,  2.21s/it]
 64%|██████▍   | 43640/67700 [26:14:56<14:44:02,  2.20s/it]
 64%|██████▍   | 43641/67700 [26:14:58<14:35:19,  2.18s/it]
 64%|██████▍   | 43642/67700 [26:15:00<14:22:16,  2.15s/it]
 64%|██████▍   | 43643/67700 [26:15:02<14:15:24,  2.13s/it]
 64%|██████▍   | 43644/67700 [26:15:04<14:06:48,  2.11s/it]
 64%|██████▍   | 43645/67700 [26:15:06<14:01:12,  2.10s/it]
 64%|██████▍   | 43646/67700 [26:15:08<13:46:42,  2.06s/it]
 64%|██████▍   | 43647/67700 [26:15:10<13:26:58,  2.01s/it]
 64%|██████▍   | 43648/67700 [26:15:12<13:17:06,  1.99s/it]
 64%|██████▍   | 43649/67700 [26:15:14<12:56:38,  1.94s/it]
 64%|██████▍   | 43650/67700 [26:15:15<12:39:47,  1.90s/it]
 64%|██████▍   | 43651/67700 [26:15:17<12:28:30,  1.87s/it]
 64%|██████▍   | 43652/67700 [26:15:19<12:22:14,  1.85s/it]
 64%|██████▍   | 43653/67700 [26:15:21<12:07:02,  1.81s/it]
 64%|██████▍   | 43654/67700 [26:15:22<11:59:21,  1.79s/it]
 64%|██████▍   | 43655/67700 [26:15:24<11:51:09,  1.77s/it]
 64%|██████▍   | 43656/67700 [26:15:26<11:41:46,  1.75s/it]
 64%|██████▍   | 43657/67700 [26:15:28<11:27:33,  1.72s/it]
 64%|██████▍   | 43658/67700 [26:15:29<11:16:49,  1.69s/it]
 64%|██████▍   | 43659/67700 [26:15:31<11:12:39,  1.68s/it]
 64%|██████▍   | 43660/67700 [26:15:32<11:04:52,  1.66s/it]
 64%|██████▍   | 43661/67700 [26:15:34<10:52:04,  1.63s/it]
 64%|██████▍   | 43662/67700 [26:15:35<10:38:35,  1.59s/it]
 64%|██████▍   | 43663/67700 [26:15:37<10:26:01,  1.56s/it]
 64%|██████▍   | 43664/67700 [26:15:38<10:15:59,  1.54s/it]
 64%|██████▍   | 43665/67700 [26:15:40<10:16:32,  1.54s/it]
 64%|██████▍   | 43666/67700 [26:15:41<10:02:30,  1.50s/it]
 65%|██████▍   | 43667/67700 [26:15:43<9:52:22,  1.48s/it] 
 65%|██████▍   | 43668/67700 [26:15:44<9:48:22,  1.47s/it]
 65%|██████▍   | 43669/67700 [26:15:46<9:38:07,  1.44s/it]
 65%|██████▍   | 43670/67700 [26:15:47<9:25:19,  1.41s/it]
 65%|██████▍   | 43671/67700 [26:15:48<9:11:14,  1.38s/it]
 65%|██████▍   | 43672/67700 [26:15:50<8:59:17,  1.35s/it]
 65%|██████▍   | 43673/67700 [26:15:51<8:44:07,  1.31s/it]
 65%|██████▍   | 43674/67700 [26:15:52<8:29:39,  1.27s/it]
 65%|██████▍   | 43675/67700 [26:15:53<8:15:37,  1.24s/it]
 65%|██████▍   | 43676/67700 [26:15:54<8:05:47,  1.21s/it]
 65%|██████▍   | 43677/67700 [26:15:55<7:47:20,  1.17s/it]
 65%|██████▍   | 43678/67700 [26:15:56<7:27:12,  1.12s/it]
 65%|██████▍   | 43679/67700 [26:15:59<10:22:59,  1.56s/it]
 65%|██████▍   | 43680/67700 [26:16:02<12:25:30,  1.86s/it]
 65%|██████▍   | 43681/67700 [26:16:04<13:49:44,  2.07s/it]
 65%|██████▍   | 43682/67700 [26:16:07<14:42:35,  2.20s/it]
 65%|██████▍   | 43683/67700 [26:16:09<15:14:15,  2.28s/it]
 65%|██████▍   | 43684/67700 [26:16:11<15:17:43,  2.29s/it]
 65%|██████▍   | 43685/67700 [26:16:14<15:22:29,  2.30s/it]
 65%|██████▍   | 43686/67700 [26:16:16<15:25:27,  2.31s/it]
 65%|██████▍   | 43687/67700 [26:16:18<15:26:19,  2.31s/it]
 65%|██████▍   | 43688/67700 [26:16:21<15:10:29,  2.28s/it]
 65%|██████▍   | 43689/67700 [26:16:23<14:48:10,  2.22s/it]
 65%|██████▍   | 43690/67700 [26:16:25<14:39:49,  2.20s/it]
 65%|██████▍   | 43691/67700 [26:16:27<14:24:07,  2.16s/it]
 65%|██████▍   | 43692/67700 [26:16:29<14:15:48,  2.14s/it]
 65%|██████▍   | 43693/67700 [26:16:31<14:04:56,  2.11s/it]
 65%|██████▍   | 43694/67700 [26:16:33<13:50:35,  2.08s/it]
 65%|██████▍   | 43695/67700 [26:16:35<13:44:08,  2.06s/it]
 65%|██████▍   | 43696/67700 [26:16:37<13:39:03,  2.05s/it]
 65%|██████▍   | 43697/67700 [26:16:39<13:20:00,  2.00s/it]
 65%|██████▍   | 43698/67700 [26:16:41<13:05:11,  1.96s/it]
 65%|██████▍   | 43699/67700 [26:16:43<12:50:17,  1.93s/it]
 65%|██████▍   | 43700/67700 [26:16:44<12:37:34,  1.89s/it]
                                                           
 65%|██████▍   | 43700/67700 [26:16:44<12:37:34,  1.89s/it]
 65%|██████▍   | 43701/67700 [26:16:46<12:31:39,  1.88s/it]
 65%|██████▍   | 43702/67700 [26:16:48<12:23:24,  1.86s/it]
 65%|██████▍   | 43703/67700 [26:16:50<12:13:53,  1.83s/it]
 65%|██████▍   | 43704/67700 [26:16:52<12:04:50,  1.81s/it]
 65%|██████▍   | 43705/67700 [26:16:53<11:52:00,  1.78s/it]
 65%|██████▍   | 43706/67700 [26:16:55<11:40:47,  1.75s/it]
 65%|██████▍   | 43707/67700 [26:16:57<11:34:00,  1.74s/it]
 65%|██████▍   | 43708/67700 [26:16:58<11:26:42,  1.72s/it]
 65%|██████▍   | 43709/67700 [26:17:00<11:14:46,  1.69s/it]
 65%|██████▍   | 43710/67700 [26:17:02<11:06:07,  1.67s/it]
 65%|██████▍   | 43711/67700 [26:17:03<10:48:50,  1.62s/it]
 65%|██████▍   | 43712/67700 [26:17:05<10:38:57,  1.60s/it]
 65%|██████▍   | 43713/67700 [26:17:06<10:26:44,  1.57s/it]
 65%|██████▍   | 43714/67700 [26:17:08<10:16:44,  1.54s/it]
 65%|██████▍   | 43715/67700 [26:17:09<10:06:50,  1.52s/it]
 65%|██████▍   | 43716/67700 [26:17:11<10:00:28,  1.50s/it]
 65%|██████▍   | 43717/67700 [26:17:12<9:43:50,  1.46s/it] 
 65%|██████▍   | 43718/67700 [26:17:13<9:30:05,  1.43s/it]
 65%|██████▍   | 43719/67700 [26:17:15<9:16:17,  1.39s/it]
 65%|██████▍   | 43720/67700 [26:17:16<9:08:10,  1.37s/it]
 65%|██████▍   | 43721/67700 [26:17:17<8:56:57,  1.34s/it]
 65%|██████▍   | 43722/67700 [26:17:18<8:44:24,  1.31s/it]
 65%|██████▍   | 43723/67700 [26:17:20<8:31:04,  1.28s/it]
 65%|██████▍   | 43724/67700 [26:17:21<8:20:16,  1.25s/it]
 65%|██████▍   | 43725/67700 [26:17:22<8:17:37,  1.25s/it]
 65%|██████▍   | 43726/67700 [26:17:23<8:01:01,  1.20s/it]
 65%|██████▍   | 43727/67700 [26:17:24<7:39:12,  1.15s/it]
 65%|██████▍   | 43728/67700 [26:17:25<7:13:50,  1.09s/it]
 65%|██████▍   | 43729/67700 [26:17:28<10:11:40,  1.53s/it]
 65%|██████▍   | 43730/67700 [26:17:30<12:14:07,  1.84s/it]
 65%|██████▍   | 43731/67700 [26:17:33<13:37:40,  2.05s/it]
 65%|██████▍   | 43732/67700 [26:17:35<14:24:31,  2.16s/it]
 65%|██████▍   | 43733/67700 [26:17:38<14:50:28,  2.23s/it]
 65%|██████▍   | 43734/67700 [26:17:40<15:10:52,  2.28s/it]
 65%|██████▍   | 43735/67700 [26:17:42<15:08:58,  2.28s/it]
 65%|██████▍   | 43736/67700 [26:17:45<15:02:57,  2.26s/it]
 65%|██████▍   | 43737/67700 [26:17:47<15:07:02,  2.27s/it]
 65%|██████▍   | 43738/67700 [26:17:49<14:55:26,  2.24s/it]
 65%|██████▍   | 43739/67700 [26:17:51<14:50:17,  2.23s/it]
 65%|██████▍   | 43740/67700 [26:17:53<14:39:28,  2.20s/it]
 65%|██████▍   | 43741/67700 [26:17:55<14:27:01,  2.17s/it]
 65%|██████▍   | 43742/67700 [26:17:58<14:32:49,  2.19s/it]
 65%|██████▍   | 43743/67700 [26:18:00<14:12:17,  2.13s/it]
 65%|██████▍   | 43744/67700 [26:18:02<14:02:47,  2.11s/it]
 65%|██████▍   | 43745/67700 [26:18:04<13:50:34,  2.08s/it]
 65%|██████▍   | 43746/67700 [26:18:06<13:44:22,  2.06s/it]
 65%|██████▍   | 43747/67700 [26:18:08<13:29:36,  2.03s/it]
 65%|██████▍   | 43748/67700 [26:18:10<13:15:19,  1.99s/it]
 65%|██████▍   | 43749/67700 [26:18:12<13:01:53,  1.96s/it]
 65%|██████▍   | 43750/67700 [26:18:13<12:50:51,  1.93s/it]
 65%|██████▍   | 43751/67700 [26:18:15<12:38:06,  1.90s/it]
 65%|██████▍   | 43752/67700 [26:18:17<12:26:56,  1.87s/it]
 65%|██████▍   | 43753/67700 [26:18:19<12:11:16,  1.83s/it]
 65%|██████▍   | 43754/67700 [26:18:21<12:06:15,  1.82s/it]
 65%|██████▍   | 43755/67700 [26:18:22<11:56:44,  1.80s/it]
 65%|██████▍   | 43756/67700 [26:18:24<11:45:10,  1.77s/it]
 65%|██████▍   | 43757/67700 [26:18:26<11:35:02,  1.74s/it]
 65%|██████▍   | 43758/67700 [26:18:27<11:26:44,  1.72s/it]
 65%|██████▍   | 43759/67700 [26:18:29<11:22:45,  1.71s/it]
 65%|██████▍   | 43760/67700 [26:18:31<11:11:04,  1.68s/it]
 65%|██████▍   | 43761/67700 [26:18:32<11:02:10,  1.66s/it]
 65%|██████▍   | 43762/67700 [26:18:34<10:50:27,  1.63s/it]
 65%|██████▍   | 43763/67700 [26:18:35<10:41:37,  1.61s/it]
 65%|██████▍   | 43764/67700 [26:18:37<10:30:44,  1.58s/it]
 65%|██████▍   | 43765/67700 [26:18:38<10:15:06,  1.54s/it]
 65%|██████▍   | 43766/67700 [26:18:40<10:03:29,  1.51s/it]
 65%|██████▍   | 43767/67700 [26:18:41<9:52:39,  1.49s/it] 
 65%|██████▍   | 43768/67700 [26:18:43<9:45:23,  1.47s/it]
 65%|██████▍   | 43769/67700 [26:18:44<9:33:14,  1.44s/it]
 65%|██████▍   | 43770/67700 [26:18:45<9:24:08,  1.41s/it]
 65%|██████▍   | 43771/67700 [26:18:47<9:07:27,  1.37s/it]
 65%|██████▍   | 43772/67700 [26:18:48<8:59:54,  1.35s/it]
 65%|██████▍   | 43773/67700 [26:18:49<8:48:53,  1.33s/it]
 65%|██████▍   | 43774/67700 [26:18:50<8:34:16,  1.29s/it]
 65%|██████▍   | 43775/67700 [26:18:52<8:20:21,  1.25s/it]
 65%|██████▍   | 43776/67700 [26:18:53<8:07:57,  1.22s/it]
 65%|██████▍   | 43777/67700 [26:18:54<7:44:51,  1.17s/it]
 65%|██████▍   | 43778/67700 [26:18:55<7:22:10,  1.11s/it]
 65%|██████▍   | 43779/67700 [26:18:57<10:19:59,  1.56s/it]
 65%|██████▍   | 43780/67700 [26:19:00<12:22:18,  1.86s/it]
 65%|██████▍   | 43781/67700 [26:19:02<13:44:53,  2.07s/it]
 65%|██████▍   | 43782/67700 [26:19:05<14:31:56,  2.19s/it]
 65%|██████▍   | 43783/67700 [26:19:07<14:54:32,  2.24s/it]
 65%|██████▍   | 43784/67700 [26:19:10<14:57:27,  2.25s/it]
 65%|██████▍   | 43785/67700 [26:19:12<14:58:37,  2.25s/it]
 65%|██████▍   | 43786/67700 [26:19:14<14:55:03,  2.25s/it]
 65%|██████▍   | 43787/67700 [26:19:16<14:48:49,  2.23s/it]
 65%|██████▍   | 43788/67700 [26:19:18<14:39:57,  2.21s/it]
 65%|██████▍   | 43789/67700 [26:19:21<14:34:56,  2.20s/it]
 65%|██████▍   | 43790/67700 [26:19:23<14:32:25,  2.19s/it]
 65%|██████▍   | 43791/67700 [26:19:25<14:16:57,  2.15s/it]
 65%|██████▍   | 43792/67700 [26:19:27<14:08:48,  2.13s/it]
 65%|██████▍   | 43793/67700 [26:19:29<13:56:50,  2.10s/it]
 65%|██████▍   | 43794/67700 [26:19:31<13:44:47,  2.07s/it]
 65%|██████▍   | 43795/67700 [26:19:33<13:38:13,  2.05s/it]
 65%|██████▍   | 43796/67700 [26:19:35<13:24:34,  2.02s/it]
 65%|██████▍   | 43797/67700 [26:19:37<13:11:01,  1.99s/it]
 65%|██████▍   | 43798/67700 [26:19:39<12:57:13,  1.95s/it]
 65%|██████▍   | 43799/67700 [26:19:41<12:50:07,  1.93s/it]
 65%|██████▍   | 43800/67700 [26:19:42<12:38:17,  1.90s/it]
                                                           
 65%|██████▍   | 43800/67700 [26:19:42<12:38:17,  1.90s/it]
 65%|██████▍   | 43801/67700 [26:19:44<12:27:24,  1.88s/it]
 65%|██████▍   | 43802/67700 [26:19:46<12:19:07,  1.86s/it]
 65%|██████▍   | 43803/67700 [26:19:48<12:07:46,  1.83s/it]
 65%|██████▍   | 43804/67700 [26:19:49<11:56:14,  1.80s/it]
 65%|██████▍   | 43805/67700 [26:19:51<11:45:17,  1.77s/it]
 65%|██████▍   | 43806/67700 [26:19:53<11:32:19,  1.74s/it]
 65%|██████▍   | 43807/67700 [26:19:55<11:24:57,  1.72s/it]
 65%|██████▍   | 43808/67700 [26:19:56<11:14:06,  1.69s/it]
 65%|██████▍   | 43809/67700 [26:19:58<11:04:15,  1.67s/it]
 65%|██████▍   | 43810/67700 [26:19:59<10:59:52,  1.66s/it]
 65%|██████▍   | 43811/67700 [26:20:01<10:48:44,  1.63s/it]
 65%|██████▍   | 43812/67700 [26:20:02<10:35:53,  1.60s/it]
 65%|██████▍   | 43813/67700 [26:20:04<10:26:41,  1.57s/it]
 65%|██████▍   | 43814/67700 [26:20:05<10:15:47,  1.55s/it]
 65%|██████▍   | 43815/67700 [26:20:07<10:05:11,  1.52s/it]
 65%|██████▍   | 43816/67700 [26:20:08<9:54:52,  1.49s/it] 
 65%|██████▍   | 43817/67700 [26:20:10<9:49:04,  1.48s/it]
 65%|██████▍   | 43818/67700 [26:20:11<9:37:29,  1.45s/it]
 65%|██████▍   | 43819/67700 [26:20:13<9:33:28,  1.44s/it]
 65%|██████▍   | 43820/67700 [26:20:14<9:21:21,  1.41s/it]
 65%|██████▍   | 43821/67700 [26:20:15<9:07:36,  1.38s/it]
 65%|██████▍   | 43822/67700 [26:20:17<8:57:07,  1.35s/it]
 65%|██████▍   | 43823/67700 [26:20:18<8:43:30,  1.32s/it]
 65%|██████▍   | 43824/67700 [26:20:19<8:31:10,  1.28s/it]
 65%|██████▍   | 43825/67700 [26:20:20<8:20:53,  1.26s/it]
 65%|██████▍   | 43826/67700 [26:20:21<8:14:10,  1.24s/it]
 65%|██████▍   | 43827/67700 [26:20:22<7:49:11,  1.18s/it]
 65%|██████▍   | 43828/67700 [26:20:23<7:30:39,  1.13s/it]
 65%|██████▍   | 43829/67700 [26:20:26<10:21:51,  1.56s/it]
 65%|██████▍   | 43830/67700 [26:20:29<12:31:16,  1.89s/it]
 65%|██████▍   | 43831/67700 [26:20:31<13:46:00,  2.08s/it]
 65%|██████▍   | 43832/67700 [26:20:34<14:33:43,  2.20s/it]
 65%|██████▍   | 43833/67700 [26:20:36<15:14:03,  2.30s/it]
 65%|██████▍   | 43834/67700 [26:20:39<15:20:05,  2.31s/it]
 65%|██████▍   | 43835/67700 [26:20:41<15:25:16,  2.33s/it]
 65%|██████▍   | 43836/67700 [26:20:43<15:17:27,  2.31s/it]
 65%|██████▍   | 43837/67700 [26:20:45<15:08:21,  2.28s/it]
 65%|██████▍   | 43838/67700 [26:20:48<15:01:45,  2.27s/it]
 65%|██████▍   | 43839/67700 [26:20:50<14:53:43,  2.25s/it]
 65%|██████▍   | 43840/67700 [26:20:52<14:37:42,  2.21s/it]
 65%|██████▍   | 43841/67700 [26:20:54<14:29:34,  2.19s/it]
 65%|██████▍   | 43842/67700 [26:20:56<14:21:01,  2.17s/it]
 65%|██████▍   | 43843/67700 [26:20:58<14:09:57,  2.14s/it]
 65%|██████▍   | 43844/67700 [26:21:00<13:52:10,  2.09s/it]
 65%|██████▍   | 43845/67700 [26:21:02<13:40:38,  2.06s/it]
 65%|██████▍   | 43846/67700 [26:21:04<13:31:30,  2.04s/it]
 65%|██████▍   | 43847/67700 [26:21:06<13:27:31,  2.03s/it]
 65%|██████▍   | 43848/67700 [26:21:08<13:14:41,  2.00s/it]
 65%|██████▍   | 43849/67700 [26:21:10<13:00:46,  1.96s/it]
 65%|██████▍   | 43850/67700 [26:21:12<12:56:01,  1.95s/it]
 65%|██████▍   | 43851/67700 [26:21:14<12:45:44,  1.93s/it]
 65%|██████▍   | 43852/67700 [26:21:16<12:32:36,  1.89s/it]
 65%|██████▍   | 43853/67700 [26:21:17<12:19:56,  1.86s/it]
 65%|██████▍   | 43854/67700 [26:21:19<12:08:56,  1.83s/it]
 65%|██████▍   | 43855/67700 [26:21:21<12:03:04,  1.82s/it]
 65%|██████▍   | 43856/67700 [26:21:23<11:55:50,  1.80s/it]
 65%|██████▍   | 43857/67700 [26:21:24<11:45:53,  1.78s/it]
 65%|██████▍   | 43858/67700 [26:21:26<11:38:09,  1.76s/it]
 65%|██████▍   | 43859/67700 [26:21:28<11:33:28,  1.75s/it]
 65%|██████▍   | 43860/67700 [26:21:30<11:25:13,  1.72s/it]
 65%|██████▍   | 43861/67700 [26:21:31<11:10:46,  1.69s/it]
 65%|██████▍   | 43862/67700 [26:21:33<10:55:27,  1.65s/it]
 65%|██████▍   | 43863/67700 [26:21:34<10:44:39,  1.62s/it]
 65%|██████▍   | 43864/67700 [26:21:36<10:33:57,  1.60s/it]
 65%|██████▍   | 43865/67700 [26:21:37<10:22:11,  1.57s/it]
 65%|██████▍   | 43866/67700 [26:21:39<10:11:12,  1.54s/it]
 65%|██████▍   | 43867/67700 [26:21:40<9:59:24,  1.51s/it] 
 65%|██████▍   | 43868/67700 [26:21:42<9:47:57,  1.48s/it]
 65%|██████▍   | 43869/67700 [26:21:43<9:37:39,  1.45s/it]
 65%|██████▍   | 43870/67700 [26:21:44<9:22:47,  1.42s/it]
 65%|██████▍   | 43871/67700 [26:21:46<9:08:55,  1.38s/it]
 65%|██████▍   | 43872/67700 [26:21:47<8:56:44,  1.35s/it]
 65%|██████▍   | 43873/67700 [26:21:48<8:44:14,  1.32s/it]
 65%|██████▍   | 43874/67700 [26:21:49<8:30:39,  1.29s/it]
 65%|██████▍   | 43875/67700 [26:21:51<8:23:06,  1.27s/it]
 65%|██████▍   | 43876/67700 [26:21:52<8:04:02,  1.22s/it]
 65%|██████▍   | 43877/67700 [26:21:53<7:44:38,  1.17s/it]
 65%|██████▍   | 43878/67700 [26:21:54<7:20:01,  1.11s/it]
 65%|██████▍   | 43879/67700 [26:21:56<10:13:31,  1.55s/it]
 65%|██████▍   | 43880/67700 [26:21:59<12:14:59,  1.85s/it]
 65%|██████▍   | 43881/67700 [26:22:01<13:35:54,  2.06s/it]
 65%|██████▍   | 43882/67700 [26:22:04<14:25:29,  2.18s/it]
 65%|██████▍   | 43883/67700 [26:22:06<14:50:05,  2.24s/it]
 65%|██████▍   | 43884/67700 [26:22:09<15:00:22,  2.27s/it]
 65%|██████▍   | 43885/67700 [26:22:11<15:06:40,  2.28s/it]
 65%|██████▍   | 43886/67700 [26:22:13<14:59:28,  2.27s/it]
 65%|██████▍   | 43887/67700 [26:22:15<14:48:11,  2.24s/it]
 65%|██████▍   | 43888/67700 [26:22:18<14:38:13,  2.21s/it]
 65%|██████▍   | 43889/67700 [26:22:20<14:28:32,  2.19s/it]
 65%|██████▍   | 43890/67700 [26:22:22<14:19:45,  2.17s/it]
 65%|██████▍   | 43891/67700 [26:22:24<14:13:22,  2.15s/it]
 65%|██████▍   | 43892/67700 [26:22:26<14:07:18,  2.14s/it]
 65%|██████▍   | 43893/67700 [26:22:28<13:56:31,  2.11s/it]
 65%|██████▍   | 43894/67700 [26:22:30<13:47:06,  2.08s/it]
 65%|██████▍   | 43895/67700 [26:22:32<13:40:01,  2.07s/it]
 65%|██████▍   | 43896/67700 [26:22:34<13:30:31,  2.04s/it]
 65%|██████▍   | 43897/67700 [26:22:36<13:11:26,  1.99s/it]
 65%|██████▍   | 43898/67700 [26:22:38<12:57:41,  1.96s/it]
 65%|██████▍   | 43899/67700 [26:22:40<12:45:50,  1.93s/it]
 65%|██████▍   | 43900/67700 [26:22:41<12:31:58,  1.90s/it]
                                                           
 65%|██████▍   | 43900/67700 [26:22:41<12:31:58,  1.90s/it]
 65%|██████▍   | 43901/67700 [26:22:43<12:22:43,  1.87s/it]
 65%|██████▍   | 43902/67700 [26:22:45<12:11:34,  1.84s/it]
 65%|██████▍   | 43903/67700 [26:22:47<11:59:05,  1.81s/it]
 65%|██████▍   | 43904/67700 [26:22:49<11:51:09,  1.79s/it]
 65%|██████▍   | 43905/67700 [26:22:50<11:40:46,  1.77s/it]
 65%|██████▍   | 43906/67700 [26:22:52<11:39:51,  1.76s/it]
 65%|██████▍   | 43907/67700 [26:22:54<11:27:37,  1.73s/it]
 65%|██████▍   | 43908/67700 [26:22:55<11:17:21,  1.71s/it]
 65%|██████▍   | 43909/67700 [26:22:57<11:07:30,  1.68s/it]
 65%|██████▍   | 43910/67700 [26:22:59<10:58:50,  1.66s/it]
 65%|██████▍   | 43911/67700 [26:23:00<10:47:39,  1.63s/it]
 65%|██████▍   | 43912/67700 [26:23:02<10:41:02,  1.62s/it]
 65%|██████▍   | 43913/67700 [26:23:03<10:35:40,  1.60s/it]
 65%|██████▍   | 43914/67700 [26:23:05<10:25:44,  1.58s/it]
 65%|██████▍   | 43915/67700 [26:23:06<10:15:21,  1.55s/it]
 65%|██████▍   | 43916/67700 [26:23:08<10:04:52,  1.53s/it]
 65%|██████▍   | 43917/67700 [26:23:09<9:53:04,  1.50s/it] 
 65%|██████▍   | 43918/67700 [26:23:11<9:43:35,  1.47s/it]
 65%|██████▍   | 43919/67700 [26:23:12<9:34:30,  1.45s/it]
 65%|██████▍   | 43920/67700 [26:23:13<9:23:13,  1.42s/it]
 65%|██████▍   | 43921/67700 [26:23:15<9:05:50,  1.38s/it]
 65%|██████▍   | 43922/67700 [26:23:16<8:51:26,  1.34s/it]
 65%|██████▍   | 43923/67700 [26:23:17<8:40:09,  1.31s/it]
 65%|██████▍   | 43924/67700 [26:23:18<8:28:28,  1.28s/it]
 65%|██████▍   | 43925/67700 [26:23:20<8:13:40,  1.25s/it]
 65%|██████▍   | 43926/67700 [26:23:21<7:57:49,  1.21s/it]
 65%|██████▍   | 43927/67700 [26:23:22<7:37:21,  1.15s/it]
 65%|██████▍   | 43928/67700 [26:23:23<7:13:02,  1.09s/it]
 65%|██████▍   | 43929/67700 [26:23:25<10:07:55,  1.53s/it]
 65%|██████▍   | 43930/67700 [26:23:28<12:02:54,  1.82s/it]
 65%|██████▍   | 43931/67700 [26:23:30<13:35:02,  2.06s/it]
 65%|██████▍   | 43932/67700 [26:23:33<14:27:25,  2.19s/it]
 65%|██████▍   | 43933/67700 [26:23:35<15:00:06,  2.27s/it]
 65%|██████▍   | 43934/67700 [26:23:38<15:04:53,  2.28s/it]
 65%|██████▍   | 43935/67700 [26:23:40<15:03:52,  2.28s/it]
 65%|██████▍   | 43936/67700 [26:23:42<15:00:16,  2.27s/it]
 65%|██████▍   | 43937/67700 [26:23:44<14:50:50,  2.25s/it]
 65%|██████▍   | 43938/67700 [26:23:47<14:46:34,  2.24s/it]
 65%|██████▍   | 43939/67700 [26:23:49<14:37:47,  2.22s/it]
 65%|██████▍   | 43940/67700 [26:23:51<14:26:46,  2.19s/it]
 65%|██████▍   | 43941/67700 [26:23:53<14:15:52,  2.16s/it]
 65%|██████▍   | 43942/67700 [26:23:55<14:05:48,  2.14s/it]
 65%|██████▍   | 43943/67700 [26:23:57<13:54:20,  2.11s/it]
 65%|██████▍   | 43944/67700 [26:23:59<13:45:28,  2.08s/it]
 65%|██████▍   | 43945/67700 [26:24:01<13:37:51,  2.07s/it]
 65%|██████▍   | 43946/67700 [26:24:03<13:26:00,  2.04s/it]
 65%|██████▍   | 43947/67700 [26:24:05<13:10:34,  2.00s/it]
 65%|██████▍   | 43948/67700 [26:24:07<12:56:13,  1.96s/it]
 65%|██████▍   | 43949/67700 [26:24:09<12:41:47,  1.92s/it]
 65%|██████▍   | 43950/67700 [26:24:11<12:33:41,  1.90s/it]
 65%|██████▍   | 43951/67700 [26:24:12<12:18:30,  1.87s/it]
 65%|██████▍   | 43952/67700 [26:24:14<12:10:30,  1.85s/it]
 65%|██████▍   | 43953/67700 [26:24:16<11:57:26,  1.81s/it]
 65%|██████▍   | 43954/67700 [26:24:18<11:49:17,  1.79s/it]
 65%|██████▍   | 43955/67700 [26:24:19<11:37:42,  1.76s/it]
 65%|██████▍   | 43956/67700 [26:24:21<11:29:51,  1.74s/it]
 65%|██████▍   | 43957/67700 [26:24:23<11:24:54,  1.73s/it]
 65%|██████▍   | 43958/67700 [26:24:24<11:19:15,  1.72s/it]
 65%|██████▍   | 43959/67700 [26:24:26<11:06:07,  1.68s/it]
 65%|██████▍   | 43960/67700 [26:24:28<11:02:45,  1.68s/it]
 65%|██████▍   | 43961/67700 [26:24:29<10:53:24,  1.65s/it]
 65%|██████▍   | 43962/67700 [26:24:31<10:40:22,  1.62s/it]
 65%|██████▍   | 43963/67700 [26:24:32<10:31:27,  1.60s/it]
 65%|██████▍   | 43964/67700 [26:24:34<10:15:57,  1.56s/it]
 65%|██████▍   | 43965/67700 [26:24:35<10:06:11,  1.53s/it]
 65%|██████▍   | 43966/67700 [26:24:37<9:54:26,  1.50s/it] 
 65%|██████▍   | 43967/67700 [26:24:38<9:46:22,  1.48s/it]
 65%|██████▍   | 43968/67700 [26:24:39<9:35:33,  1.46s/it]
 65%|██████▍   | 43969/67700 [26:24:41<9:24:12,  1.43s/it]
 65%|██████▍   | 43970/67700 [26:24:42<9:10:53,  1.39s/it]
 65%|██████▍   | 43971/67700 [26:24:43<8:56:36,  1.36s/it]
 65%|██████▍   | 43972/67700 [26:24:45<8:41:30,  1.32s/it]
 65%|██████▍   | 43973/67700 [26:24:46<8:28:40,  1.29s/it]
 65%|██████▍   | 43974/67700 [26:24:47<8:16:38,  1.26s/it]
 65%|██████▍   | 43975/67700 [26:24:48<8:02:54,  1.22s/it]
 65%|██████▍   | 43976/67700 [26:24:49<7:50:13,  1.19s/it]
 65%|██████▍   | 43977/67700 [26:24:50<7:30:19,  1.14s/it]
 65%|██████▍   | 43978/67700 [26:24:51<7:07:53,  1.08s/it]
 65%|██████▍   | 43979/67700 [26:24:54<10:02:35,  1.52s/it]
 65%|██████▍   | 43980/67700 [26:24:56<11:58:57,  1.82s/it]
 65%|██████▍   | 43981/67700 [26:24:59<13:07:44,  1.99s/it]
 65%|██████▍   | 43982/67700 [26:25:01<13:39:27,  2.07s/it]
 65%|██████▍   | 43983/67700 [26:25:03<13:57:41,  2.12s/it]
 65%|██████▍   | 43984/67700 [26:25:05<14:08:30,  2.15s/it]
 65%|██████▍   | 43985/67700 [26:25:08<14:03:51,  2.13s/it]
 65%|██████▍   | 43986/67700 [26:25:10<14:00:18,  2.13s/it]
 65%|██████▍   | 43987/67700 [26:25:12<13:49:01,  2.10s/it]
 65%|██████▍   | 43988/67700 [26:25:14<13:38:50,  2.07s/it]
 65%|██████▍   | 43989/67700 [26:25:16<13:26:03,  2.04s/it]
 65%|██████▍   | 43990/67700 [26:25:18<13:05:06,  1.99s/it]
 65%|██████▍   | 43991/67700 [26:25:19<12:46:12,  1.94s/it]
 65%|██████▍   | 43992/67700 [26:25:21<12:26:49,  1.89s/it]
 65%|██████▍   | 43993/67700 [26:25:23<12:04:46,  1.83s/it]
 65%|██████▍   | 43994/67700 [26:25:25<11:48:21,  1.79s/it]
 65%|██████▍   | 43995/67700 [26:25:26<11:31:28,  1.75s/it]
 65%|██████▍   | 43996/67700 [26:25:28<11:15:00,  1.71s/it]
 65%|██████▍   | 43997/67700 [26:25:29<10:58:38,  1.67s/it]
 65%|██████▍   | 43998/67700 [26:25:31<10:39:34,  1.62s/it]
 65%|██████▍   | 43999/67700 [26:25:32<10:23:36,  1.58s/it]
 65%|██████▍   | 44000/67700 [26:25:34<10:04:54,  1.53s/it]
                                                           
 65%|██████▍   | 44000/67700 [26:25:34<10:04:54,  1.53s/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': 0.8461813926696777, 'eval_wer': 0.8579910935180604, 'eval_cer': 0.21995583216221642, 'eval_runtime': 113.6821, 'eval_samples_per_second': 17.778, 'eval_steps_per_second': 2.226, 'epoch': 64.25}
+{'loss': 1.5826, 'learning_rate': 2.7536529680365295e-05, 'epoch': 64.4}
+{'loss': 1.5888, 'learning_rate': 2.7422374429223743e-05, 'epoch': 64.55}
+{'loss': 1.5746, 'learning_rate': 2.730821917808219e-05, 'epoch': 64.7}
+{'loss': 1.5332, 'learning_rate': 2.719406392694064e-05, 'epoch': 64.84}
+{'loss': 1.5115, 'learning_rate': 2.7079908675799087e-05, 'epoch': 64.99}
+
+
  0%|          | 0/253 [00:00<?, ?it/s]
+
  1%|          | 2/253 [00:00<00:40,  6.14it/s]
+
  1%|          | 3/253 [00:00<00:58,  4.28it/s]
+
  2%|▏         | 4/253 [00:00<01:03,  3.91it/s]
+
  2%|▏         | 5/253 [00:01<01:10,  3.50it/s]
+
  2%|▏         | 6/253 [00:01<01:11,  3.44it/s]
+
  3%|▎         | 7/253 [00:01<01:16,  3.23it/s]
+
  3%|▎         | 8/253 [00:02<01:17,  3.14it/s]
+
  4%|▎         | 9/253 [00:02<01:23,  2.94it/s]
+
  4%|▍         | 10/253 [00:03<01:22,  2.94it/s]
+
  4%|▍         | 11/253 [00:03<01:22,  2.95it/s]
+
  5%|▍         | 12/253 [00:03<01:20,  3.01it/s]
+
  5%|▌         | 13/253 [00:04<01:21,  2.95it/s]
+
  6%|▌         | 14/253 [00:04<01:19,  3.02it/s]
+
  6%|▌         | 15/253 [00:04<01:20,  2.94it/s]
+
  6%|▋         | 16/253 [00:05<01:19,  2.96it/s]
+
  7%|▋         | 17/253 [00:05<01:23,  2.83it/s]
+
  7%|▋         | 18/253 [00:05<01:21,  2.87it/s]
+
  8%|▊         | 19/253 [00:06<01:18,  3.00it/s]
+
  8%|▊         | 20/253 [00:06<01:14,  3.11it/s]
+
  8%|▊         | 21/253 [00:06<01:16,  3.03it/s]
+
  9%|▊         | 22/253 [00:07<01:16,  3.01it/s]
+
  9%|▉         | 23/253 [00:07<01:17,  2.95it/s]
+
  9%|▉         | 24/253 [00:07<01:15,  3.01it/s]
+
 10%|▉         | 25/253 [00:08<01:15,  3.01it/s]
+
 10%|█         | 26/253 [00:08<01:15,  3.01it/s]
+
 11%|█         | 27/253 [00:08<01:16,  2.97it/s]
+
 11%|█         | 28/253 [00:09<01:14,  3.03it/s]
+
 11%|█▏        | 29/253 [00:09<01:15,  2.98it/s]
+
 12%|█▏        | 30/253 [00:09<01:15,  2.94it/s]
+
 12%|█▏        | 31/253 [00:10<01:15,  2.94it/s]
+
 13%|█▎        | 32/253 [00:10<01:16,  2.91it/s]
+
 13%|█▎        | 33/253 [00:10<01:14,  2.95it/s]
+
 13%|█▎        | 34/253 [00:11<01:14,  2.95it/s]
+
 14%|█▍        | 35/253 [00:11<01:12,  3.00it/s]
+
 14%|█▍        | 36/253 [00:11<01:09,  3.11it/s]
+
 15%|█▍        | 37/253 [00:12<01:08,  3.14it/s]
+
 15%|█▌        | 38/253 [00:12<01:10,  3.03it/s]
+
 15%|█▌        | 39/253 [00:12<01:09,  3.07it/s]
+
 16%|█▌        | 40/253 [00:12<01:07,  3.17it/s]
+
 16%|��▌        | 41/253 [00:13<01:07,  3.14it/s]
+
 17%|█▋        | 42/253 [00:13<01:07,  3.13it/s]
+
 17%|█▋        | 43/253 [00:13<01:04,  3.25it/s]
+
 17%|█▋        | 44/253 [00:14<01:06,  3.15it/s]
+
 18%|█▊        | 45/253 [00:14<01:07,  3.10it/s]
+
 18%|█▊        | 46/253 [00:14<01:04,  3.22it/s]
+
 19%|█▊        | 47/253 [00:15<01:05,  3.14it/s]
+
 19%|█▉        | 48/253 [00:15<01:05,  3.14it/s]
+
 19%|█▉        | 49/253 [00:15<01:04,  3.19it/s]
+
 20%|█▉        | 50/253 [00:16<01:03,  3.20it/s]
+
 20%|██        | 51/253 [00:16<01:04,  3.13it/s]
+
 21%|██        | 52/253 [00:16<01:04,  3.10it/s]
+
 21%|██        | 53/253 [00:17<01:04,  3.10it/s]
+
 21%|██▏       | 54/253 [00:17<01:05,  3.06it/s]
+
 22%|██▏       | 55/253 [00:17<01:03,  3.14it/s]
+
 22%|██▏       | 56/253 [00:18<01:03,  3.10it/s]
+
 23%|██▎       | 57/253 [00:18<01:01,  3.18it/s]
+
 23%|██▎       | 58/253 [00:18<01:01,  3.17it/s]
+
 23%|██▎       | 59/253 [00:19<01:01,  3.15it/s]
+
 24%|██▎       | 60/253 [00:19<01:00,  3.19it/s]
+
 24%|██▍       | 61/253 [00:19<01:01,  3.11it/s]
+
 25%|██▍       | 62/253 [00:19<00:59,  3.21it/s]
+
 25%|██▍       | 63/253 [00:20<01:00,  3.13it/s]
+
 25%|██▌       | 64/253 [00:20<01:00,  3.11it/s]
+
 26%|██▌       | 65/253 [00:20<01:00,  3.10it/s]
+
 26%|██▌       | 66/253 [00:21<01:01,  3.05it/s]
+
 26%|██▋       | 67/253 [00:21<01:02,  2.96it/s]
+
 27%|██▋       | 68/253 [00:21<01:00,  3.06it/s]
+
 27%|██▋       | 69/253 [00:22<00:58,  3.13it/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<00:56,  3.19it/s]
+
 29%|██▉       | 73/253 [00:23<00:55,  3.25it/s]
+
 29%|██▉       | 74/253 [00:23<00:57,  3.12it/s]
+
 30%|██▉       | 75/253 [00:24<00:57,  3.10it/s]
+
 30%|███       | 76/253 [00:24<00:57,  3.07it/s]
+
 30%|███       | 77/253 [00:24<00:57,  3.08it/s]
+
 31%|███       | 78/253 [00:25<00:58,  3.01it/s]
+
 31%|███       | 79/253 [00:25<00:58,  2.96it/s]
+
 32%|███▏      | 80/253 [00:25<00:59,  2.92it/s]
+
 32%|███▏      | 81/253 [00:26<00:58,  2.96it/s]
+
 32%|███▏      | 82/253 [00:26<00:54,  3.16it/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,  3.04it/s]
+
 34%|███▍      | 86/253 [00:27<00:52,  3.16it/s]
+
 34%|███▍      | 87/253 [00:28<00:52,  3.14it/s]
+
 35%|███▍      | 88/253 [00:28<00:50,  3.29it/s]
+
 35%|███▌      | 89/253 [00:28<00:51,  3.18it/s]
+
 36%|███▌      | 90/253 [00:28<00:51,  3.14it/s]
+
 36%|███▌      | 91/253 [00:29<00:51,  3.16it/s]
+
 36%|███▋      | 92/253 [00:29<00:51,  3.12it/s]
+
 37%|███▋      | 93/253 [00:29<00:52,  3.02it/s]
+
 37%|███▋      | 94/253 [00:30<00:51,  3.07it/s]
+
 38%|███▊      | 95/253 [00:30<00:50,  3.16it/s]
+
 38%|███▊      | 96/253 [00:30<00:49,  3.18it/s]
+
 38%|███▊      | 97/253 [00:31<00:50,  3.11it/s]
+
 39%|███▊      | 98/253 [00:31<00:49,  3.14it/s]
+
 39%|███▉      | 99/253 [00:31<00:50,  3.03it/s]
+
 40%|███▉      | 100/253 [00:32<00:49,  3.10it/s]
+
 40%|███▉      | 101/253 [00:32<00:47,  3.17it/s]
+
 40%|████      | 102/253 [00:32<00:47,  3.17it/s]
+
 41%|████      | 103/253 [00:33<00:48,  3.07it/s]
+
 41%|████      | 104/253 [00:33<00:47,  3.11it/s]
+
 42%|████▏     | 105/253 [00:33<00:47,  3.10it/s]
+
 42%|████▏     | 106/253 [00:34<00:45,  3.20it/s]
+
 42%|████▏     | 107/253 [00:34<00:42,  3.45it/s]
+
 43%|████▎     | 108/253 [00:34<00:44,  3.29it/s]
+
 43%|████▎     | 109/253 [00:34<00:41,  3.45it/s]
+
 43%|████▎     | 110/253 [00:35<00:42,  3.40it/s]
+
 44%|████▍     | 111/253 [00:35<00:42,  3.31it/s]
+
 44%|████▍     | 112/253 [00:35<00:42,  3.29it/s]
+
 45%|████▍     | 113/253 [00:36<00:43,  3.24it/s]
+
 45%|████▌     | 114/253 [00:36<00:44,  3.13it/s]
+
 45%|████▌     | 115/253 [00:36<00:43,  3.18it/s]
+
 46%|████▌     | 116/253 [00:37<00:44,  3.09it/s]
+
 46%|████▌     | 117/253 [00:37<00:43,  3.10it/s]
+
 47%|████▋     | 118/253 [00:37<00:41,  3.22it/s]
+
 47%|████▋     | 119/253 [00:38<00:41,  3.23it/s]
+
 47%|████▋     | 120/253 [00:38<00:42,  3.10it/s]
+
 48%|████▊     | 121/253 [00:38<00:42,  3.09it/s]
+
 48%|████▊     | 122/253 [00:39<00:39,  3.29it/s]
+
 49%|████▊     | 123/253 [00:39<00:40,  3.23it/s]
+
 49%|████▉     | 124/253 [00:39<00:40,  3.17it/s]
+
 49%|████▉     | 125/253 [00:40<00:41,  3.11it/s]
+
 50%|████▉     | 126/253 [00:40<00:40,  3.10it/s]
+
 50%|█████     | 127/253 [00:40<00:41,  3.04it/s]
+
 51%|█████     | 128/253 [00:41<00:40,  3.06it/s]
+
 51%|█████     | 129/253 [00:41<00:42,  2.94it/s]
+
 51%|█████▏    | 130/253 [00:41<00:42,  2.89it/s]
+
 52%|█████▏    | 131/253 [00:42<00:41,  2.95it/s]
+
 52%|█████▏    | 132/253 [00:42<00:39,  3.06it/s]
+
 53%|█████▎    | 133/253 [00:42<00:38,  3.08it/s]
+
 53%|█████▎    | 134/253 [00:43<00:38,  3.10it/s]
+
 53%|█████▎    | 135/253 [00:43<00:38,  3.06it/s]
+
 54%|█████▍    | 136/253 [00:43<00:37,  3.14it/s]
+
 54%|█████▍    | 137/253 [00:43<00:37,  3.10it/s]
+
 55%|█████▍    | 138/253 [00:44<00:37,  3.10it/s]
+
 55%|█████▍    | 139/253 [00:44<00:37,  3.08it/s]
+
 55%|█████▌    | 140/253 [00:44<00:36,  3.12it/s]
+
 56%|█████▌    | 141/253 [00:45<00:36,  3.07it/s]
+
 56%|█████▌    | 142/253 [00:45<00:35,  3.16it/s]
+
 57%|█████▋    | 143/253 [00:45<00:36,  3.03it/s]
+
 57%|█████▋    | 144/253 [00:46<00:35,  3.11it/s]
+
 57%|█████▋    | 145/253 [00:46<00:34,  3.11it/s]
+
 58%|█████▊    | 146/253 [00:46<00:34,  3.10it/s]
+
 58%|█████▊    | 147/253 [00:47<00:34,  3.06it/s]
+
 58%|█████▊    | 148/253 [00:47<00:34,  3.04it/s]
+
 59%|█████▉    | 149/253 [00:47<00:35,  2.93it/s]
+
 59%|█████▉    | 150/253 [00:48<00:34,  3.03it/s]
+
 60%|█████▉    | 151/253 [00:48<00:33,  3.08it/s]
+
 60%|██████    | 152/253 [00:48<00:33,  2.98it/s]
+
 60%|██████    | 153/253 [00:49<00:34,  2.90it/s]
+
 61%|██████    | 154/253 [00:49<00:33,  2.99it/s]
+
 61%|██████▏   | 155/253 [00:49<00:32,  2.98it/s]
+
 62%|██████▏   | 156/253 [00:50<00:33,  2.93it/s]
+
 62%|██████▏   | 157/253 [00:50<00:34,  2.79it/s]
+
 62%|██████▏   | 158/253 [00:50<00:33,  2.87it/s]
+
 63%|██████▎   | 159/253 [00:51<00:30,  3.05it/s]
+
 63%|██████▎   | 160/253 [00:51<00:30,  3.09it/s]
+
 64%|██████▎   | 161/253 [00:51<00:30,  3.04it/s]
+
 64%|██████▍   | 162/253 [00:52<00:29,  3.09it/s]
+
 64%|██████▍   | 163/253 [00:52<00:28,  3.14it/s]
+
 65%|██████▍   | 164/253 [00:52<00:28,  3.18it/s]
+
 65%|██████▌   | 165/253 [00:53<00:28,  3.13it/s]
+
 66%|██████▌   | 166/253 [00:53<00:27,  3.12it/s]
+
 66%|██████▌   | 167/253 [00:53<00:28,  3.06it/s]
+
 66%|██████▋   | 168/253 [00:54<00:26,  3.17it/s]
+
 67%|██████▋   | 169/253 [00:54<00:26,  3.17it/s]
+
 67%|██████▋   | 170/253 [00:54<00:27,  3.07it/s]
+
 68%|██████▊   | 171/253 [00:55<00:25,  3.17it/s]
+
 68%|██████▊   | 172/253 [00:55<00:25,  3.21it/s]
+
 68%|██████▊   | 173/253 [00:55<00:24,  3.30it/s]
+
 69%|██████▉   | 174/253 [00:56<00:25,  3.08it/s]
+
 69%|██████▉   | 175/253 [00:56<00:24,  3.20it/s]
+
 70%|██████▉   | 176/253 [00:56<00:23,  3.29it/s]
+
 70%|██████▉   | 177/253 [00:56<00:24,  3.14it/s]
+
 70%|███████   | 178/253 [00:57<00:24,  3.10it/s]
+
 71%|███████   | 179/253 [00:57<00:24,  3.01it/s]
+
 71%|███████   | 180/253 [00:58<00:24,  2.92it/s]
+
 72%|███████▏  | 181/253 [00:58<00:24,  2.99it/s]
+
 72%|███████▏  | 182/253 [00:58<00:24,  2.93it/s]
+
 72%|███████▏  | 183/253 [00:59<00:23,  3.02it/s]
+
 73%|███████▎  | 184/253 [00:59<00:23,  2.90it/s]
+
 73%|███████▎  | 185/253 [00:59<00:23,  2.94it/s]
+
 74%|███████▎  | 186/253 [01:00<00:22,  2.98it/s]
+
 74%|███████▍  | 187/253 [01:00<00:22,  3.00it/s]
+
 74%|███████▍  | 188/253 [01:00<00:21,  3.02it/s]
+
 75%|███████▍  | 189/253 [01:00<00:20,  3.13it/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,  3.12it/s]
+
 77%|███████▋  | 195/253 [01:02<00:18,  3.15it/s]
+
 77%|███████▋  | 196/253 [01:03<00:18,  3.07it/s]
+
 78%|███████▊  | 197/253 [01:03<00:17,  3.18it/s]
+
 78%|███████▊  | 198/253 [01:03<00:17,  3.13it/s]
+
 79%|���██████▊  | 199/253 [01:04<00:17,  3.04it/s]
+
 79%|███████▉  | 200/253 [01:04<00:17,  2.97it/s]
+
 79%|███████▉  | 201/253 [01:04<00:17,  3.00it/s]
+
 80%|███████▉  | 202/253 [01:05<00:16,  3.01it/s]
+
 80%|████████  | 203/253 [01:05<00:16,  3.06it/s]
+
 81%|████████  | 204/253 [01:05<00:16,  2.97it/s]
+
 81%|████████  | 205/253 [01:06<00:16,  2.96it/s]
+
 81%|████████▏ | 206/253 [01:06<00:16,  2.91it/s]
+
 82%|████████▏ | 207/253 [01:06<00:15,  2.93it/s]
+
 82%|████████▏ | 208/253 [01:07<00:15,  2.91it/s]
+
 83%|████████▎ | 209/253 [01:07<00:15,  2.90it/s]
+
 83%|████████▎ | 210/253 [01:07<00:14,  3.00it/s]
+
 83%|████████▎ | 211/253 [01:08<00:14,  2.94it/s]
+
 84%|████████▍ | 212/253 [01:08<00:14,  2.87it/s]
+
 84%|████████▍ | 213/253 [01:09<00:13,  2.88it/s]
+
 85%|████████▍ | 214/253 [01:09<00:13,  2.88it/s]
+
 85%|████████▍ | 215/253 [01:09<00:12,  2.93it/s]
+
 85%|████████▌ | 216/253 [01:10<00:12,  2.96it/s]
+
 86%|████████▌ | 217/253 [01:10<00:11,  3.06it/s]
+
 86%|████████▌ | 218/253 [01:10<00:11,  3.11it/s]
+
 87%|████████▋ | 219/253 [01:10<00:10,  3.10it/s]
+
 87%|████████▋ | 220/253 [01:11<00:11,  2.96it/s]
+
 87%|████████▋ | 221/253 [01:11<00:10,  2.95it/s]
+
 88%|████████▊ | 222/253 [01:12<00:10,  2.97it/s]
+
 88%|████████▊ | 223/253 [01:12<00:10,  2.97it/s]
+
 89%|████████▊ | 224/253 [01:12<00:09,  3.06it/s]
+
 89%|████████▉ | 225/253 [01:13<00:09,  3.01it/s]
+
 89%|████████▉ | 226/253 [01:13<00:08,  3.05it/s]
+
 90%|████████▉ | 227/253 [01:13<00:08,  3.18it/s]
+
 90%|█████████ | 228/253 [01:13<00:07,  3.15it/s]
+
 91%|█████████ | 229/253 [01:14<00:07,  3.11it/s]
+
 91%|█████████ | 230/253 [01:14<00:07,  3.06it/s]
+
 91%|█████████▏| 231/253 [01:14<00:07,  3.03it/s]
+
 92%|█████████▏| 232/253 [01:15<00:06,  3.06it/s]
+
 92%|█████████▏| 233/253 [01:15<00:06,  3.06it/s]
+
 92%|█████████▏| 234/253 [01:15<00:06,  3.08it/s]
+
 93%|█████████▎| 235/253 [01:16<00:05,  3.24it/s]
+
 93%|█████████▎| 236/253 [01:16<00:05,  3.26it/s]
+
 94%|█████████▎| 237/253 [01:16<00:04,  3.25it/s]
+
 94%|█████████▍| 238/253 [01:17<00:04,  3.03it/s]
+
 94%|█████████▍| 239/253 [01:17<00:04,  3.07it/s]
+
 95%|█████████▍| 240/253 [01:17<00:04,  3.01it/s]
+
 95%|█████████▌| 241/253 [01:18<00:04,  2.95it/s]
+
 96%|█████████▌| 242/253 [01:18<00:03,  2.86it/s]
+
 96%|█████████▌| 243/253 [01:18<00:03,  2.83it/s]
+
 96%|█████████▋| 244/253 [01:19<00:03,  2.82it/s]
+
 97%|█████████▋| 245/253 [01:19<00:02,  2.94it/s]
+
 97%|█████████▋| 246/253 [01:19<00:02,  2.91it/s]
+
 98%|█████████▊| 247/253 [01:20<00:02,  2.85it/s]
+
 98%|█████████▊| 248/253 [01:20<00:01,  2.76it/s]
+
 98%|█████████▊| 249/253 [01:21<00:01,  2.79it/s]
+
 99%|█████████▉| 250/253 [01:21<00:01,  2.83it/s]
+
 99%|█████████▉| 251/253 [01:21<00:00,  2.89it/s]
+
+
                                                           
+
                                                 
 65%|██████▍   | 44000/67700 [26:27:28<10:04:54,  1.53s/it]
+
+
                                                 Saving model checkpoint to ./checkpoint-44000
+Configuration saved in ./checkpoint-44000/config.json
+Model weights saved in ./checkpoint-44000/pytorch_model.bin
+Configuration saved in ./checkpoint-44000/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:f63336b93d2b599006899bbadb1ad3c1b0a6beace161269e4126fa138f30da8c
+oid sha256:2a10be63ee568995958d9faad185419ed8308692e52fbe0282d1530b88a53460
 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 sha256:960da41c7abfe4a85062162c236d2467bbfba2c562b53e67078d401883db24b0
-size 105563
+oid sha256:daba43470c25d04aa27131ecd7e864849b887a43fb328e7cd8a8e7bd1f9d5dc8
+size 106735