Training in progress, step 45000

nohup.out

@@ -24710,3 +24710,275 @@ Configuration saved in ./checkpoint-44500/config.json
 Model weights saved in ./checkpoint-44500/pytorch_model.bin
 Configuration saved in ./checkpoint-44500/preprocessor_config.json
 Configuration saved in ./preprocessor_config.json
+Deleting older checkpoint [checkpoint-43000] due to args.save_total_limit
+
 66%|██████▌   | 44501/67700 [26:46:57<382:06:54, 59.30s/it]
 66%|██████▌   | 44502/67700 [26:46:58<269:42:00, 41.85s/it]
 66%|██████▌   | 44503/67700 [26:46:59<190:51:43, 29.62s/it]
 66%|██████▌   | 44504/67700 [26:47:00<135:38:34, 21.05s/it]
 66%|██████▌   | 44505/67700 [26:47:01<96:55:21, 15.04s/it] 
 66%|██████▌   | 44506/67700 [26:47:04<72:53:42, 11.31s/it]
 66%|██████▌   | 44507/67700 [26:47:06<55:59:45,  8.69s/it]
 66%|██████▌   | 44508/67700 [26:47:09<44:00:55,  6.83s/it]
 66%|██████▌   | 44509/67700 [26:47:11<35:34:51,  5.52s/it]
 66%|██████▌   | 44510/67700 [26:47:14<29:34:21,  4.59s/it]
 66%|██████▌   | 44511/67700 [26:47:16<25:04:08,  3.89s/it]
 66%|██████▌   | 44512/67700 [26:47:18<21:57:07,  3.41s/it]
 66%|██████▌   | 44513/67700 [26:47:20<19:45:14,  3.07s/it]
 66%|██████▌   | 44514/67700 [26:47:23<18:04:49,  2.81s/it]
 66%|██████▌   | 44515/67700 [26:47:25<16:48:17,  2.61s/it]
 66%|██████▌   | 44516/67700 [26:47:27<15:59:33,  2.48s/it]
 66%|██████▌   | 44517/67700 [26:47:29<15:31:59,  2.41s/it]
 66%|██████▌   | 44518/67700 [26:47:31<14:57:39,  2.32s/it]
 66%|██████▌   | 44519/67700 [26:47:33<14:34:36,  2.26s/it]
 66%|██████▌   | 44520/67700 [26:47:36<14:11:49,  2.20s/it]
 66%|██████▌   | 44521/67700 [26:47:38<13:53:09,  2.16s/it]
 66%|██████▌   | 44522/67700 [26:47:40<13:45:03,  2.14s/it]
 66%|██████▌   | 44523/67700 [26:47:42<13:29:08,  2.09s/it]
 66%|██████▌   | 44524/67700 [26:47:44<13:05:41,  2.03s/it]
 66%|██████▌   | 44525/67700 [26:47:45<12:49:35,  1.99s/it]
 66%|██████▌   | 44526/67700 [26:47:47<12:37:04,  1.96s/it]
 66%|██████▌   | 44527/67700 [26:47:49<12:23:15,  1.92s/it]
 66%|██████▌   | 44528/67700 [26:47:51<12:14:53,  1.90s/it]
 66%|██████▌   | 44529/67700 [26:47:53<12:01:27,  1.87s/it]
 66%|██████▌   | 44530/67700 [26:47:55<11:52:34,  1.85s/it]
 66%|██████▌   | 44531/67700 [26:47:56<11:40:49,  1.81s/it]
 66%|██████▌   | 44532/67700 [26:47:58<11:40:43,  1.81s/it]
 66%|██████▌   | 44533/67700 [26:48:00<11:28:20,  1.78s/it]
 66%|██████▌   | 44534/67700 [26:48:02<11:16:14,  1.75s/it]
 66%|██████▌   | 44535/67700 [26:48:03<11:05:14,  1.72s/it]
 66%|██████▌   | 44536/67700 [26:48:05<10:53:53,  1.69s/it]
 66%|██████▌   | 44537/67700 [26:48:06<10:42:40,  1.66s/it]
 66%|██████▌   | 44538/67700 [26:48:08<10:37:01,  1.65s/it]
 66%|██████▌   | 44539/67700 [26:48:10<10:29:21,  1.63s/it]
 66%|██████▌   | 44540/67700 [26:48:11<10:20:54,  1.61s/it]
 66%|██████▌   | 44541/67700 [26:48:13<10:09:16,  1.58s/it]
 66%|██████▌   | 44542/67700 [26:48:14<9:54:11,  1.54s/it] 
 66%|██████▌   | 44543/67700 [26:48:16<9:44:07,  1.51s/it]
 66%|██████▌   | 44544/67700 [26:48:17<9:36:39,  1.49s/it]
 66%|██████▌   | 44545/67700 [26:48:18<9:27:10,  1.47s/it]
 66%|██████▌   | 44546/67700 [26:48:20<9:17:39,  1.45s/it]
 66%|██████▌   | 44547/67700 [26:48:21<9:01:33,  1.40s/it]
 66%|██████▌   | 44548/67700 [26:48:22<8:48:09,  1.37s/it]
 66%|██████▌   | 44549/67700 [26:48:24<8:33:16,  1.33s/it]
 66%|██████▌   | 44550/67700 [26:48:25<8:20:32,  1.30s/it]
 66%|██████▌   | 44551/67700 [26:48:26<8:06:41,  1.26s/it]
 66%|██████▌   | 44552/67700 [26:48:27<8:00:10,  1.24s/it]
 66%|██████▌   | 44553/67700 [26:48:28<7:48:41,  1.21s/it]
 66%|██████▌   | 44554/67700 [26:48:29<7:29:53,  1.17s/it]
 66%|██████▌   | 44555/67700 [26:48:30<7:08:19,  1.11s/it]
 66%|██████▌   | 44556/67700 [26:48:33<10:00:35,  1.56s/it]
 66%|██████▌   | 44557/67700 [26:48:36<11:53:29,  1.85s/it]
 66%|██████▌   | 44558/67700 [26:48:38<13:06:59,  2.04s/it]
 66%|██████▌   | 44559/67700 [26:48:41<13:56:59,  2.17s/it]
 66%|██████▌   | 44560/67700 [26:48:43<14:29:30,  2.25s/it]
 66%|██████▌   | 44561/67700 [26:48:45<14:41:18,  2.29s/it]
 66%|██████▌   | 44562/67700 [26:48:48<14:45:48,  2.30s/it]
 66%|██████▌   | 44563/67700 [26:48:50<14:37:54,  2.28s/it]
 66%|██████▌   | 44564/67700 [26:48:52<14:36:40,  2.27s/it]
 66%|██████▌   | 44565/67700 [26:48:54<14:20:45,  2.23s/it]
 66%|██████▌   | 44566/67700 [26:48:57<14:20:25,  2.23s/it]
 66%|██████▌   | 44567/67700 [26:48:59<14:14:57,  2.22s/it]
 66%|██████▌   | 44568/67700 [26:49:01<14:18:12,  2.23s/it]
 66%|██████▌   | 44569/67700 [26:49:03<14:08:29,  2.20s/it]
 66%|██████▌   | 44570/67700 [26:49:05<13:49:55,  2.15s/it]
 66%|██████▌   | 44571/67700 [26:49:07<13:38:09,  2.12s/it]
 66%|██████▌   | 44572/67700 [26:49:09<13:22:12,  2.08s/it]
 66%|██████▌   | 44573/67700 [26:49:11<13:15:00,  2.06s/it]
 66%|██████▌   | 44574/67700 [26:49:13<13:01:22,  2.03s/it]
 66%|██████▌   | 44575/67700 [26:49:15<12:49:51,  2.00s/it]
 66%|██████▌   | 44576/67700 [26:49:17<12:35:27,  1.96s/it]
 66%|██████▌   | 44577/67700 [26:49:19<12:26:43,  1.94s/it]
 66%|██████▌   | 44578/67700 [26:49:21<12:12:49,  1.90s/it]
 66%|██████▌   | 44579/67700 [26:49:22<11:57:25,  1.86s/it]
 66%|██████▌   | 44580/67700 [26:49:24<11:44:01,  1.83s/it]
 66%|██████▌   | 44581/67700 [26:49:26<11:33:35,  1.80s/it]
 66%|██████▌   | 44582/67700 [26:49:28<11:22:14,  1.77s/it]
 66%|██████▌   | 44583/67700 [26:49:29<11:11:40,  1.74s/it]
 66%|██████▌   | 44584/67700 [26:49:31<11:02:52,  1.72s/it]
 66%|██████▌   | 44585/67700 [26:49:33<10:56:23,  1.70s/it]
 66%|██████▌   | 44586/67700 [26:49:34<10:47:10,  1.68s/it]
 66%|██████▌   | 44587/67700 [26:49:36<10:38:38,  1.66s/it]
 66%|██████▌   | 44588/67700 [26:49:37<10:25:32,  1.62s/it]
 66%|██████▌   | 44589/67700 [26:49:39<10:19:22,  1.61s/it]
 66%|██████▌   | 44590/67700 [26:49:41<10:11:02,  1.59s/it]
 66%|██████▌   | 44591/67700 [26:49:42<10:00:29,  1.56s/it]
 66%|██████▌   | 44592/67700 [26:49:43<9:51:44,  1.54s/it] 
 66%|██████▌   | 44593/67700 [26:49:45<9:43:40,  1.52s/it]
 66%|██████▌   | 44594/67700 [26:49:46<9:30:26,  1.48s/it]
 66%|██████▌   | 44595/67700 [26:49:48<9:21:48,  1.46s/it]
 66%|██████▌   | 44596/67700 [26:49:49<9:13:38,  1.44s/it]
 66%|██████▌   | 44597/67700 [26:49:51<9:03:44,  1.41s/it]
 66%|██████▌   | 44598/67700 [26:49:52<8:48:23,  1.37s/it]
 66%|██████▌   | 44599/67700 [26:49:53<8:33:40,  1.33s/it]
 66%|██████▌   | 44600/67700 [26:49:54<8:23:59,  1.31s/it]
                                                          
 66%|██████▌   | 44600/67700 [26:49:54<8:23:59,  1.31s/it]
 66%|██████▌   | 44601/67700 [26:49:56<8:13:52,  1.28s/it]
 66%|██████▌   | 44602/67700 [26:49:57<8:04:37,  1.26s/it]
 66%|██████▌   | 44603/67700 [26:49:58<7:56:30,  1.24s/it]
 66%|██████▌   | 44604/67700 [26:49:59<7:34:55,  1.18s/it]
 66%|██████▌   | 44605/67700 [26:50:00<7:07:48,  1.11s/it]
 66%|██████▌   | 44606/67700 [26:50:02<9:56:22,  1.55s/it]
 66%|██████▌   | 44607/67700 [26:50:05<11:47:19,  1.84s/it]
 66%|██████▌   | 44608/67700 [26:50:07<13:06:06,  2.04s/it]
 66%|██████▌   | 44609/67700 [26:50:10<13:57:28,  2.18s/it]
 66%|██████▌   | 44610/67700 [26:50:12<14:28:38,  2.26s/it]
 66%|██████▌   | 44611/67700 [26:50:15<14:33:36,  2.27s/it]
 66%|██████▌   | 44612/67700 [26:50:17<14:35:51,  2.28s/it]
 66%|██████▌   | 44613/67700 [26:50:19<14:32:42,  2.27s/it]
 66%|██████▌   | 44614/67700 [26:50:21<14:25:13,  2.25s/it]
 66%|██████▌   | 44615/67700 [26:50:24<14:14:35,  2.22s/it]
 66%|██████▌   | 44616/67700 [26:50:26<14:03:10,  2.19s/it]
 66%|██████▌   | 44617/67700 [26:50:28<13:55:02,  2.17s/it]
 66%|██████▌   | 44618/67700 [26:50:30<13:47:11,  2.15s/it]
 66%|██████▌   | 44619/67700 [26:50:32<13:37:47,  2.13s/it]
 66%|██████▌   | 44620/67700 [26:50:34<13:29:12,  2.10s/it]
 66%|██████▌   | 44621/67700 [26:50:36<13:16:11,  2.07s/it]
 66%|██████▌   | 44622/67700 [26:50:38<13:06:22,  2.04s/it]
 66%|██████▌   | 44623/67700 [26:50:40<13:00:44,  2.03s/it]
 66%|██████▌   | 44624/67700 [26:50:42<12:51:27,  2.01s/it]
 66%|██████▌   | 44625/67700 [26:50:44<12:37:04,  1.97s/it]
 66%|██████▌   | 44626/67700 [26:50:46<12:23:30,  1.93s/it]
 66%|██████▌   | 44627/67700 [26:50:48<12:11:06,  1.90s/it]
 66%|██████▌   | 44628/67700 [26:50:49<11:59:33,  1.87s/it]
 66%|██████▌   | 44629/67700 [26:50:51<11:50:48,  1.85s/it]
 66%|██████▌   | 44630/67700 [26:50:53<11:38:44,  1.82s/it]
 66%|██████▌   | 44631/67700 [26:50:55<11:32:11,  1.80s/it]
 66%|██████▌   | 44632/67700 [26:50:56<11:19:51,  1.77s/it]
 66%|██████���   | 44633/67700 [26:50:58<11:13:36,  1.75s/it]
 66%|██████▌   | 44634/67700 [26:51:00<11:05:10,  1.73s/it]
 66%|██████▌   | 44635/67700 [26:51:01<10:58:53,  1.71s/it]
 66%|██████▌   | 44636/67700 [26:51:03<10:45:07,  1.68s/it]
 66%|██████▌   | 44637/67700 [26:51:05<10:32:08,  1.64s/it]
 66%|██████▌   | 44638/67700 [26:51:06<10:19:08,  1.61s/it]
 66%|██████▌   | 44639/67700 [26:51:08<10:11:42,  1.59s/it]
 66%|██████▌   | 44640/67700 [26:51:09<10:02:24,  1.57s/it]
 66%|██████▌   | 44641/67700 [26:51:11<9:53:09,  1.54s/it] 
 66%|██████▌   | 44642/67700 [26:51:12<9:44:57,  1.52s/it]
 66%|██████▌   | 44643/67700 [26:51:14<9:34:02,  1.49s/it]
 66%|██████▌   | 44644/67700 [26:51:15<9:25:36,  1.47s/it]
 66%|██████▌   | 44645/67700 [26:51:16<9:15:43,  1.45s/it]
 66%|██████▌   | 44646/67700 [26:51:18<9:05:55,  1.42s/it]
 66%|██████▌   | 44647/67700 [26:51:19<8:50:37,  1.38s/it]
 66%|██████▌   | 44648/67700 [26:51:20<8:37:04,  1.35s/it]
 66%|██████▌   | 44649/67700 [26:51:22<8:24:53,  1.31s/it]
 66%|██████▌   | 44650/67700 [26:51:23<8:12:04,  1.28s/it]
 66%|██████▌   | 44651/67700 [26:51:24<7:58:49,  1.25s/it]
 66%|██████▌   | 44652/67700 [26:51:25<7:50:31,  1.22s/it]
 66%|██████▌   | 44653/67700 [26:51:26<7:40:58,  1.20s/it]
 66%|██████▌   | 44654/67700 [26:51:27<7:23:53,  1.16s/it]
 66%|██████▌   | 44655/67700 [26:51:28<7:01:08,  1.10s/it]
 66%|██████▌   | 44656/67700 [26:51:31<9:46:56,  1.53s/it]
 66%|██████▌   | 44657/67700 [26:51:33<11:37:32,  1.82s/it]
 66%|██████▌   | 44658/67700 [26:51:36<12:36:36,  1.97s/it]
 66%|██████▌   | 44659/67700 [26:51:38<13:09:27,  2.06s/it]
 66%|██████▌   | 44660/67700 [26:51:40<13:22:02,  2.09s/it]
 66%|██████▌   | 44661/67700 [26:51:42<13:27:51,  2.10s/it]
 66%|██████▌   | 44662/67700 [26:51:44<13:28:46,  2.11s/it]
 66%|██████▌   | 44663/67700 [26:51:46<13:29:07,  2.11s/it]
 66%|██████▌   | 44664/67700 [26:51:48<13:20:20,  2.08s/it]
 66%|██████▌   | 44665/67700 [26:51:50<13:08:58,  2.06s/it]
 66%|██████▌   | 44666/67700 [26:51:52<12:48:31,  2.00s/it]
 66%|██████▌   | 44667/67700 [26:51:54<12:30:56,  1.96s/it]
 66%|██████▌   | 44668/67700 [26:51:56<12:11:32,  1.91s/it]
 66%|██████▌   | 44669/67700 [26:51:58<11:58:40,  1.87s/it]
 66%|██████▌   | 44670/67700 [26:51:59<11:42:16,  1.83s/it]
 66%|██████▌   | 44671/67700 [26:52:01<11:24:08,  1.78s/it]
 66%|██████▌   | 44672/67700 [26:52:03<11:09:11,  1.74s/it]
 66%|██████▌   | 44673/67700 [26:52:04<10:58:31,  1.72s/it]
 66%|██████▌   | 44674/67700 [26:52:06<10:43:15,  1.68s/it]
 66%|██████▌   | 44675/67700 [26:52:07<10:22:14,  1.62s/it]
 66%|██████▌   | 44676/67700 [26:52:09<10:05:13,  1.58s/it]
 66%|██████▌   | 44677/67700 [26:52:10<9:43:02,  1.52s/it] 
 66%|██████▌   | 44678/67700 [26:52:12<9:19:48,  1.46s/it]
 66%|██████▌   | 44679/67700 [26:52:13<8:57:06,  1.40s/it]
 66%|██████▌   | 44680/67700 [26:52:14<8:36:32,  1.35s/it]
 66%|██████▌   | 44681/67700 [26:52:15<8:14:51,  1.29s/it]
 66%|██████▌   | 44682/67700 [26:52:16<7:51:04,  1.23s/it]
 66%|██████▌   | 44683/67700 [26:52:19<10:51:59,  1.70s/it]
 66%|██████▌   | 44684/67700 [26:52:22<12:29:59,  1.96s/it]
 66%|██████▌   | 44685/67700 [26:52:24<13:32:38,  2.12s/it]
 66%|██████▌   | 44686/67700 [26:52:27<14:10:01,  2.22s/it]
 66%|██████▌   | 44687/67700 [26:52:29<14:24:28,  2.25s/it]
 66%|██████▌   | 44688/67700 [26:52:31<14:25:34,  2.26s/it]
 66%|██████▌   | 44689/67700 [26:52:34<14:35:52,  2.28s/it]
 66%|██████▌   | 44690/67700 [26:52:36<14:31:02,  2.27s/it]
 66%|██████▌   | 44691/67700 [26:52:38<14:21:51,  2.25s/it]
 66%|██████▌   | 44692/67700 [26:52:40<14:06:28,  2.21s/it]
 66%|██████▌   | 44693/67700 [26:52:42<13:57:46,  2.18s/it]
 66%|██████▌   | 44694/67700 [26:52:44<13:45:46,  2.15s/it]
 66%|██████▌   | 44695/67700 [26:52:46<13:37:12,  2.13s/it]
 66%|██████▌   | 44696/67700 [26:52:49<13:24:30,  2.10s/it]
 66%|██████▌   | 44697/67700 [26:52:51<13:17:24,  2.08s/it]
 66%|██████▌   | 44698/67700 [26:52:52<13:02:18,  2.04s/it]
 66%|██████▌   | 44699/67700 [26:52:54<12:57:16,  2.03s/it]
 66%|██████▌   | 44700/67700 [26:52:56<12:54:01,  2.02s/it]
                                                           
 66%|██████▌   | 44700/67700 [26:52:56<12:54:01,  2.02s/it]
 66%|██████▌   | 44701/67700 [26:52:58<12:39:13,  1.98s/it]
 66%|██████▌   | 44702/67700 [26:53:00<12:25:54,  1.95s/it]
 66%|██████▌   | 44703/67700 [26:53:02<12:13:38,  1.91s/it]
 66%|██████▌   | 44704/67700 [26:53:04<12:01:22,  1.88s/it]
 66%|██████▌   | 44705/67700 [26:53:06<11:51:04,  1.86s/it]
 66%|██████▌   | 44706/67700 [26:53:07<11:42:18,  1.83s/it]
 66%|██████▌   | 44707/67700 [26:53:09<11:33:51,  1.81s/it]
 66%|██████▌   | 44708/67700 [26:53:11<11:25:42,  1.79s/it]
 66%|██████▌   | 44709/67700 [26:53:13<11:16:52,  1.77s/it]
 66%|██████▌   | 44710/67700 [26:53:14<11:07:05,  1.74s/it]
 66%|██████▌   | 44711/67700 [26:53:16<11:04:45,  1.73s/it]
 66%|██████▌   | 44712/67700 [26:53:18<10:53:48,  1.71s/it]
 66%|██████▌   | 44713/67700 [26:53:19<10:42:47,  1.68s/it]
 66%|██████▌   | 44714/67700 [26:53:21<10:33:16,  1.65s/it]
 66%|██████▌   | 44715/67700 [26:53:22<10:22:39,  1.63s/it]
 66%|██████▌   | 44716/67700 [26:53:24<10:14:00,  1.60s/it]
 66%|██████▌   | 44717/67700 [26:53:26<10:03:03,  1.57s/it]
 66%|██████▌   | 44718/67700 [26:53:27<9:59:10,  1.56s/it] 
 66%|██████▌   | 44719/67700 [26:53:29<9:53:12,  1.55s/it]
 66%|██████▌   | 44720/67700 [26:53:30<9:43:12,  1.52s/it]
 66%|██████▌   | 44721/67700 [26:53:31<9:31:18,  1.49s/it]
 66%|██████▌   | 44722/67700 [26:53:33<9:20:04,  1.46s/it]
 66%|██████▌   | 44723/67700 [26:53:34<9:11:55,  1.44s/it]
 66%|██████▌   | 44724/67700 [26:53:36<8:58:19,  1.41s/it]
 66%|██████▌   | 44725/67700 [26:53:37<8:45:09,  1.37s/it]
 66%|██████▌   | 44726/67700 [26:53:38<8:31:32,  1.34s/it]
 66%|██████▌   | 44727/67700 [26:53:39<8:18:35,  1.30s/it]
 66%|██████▌   | 44728/67700 [26:53:41<8:09:03,  1.28s/it]
 66%|██████▌   | 44729/67700 [26:53:42<7:57:43,  1.25s/it]
 66%|██████▌   | 44730/67700 [26:53:43<7:42:21,  1.21s/it]
 66%|██████▌   | 44731/67700 [26:53:44<7:21:38,  1.15s/it]
 66%|██████▌   | 44732/67700 [26:53:45<7:00:26,  1.10s/it]
 66%|██████▌   | 44733/67700 [26:53:47<9:52:51,  1.55s/it]
 66%|██████▌   | 44734/67700 [26:53:50<11:51:15,  1.86s/it]
 66%|██████▌   | 44735/67700 [26:53:53<13:01:25,  2.04s/it]
 66%|██████▌   | 44736/67700 [26:53:55<13:52:33,  2.18s/it]
 66%|██████▌   | 44737/67700 [26:53:57<14:12:01,  2.23s/it]
 66%|██████▌   | 44738/67700 [26:54:00<14:17:22,  2.24s/it]
 66%|██████▌   | 44739/67700 [26:54:02<14:18:56,  2.24s/it]
 66%|██████▌   | 44740/67700 [26:54:04<14:14:36,  2.23s/it]
 66%|██████▌   | 44741/67700 [26:54:06<14:09:17,  2.22s/it]
 66%|██████▌   | 44742/67700 [26:54:08<14:00:18,  2.20s/it]
 66%|██████▌   | 44743/67700 [26:54:11<13:54:47,  2.18s/it]
 66%|██████▌   | 44744/67700 [26:54:13<13:46:24,  2.16s/it]
 66%|██████▌   | 44745/67700 [26:54:15<13:37:10,  2.14s/it]
 66%|██████▌   | 44746/67700 [26:54:17<13:32:11,  2.12s/it]
 66%|██████▌   | 44747/67700 [26:54:19<13:22:20,  2.10s/it]
 66%|██████▌   | 44748/67700 [26:54:21<13:15:22,  2.08s/it]
 66%|██████▌   | 44749/67700 [26:54:23<13:08:01,  2.06s/it]
 66%|██████▌   | 44750/67700 [26:54:25<13:03:59,  2.05s/it]
 66%|██████▌   | 44751/67700 [26:54:27<12:54:41,  2.03s/it]
 66%|██████▌   | 44752/67700 [26:54:29<12:38:15,  1.98s/it]
 66%|██████▌   | 44753/67700 [26:54:31<12:29:00,  1.96s/it]
 66%|██████▌   | 44754/67700 [26:54:33<12:16:25,  1.93s/it]
 66%|██████▌   | 44755/67700 [26:54:34<12:02:45,  1.89s/it]
 66%|██████▌   | 44756/67700 [26:54:36<11:50:44,  1.86s/it]
 66%|██████▌   | 44757/67700 [26:54:38<11:37:28,  1.82s/it]
 66%|██████▌   | 44758/67700 [26:54:40<11:29:13,  1.80s/it]
 66%|██████▌   | 44759/67700 [26:54:41<11:17:48,  1.77s/it]
 66%|██████▌   | 44760/67700 [26:54:43<11:10:27,  1.75s/it]
 66%|██████▌   | 44761/67700 [26:54:45<11:00:25,  1.73s/it]
 66%|██████▌   | 44762/67700 [26:54:46<10:52:27,  1.71s/it]
 66%|██████▌   | 44763/67700 [26:54:48<10:42:41,  1.68s/it]
 66%|██████▌   | 44764/67700 [26:54:50<10:33:03,  1.66s/it]
 66%|██████▌   | 44765/67700 [26:54:51<10:20:50,  1.62s/it]
 66%|██████▌   | 44766/67700 [26:54:53<10:20:36,  1.62s/it]
 66%|██████▌   | 44767/67700 [26:54:54<10:07:46,  1.59s/it]
 66%|██████▌   | 44768/67700 [26:54:56<9:56:48,  1.56s/it] 
 66%|██████▌   | 44769/67700 [26:54:57<9:44:12,  1.53s/it]
 66%|██████▌   | 44770/67700 [26:54:59<9:36:46,  1.51s/it]
 66%|██████▌   | 44771/67700 [26:55:00<9:27:57,  1.49s/it]
 66%|██████▌   | 44772/67700 [26:55:02<9:19:17,  1.46s/it]
 66%|██████▌   | 44773/67700 [26:55:03<9:10:16,  1.44s/it]
 66%|██████▌   | 44774/67700 [26:55:04<9:01:43,  1.42s/it]
 66%|██████▌   | 44775/67700 [26:55:06<8:44:56,  1.37s/it]
 66%|██████▌   | 44776/67700 [26:55:07<8:29:37,  1.33s/it]
 66%|██████▌   | 44777/67700 [26:55:08<8:16:34,  1.30s/it]
 66%|██████▌   | 44778/67700 [26:55:09<8:05:28,  1.27s/it]
 66%|██████▌   | 44779/67700 [26:55:10<7:55:19,  1.24s/it]
 66%|██████▌   | 44780/67700 [26:55:12<7:41:54,  1.21s/it]
 66%|██████▌   | 44781/67700 [26:55:13<7:22:26,  1.16s/it]
 66%|██████▌   | 44782/67700 [26:55:14<6:58:47,  1.10s/it]
 66%|██████▌   | 44783/67700 [26:55:16<9:46:44,  1.54s/it]
 66%|██████▌   | 44784/67700 [26:55:19<11:40:55,  1.84s/it]
 66%|██████▌   | 44785/67700 [26:55:21<12:57:02,  2.03s/it]
 66%|██████▌   | 44786/67700 [26:55:24<13:40:08,  2.15s/it]
 66%|██████▌   | 44787/67700 [26:55:26<14:02:20,  2.21s/it]
 66%|██████▌   | 44788/67700 [26:55:28<14:15:09,  2.24s/it]
 66%|██████▌   | 44789/67700 [26:55:30<14:16:34,  2.24s/it]
 66%|██████▌   | 44790/67700 [26:55:33<14:13:55,  2.24s/it]
 66%|██████▌   | 44791/67700 [26:55:35<14:15:52,  2.24s/it]
 66%|██████▌   | 44792/67700 [26:55:37<14:06:44,  2.22s/it]
 66%|██████▌   | 44793/67700 [26:55:39<13:56:09,  2.19s/it]
 66%|██████▌   | 44794/67700 [26:55:41<13:46:33,  2.17s/it]
 66%|██████▌   | 44795/67700 [26:55:43<13:36:54,  2.14s/it]
 66%|██████▌   | 44796/67700 [26:55:45<13:29:42,  2.12s/it]
 66%|██████▌   | 44797/67700 [26:55:47<13:19:02,  2.09s/it]
 66%|██████▌   | 44798/67700 [26:55:50<13:10:16,  2.07s/it]
 66%|██████▌   | 44799/67700 [26:55:51<12:56:51,  2.04s/it]
 66%|██████▌   | 44800/67700 [26:55:53<12:52:52,  2.03s/it]
                                                           
 66%|██████▌   | 44800/67700 [26:55:53<12:52:52,  2.03s/it]
 66%|██████▌   | 44801/67700 [26:55:55<12:39:25,  1.99s/it]
 66%|██████▌   | 44802/67700 [26:55:57<12:25:40,  1.95s/it]
 66%|██████▌   | 44803/67700 [26:55:59<12:12:36,  1.92s/it]
 66%|██████▌   | 44804/67700 [26:56:01<12:03:42,  1.90s/it]
 66%|██████▌   | 44805/67700 [26:56:03<11:50:10,  1.86s/it]
 66%|██████▌   | 44806/67700 [26:56:05<11:52:23,  1.87s/it]
 66%|██████▌   | 44807/67700 [26:56:06<11:38:41,  1.83s/it]
 66%|██████▌   | 44808/67700 [26:56:08<11:27:07,  1.80s/it]
 66%|██████▌   | 44809/67700 [26:56:10<11:11:21,  1.76s/it]
 66%|██████▌   | 44810/67700 [26:56:11<11:02:34,  1.74s/it]
 66%|██████▌   | 44811/67700 [26:56:13<10:51:15,  1.71s/it]
 66%|██████▌   | 44812/67700 [26:56:15<10:50:26,  1.71s/it]
 66%|██████▌   | 44813/67700 [26:56:16<10:39:54,  1.68s/it]
 66%|██████▌   | 44814/67700 [26:56:18<10:35:12,  1.67s/it]
 66%|██████▌   | 44815/67700 [26:56:20<10:28:18,  1.65s/it]
 66%|██████▌   | 44816/67700 [26:56:21<10:18:38,  1.62s/it]
 66%|██████▌   | 44817/67700 [26:56:23<10:06:18,  1.59s/it]
 66%|██████▌   | 44818/67700 [26:56:24<9:54:33,  1.56s/it] 
 66%|██████▌   | 44819/67700 [26:56:26<9:43:23,  1.53s/it]
 66%|██████▌   | 44820/67700 [26:56:27<9:34:33,  1.51s/it]
 66%|██████▌   | 44821/67700 [26:56:28<9:22:30,  1.48s/it]
 66%|██████▌   | 44822/67700 [26:56:30<9:14:33,  1.45s/it]
 66%|██████▌   | 44823/67700 [26:56:31<9:05:00,  1.43s/it]
 66%|██████▌   | 44824/67700 [26:56:33<8:52:59,  1.40s/it]
 66%|██████▌   | 44825/67700 [26:56:34<8:41:33,  1.37s/it]
 66%|██████▌   | 44826/67700 [26:56:35<8:25:03,  1.32s/it]
 66%|██████▌   | 44827/67700 [26:56:36<8:09:28,  1.28s/it]
 66%|██████▌   | 44828/67700 [26:56:37<7:55:32,  1.25s/it]
 66%|██████▌   | 44829/67700 [26:56:39<7:43:01,  1.21s/it]
 66%|██████▌   | 44830/67700 [26:56:40<7:28:59,  1.18s/it]
 66%|██████▌   | 44831/67700 [26:56:41<7:09:42,  1.13s/it]
 66%|██████▌   | 44832/67700 [26:56:42<6:52:07,  1.08s/it]
 66%|██████▌   | 44833/67700 [26:56:44<9:40:00,  1.52s/it]
 66%|██████▌   | 44834/67700 [26:56:47<11:36:47,  1.83s/it]
 66%|██████▌   | 44835/67700 [26:56:49<12:51:00,  2.02s/it]
 66%|██████▌   | 44836/67700 [26:56:52<13:37:03,  2.14s/it]
 66%|██████▌   | 44837/67700 [26:56:54<14:15:58,  2.25s/it]
 66%|█���████▌   | 44838/67700 [26:56:56<14:25:37,  2.27s/it]
 66%|██████▌   | 44839/67700 [26:56:59<14:28:12,  2.28s/it]
 66%|██████▌   | 44840/67700 [26:57:01<14:30:49,  2.29s/it]
 66%|██████▌   | 44841/67700 [26:57:03<14:25:40,  2.27s/it]
 66%|██████▌   | 44842/67700 [26:57:06<14:15:47,  2.25s/it]
 66%|██████▌   | 44843/67700 [26:57:08<13:59:21,  2.20s/it]
 66%|██████▌   | 44844/67700 [26:57:10<13:52:21,  2.19s/it]
 66%|██████▌   | 44845/67700 [26:57:12<13:44:53,  2.17s/it]
 66%|██████▌   | 44846/67700 [26:57:14<13:36:54,  2.14s/it]
 66%|██████▌   | 44847/67700 [26:57:16<13:27:15,  2.12s/it]
 66%|██████▌   | 44848/67700 [26:57:18<13:15:24,  2.09s/it]
 66%|██████▌   | 44849/67700 [26:57:20<13:08:46,  2.07s/it]
 66%|██████▌   | 44850/67700 [26:57:22<13:00:38,  2.05s/it]
 66%|██████▌   | 44851/67700 [26:57:24<12:49:23,  2.02s/it]
 66%|██████▋   | 44852/67700 [26:57:26<12:33:51,  1.98s/it]
 66%|██████▋   | 44853/67700 [26:57:28<12:25:41,  1.96s/it]
 66%|██████▋   | 44854/67700 [26:57:30<12:12:35,  1.92s/it]
 66%|██████▋   | 44855/67700 [26:57:32<12:02:31,  1.90s/it]
 66%|██████▋   | 44856/67700 [26:57:33<11:54:20,  1.88s/it]
 66%|██████▋   | 44857/67700 [26:57:35<11:42:36,  1.85s/it]
 66%|██████▋   | 44858/67700 [26:57:37<11:29:05,  1.81s/it]
 66%|██████▋   | 44859/67700 [26:57:39<11:20:18,  1.79s/it]
 66%|██████▋   | 44860/67700 [26:57:40<11:10:28,  1.76s/it]
 66%|██████▋   | 44861/67700 [26:57:42<11:02:29,  1.74s/it]
 66%|██████▋   | 44862/67700 [26:57:44<10:54:50,  1.72s/it]
 66%|██████▋   | 44863/67700 [26:57:45<10:46:26,  1.70s/it]
 66%|██████▋   | 44864/67700 [26:57:47<10:37:52,  1.68s/it]
 66%|██████▋   | 44865/67700 [26:57:49<10:29:57,  1.66s/it]
 66%|██████▋   | 44866/67700 [26:57:50<10:21:32,  1.63s/it]
 66%|██████▋   | 44867/67700 [26:57:52<10:12:54,  1.61s/it]
 66%|██████▋   | 44868/67700 [26:57:53<10:03:13,  1.59s/it]
 66%|██████▋   | 44869/67700 [26:57:55<9:51:31,  1.55s/it] 
 66%|██████▋   | 44870/67700 [26:57:56<9:41:50,  1.53s/it]
 66%|██████▋   | 44871/67700 [26:57:58<9:30:32,  1.50s/it]
 66%|██████▋   | 44872/67700 [26:57:59<9:19:26,  1.47s/it]
 66%|██████▋   | 44873/67700 [26:58:00<9:10:29,  1.45s/it]
 66%|██████▋   | 44874/67700 [26:58:02<8:59:38,  1.42s/it]
 66%|██████▋   | 44875/67700 [26:58:03<8:43:35,  1.38s/it]
 66%|██████▋   | 44876/67700 [26:58:04<8:32:51,  1.35s/it]
 66%|██████▋   | 44877/67700 [26:58:06<8:21:49,  1.32s/it]
 66%|██████▋   | 44878/67700 [26:58:07<8:08:17,  1.28s/it]
 66%|██████▋   | 44879/67700 [26:58:08<7:52:25,  1.24s/it]
 66%|██████▋   | 44880/67700 [26:58:09<7:28:28,  1.18s/it]
 66%|██████▋   | 44881/67700 [26:58:10<7:02:42,  1.11s/it]
 66%|██████▋   | 44882/67700 [26:58:11<6:50:47,  1.08s/it]
 66%|██████▋   | 44883/67700 [26:58:13<9:36:47,  1.52s/it]
 66%|██████▋   | 44884/67700 [26:58:16<11:38:59,  1.84s/it]
 66%|██████▋   | 44885/67700 [26:58:18<12:53:28,  2.03s/it]
 66%|██████▋   | 44886/67700 [26:58:21<13:46:04,  2.17s/it]
 66%|██████▋   | 44887/67700 [26:58:23<14:17:58,  2.26s/it]
 66%|██████▋   | 44888/67700 [26:58:26<14:26:36,  2.28s/it]
 66%|██████▋   | 44889/67700 [26:58:28<14:26:42,  2.28s/it]
 66%|██████▋   | 44890/67700 [26:58:30<14:22:30,  2.27s/it]
 66%|██████▋   | 44891/67700 [26:58:33<14:22:13,  2.27s/it]
 66%|██████▋   | 44892/67700 [26:58:35<14:12:01,  2.24s/it]
 66%|██████▋   | 44893/67700 [26:58:37<14:03:00,  2.22s/it]
 66%|██████▋   | 44894/67700 [26:58:39<13:55:27,  2.20s/it]
 66%|██████▋   | 44895/67700 [26:58:41<13:44:01,  2.17s/it]
 66%|██████▋   | 44896/67700 [26:58:43<13:34:02,  2.14s/it]
 66%|██████▋   | 44897/67700 [26:58:45<13:22:31,  2.11s/it]
 66%|██████▋   | 44898/67700 [26:58:47<13:12:09,  2.08s/it]
 66%|██████▋   | 44899/67700 [26:58:49<13:01:33,  2.06s/it]
 66%|██████▋   | 44900/67700 [26:58:51<12:52:01,  2.03s/it]
                                                           
 66%|██████▋   | 44900/67700 [26:58:51<12:52:01,  2.03s/it]
 66%|██████▋   | 44901/67700 [26:58:53<12:38:40,  2.00s/it]
 66%|██████▋   | 44902/67700 [26:58:55<12:25:38,  1.96s/it]
 66%|██████▋   | 44903/67700 [26:58:57<12:14:34,  1.93s/it]
 66%|██████▋   | 44904/67700 [26:58:59<12:06:47,  1.91s/it]
 66%|██████▋   | 44905/67700 [26:59:01<12:01:46,  1.90s/it]
 66%|██████▋   | 44906/67700 [26:59:02<11:57:01,  1.89s/it]
 66%|██████▋   | 44907/67700 [26:59:04<11:40:58,  1.85s/it]
 66%|██████▋   | 44908/67700 [26:59:06<11:30:59,  1.82s/it]
 66%|██████▋   | 44909/67700 [26:59:08<11:21:28,  1.79s/it]
 66%|██████▋   | 44910/67700 [26:59:09<11:11:24,  1.77s/it]
 66%|██████▋   | 44911/67700 [26:59:11<11:03:52,  1.75s/it]
 66%|██████▋   | 44912/67700 [26:59:13<10:58:44,  1.73s/it]
 66%|██████▋   | 44913/67700 [26:59:15<10:51:49,  1.72s/it]
 66%|██████▋   | 44914/67700 [26:59:16<10:42:17,  1.69s/it]
 66%|██████▋   | 44915/67700 [26:59:18<10:36:55,  1.68s/it]
 66%|██████▋   | 44916/67700 [26:59:19<10:26:49,  1.65s/it]
 66%|██████▋   | 44917/67700 [26:59:21<10:16:47,  1.62s/it]
 66%|██████▋   | 44918/67700 [26:59:22<10:04:15,  1.59s/it]
 66%|██████▋   | 44919/67700 [26:59:24<9:52:20,  1.56s/it] 
 66%|██████▋   | 44920/67700 [26:59:25<9:41:30,  1.53s/it]
 66%|██████▋   | 44921/67700 [26:59:27<9:32:01,  1.51s/it]
 66%|██████▋   | 44922/67700 [26:59:28<9:23:56,  1.49s/it]
 66%|██████▋   | 44923/67700 [26:59:30<9:12:04,  1.45s/it]
 66%|██████▋   | 44924/67700 [26:59:31<9:00:40,  1.42s/it]
 66%|██████▋   | 44925/67700 [26:59:32<8:59:28,  1.42s/it]
 66%|██████▋   | 44926/67700 [26:59:34<8:47:26,  1.39s/it]
 66%|██████▋   | 44927/67700 [26:59:35<8:37:23,  1.36s/it]
 66%|██████▋   | 44928/67700 [26:59:36<8:30:19,  1.34s/it]
 66%|██████▋   | 44929/67700 [26:59:38<8:18:59,  1.31s/it]
 66%|██████▋   | 44930/67700 [26:59:39<7:59:22,  1.26s/it]
 66%|██████▋   | 44931/67700 [26:59:40<7:30:49,  1.19s/it]
 66%|██████▋   | 44932/67700 [26:59:41<7:03:07,  1.12s/it]
 66%|██████▋   | 44933/67700 [26:59:43<9:49:38,  1.55s/it]
 66%|██████▋   | 44934/67700 [26:59:46<11:45:29,  1.86s/it]
 66%|██████▋   | 44935/67700 [26:59:48<12:59:11,  2.05s/it]
 66%|██████▋   | 44936/67700 [26:59:51<13:48:46,  2.18s/it]
 66%|██████▋   | 44937/67700 [26:59:53<14:12:16,  2.25s/it]
 66%|██████▋   | 44938/67700 [26:59:56<14:21:24,  2.27s/it]
 66%|██████▋   | 44939/67700 [26:59:58<14:22:10,  2.27s/it]
 66%|██████▋   | 44940/67700 [27:00:00<14:22:26,  2.27s/it]
 66%|██████▋   | 44941/67700 [27:00:02<14:16:42,  2.26s/it]
 66%|██████▋   | 44942/67700 [27:00:04<14:03:10,  2.22s/it]
 66%|██████▋   | 44943/67700 [27:00:07<13:54:13,  2.20s/it]
 66%|██████▋   | 44944/67700 [27:00:09<13:45:55,  2.18s/it]
 66%|██████▋   | 44945/67700 [27:00:11<13:37:24,  2.16s/it]
 66%|██████▋   | 44946/67700 [27:00:13<13:28:38,  2.13s/it]
 66%|██████▋   | 44947/67700 [27:00:15<13:15:47,  2.10s/it]
 66%|██████▋   | 44948/67700 [27:00:17<13:06:58,  2.08s/it]
 66%|██████▋   | 44949/67700 [27:00:19<12:58:56,  2.05s/it]
 66%|██████▋   | 44950/67700 [27:00:21<12:55:10,  2.04s/it]
 66%|██████▋   | 44951/67700 [27:00:23<12:38:28,  2.00s/it]
 66%|██████▋   | 44952/67700 [27:00:25<12:28:30,  1.97s/it]
 66%|██████▋   | 44953/67700 [27:00:27<12:15:28,  1.94s/it]
 66%|██████▋   | 44954/67700 [27:00:29<12:11:43,  1.93s/it]
 66%|██████▋   | 44955/67700 [27:00:30<11:57:44,  1.89s/it]
 66%|██████▋   | 44956/67700 [27:00:32<11:45:13,  1.86s/it]
 66%|██████▋   | 44957/67700 [27:00:34<11:31:21,  1.82s/it]
 66%|██████▋   | 44958/67700 [27:00:36<11:23:47,  1.80s/it]
 66%|██████▋   | 44959/67700 [27:00:37<11:13:27,  1.78s/it]
 66%|██████▋   | 44960/67700 [27:00:39<11:05:22,  1.76s/it]
 66%|██████▋   | 44961/67700 [27:00:41<10:54:09,  1.73s/it]
 66%|██████▋   | 44962/67700 [27:00:42<10:44:31,  1.70s/it]
 66%|██████▋   | 44963/67700 [27:00:44<10:36:24,  1.68s/it]
 66%|██████▋   | 44964/67700 [27:00:46<10:27:44,  1.66s/it]
 66%|██████▋   | 44965/67700 [27:00:47<10:19:14,  1.63s/it]
 66%|██████▋   | 44966/67700 [27:00:49<10:07:26,  1.60s/it]
 66%|██████▋   | 44967/67700 [27:00:50<9:57:55,  1.58s/it] 
 66%|██████▋   | 44968/67700 [27:00:52<9:45:33,  1.55s/it]
 66%|██████▋   | 44969/67700 [27:00:53<9:36:00,  1.52s/it]
 66%|██████▋   | 44970/67700 [27:00:55<9:30:49,  1.51s/it]
 66%|██████▋   | 44971/67700 [27:00:56<9:26:21,  1.50s/it]
 66%|██████▋   | 44972/67700 [27:00:58<9:15:04,  1.47s/it]
 66%|██████▋   | 44973/67700 [27:00:59<9:08:51,  1.45s/it]
 66%|██████▋   | 44974/67700 [27:01:00<8:55:45,  1.41s/it]
 66%|██████▋   | 44975/67700 [27:01:02<8:42:07,  1.38s/it]
 66%|██████▋   | 44976/67700 [27:01:03<8:27:15,  1.34s/it]
 66%|██████▋   | 44977/67700 [27:01:04<8:11:51,  1.30s/it]
 66%|██████▋   | 44978/67700 [27:01:05<8:03:49,  1.28s/it]
 66%|██████▋   | 44979/67700 [27:01:06<7:52:00,  1.25s/it]
 66%|██████▋   | 44980/67700 [27:01:08<7:39:12,  1.21s/it]
 66%|██████▋   | 44981/67700 [27:01:09<7:24:12,  1.17s/it]
 66%|██████▋   | 44982/67700 [27:01:10<6:59:40,  1.11s/it]
 66%|██████▋   | 44983/67700 [27:01:12<9:48:46,  1.56s/it]
 66%|██████▋   | 44984/67700 [27:01:15<11:42:54,  1.86s/it]
 66%|██████▋   | 44985/67700 [27:01:17<12:57:17,  2.05s/it]
 66%|██████▋   | 44986/67700 [27:01:20<13:38:12,  2.16s/it]
 66%|██████▋   | 44987/67700 [27:01:22<14:10:19,  2.25s/it]
 66%|██████▋   | 44988/67700 [27:01:24<14:16:59,  2.26s/it]
 66%|██████▋   | 44989/67700 [27:01:27<14:16:11,  2.26s/it]
 66%|██████▋   | 44990/67700 [27:01:29<14:07:30,  2.24s/it]
 66%|██████▋   | 44991/67700 [27:01:31<14:03:48,  2.23s/it]
 66%|██████▋   | 44992/67700 [27:01:33<13:56:41,  2.21s/it]
 66%|██████▋   | 44993/67700 [27:01:35<13:46:23,  2.18s/it]
 66%|██████▋   | 44994/67700 [27:01:37<13:37:59,  2.16s/it]
 66%|██████▋   | 44995/67700 [27:01:40<13:28:29,  2.14s/it]
 66%|██████▋   | 44996/67700 [27:01:42<13:21:16,  2.12s/it]
 66%|██████▋   | 44997/67700 [27:01:44<13:19:44,  2.11s/it]
 66%|██████▋   | 44998/67700 [27:01:46<13:09:06,  2.09s/it]
 66%|██████▋   | 44999/67700 [27:01:48<12:58:56,  2.06s/it]
 66%|██████▋   | 45000/67700 [27:01:50<12:50:50,  2.04s/it]
                                                           
 66%|██████▋   | 45000/67700 [27:01:50<12:50:50,  2.04s/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': 0.8505166172981262, 'eval_wer': 0.8668975754576942, 'eval_cer': 0.22043766311985544, 'eval_runtime': 114.0059, 'eval_samples_per_second': 17.727, 'eval_steps_per_second': 2.219, 'epoch': 65.73}
+{'loss': 1.5391, 'learning_rate': 2.6394977168949772e-05, 'epoch': 65.88}
+{'loss': 1.5263, 'learning_rate': 2.628082191780822e-05, 'epoch': 66.03}
+{'loss': 1.5159, 'learning_rate': 2.6166666666666668e-05, 'epoch': 66.17}
+{'loss': 1.5416, 'learning_rate': 2.6052511415525113e-05, 'epoch': 66.32}
+{'loss': 1.5597, 'learning_rate': 2.593835616438356e-05, 'epoch': 66.47}
+
+
  0%|          | 0/253 [00:00<?, ?it/s]
+
  1%|          | 2/253 [00:00<00:41,  6.08it/s]
+
  1%|          | 3/253 [00:00<00:57,  4.34it/s]
+
  2%|▏         | 4/253 [00:00<01:03,  3.95it/s]
+
  2%|▏         | 5/253 [00:01<01:10,  3.54it/s]
+
  2%|▏         | 6/253 [00:01<01:11,  3.45it/s]
+
  3%|▎         | 7/253 [00:01<01:15,  3.25it/s]
+
  3%|▎         | 8/253 [00:02<01:17,  3.17it/s]
+
  4%|▎         | 9/253 [00:02<01:17,  3.13it/s]
+
  4%|▍         | 10/253 [00:02<01:18,  3.08it/s]
+
  4%|▍         | 11/253 [00:03<01:19,  3.06it/s]
+
  5%|▍         | 12/253 [00:03<01:17,  3.12it/s]
+
  5%|▌         | 13/253 [00:03<01:18,  3.04it/s]
+
  6%|▌         | 14/253 [00:04<01:15,  3.18it/s]
+
  6%|▌         | 15/253 [00:04<01:17,  3.08it/s]
+
  6%|▋         | 16/253 [00:04<01:15,  3.13it/s]
+
  7%|▋         | 17/253 [00:05<01:18,  2.99it/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,  3.17it/s]
+
  8%|▊         | 21/253 [00:06<01:16,  3.05it/s]
+
  9%|▊         | 22/253 [00:06<01:18,  2.96it/s]
+
  9%|▉         | 23/253 [00:07<01:19,  2.88it/s]
+
  9%|▉         | 24/253 [00:07<01:17,  2.94it/s]
+
 10%|▉         | 25/253 [00:07<01:17,  2.94it/s]
+
 10%|█         | 26/253 [00:08<01:16,  2.95it/s]
+
 11%|█         | 27/253 [00:08<01:18,  2.89it/s]
+
 11%|█         | 28/253 [00:08<01:15,  2.96it/s]
+
 11%|█▏        | 29/253 [00:09<01:16,  2.94it/s]
+
 12%|█▏        | 30/253 [00:09<01:17,  2.89it/s]
+
 12%|█▏        | 31/253 [00:09<01:15,  2.94it/s]
+
 13%|█▎        | 32/253 [00:10<01:24,  2.63it/s]
+
 13%|█▎        | 33/253 [00:10<01:21,  2.70it/s]
+
 13%|█▎        | 34/253 [00:11<01:19,  2.76it/s]
+
 14%|█▍        | 35/253 [00:11<01:16,  2.84it/s]
+
 14%|█▍        | 36/253 [00:11<01:12,  2.98it/s]
+
 15%|█▍        | 37/253 [00:12<01:11,  3.03it/s]
+
 15%|█▌        | 38/253 [00:12<01:13,  2.94it/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,  3.07it/s]
+
 17%|█▋        | 42/253 [00:13<01:12,  2.90it/s]
+
 17%|█▋        | 43/253 [00:14<01:08,  3.06it/s]
+
 17%|█▋        | 44/253 [00:14<01:09,  2.99it/s]
+
 18%|█▊        | 45/253 [00:14<01:09,  2.99it/s]
+
 18%|█▊        | 46/253 [00:15<01:06,  3.13it/s]
+
 19%|█▊        | 47/253 [00:15<01:06,  3.10it/s]
+
 19%|█▉        | 48/253 [00:15<01:05,  3.11it/s]
+
 19%|█▉        | 49/253 [00:15<01:04,  3.17it/s]
+
 20%|█▉        | 50/253 [00:16<01:03,  3.17it/s]
+
 20%|██        | 51/253 [00:16<01:05,  3.10it/s]
+
 21%|██        | 52/253 [00:16<01:06,  3.00it/s]
+
 21%|██        | 53/253 [00:17<01:05,  3.03it/s]
+
 21%|██▏       | 54/253 [00:17<01:06,  3.01it/s]
+
 22%|██▏       | 55/253 [00:17<01:04,  3.08it/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,  3.15it/s]
+
 23%|██▎       | 59/253 [00:19<01:02,  3.08it/s]
+
 24%|██▎       | 60/253 [00:19<01:00,  3.17it/s]
+
 24%|██▍       | 61/253 [00:19<01:02,  3.09it/s]
+
 25%|██▍       | 62/253 [00:20<00:59,  3.20it/s]
+
 25%|██▍       | 63/253 [00:20<01:00,  3.11it/s]
+
 25%|██▌       | 64/253 [00:20<01:01,  3.09it/s]
+
 26%|██▌       | 65/253 [00:21<01:01,  3.06it/s]
+
 26%|██▌       | 66/253 [00:21<01:02,  3.00it/s]
+
 26%|██▋       | 67/253 [00:21<01:04,  2.87it/s]
+
 27%|██▋       | 68/253 [00:22<01:02,  2.96it/s]
+
 27%|██▋       | 69/253 [00:22<00:59,  3.07it/s]
+
 28%|██▊       | 70/253 [00:22<00:57,  3.20it/s]
+
 28%|██▊       | 71/253 [00:23<01:00,  3.00it/s]
+
 28%|██▊       | 72/253 [00:23<00:57,  3.14it/s]
+
 29%|██▉       | 73/253 [00:23<00:56,  3.19it/s]
+
 29%|██▉       | 74/253 [00:24<00:57,  3.09it/s]
+
 30%|██▉       | 75/253 [00:24<00:58,  3.06it/s]
+
 30%|███       | 76/253 [00:24<00:58,  3.03it/s]
+
 30%|███       | 77/253 [00:25<00:58,  3.03it/s]
+
 31%|███       | 78/253 [00:25<00:58,  2.99it/s]
+
 31%|███       | 79/253 [00:25<00:59,  2.95it/s]
+
 32%|███▏      | 80/253 [00:26<00:59,  2.90it/s]
+
 32%|███▏      | 81/253 [00:26<00:58,  2.93it/s]
+
 32%|███▏      | 82/253 [00:26<00:55,  3.09it/s]
+
 33%|███▎      | 83/253 [00:27<00:53,  3.18it/s]
+
 33%|███▎      | 84/253 [00:27<00:54,  3.11it/s]
+
 34%|███▎      | 85/253 [00:27<00:54,  3.06it/s]
+
 34%|███▍      | 86/253 [00:28<00:52,  3.18it/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,  3.16it/s]
+
 36%|███▌      | 90/253 [00:29<00:52,  3.11it/s]
+
 36%|███▌      | 91/253 [00:29<00:51,  3.12it/s]
+
 36%|███▋      | 92/253 [00:29<00:51,  3.10it/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,  3.17it/s]
+
 38%|███▊      | 97/253 [00:31<00:50,  3.11it/s]
+
 39%|███▊      | 98/253 [00:31<00:49,  3.13it/s]
+
 39%|███▉      | 99/253 [00:32<00:51,  3.02it/s]
+
 40%|███▉      | 100/253 [00:32<00:50,  3.03it/s]
+
 40%|███▉      | 101/253 [00:32<00:48,  3.10it/s]
+
 40%|████      | 102/253 [00:33<00:48,  3.13it/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,  3.07it/s]
+
 42%|████▏     | 106/253 [00:34<00:46,  3.18it/s]
+
 42%|████▏     | 107/253 [00:34<00:42,  3.41it/s]
+
 43%|████▎     | 108/253 [00:35<00:44,  3.26it/s]
+
 43%|████▎     | 109/253 [00:35<00:41,  3.44it/s]
+
 43%|████▎     | 110/253 [00:35<00:42,  3.37it/s]
+
 44%|████▍     | 111/253 [00:35<00:43,  3.28it/s]
+
 44%|████▍     | 112/253 [00:36<00:43,  3.27it/s]
+
 45%|████▍     | 113/253 [00:36<00:43,  3.21it/s]
+
 45%|████▌     | 114/253 [00:36<00:44,  3.12it/s]
+
 45%|████▌     | 115/253 [00:37<00:43,  3.16it/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<00:42,  3.18it/s]
+
 47%|████▋     | 120/253 [00:38<00:43,  3.06it/s]
+
 48%|████▊     | 121/253 [00:39<00:43,  3.06it/s]
+
 48%|████▊     | 122/253 [00:39<00:40,  3.25it/s]
+
 49%|████▊     | 123/253 [00:39<00:40,  3.17it/s]
+
 49%|████▉     | 124/253 [00:40<00:41,  3.10it/s]
+
 49%|████▉     | 125/253 [00:40<00:41,  3.06it/s]
+
 50%|████▉     | 126/253 [00:40<00:41,  3.03it/s]
+
 50%|█████     | 127/253 [00:41<00:42,  2.96it/s]
+
 51%|█████     | 128/253 [00:41<00:41,  3.01it/s]
+
 51%|█████     | 129/253 [00:41<00:42,  2.89it/s]
+
 51%|█████▏    | 130/253 [00:42<00:43,  2.82it/s]
+
 52%|█████▏    | 131/253 [00:42<00:41,  2.91it/s]
+
 52%|█████▏    | 132/253 [00:42<00:40,  3.01it/s]
+
 53%|█████▎    | 133/253 [00:43<00:39,  3.01it/s]
+
 53%|█████▎    | 134/253 [00:43<00:39,  3.03it/s]
+
 53%|█████▎    | 135/253 [00:43<00:39,  3.01it/s]
+
 54%|█████▍    | 136/253 [00:44<00:38,  3.08it/s]
+
 54%|█████▍    | 137/253 [00:44<00:38,  3.04it/s]
+
 55%|█████▍    | 138/253 [00:44<00:37,  3.03it/s]
+
 55%|█████▍    | 139/253 [00:45<00:38,  2.97it/s]
+
 55%|█████▌    | 140/253 [00:45<00:37,  3.04it/s]
+
 56%|█████▌    | 141/253 [00:45<00:37,  3.00it/s]
+
 56%|█████▌    | 142/253 [00:46<00:35,  3.11it/s]
+
 57%|█████▋    | 143/253 [00:46<00:37,  2.96it/s]
+
 57%|█████▋    | 144/253 [00:46<00:36,  3.01it/s]
+
 57%|█████▋    | 145/253 [00:47<00:35,  3.01it/s]
+
 58%|█████▊    | 146/253 [00:47<00:35,  3.03it/s]
+
 58%|█████▊    | 147/253 [00:47<00:35,  3.00it/s]
+
 58%|█████▊    | 148/253 [00:48<00:34,  3.07it/s]
+
 59%|█████▉    | 149/253 [00:48<00:34,  3.02it/s]
+
 59%|█████▉    | 150/253 [00:48<00:33,  3.09it/s]
+
 60%|█████▉    | 151/253 [00:49<00:32,  3.14it/s]
+
 60%|██████    | 152/253 [00:49<00:32,  3.08it/s]
+
 60%|██████    | 153/253 [00:49<00:33,  3.00it/s]
+
 61%|██████    | 154/253 [00:50<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 [00:51<00:30,  3.15it/s]
+
 62%|██████▏   | 158/253 [00:51<00:30,  3.10it/s]
+
 63%|██████▎   | 159/253 [00:51<00:29,  3.23it/s]
+
 63%|██████▎   | 160/253 [00:51<00:29,  3.21it/s]
+
 64%|██████▎   | 161/253 [00:52<00:29,  3.11it/s]
+
 64%|██████▍   | 162/253 [00:52<00:28,  3.14it/s]
+
 64%|██████▍   | 163/253 [00:52<00:28,  3.17it/s]
+
 65%|██████▍   | 164/253 [00:53<00:27,  3.23it/s]
+
 65%|██████▌   | 165/253 [00:53<00:27,  3.18it/s]
+
 66%|██████▌   | 166/253 [00:53<00:27,  3.15it/s]
+
 66%|██████▌   | 167/253 [00:54<00:27,  3.08it/s]
+
 66%|██████▋   | 168/253 [00:54<00:26,  3.18it/s]
+
 67%|██████▋   | 169/253 [00:54<00:26,  3.21it/s]
+
 67%|██████▋   | 170/253 [00:55<00:26,  3.14it/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<00:23,  3.35it/s]
+
 69%|██████▉   | 174/253 [00:56<00:25,  3.10it/s]
+
 69%|██████▉   | 175/253 [00:56<00:24,  3.21it/s]
+
 70%|██████▉   | 176/253 [00:56<00:23,  3.32it/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,  3.08it/s]
+
 72%|███████▏  | 181/253 [00:58<00:23,  3.12it/s]
+
 72%|███████▏  | 182/253 [00:58<00:23,  3.00it/s]
+
 72%|███████▏  | 183/253 [00:59<00:22,  3.06it/s]
+
 73%|███████▎  | 184/253 [00:59<00:23,  2.94it/s]
+
 73%|███████▎  | 185/253 [00:59<00:22,  2.97it/s]
+
 74%|███████▎  | 186/253 [01:00<00:22,  2.99it/s]
+
 74%|███████▍  | 187/253 [01:00<00:21,  3.00it/s]
+
 74%|███████▍  | 188/253 [01:00<00:22,  2.90it/s]
+
 75%|███████▍  | 189/253 [01:01<00:20,  3.05it/s]
+
 75%|███████▌  | 190/253 [01:01<00:21,  3.00it/s]
+
 75%|███████▌  | 191/253 [01:01<00:21,  2.92it/s]
+
 76%|███████▌  | 192/253 [01:02<00:20,  2.98it/s]
+
 76%|███████▋  | 193/253 [01:02<00:19,  3.13it/s]
+
 77%|███████▋  | 194/253 [01:02<00:19,  3.10it/s]
+
 77%|███████▋  | 195/253 [01:03<00:18,  3.13it/s]
+
 77%|███████▋  | 196/253 [01:03<00:18,  3.06it/s]
+
 78%|███████▊  | 197/253 [01:03<00:17,  3.17it/s]
+
 78%|███████▊  | 198/253 [01:04<00:17,  3.11it/s]
+
 79%|███████▊  | 199/253 [01:04<00:17,  3.02it/s]
+
 79%|███████▉  | 200/253 [01:04<00:17,  2.95it/s]
+
 79%|███████▉  | 201/253 [01:05<00:17,  2.99it/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,  2.95it/s]
+
 81%|████████  | 205/253 [01:06<00:16,  2.94it/s]
+
 81%|████████▏ | 206/253 [01:06<00:16,  2.87it/s]
+
 82%|████████▏ | 207/253 [01:07<00:15,  2.89it/s]
+
 82%|████████▏ | 208/253 [01:07<00:15,  2.88it/s]
+
 83%|████████▎ | 209/253 [01:07<00:15,  2.88it/s]
+
 83%|████████▎ | 210/253 [01:08<00:14,  3.00it/s]
+
 83%|████████▎ | 211/253 [01:08<00:14,  2.95it/s]
+
 84%|████████▍ | 212/253 [01:09<00:14,  2.86it/s]
+
 84%|████████▍ | 213/253 [01:09<00:13,  2.88it/s]
+
 85%|████████▍ | 214/253 [01:09<00:13,  2.88it/s]
+
 85%|████████▍ | 215/253 [01:10<00:12,  2.93it/s]
+
 85%|████████▌ | 216/253 [01:10<00:12,  2.95it/s]
+
 86%|████████▌ | 217/253 [01:10<00:11,  3.07it/s]
+
 86%|████████▌ | 218/253 [01:10<00:11,  3.10it/s]
+
 87%|████████▋ | 219/253 [01:11<00:11,  3.05it/s]
+
 87%|████████▋ | 220/253 [01:11<00:11,  2.93it/s]
+
 87%|████████▋ | 221/253 [01:12<00:11,  2.90it/s]
+
 88%|████████▊ | 222/253 [01:12<00:10,  2.93it/s]
+
 88%|████████▊ | 223/253 [01:12<00:10,  2.96it/s]
+
 89%|████████▊ | 224/253 [01:13<00:09,  3.04it/s]
+
 89%|████████▉ | 225/253 [01:13<00:09,  3.00it/s]
+
 89%|████████▉ | 226/253 [01:13<00:08,  3.01it/s]
+
 90%|████████▉ | 227/253 [01:13<00:08,  3.12it/s]
+
 90%|█████████ | 228/253 [01:14<00:08,  3.12it/s]
+
 91%|█████████ | 229/253 [01:14<00:07,  3.10it/s]
+
 91%|█████████ | 230/253 [01:14<00:07,  3.07it/s]
+
 91%|█████████▏| 231/253 [01:15<00:07,  3.03it/s]
+
 92%|█████████▏| 232/253 [01:15<00:06,  3.07it/s]
+
 92%|█████████▏| 233/253 [01:15<00:06,  3.07it/s]
+
 92%|█████████▏| 234/253 [01:16<00:06,  3.09it/s]
+
 93%|█████████▎| 235/253 [01:16<00:05,  3.25it/s]
+
 93%|█████████▎| 236/253 [01:16<00:05,  3.23it/s]
+
 94%|█████████▎| 237/253 [01:17<00:04,  3.22it/s]
+
 94%|█████████▍| 238/253 [01:17<00:04,  3.02it/s]
+
 94%|█████████▍| 239/253 [01:17<00:04,  3.04it/s]
+
 95%|█████████▍| 240/253 [01:18<00:04,  2.98it/s]
+
 95%|█████████▌| 241/253 [01:18<00:04,  2.92it/s]
+
 96%|█████████▌| 242/253 [01:18<00:03,  2.80it/s]
+
 96%|█████████▌| 243/253 [01:19<00:03,  2.79it/s]
+
 96%|█████████▋| 244/253 [01:19<00:03,  2.79it/s]
+
 97%|█████████▋| 245/253 [01:20<00:02,  2.87it/s]
+
 97%|█████████▋| 246/253 [01:20<00:02,  2.87it/s]
+
 98%|█████████▊| 247/253 [01:20<00:02,  2.85it/s]
+
 98%|█████████▊| 248/253 [01:21<00:01,  2.77it/s]
+
 98%|█████████▊| 249/253 [01:21<00:01,  2.82it/s]
+
 99%|█████████▉| 250/253 [01:21<00:01,  2.86it/s]
+
 99%|█████████▉| 251/253 [01:22<00:00,  2.93it/s]
+
+
                                                           
+
                                                 
 66%|██████▋   | 45000/67700 [27:03:44<12:50:50,  2.04s/it]
+
+
                                                 Saving model checkpoint to ./checkpoint-45000
+Configuration saved in ./checkpoint-45000/config.json
+Model weights saved in ./checkpoint-45000/pytorch_model.bin
+Configuration saved in ./checkpoint-45000/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:e94bffe9106a56510742e962602df7b5537de199f96a6bfc7a7314d5f19ee260
+oid sha256:fdbb4959405ec35ddb1d2b74ca7593c592ea5070ab1187d2c2b7272d32e3aeb2
 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:b1354a49d4c9d15982969202ed1ee366c3a86953c0a25f87d36b5eacf9c8fd2f
-size 107907
+oid sha256:ddb39abf3884df3073a77dba2c2225943b10cdcbff47c90351be6ccb1716bedd
+size 109451