Training in progress, step 1000

nohup.out

@@ -582,4 +582,79 @@ The following columns in the training set  don't have a corresponding argument i
 Configuration saved in ./checkpoint-500/config.json
 Model weights saved in ./checkpoint-500/pytorch_model.bin
 Configuration saved in ./checkpoint-500/preprocessor_config.json
+Configuration saved in ./preprocessor_config.json
+
  1%|▏         | 501/34750 [48:33<488:04:10, 51.30s/it]
  1%|▏         | 502/34750 [48:43<369:41:00, 38.86s/it]
  1%|▏         | 503/34750 [48:52<285:42:40, 30.03s/it]
  1%|▏         | 504/34750 [49:01<224:35:11, 23.61s/it]
  1%|▏         | 505/34750 [49:09<181:15:43, 19.06s/it]
  1%|▏         | 506/34750 [49:17<150:09:42, 15.79s/it]
  1%|▏         | 507/34750 [49:25<126:51:59, 13.34s/it]
  1%|▏         | 508/34750 [49:32<110:26:15, 11.61s/it]
  1%|▏         | 509/34750 [49:40<97:53:56, 10.29s/it] 
  1%|▏         | 510/34750 [49:47<88:52:52,  9.34s/it]
  1%|▏         | 511/34750 [49:54<83:04:40,  8.74s/it]
  1%|▏         | 512/34750 [50:01<78:21:52,  8.24s/it]
  1%|▏         | 513/34750 [50:08<72:55:19,  7.67s/it]
  1%|▏         | 514/34750 [50:14<69:34:52,  7.32s/it]
  1%|▏         | 515/34750 [50:20<66:58:07,  7.04s/it]
  1%|▏         | 516/34750 [50:27<64:30:16,  6.78s/it]
  1%|▏         | 517/34750 [50:33<62:03:01,  6.53s/it]
  1%|▏         | 518/34750 [50:38<60:11:15,  6.33s/it]
  1%|▏         | 519/34750 [50:44<59:00:28,  6.21s/it]
  1%|▏         | 520/34750 [50:50<57:52:57,  6.09s/it]
  1%|▏         | 521/34750 [50:56<56:36:39,  5.95s/it]
  2%|▏         | 522/34750 [51:01<55:05:05,  5.79s/it]
  2%|▏         | 523/34750 [51:07<53:40:02,  5.64s/it]
  2%|▏         | 524/34750 [51:12<52:50:28,  5.56s/it]
  2%|▏         | 525/34750 [51:17<52:05:55,  5.48s/it]
  2%|▏         | 526/34750 [51:23<51:37:33,  5.43s/it]
  2%|▏         | 527/34750 [51:28<50:46:09,  5.34s/it]
  2%|▏         | 528/34750 [51:33<49:30:23,  5.21s/it]
  2%|▏         | 529/34750 [51:37<48:24:11,  5.09s/it]
  2%|▏         | 530/34750 [51:42<47:36:31,  5.01s/it]
  2%|▏         | 531/34750 [51:47<46:29:31,  4.89s/it]
  2%|▏         | 532/34750 [51:52<46:01:00,  4.84s/it]
  2%|▏         | 533/34750 [51:56<46:02:32,  4.84s/it]
  2%|▏         | 534/34750 [52:01<46:06:59,  4.85s/it]
  2%|▏         | 535/34750 [52:06<45:04:07,  4.74s/it]
  2%|▏         | 536/34750 [52:10<44:12:33,  4.65s/it]
  2%|▏         | 537/34750 [52:14<43:03:13,  4.53s/it]
  2%|▏         | 538/34750 [52:18<41:46:06,  4.40s/it]
  2%|▏         | 539/34750 [52:23<40:47:46,  4.29s/it]
  2%|▏         | 540/34750 [52:27<40:04:18,  4.22s/it]
  2%|▏         | 541/34750 [52:31<39:18:20,  4.14s/it]
  2%|▏         | 542/34750 [52:34<38:25:21,  4.04s/it]
  2%|▏         | 543/34750 [52:38<37:48:06,  3.98s/it]
  2%|▏         | 544/34750 [52:42<37:11:36,  3.91s/it]
  2%|▏         | 545/34750 [52:46<36:29:44,  3.84s/it]
  2%|▏         | 546/34750 [52:49<35:57:11,  3.78s/it]
  2%|▏         | 547/34750 [52:53<35:21:44,  3.72s/it]
  2%|▏         | 548/34750 [52:56<34:06:22,  3.59s/it]
  2%|▏         | 549/34750 [52:59<32:53:20,  3.46s/it]
  2%|▏         | 550/34750 [53:02<31:22:39,  3.30s/it]
  2%|▏         | 551/34750 [53:14<54:19:19,  5.72s/it]
  2%|▏         | 552/34750 [53:23<65:30:36,  6.90s/it]
  2%|▏         | 553/34750 [53:32<71:28:50,  7.52s/it]
  2%|▏         | 554/34750 [53:41<74:38:26,  7.86s/it]
  2%|▏         | 555/34750 [53:49<75:53:31,  7.99s/it]
  2%|▏         | 556/34750 [53:57<76:18:30,  8.03s/it]
  2%|▏         | 557/34750 [54:05<75:29:04,  7.95s/it]
  2%|▏         | 558/34750 [54:12<74:06:11,  7.80s/it]
  2%|▏         | 559/34750 [54:20<72:14:01,  7.61s/it]
  2%|▏         | 560/34750 [54:27<70:58:03,  7.47s/it]
  2%|▏         | 561/34750 [54:34<70:10:13,  7.39s/it]
  2%|▏         | 562/34750 [54:41<68:18:17,  7.19s/it]
  2%|▏         | 563/34750 [54:47<66:15:44,  6.98s/it]
  2%|▏         | 564/34750 [54:53<63:55:23,  6.73s/it]
  2%|▏         | 565/34750 [55:00<62:36:26,  6.59s/it]
  2%|▏         | 566/34750 [55:06<60:54:05,  6.41s/it]
  2%|▏         | 567/34750 [55:11<59:21:22,  6.25s/it]
  2%|▏         | 568/34750 [55:17<57:47:27,  6.09s/it]
  2%|▏         | 569/34750 [55:23<56:20:39,  5.93s/it]
  2%|▏         | 570/34750 [55:28<55:02:34,  5.80s/it]
  2%|▏         | 571/34750 [55:34<54:26:24,  5.73s/it]
  2%|▏         | 572/34750 [55:39<53:45:48,  5.66s/it]
  2%|▏         | 573/34750 [55:45<52:51:30,  5.57s/it]
  2%|▏         | 574/34750 [55:50<51:47:50,  5.46s/it]
  2%|▏         | 575/34750 [55:55<51:21:33,  5.41s/it]
  2%|▏         | 576/34750 [56:00<50:24:02,  5.31s/it]
  2%|▏         | 577/34750 [56:05<49:40:03,  5.23s/it]
  2%|▏         | 578/34750 [56:10<48:30:04,  5.11s/it]
  2%|▏         | 579/34750 [56:15<47:21:37,  4.99s/it]
  2%|▏         | 580/34750 [56:20<46:39:54,  4.92s/it]
  2%|▏         | 581/34750 [56:24<45:55:41,  4.84s/it]
  2%|▏         | 582/34750 [56:29<45:01:05,  4.74s/it]
  2%|▏         | 583/34750 [56:33<44:10:30,  4.65s/it]
  2%|▏         | 584/34750 [56:38<43:35:30,  4.59s/it]
  2%|▏         | 585/34750 [56:42<42:42:26,  4.50s/it]
  2%|▏         | 586/34750 [56:46<42:04:37,  4.43s/it]
  2%|▏         | 587/34750 [56:50<41:02:09,  4.32s/it]
  2%|▏         | 588/34750 [56:54<40:12:39,  4.24s/it]
  2%|▏         | 589/34750 [56:58<39:43:34,  4.19s/it]
  2%|▏         | 590/34750 [57:02<39:13:27,  4.13s/it]
  2%|▏         | 591/34750 [57:06<38:22:53,  4.05s/it]
  2%|▏         | 592/34750 [57:10<37:49:15,  3.99s/it]
  2%|▏         | 593/34750 [57:14<37:10:32,  3.92s/it]
  2%|▏         | 594/34750 [57:18<36:35:59,  3.86s/it]
  2%|▏         | 595/34750 [57:21<35:57:28,  3.79s/it]
  2%|▏         | 596/34750 [57:25<35:16:45,  3.72s/it]
  2%|▏         | 597/34750 [57:28<34:23:20,  3.62s/it]
  2%|▏         | 598/34750 [57:31<33:21:30,  3.52s/it]
  2%|▏         | 599/34750 [57:34<32:05:03,  3.38s/it]
  2%|▏         | 600/34750 [57:37<30:30:21,  3.22s/it]
                                                      
  2%|▏         | 600/34750 [57:37<30:30:21,  3.22s/it]
  2%|▏         | 601/34750 [57:49<55:32:04,  5.85s/it]
  2%|▏         | 602/34750 [57:59<66:59:36,  7.06s/it]
  2%|▏         | 603/34750 [58:08<71:58:37,  7.59s/it]
  2%|▏         | 604/34750 [58:16<74:05:47,  7.81s/it]
  2%|▏         | 605/34750 [58:25<75:11:02,  7.93s/it]
  2%|▏         | 606/34750 [58:33<75:30:14,  7.96s/it]
  2%|▏         | 607/34750 [58:40<74:27:01,  7.85s/it]
  2%|▏         | 608/34750 [58:48<73:00:12,  7.70s/it]
  2%|▏         | 609/34750 [58:55<71:27:32,  7.54s/it]
  2%|▏         | 610/34750 [59:02<70:22:20,  7.42s/it]
  2%|▏         | 611/34750 [59:09<68:27:21,  7.22s/it]
  2%|▏         | 612/34750 [59:15<66:35:00,  7.02s/it]
  2%|▏         | 613/34750 [59:21<64:22:57,  6.79s/it]
  2%|▏         | 614/34750 [59:28<62:54:51,  6.63s/it]
  2%|▏         | 615/34750 [59:34<61:45:08,  6.51s/it]
  2%|▏         | 616/34750 [59:40<60:25:06,  6.37s/it]
  2%|▏         | 617/34750 [59:46<59:09:03,  6.24s/it]
  2%|▏         | 618/34750 [59:52<58:05:11,  6.13s/it]
  2%|▏         | 619/34750 [59:57<56:19:06,  5.94s/it]
  2%|▏         | 620/34750 [1:00:03<55:11:50,  5.82s/it]
  2%|▏         | 621/34750 [1:00:08<54:02:33,  5.70s/it]
  2%|▏         | 622/34750 [1:00:13<52:48:32,  5.57s/it]
  2%|▏         | 623/34750 [1:00:19<51:44:09,  5.46s/it]
  2%|▏         | 624/34750 [1:00:24<51:10:26,  5.40s/it]
  2%|▏         | 625/34750 [1:00:29<50:41:48,  5.35s/it]
  2%|▏         | 626/34750 [1:00:34<50:15:21,  5.30s/it]
  2%|▏         | 627/34750 [1:00:39<48:43:36,  5.14s/it]
  2%|▏         | 628/34750 [1:00:44<47:35:55,  5.02s/it]
  2%|▏         | 629/34750 [1:00:49<46:48:03,  4.94s/it]
  2%|▏         | 630/34750 [1:00:53<45:52:39,  4.84s/it]
  2%|▏         | 631/34750 [1:00:58<45:12:04,  4.77s/it]
  2%|▏         | 632/34750 [1:01:02<44:29:10,  4.69s/it]
  2%|▏         | 633/34750 [1:01:07<43:47:01,  4.62s/it]
  2%|▏         | 634/34750 [1:01:11<42:56:31,  4.53s/it]
  2%|▏         | 635/34750 [1:01:15<42:19:56,  4.47s/it]
  2%|▏         | 636/34750 [1:01:20<41:53:02,  4.42s/it]
  2%|▏         | 637/34750 [1:01:24<40:46:47,  4.30s/it]
  2%|▏         | 638/34750 [1:01:28<40:02:58,  4.23s/it]
  2%|▏         | 639/34750 [1:01:32<39:21:28,  4.15s/it]
  2%|▏         | 640/34750 [1:01:36<38:49:56,  4.10s/it]
  2%|▏         | 641/34750 [1:01:40<38:05:54,  4.02s/it]
  2%|▏         | 642/34750 [1:01:43<37:31:35,  3.96s/it]
  2%|▏         | 643/34750 [1:01:47<37:07:35,  3.92s/it]
  2%|▏         | 644/34750 [1:01:51<36:28:21,  3.85s/it]
  2%|▏         | 645/34750 [1:01:55<35:44:59,  3.77s/it]
  2%|▏         | 646/34750 [1:01:58<35:18:08,  3.73s/it]
  2%|▏         | 647/34750 [1:02:02<34:15:42,  3.62s/it]
  2%|▏         | 648/34750 [1:02:05<33:20:51,  3.52s/it]
  2%|▏         | 649/34750 [1:02:08<31:55:27,  3.37s/it]
  2%|▏         | 650/34750 [1:02:11<30:21:39,  3.21s/it]
  2%|▏         | 651/34750 [1:02:22<53:35:26,  5.66s/it]
  2%|▏         | 652/34750 [1:02:31<63:50:52,  6.74s/it]
  2%|▏         | 653/34750 [1:02:40<70:30:24,  7.44s/it]
  2%|▏         | 654/34750 [1:02:49<73:34:45,  7.77s/it]
  2%|▏         | 655/34750 [1:02:57<74:43:57,  7.89s/it]
  2%|▏         | 656/34750 [1:03:05<74:26:11,  7.86s/it]
  2%|▏         | 657/34750 [1:03:12<73:26:25,  7.75s/it]
  2%|▏         | 658/34750 [1:03:20<72:22:16,  7.64s/it]
  2%|▏         | 659/34750 [1:03:27<71:26:26,  7.54s/it]
  2%|▏         | 660/34750 [1:03:34<70:30:03,  7.45s/it]
  2%|▏         | 661/34750 [1:03:41<68:39:08,  7.25s/it]
  2%|▏         | 662/34750 [1:03:48<66:27:09,  7.02s/it]
  2%|▏         | 663/34750 [1:03:54<64:24:53,  6.80s/it]
  2%|▏         | 664/34750 [1:04:00<63:37:23,  6.72s/it]
  2%|▏         | 665/34750 [1:04:07<62:07:11,  6.56s/it]
  2%|▏         | 666/34750 [1:04:13<60:21:57,  6.38s/it]
  2%|▏         | 667/34750 [1:04:18<58:18:53,  6.16s/it]
  2%|▏         | 668/34750 [1:04:24<56:52:44,  6.01s/it]
  2%|▏         | 669/34750 [1:04:29<55:47:03,  5.89s/it]
  2%|▏         | 670/34750 [1:04:35<54:17:55,  5.74s/it]
  2%|▏         | 671/34750 [1:04:40<53:35:04,  5.66s/it]
  2%|▏         | 672/34750 [1:04:46<52:24:57,  5.54s/it]
  2%|▏         | 673/34750 [1:04:51<52:12:57,  5.52s/it]
  2%|▏         | 674/34750 [1:04:56<51:14:24,  5.41s/it]
  2%|▏         | 675/34750 [1:05:01<50:05:26,  5.29s/it]
  2%|▏         | 676/34750 [1:05:06<49:54:31,  5.27s/it]
  2%|▏         | 677/34750 [1:05:11<48:17:09,  5.10s/it]
  2%|▏         | 678/34750 [1:05:16<46:57:42,  4.96s/it]
  2%|▏         | 679/34750 [1:05:20<46:10:40,  4.88s/it]
  2%|▏         | 680/34750 [1:05:25<45:03:54,  4.76s/it]
  2%|▏         | 681/34750 [1:05:29<43:59:13,  4.65s/it]
  2%|▏         | 682/34750 [1:05:34<43:09:35,  4.56s/it]
  2%|▏         | 683/34750 [1:05:38<42:14:38,  4.46s/it]
  2%|▏         | 684/34750 [1:05:42<41:38:02,  4.40s/it]
  2%|▏         | 685/34750 [1:05:46<41:05:02,  4.34s/it]
  2%|▏         | 686/34750 [1:05:51<40:40:30,  4.30s/it]
  2%|▏         | 687/34750 [1:05:54<39:25:27,  4.17s/it]
  2%|▏         | 688/34750 [1:05:58<38:39:35,  4.09s/it]
  2%|▏         | 689/34750 [1:06:02<38:21:34,  4.05s/it]
  2%|▏         | 690/34750 [1:06:06<37:53:58,  4.01s/it]
  2%|▏         | 691/34750 [1:06:10<37:02:17,  3.91s/it]
  2%|▏         | 692/34750 [1:06:14<36:15:09,  3.83s/it]
  2%|▏         | 693/34750 [1:06:17<34:57:24,  3.70s/it]
  2%|▏         | 694/34750 [1:06:20<33:29:33,  3.54s/it]
  2%|▏         | 695/34750 [1:06:23<32:20:58,  3.42s/it]
  2%|▏         | 696/34750 [1:06:38<64:10:18,  6.78s/it]
  2%|▏         | 697/34750 [1:06:48<72:47:59,  7.70s/it]
  2%|▏         | 698/34750 [1:06:57<77:12:28,  8.16s/it]
  2%|▏         | 699/34750 [1:07:05<77:43:19,  8.22s/it]
  2%|▏         | 700/34750 [1:07:13<76:09:52,  8.05s/it]
                                                        
  2%|▏         | 700/34750 [1:07:13<76:09:52,  8.05s/it]
  2%|▏         | 701/34750 [1:07:21<75:49:52,  8.02s/it]
  2%|▏         | 702/34750 [1:07:28<73:58:45,  7.82s/it]
  2%|▏         | 703/34750 [1:07:36<72:47:47,  7.70s/it]
  2%|▏         | 704/34750 [1:07:43<71:30:17,  7.56s/it]
  2%|▏         | 705/34750 [1:07:50<69:43:18,  7.37s/it]
  2%|▏         | 706/34750 [1:07:57<68:49:46,  7.28s/it]
  2%|▏         | 707/34750 [1:08:03<66:42:37,  7.05s/it]
  2%|▏         | 708/34750 [1:08:10<65:34:44,  6.94s/it]
  2%|▏         | 709/34750 [1:08:16<63:54:16,  6.76s/it]
  2%|▏         | 710/34750 [1:08:23<62:05:31,  6.57s/it]
  2%|▏         | 711/34750 [1:08:29<60:45:51,  6.43s/it]
  2%|▏         | 712/34750 [1:08:35<59:35:05,  6.30s/it]
  2%|▏         | 713/34750 [1:08:40<58:02:09,  6.14s/it]
  2%|▏         | 714/34750 [1:08:46<56:56:15,  6.02s/it]
  2%|▏         | 715/34750 [1:08:52<55:39:30,  5.89s/it]
  2%|▏         | 716/34750 [1:08:57<54:43:32,  5.79s/it]
  2%|▏         | 717/34750 [1:09:03<53:30:34,  5.66s/it]
  2%|▏         | 718/34750 [1:09:08<52:36:59,  5.57s/it]
  2%|▏         | 719/34750 [1:09:13<51:58:15,  5.50s/it]
  2%|▏         | 720/34750 [1:09:19<50:58:28,  5.39s/it]
  2%|▏         | 721/34750 [1:09:24<50:31:39,  5.35s/it]
  2%|▏         | 722/34750 [1:09:29<50:11:06,  5.31s/it]
  2%|▏         | 723/34750 [1:09:34<50:00:49,  5.29s/it]
  2%|▏         | 724/34750 [1:09:39<48:56:45,  5.18s/it]
  2%|▏         | 725/34750 [1:09:44<48:16:15,  5.11s/it]
  2%|▏         | 726/34750 [1:09:49<47:11:45,  4.99s/it]
  2%|▏         | 727/34750 [1:09:53<46:12:46,  4.89s/it]
  2%|▏         | 728/34750 [1:09:58<46:10:28,  4.89s/it]
  2%|▏         | 729/34750 [1:10:03<44:47:08,  4.74s/it]
  2%|▏         | 730/34750 [1:10:07<43:55:00,  4.65s/it]
  2%|▏         | 731/34750 [1:10:11<42:47:34,  4.53s/it]
  2%|▏         | 732/34750 [1:10:16<41:53:06,  4.43s/it]
  2%|▏         | 733/34750 [1:10:20<41:09:17,  4.36s/it]
  2%|▏         | 734/34750 [1:10:24<40:30:23,  4.29s/it]
  2%|▏         | 735/34750 [1:10:28<39:45:02,  4.21s/it]
  2%|▏         | 736/34750 [1:10:32<38:58:05,  4.12s/it]
  2%|▏         | 737/34750 [1:10:36<38:11:12,  4.04s/it]
  2%|▏         | 738/34750 [1:10:40<37:34:50,  3.98s/it]
  2%|▏         | 739/34750 [1:10:43<36:58:38,  3.91s/it]
  2%|▏         | 740/34750 [1:10:47<36:18:03,  3.84s/it]
  2%|▏         | 741/34750 [1:10:51<35:39:24,  3.77s/it]
  2%|▏         | 742/34750 [1:10:54<34:44:06,  3.68s/it]
  2%|▏         | 743/34750 [1:10:57<33:25:43,  3.54s/it]
  2%|▏         | 744/34750 [1:11:00<32:14:37,  3.41s/it]
  2%|▏         | 745/34750 [1:11:03<30:44:22,  3.25s/it]
  2%|▏         | 746/34750 [1:11:15<54:20:17,  5.75s/it]
  2%|▏         | 747/34750 [1:11:24<64:58:55,  6.88s/it]
  2%|▏         | 748/34750 [1:11:33<70:58:42,  7.51s/it]
  2%|▏         | 749/34750 [1:11:41<71:59:55,  7.62s/it]
  2%|▏         | 750/34750 [1:11:49<73:28:42,  7.78s/it]
  2%|▏         | 751/34750 [1:11:57<73:46:54,  7.81s/it]
  2%|▏         | 752/34750 [1:12:05<72:37:07,  7.69s/it]
  2%|▏         | 753/34750 [1:12:12<70:45:11,  7.49s/it]
  2%|▏         | 754/34750 [1:12:19<69:39:09,  7.38s/it]
  2%|▏         | 755/34750 [1:12:26<68:21:06,  7.24s/it]
  2%|▏         | 756/34750 [1:12:32<66:43:46,  7.07s/it]
  2%|▏         | 757/34750 [1:12:39<64:41:03,  6.85s/it]
  2%|▏         | 758/34750 [1:12:45<63:10:27,  6.69s/it]
  2%|▏         | 759/34750 [1:12:51<62:03:36,  6.57s/it]
  2%|▏         | 760/34750 [1:12:58<60:54:20,  6.45s/it]
  2%|▏         | 761/34750 [1:13:03<59:23:58,  6.29s/it]
  2%|▏         | 762/34750 [1:13:10<59:26:31,  6.30s/it]
  2%|▏         | 763/34750 [1:13:16<57:58:42,  6.14s/it]
  2%|▏         | 764/34750 [1:13:21<56:50:30,  6.02s/it]
  2%|▏         | 765/34750 [1:13:27<55:21:24,  5.86s/it]
  2%|▏         | 766/34750 [1:13:32<54:24:39,  5.76s/it]
  2%|▏         | 767/34750 [1:13:38<53:31:49,  5.67s/it]
  2%|▏         | 768/34750 [1:13:43<52:49:51,  5.60s/it]
  2%|▏         | 769/34750 [1:13:48<51:33:54,  5.46s/it]
  2%|▏         | 770/34750 [1:13:54<51:00:25,  5.40s/it]
  2%|▏         | 771/34750 [1:13:59<50:22:33,  5.34s/it]
  2%|▏         | 772/34750 [1:14:04<49:39:48,  5.26s/it]
  2%|▏         | 773/34750 [1:14:09<48:24:48,  5.13s/it]
  2%|▏         | 774/34750 [1:14:13<47:16:43,  5.01s/it]
  2%|▏         | 775/34750 [1:14:18<46:16:02,  4.90s/it]
  2%|▏         | 776/34750 [1:14:23<45:18:44,  4.80s/it]
  2%|▏         | 777/34750 [1:14:27<44:41:11,  4.74s/it]
  2%|▏         | 778/34750 [1:14:32<43:41:45,  4.63s/it]
  2%|▏         | 779/34750 [1:14:36<42:54:00,  4.55s/it]
  2%|▏         | 780/34750 [1:14:40<42:14:27,  4.48s/it]
  2%|▏         | 781/34750 [1:14:44<41:33:38,  4.40s/it]
  2%|▏         | 782/34750 [1:14:49<40:39:50,  4.31s/it]
  2%|▏         | 783/34750 [1:14:53<39:55:25,  4.23s/it]
  2%|▏         | 784/34750 [1:14:57<39:05:17,  4.14s/it]
  2%|▏         | 785/34750 [1:15:00<38:29:04,  4.08s/it]
  2%|▏         | 786/34750 [1:15:04<37:55:57,  4.02s/it]
  2%|▏         | 787/34750 [1:15:08<37:39:28,  3.99s/it]
  2%|▏         | 788/34750 [1:15:12<37:44:10,  4.00s/it]
  2%|▏         | 789/34750 [1:15:16<36:47:55,  3.90s/it]
  2%|▏         | 790/34750 [1:15:20<35:58:08,  3.81s/it]
  2%|▏         | 791/34750 [1:15:23<34:58:36,  3.71s/it]
  2%|▏         | 792/34750 [1:15:26<33:35:45,  3.56s/it]
  2%|▏         | 793/34750 [1:15:29<32:30:19,  3.45s/it]
  2%|▏         | 794/34750 [1:15:32<31:16:22,  3.32s/it]
  2%|▏         | 795/34750 [1:15:35<29:54:12,  3.17s/it]
  2%|▏         | 796/34750 [1:15:46<52:25:01,  5.56s/it]
  2%|▏         | 797/34750 [1:15:56<64:08:48,  6.80s/it]
  2%|▏         | 798/34750 [1:16:05<70:49:42,  7.51s/it]
  2%|▏         | 799/34750 [1:16:14<73:11:23,  7.76s/it]
  2%|▏         | 800/34750 [1:16:22<74:36:41,  7.91s/it]
                                                        
  2%|▏         | 800/34750 [1:16:22<74:36:41,  7.91s/it]
  2%|▏         | 801/34750 [1:16:30<74:18:50,  7.88s/it]
  2%|▏         | 802/34750 [1:16:37<73:43:48,  7.82s/it]
  2%|▏         | 803/34750 [1:16:45<72:37:54,  7.70s/it]
  2%|▏         | 804/34750 [1:16:52<70:56:13,  7.52s/it]
  2%|▏         | 805/34750 [1:16:59<69:53:06,  7.41s/it]
  2%|▏         | 806/34750 [1:17:06<68:45:05,  7.29s/it]
  2%|▏         | 807/34750 [1:17:13<66:54:20,  7.10s/it]
  2%|▏         | 808/34750 [1:17:19<64:38:18,  6.86s/it]
  2%|▏         | 809/34750 [1:17:25<62:42:14,  6.65s/it]
  2%|▏         | 810/34750 [1:17:31<60:54:20,  6.46s/it]
  2%|▏         | 811/34750 [1:17:37<59:28:09,  6.31s/it]
  2%|▏         | 812/34750 [1:17:43<58:59:33,  6.26s/it]
  2%|▏         | 813/34750 [1:17:49<57:36:27,  6.11s/it]
  2%|▏         | 814/34750 [1:17:55<56:02:31,  5.95s/it]
  2%|▏         | 815/34750 [1:18:00<55:00:45,  5.84s/it]
  2%|▏         | 816/34750 [1:18:06<54:11:52,  5.75s/it]
  2%|▏         | 817/34750 [1:18:11<53:22:01,  5.66s/it]
  2%|▏         | 818/34750 [1:18:17<52:29:52,  5.57s/it]
  2%|▏         | 819/34750 [1:18:22<51:23:46,  5.45s/it]
  2%|▏         | 820/34750 [1:18:27<51:05:56,  5.42s/it]
  2%|▏         | 821/34750 [1:18:32<50:41:36,  5.38s/it]
  2%|▏         | 822/34750 [1:18:37<49:55:33,  5.30s/it]
  2%|▏         | 823/34750 [1:18:42<48:38:56,  5.16s/it]
  2%|▏         | 824/34750 [1:18:47<48:33:18,  5.15s/it]
  2%|▏         | 825/34750 [1:18:52<48:12:29,  5.12s/it]
  2%|▏         | 826/34750 [1:18:57<47:11:38,  5.01s/it]
  2%|▏         | 827/34750 [1:19:02<45:57:46,  4.88s/it]
  2%|▏         | 828/34750 [1:19:06<44:48:56,  4.76s/it]
  2%|▏         | 829/34750 [1:19:11<43:52:48,  4.66s/it]
  2%|▏         | 830/34750 [1:19:15<42:49:06,  4.54s/it]
  2%|▏         | 831/34750 [1:19:19<41:52:59,  4.45s/it]
  2%|▏         | 832/34750 [1:19:23<41:12:46,  4.37s/it]
  2%|▏         | 833/34750 [1:19:27<40:14:29,  4.27s/it]
  2%|▏         | 834/34750 [1:19:32<39:40:23,  4.21s/it]
  2%|▏         | 835/34750 [1:19:35<38:55:23,  4.13s/it]
  2%|▏         | 836/34750 [1:19:39<38:20:14,  4.07s/it]
  2%|▏         | 837/34750 [1:19:43<37:34:08,  3.99s/it]
  2%|▏         | 838/34750 [1:19:47<36:54:52,  3.92s/it]
  2%|▏         | 839/34750 [1:19:51<36:14:40,  3.85s/it]
  2%|▏         | 840/34750 [1:19:54<35:34:36,  3.78s/it]
  2%|▏         | 841/34750 [1:19:58<35:09:15,  3.73s/it]
  2%|▏         | 842/34750 [1:20:01<34:24:06,  3.65s/it]
  2%|▏         | 843/34750 [1:20:05<33:06:39,  3.52s/it]
  2%|▏         | 844/34750 [1:20:08<31:38:48,  3.36s/it]
  2%|▏         | 845/34750 [1:20:10<30:05:23,  3.19s/it]
  2%|▏         | 846/34750 [1:20:22<53:31:16,  5.68s/it]
  2%|▏         | 847/34750 [1:20:31<64:37:23,  6.86s/it]
  2%|▏         | 848/34750 [1:20:41<71:00:13,  7.54s/it]
  2%|▏         | 849/34750 [1:20:49<74:24:23,  7.90s/it]
  2%|▏         | 850/34750 [1:20:57<75:10:12,  7.98s/it]
  2%|▏         | 851/34750 [1:21:06<75:25:03,  8.01s/it]
  2%|▏         | 852/34750 [1:21:13<74:52:05,  7.95s/it]
  2%|▏         | 853/34750 [1:21:21<73:23:36,  7.79s/it]
  2%|▏         | 854/34750 [1:21:28<71:50:35,  7.63s/it]
  2%|▏         | 855/34750 [1:21:35<70:27:49,  7.48s/it]
  2%|▏         | 856/34750 [1:21:43<70:30:05,  7.49s/it]
  2%|▏         | 857/34750 [1:21:49<68:00:04,  7.22s/it]
  2%|▏         | 858/34750 [1:21:56<65:28:21,  6.95s/it]
  2%|▏         | 859/34750 [1:22:02<63:19:03,  6.73s/it]
  2%|▏         | 860/34750 [1:22:08<61:49:20,  6.57s/it]
  2%|▏         | 861/34750 [1:22:14<60:30:21,  6.43s/it]
  2%|▏         | 862/34750 [1:22:20<58:48:41,  6.25s/it]
  2%|▏         | 863/34750 [1:22:26<57:44:49,  6.13s/it]
  2%|▏         | 864/34750 [1:22:32<57:09:11,  6.07s/it]
  2%|▏         | 865/34750 [1:22:37<55:29:43,  5.90s/it]
  2%|▏         | 866/34750 [1:22:43<54:17:33,  5.77s/it]
  2%|▏         | 867/34750 [1:22:48<53:01:14,  5.63s/it]
  2%|▏         | 868/34750 [1:22:53<52:14:45,  5.55s/it]
  3%|▎         | 869/34750 [1:22:59<51:12:03,  5.44s/it]
  3%|▎         | 870/34750 [1:23:04<50:23:00,  5.35s/it]
  3%|▎         | 871/34750 [1:23:09<49:59:50,  5.31s/it]
  3%|▎         | 872/34750 [1:23:14<50:09:17,  5.33s/it]
  3%|▎         | 873/34750 [1:23:19<48:45:41,  5.18s/it]
  3%|▎         | 874/34750 [1:23:24<47:19:43,  5.03s/it]
  3%|▎         | 875/34750 [1:23:28<46:02:32,  4.89s/it]
  3%|▎         | 876/34750 [1:23:33<45:08:28,  4.80s/it]
  3%|▎         | 877/34750 [1:23:37<44:05:57,  4.69s/it]
  3%|▎         | 878/34750 [1:23:42<43:22:19,  4.61s/it]
  3%|▎         | 879/34750 [1:23:46<42:33:13,  4.52s/it]
  3%|▎         | 880/34750 [1:23:50<41:40:30,  4.43s/it]
  3%|▎         | 881/34750 [1:23:55<41:08:47,  4.37s/it]
  3%|▎         | 882/34750 [1:23:59<40:23:34,  4.29s/it]
  3%|▎         | 883/34750 [1:24:03<39:32:40,  4.20s/it]
  3%|▎         | 884/34750 [1:24:07<39:04:27,  4.15s/it]
  3%|▎         | 885/34750 [1:24:11<38:34:04,  4.10s/it]
  3%|▎         | 886/34750 [1:24:15<38:00:15,  4.04s/it]
  3%|▎         | 887/34750 [1:24:18<37:30:47,  3.99s/it]
  3%|▎         | 888/34750 [1:24:22<36:58:38,  3.93s/it]
  3%|▎         | 889/34750 [1:24:26<36:17:14,  3.86s/it]
  3%|▎         | 890/34750 [1:24:30<35:35:36,  3.78s/it]
  3%|▎         | 891/34750 [1:24:33<34:48:06,  3.70s/it]
  3%|▎         | 892/34750 [1:24:36<33:29:25,  3.56s/it]
  3%|▎         | 893/34750 [1:24:39<32:20:23,  3.44s/it]
  3%|▎         | 894/34750 [1:24:43<31:13:17,  3.32s/it]
  3%|▎         | 895/34750 [1:24:45<29:53:54,  3.18s/it]
  3%|▎         | 896/34750 [1:24:57<53:28:40,  5.69s/it]
  3%|▎         | 897/34750 [1:25:07<64:54:47,  6.90s/it]
  3%|▎         | 898/34750 [1:25:16<71:19:07,  7.58s/it]
  3%|▎         | 899/34750 [1:25:24<74:22:12,  7.91s/it]
  3%|▎         | 900/34750 [1:25:33<75:17:07,  8.01s/it]
                                                        
  3%|▎         | 900/34750 [1:25:33<75:17:07,  8.01s/it]
  3%|▎         | 901/34750 [1:25:40<73:49:23,  7.85s/it]
  3%|▎         | 902/34750 [1:25:48<74:04:14,  7.88s/it]
  3%|▎         | 903/34750 [1:25:56<73:53:20,  7.86s/it]
  3%|▎         | 904/34750 [1:26:03<72:30:08,  7.71s/it]
  3%|▎         | 905/34750 [1:26:10<70:12:44,  7.47s/it]
  3%|▎         | 906/34750 [1:26:17<68:54:22,  7.33s/it]
  3%|▎         | 907/34750 [1:26:24<67:34:42,  7.19s/it]
  3%|▎         | 908/34750 [1:26:30<65:13:31,  6.94s/it]
  3%|▎         | 909/34750 [1:26:37<63:15:37,  6.73s/it]
  3%|▎         | 910/34750 [1:26:43<62:13:16,  6.62s/it]
  3%|▎         | 911/34750 [1:26:49<61:17:22,  6.52s/it]
  3%|▎         | 912/34750 [1:26:55<59:51:24,  6.37s/it]
  3%|▎         | 913/34750 [1:27:01<58:36:15,  6.24s/it]
  3%|▎         | 914/34750 [1:27:07<57:18:55,  6.10s/it]
  3%|▎         | 915/34750 [1:27:13<55:48:47,  5.94s/it]
  3%|▎         | 916/34750 [1:27:18<54:48:28,  5.83s/it]
  3%|▎         | 917/34750 [1:27:24<53:33:48,  5.70s/it]
  3%|▎         | 918/34750 [1:27:29<52:49:59,  5.62s/it]
  3%|▎         | 919/34750 [1:27:34<52:09:25,  5.55s/it]
  3%|▎         | 920/34750 [1:27:40<51:08:19,  5.44s/it]
  3%|▎         | 921/34750 [1:27:45<50:32:44,  5.38s/it]
  3%|▎         | 922/34750 [1:27:50<49:48:13,  5.30s/it]
  3%|▎         | 923/34750 [1:27:55<48:39:12,  5.18s/it]
  3%|▎         | 924/34750 [1:28:00<47:36:44,  5.07s/it]
  3%|▎         | 925/34750 [1:28:04<46:50:07,  4.98s/it]
  3%|▎         | 926/34750 [1:28:09<46:09:52,  4.91s/it]
  3%|▎         | 927/34750 [1:28:14<46:13:55,  4.92s/it]
  3%|▎         | 928/34750 [1:28:19<46:09:20,  4.91s/it]
  3%|▎         | 929/34750 [1:28:24<45:32:25,  4.85s/it]
  3%|▎         | 930/34750 [1:28:28<45:01:44,  4.79s/it]
  3%|▎         | 931/34750 [1:28:33<44:21:19,  4.72s/it]
  3%|▎         | 932/34750 [1:28:37<43:28:15,  4.63s/it]
  3%|▎         | 933/34750 [1:28:41<41:46:46,  4.45s/it]
  3%|▎         | 934/34750 [1:28:45<40:27:48,  4.31s/it]
  3%|▎         | 935/34750 [1:28:49<39:24:45,  4.20s/it]
  3%|▎         | 936/34750 [1:28:53<38:38:20,  4.11s/it]
  3%|▎         | 937/34750 [1:28:57<38:00:40,  4.05s/it]
  3%|▎         | 938/34750 [1:29:01<37:13:11,  3.96s/it]
  3%|▎         | 939/34750 [1:29:05<36:39:09,  3.90s/it]
  3%|▎         | 940/34750 [1:29:08<35:50:08,  3.82s/it]
  3%|▎         | 941/34750 [1:29:12<35:18:12,  3.76s/it]
  3%|▎         | 942/34750 [1:29:15<34:39:12,  3.69s/it]
  3%|▎         | 943/34750 [1:29:19<33:59:44,  3.62s/it]
  3%|▎         | 944/34750 [1:29:22<32:37:24,  3.47s/it]
  3%|▎         | 945/34750 [1:29:25<30:55:34,  3.29s/it]
  3%|▎         | 946/34750 [1:29:37<54:39:42,  5.82s/it]
  3%|▎         | 947/34750 [1:29:47<66:13:55,  7.05s/it]
  3%|▎         | 948/34750 [1:29:55<70:47:30,  7.54s/it]
  3%|▎         | 949/34750 [1:30:04<72:59:15,  7.77s/it]
  3%|▎         | 950/34750 [1:30:12<74:01:46,  7.88s/it]
  3%|▎         | 951/34750 [1:30:20<74:06:49,  7.89s/it]
  3%|▎         | 952/34750 [1:30:27<73:32:32,  7.83s/it]
  3%|▎         | 953/34750 [1:30:34<71:46:39,  7.65s/it]
  3%|▎         | 954/34750 [1:30:42<70:10:35,  7.48s/it]
  3%|▎         | 955/34750 [1:30:48<68:38:17,  7.31s/it]
  3%|▎         | 956/34750 [1:30:55<67:22:17,  7.18s/it]
  3%|▎         | 957/34750 [1:31:02<65:16:33,  6.95s/it]
  3%|▎         | 958/34750 [1:31:08<62:53:27,  6.70s/it]
  3%|▎         | 959/34750 [1:31:14<61:08:38,  6.51s/it]
  3%|▎         | 960/34750 [1:31:20<59:33:31,  6.35s/it]
  3%|▎         | 961/34750 [1:31:26<58:32:28,  6.24s/it]
  3%|▎         | 962/34750 [1:31:32<57:36:05,  6.14s/it]
  3%|▎         | 963/34750 [1:31:38<56:24:35,  6.01s/it]
  3%|▎         | 964/34750 [1:31:43<54:52:47,  5.85s/it]
  3%|▎         | 965/34750 [1:31:48<53:40:15,  5.72s/it]
  3%|▎         | 966/34750 [1:31:54<53:49:36,  5.74s/it]
  3%|▎         | 967/34750 [1:32:00<52:58:20,  5.64s/it]
  3%|▎         | 968/34750 [1:32:05<51:48:24,  5.52s/it]
  3%|▎         | 969/34750 [1:32:10<50:42:48,  5.40s/it]
  3%|▎         | 970/34750 [1:32:15<50:01:42,  5.33s/it]
  3%|▎         | 971/34750 [1:32:20<49:01:35,  5.22s/it]
  3%|▎         | 972/34750 [1:32:25<47:54:42,  5.11s/it]
  3%|▎         | 973/34750 [1:32:30<46:55:40,  5.00s/it]
  3%|▎         | 974/34750 [1:32:35<46:29:19,  4.95s/it]
  3%|▎         | 975/34750 [1:32:39<45:31:30,  4.85s/it]
  3%|▎         | 976/34750 [1:32:44<44:31:18,  4.75s/it]
  3%|▎         | 977/34750 [1:32:48<43:51:09,  4.67s/it]
  3%|▎         | 978/34750 [1:32:53<42:56:30,  4.58s/it]
  3%|▎         | 979/34750 [1:32:57<42:27:20,  4.53s/it]
  3%|▎         | 980/34750 [1:33:01<41:53:04,  4.47s/it]
  3%|▎         | 981/34750 [1:33:06<41:24:13,  4.41s/it]
  3%|▎         | 982/34750 [1:33:10<40:38:29,  4.33s/it]
  3%|▎         | 983/34750 [1:33:14<40:23:48,  4.31s/it]
  3%|▎         | 984/34750 [1:33:18<39:38:35,  4.23s/it]
  3%|▎         | 985/34750 [1:33:22<39:02:28,  4.16s/it]
  3%|▎         | 986/34750 [1:33:26<38:06:14,  4.06s/it]
  3%|▎         | 987/34750 [1:33:30<37:32:21,  4.00s/it]
  3%|▎         | 988/34750 [1:33:33<36:51:01,  3.93s/it]
  3%|▎         | 989/34750 [1:33:37<36:06:13,  3.85s/it]
  3%|▎         | 990/34750 [1:33:41<35:42:15,  3.81s/it]
  3%|▎         | 991/34750 [1:33:44<35:03:18,  3.74s/it]
  3%|▎         | 992/34750 [1:33:48<34:08:23,  3.64s/it]
  3%|▎         | 993/34750 [1:33:51<33:12:26,  3.54s/it]
  3%|▎         | 994/34750 [1:33:54<32:02:33,  3.42s/it]
  3%|▎         | 995/34750 [1:33:57<30:28:57,  3.25s/it]
  3%|▎         | 996/34750 [1:34:09<54:41:30,  5.83s/it]
  3%|▎         | 997/34750 [1:34:19<65:27:01,  6.98s/it]
  3%|▎         | 998/34750 [1:34:27<70:16:48,  7.50s/it]
  3%|▎         | 999/34750 [1:34:36<73:04:48,  7.79s/it]
  3%|▎         | 1000/34750 [1:34:44<72:52:04,  7.77s/it]
                                                         
  3%|▎         | 1000/34750 [1:34:44<72:52:04,  7.77s/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 = 456
+  Batch size = 8
+{'eval_loss': 4.657182693481445, 'eval_wer': 0.9984898822108125, 'eval_runtime': 61.7478, 'eval_samples_per_second': 7.385, 'eval_steps_per_second': 0.923, 'epoch': 0.72}
+{'loss': 4.5246, 'learning_rate': 2.2349999999999998e-05, 'epoch': 0.86}
+{'loss': 3.8527, 'learning_rate': 2.6099999999999997e-05, 'epoch': 1.01}
+{'loss': 3.0344, 'learning_rate': 2.985e-05, 'epoch': 1.15}
+{'loss': 2.7616, 'learning_rate': 3.36e-05, 'epoch': 1.29}
+{'loss': 2.6314, 'learning_rate': 3.735e-05, 'epoch': 1.44}
+
+
  0%|          | 0/57 [00:00<?, ?it/s]
+
  4%|▎         | 2/57 [00:01<00:28,  1.92it/s]
+
  5%|▌         | 3/57 [00:01<00:36,  1.47it/s]
+
  7%|▋         | 4/57 [00:02<00:41,  1.27it/s]
+
  9%|▉         | 5/57 [00:03<00:40,  1.28it/s]
+
 11%|█         | 6/57 [00:04<00:41,  1.22it/s]
+
 12%|█▏        | 7/57 [00:05<00:41,  1.20it/s]
+
 14%|█▍        | 8/57 [00:06<00:41,  1.19it/s]
+
 16%|█▌        | 9/57 [00:07<00:39,  1.21it/s]
+
 18%|█▊        | 10/57 [00:07<00:38,  1.22it/s]
+
 19%|█▉        | 11/57 [00:08<00:39,  1.18it/s]
+
 21%|██        | 12/57 [00:09<00:40,  1.11it/s]
+
 23%|██▎       | 13/57 [00:10<00:42,  1.03it/s]
+
 25%|██▍       | 14/57 [00:11<00:41,  1.04it/s]
+
 26%|██▋       | 15/57 [00:13<00:42,  1.01s/it]
+
 28%|██▊       | 16/57 [00:14<00:41,  1.01s/it]
+
 30%|██▉       | 17/57 [00:15<00:40,  1.02s/it]
+
 32%|███▏      | 18/57 [00:15<00:38,  1.02it/s]
+
 33%|███▎      | 19/57 [00:17<00:37,  1.01it/s]
+
 35%|███▌      | 20/57 [00:17<00:35,  1.04it/s]
+
 37%|███▋      | 21/57 [00:18<00:34,  1.03it/s]
+
 39%|███▊      | 22/57 [00:19<00:34,  1.01it/s]
+
 40%|████      | 23/57 [00:20<00:31,  1.07it/s]
+
 42%|████▏     | 24/57 [00:21<00:29,  1.10it/s]
+
 44%|████▍     | 25/57 [00:22<00:27,  1.17it/s]
+
 46%|████▌     | 26/57 [00:22<00:24,  1.26it/s]
+
 47%|████▋     | 27/57 [00:23<00:25,  1.19it/s]
+
 49%|████▉     | 28/57 [00:25<00:26,  1.08it/s]
+
 51%|█████     | 29/57 [00:26<00:28,  1.00s/it]
+
 53%|█████▎    | 30/57 [00:27<00:26,  1.03it/s]
+
 54%|█████▍    | 31/57 [00:28<00:27,  1.06s/it]
+
 56%|█████▌    | 32/57 [00:29<00:24,  1.01it/s]
+
 58%|█████▊    | 33/57 [00:30<00:24,  1.00s/it]
+
 60%|█████▉    | 34/57 [00:31<00:23,  1.01s/it]
+
 61%|██████▏   | 35/57 [00:32<00:21,  1.04it/s]
+
 63%|██████▎   | 36/57 [00:33<00:21,  1.00s/it]
+
 65%|██████▍   | 37/57 [00:33<00:17,  1.12it/s]
+
 67%|██████▋   | 38/57 [00:34<00:18,  1.04it/s]
+
 68%|██████▊   | 39/57 [00:35<00:16,  1.10it/s]
+
 70%|███████   | 40/57 [00:36<00:17,  1.01s/it]
+
 72%|███████▏  | 41/57 [00:38<00:16,  1.05s/it]
+
 74%|███████▎  | 42/57 [00:39<00:15,  1.01s/it]
+
 75%|███████▌  | 43/57 [00:39<00:13,  1.05it/s]
+
 77%|███████▋  | 44/57 [00:40<00:11,  1.10it/s]
+
 79%|███████▉  | 45/57 [00:41<00:11,  1.06it/s]
+
 81%|████████  | 46/57 [00:42<00:10,  1.05it/s]
+
 82%|████████▏ | 47/57 [00:43<00:08,  1.15it/s]
+
 84%|████████▍ | 48/57 [00:44<00:07,  1.19it/s]
+
 86%|████████▌ | 49/57 [00:44<00:06,  1.19it/s]
+
 88%|████████▊ | 50/57 [00:45<00:05,  1.18it/s]
+
 89%|████████▉ | 51/57 [00:46<00:04,  1.21it/s]
+
 91%|█████████ | 52/57 [00:47<00:04,  1.20it/s]
+
 93%|█████████▎| 53/57 [00:48<00:03,  1.20it/s]
+
 95%|█████████▍| 54/57 [00:48<00:02,  1.31it/s]
+
 96%|█████████▋| 55/57 [00:49<00:01,  1.36it/s]
+
 98%|█████████▊| 56/57 [00:50<00:00,  1.36it/s]
+
                                                         
+
                                               
  3%|▎         | 1000/34750 [1:35:41<72:52:04,  7.77s/it]
+
+
                                               Saving model checkpoint to ./checkpoint-1000
+Configuration saved in ./checkpoint-1000/config.json
+Model weights saved in ./checkpoint-1000/pytorch_model.bin
+Configuration saved in ./checkpoint-1000/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 sha256:450eabd0a5373e1ecd8ce2213749283b3b63609903c85ed7ae272817327b3b59
+oid sha256:ec8a163e9a558bd8062da873f6f54f2138f0d7a2f88600f2bd2b7d5f45b14d8c
 size 3856497393