Training in progress, step 1000

nohup.out

@@ -548,3 +548,63 @@ 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
+
 40%|████      | 501/1250 [13:45<3:02:23, 14.61s/it]
 40%|████      | 502/1250 [13:47<2:13:45, 10.73s/it]
 40%|████      | 503/1250 [13:48<1:39:10,  7.97s/it]
 40%|████      | 504/1250 [13:50<1:14:34,  6.00s/it]
 40%|████      | 505/1250 [13:51<56:37,  4.56s/it]  
 40%|████      | 506/1250 [13:52<43:34,  3.51s/it]
 41%|████      | 507/1250 [13:54<39:07,  3.16s/it]
 41%|████      | 508/1250 [13:56<34:15,  2.77s/it]
 41%|████      | 509/1250 [13:58<29:45,  2.41s/it]
 41%|████      | 510/1250 [13:59<25:49,  2.09s/it]
 41%|████      | 511/1250 [14:00<22:25,  1.82s/it]
 41%|████      | 512/1250 [14:01<19:15,  1.57s/it]
 41%|████      | 513/1250 [14:04<22:15,  1.81s/it]
 41%|████      | 514/1250 [14:05<21:55,  1.79s/it]
 41%|████      | 515/1250 [14:07<20:56,  1.71s/it]
 41%|████▏     | 516/1250 [14:08<19:31,  1.60s/it]
 41%|████▏     | 517/1250 [14:09<17:54,  1.47s/it]
 41%|████▏     | 518/1250 [14:10<16:11,  1.33s/it]
 42%|████▏     | 519/1250 [14:13<19:56,  1.64s/it]
 42%|████▏     | 520/1250 [14:14<20:11,  1.66s/it]
 42%|████▏     | 521/1250 [14:16<19:21,  1.59s/it]
 42%|████▏     | 522/1250 [14:17<18:22,  1.51s/it]
 42%|████▏     | 523/1250 [14:18<16:55,  1.40s/it]
 42%|████▏     | 524/1250 [14:19<15:18,  1.27s/it]
 42%|████▏     | 525/1250 [14:21<17:22,  1.44s/it]
 42%|████▏     | 526/1250 [14:24<22:06,  1.83s/it]
 42%|████▏     | 527/1250 [14:26<21:32,  1.79s/it]
 42%|████▏     | 528/1250 [14:27<20:13,  1.68s/it]
 42%|████▏     | 529/1250 [14:28<18:59,  1.58s/it]
 42%|████▏     | 530/1250 [14:30<17:33,  1.46s/it]
 42%|████▏     | 531/1250 [14:31<15:50,  1.32s/it]
 43%|████▎     | 532/1250 [14:33<20:04,  1.68s/it]
 43%|████▎     | 533/1250 [14:35<20:10,  1.69s/it]
 43%|████▎     | 534/1250 [14:36<19:25,  1.63s/it]
 43%|████▎     | 535/1250 [14:38<18:30,  1.55s/it]
 43%|████▎     | 536/1250 [14:39<17:11,  1.44s/it]
 43%|████▎     | 537/1250 [14:40<15:32,  1.31s/it]
 43%|████▎     | 538/1250 [14:42<19:16,  1.62s/it]
 43%|████▎     | 539/1250 [14:44<19:51,  1.68s/it]
 43%|████▎     | 540/1250 [14:46<19:32,  1.65s/it]
 43%|████▎     | 541/1250 [14:47<18:35,  1.57s/it]
 43%|████▎     | 542/1250 [14:48<17:14,  1.46s/it]
 43%|████▎     | 543/1250 [14:49<15:31,  1.32s/it]
 44%|████▎     | 544/1250 [14:52<19:16,  1.64s/it]
 44%|████▎     | 545/1250 [14:53<19:33,  1.66s/it]
 44%|████▎     | 546/1250 [14:55<18:47,  1.60s/it]
 44%|████▍     | 547/1250 [14:56<17:40,  1.51s/it]
 44%|████▍     | 548/1250 [14:57<16:17,  1.39s/it]
 44%|████▍     | 549/1250 [14:58<14:43,  1.26s/it]
 44%|████▍     | 550/1250 [15:00<16:04,  1.38s/it]
 44%|████▍     | 551/1250 [15:03<21:04,  1.81s/it]
 44%|████▍     | 552/1250 [15:04<20:40,  1.78s/it]
 44%|████▍     | 553/1250 [15:06<19:33,  1.68s/it]
 44%|████▍     | 554/1250 [15:07<18:17,  1.58s/it]
 44%|████▍     | 555/1250 [15:08<16:56,  1.46s/it]
 44%|████▍     | 556/1250 [15:09<15:27,  1.34s/it]
 45%|████▍     | 557/1250 [15:12<19:05,  1.65s/it]
 45%|████▍     | 558/1250 [15:14<19:34,  1.70s/it]
 45%|████▍     | 559/1250 [15:15<18:49,  1.63s/it]
 45%|████▍     | 560/1250 [15:16<17:42,  1.54s/it]
 45%|████▍     | 561/1250 [15:17<16:21,  1.42s/it]
 45%|████▍     | 562/1250 [15:18<14:47,  1.29s/it]
 45%|████▌     | 563/1250 [15:21<18:25,  1.61s/it]
 45%|████▌     | 564/1250 [15:23<18:52,  1.65s/it]
 45%|████▌     | 565/1250 [15:24<18:19,  1.61s/it]
 45%|████▌     | 566/1250 [15:25<17:22,  1.52s/it]
 45%|████▌     | 567/1250 [15:27<16:11,  1.42s/it]
 45%|████▌     | 568/1250 [15:28<14:37,  1.29s/it]
 46%|████▌     | 569/1250 [15:30<17:56,  1.58s/it]
 46%|████▌     | 570/1250 [15:31<18:17,  1.61s/it]
 46%|████▌     | 571/1250 [15:33<18:00,  1.59s/it]
 46%|████▌     | 572/1250 [15:34<17:18,  1.53s/it]
 46%|████▌     | 573/1250 [15:36<16:09,  1.43s/it]
 46%|████▌     | 574/1250 [15:37<14:39,  1.30s/it]
 46%|████▌     | 575/1250 [15:38<16:34,  1.47s/it]
 46%|████▌     | 576/1250 [15:41<20:49,  1.85s/it]
 46%|████▌     | 577/1250 [15:43<20:21,  1.82s/it]
 46%|████▌     | 578/1250 [15:44<19:21,  1.73s/it]
 46%|████▋     | 579/1250 [15:46<18:02,  1.61s/it]
 46%|████▋     | 580/1250 [15:47<16:36,  1.49s/it]
 46%|█���██▋     | 581/1250 [15:48<14:48,  1.33s/it]
 47%|████▋     | 582/1250 [15:50<18:08,  1.63s/it]
 47%|████▋     | 583/1250 [15:52<18:36,  1.67s/it]
 47%|████▋     | 584/1250 [15:54<18:13,  1.64s/it]
 47%|████▋     | 585/1250 [15:55<17:20,  1.56s/it]
 47%|████▋     | 586/1250 [15:56<16:06,  1.46s/it]
 47%|████▋     | 587/1250 [15:57<14:39,  1.33s/it]
 47%|████▋     | 588/1250 [15:59<17:36,  1.60s/it]
 47%|████▋     | 589/1250 [16:01<17:51,  1.62s/it]
 47%|████▋     | 590/1250 [16:03<17:15,  1.57s/it]
 47%|████▋     | 591/1250 [16:04<16:15,  1.48s/it]
 47%|████▋     | 592/1250 [16:05<15:05,  1.38s/it]
 47%|████▋     | 593/1250 [16:06<13:38,  1.25s/it]
 48%|████▊     | 594/1250 [16:08<17:27,  1.60s/it]
 48%|████▊     | 595/1250 [16:10<17:50,  1.63s/it]
 48%|████▊     | 596/1250 [16:12<17:17,  1.59s/it]
 48%|████▊     | 597/1250 [16:13<16:26,  1.51s/it]
 48%|████▊     | 598/1250 [16:14<15:18,  1.41s/it]
 48%|████▊     | 599/1250 [16:15<13:53,  1.28s/it]
 48%|████▊     | 600/1250 [16:17<15:59,  1.48s/it]
                                                  
 48%|████▊     | 600/1250 [16:17<15:59,  1.48s/it]
 48%|████▊     | 601/1250 [16:20<20:30,  1.90s/it]
 48%|████▊     | 602/1250 [16:22<20:08,  1.86s/it]
 48%|████▊     | 603/1250 [16:23<19:03,  1.77s/it]
 48%|████▊     | 604/1250 [16:25<17:37,  1.64s/it]
 48%|████▊     | 605/1250 [16:26<16:12,  1.51s/it]
 48%|████▊     | 606/1250 [16:27<14:25,  1.34s/it]
 49%|████▊     | 607/1250 [16:29<17:47,  1.66s/it]
 49%|████▊     | 608/1250 [16:31<17:50,  1.67s/it]
 49%|████▊     | 609/1250 [16:32<17:20,  1.62s/it]
 49%|████▉     | 610/1250 [16:34<16:29,  1.55s/it]
 49%|████▉     | 611/1250 [16:35<15:16,  1.43s/it]
 49%|████▉     | 612/1250 [16:36<13:48,  1.30s/it]
 49%|████▉     | 613/1250 [16:38<16:51,  1.59s/it]
 49%|████▉     | 614/1250 [16:40<17:25,  1.64s/it]
 49%|████▉     | 615/1250 [16:41<17:00,  1.61s/it]
 49%|████▉     | 616/1250 [16:43<16:15,  1.54s/it]
 49%|████▉     | 617/1250 [16:44<15:09,  1.44s/it]
 49%|████▉     | 618/1250 [16:45<13:43,  1.30s/it]
 50%|████▉     | 619/1250 [16:47<17:00,  1.62s/it]
 50%|████▉     | 620/1250 [16:49<17:25,  1.66s/it]
 50%|████▉     | 621/1250 [16:51<16:57,  1.62s/it]
 50%|████▉     | 622/1250 [16:52<16:05,  1.54s/it]
 50%|████▉     | 623/1250 [16:53<14:49,  1.42s/it]
 50%|████▉     | 624/1250 [16:54<13:25,  1.29s/it]
 50%|█████     | 625/1250 [16:56<14:38,  1.41s/it]
 50%|█████     | 626/1250 [16:59<19:06,  1.84s/it]
 50%|█████     | 627/1250 [17:00<18:41,  1.80s/it]
 50%|█████     | 628/1250 [17:02<17:47,  1.72s/it]
 50%|█████     | 629/1250 [17:03<16:47,  1.62s/it]
 50%|█████     | 630/1250 [17:04<15:26,  1.49s/it]
 50%|█████     | 631/1250 [17:05<13:57,  1.35s/it]
 51%|█████     | 632/1250 [17:08<16:53,  1.64s/it]
 51%|█████     | 633/1250 [17:09<17:05,  1.66s/it]
 51%|█████     | 634/1250 [17:11<16:41,  1.63s/it]
 51%|█████     | 635/1250 [17:12<15:50,  1.55s/it]
 51%|█████     | 636/1250 [17:14<14:41,  1.44s/it]
 51%|█████     | 637/1250 [17:15<13:16,  1.30s/it]
 51%|█████     | 638/1250 [17:17<16:26,  1.61s/it]
 51%|█████     | 639/1250 [17:19<16:42,  1.64s/it]
 51%|█████     | 640/1250 [17:20<16:08,  1.59s/it]
 51%|█████▏    | 641/1250 [17:21<15:12,  1.50s/it]
 51%|█████▏    | 642/1250 [17:22<14:06,  1.39s/it]
 51%|█████▏    | 643/1250 [17:23<12:49,  1.27s/it]
 52%|█████▏    | 644/1250 [17:26<16:01,  1.59s/it]
 52%|█████▏    | 645/1250 [17:28<16:27,  1.63s/it]
 52%|█████▏    | 646/1250 [17:29<16:05,  1.60s/it]
 52%|█████▏    | 647/1250 [17:30<15:29,  1.54s/it]
 52%|█████▏    | 648/1250 [17:32<14:30,  1.45s/it]
 52%|█████▏    | 649/1250 [17:33<13:11,  1.32s/it]
 52%|█████▏    | 650/1250 [17:34<14:13,  1.42s/it]
 52%|█████▏    | 651/1250 [17:37<18:25,  1.85s/it]
 52%|█████▏    | 652/1250 [17:39<18:01,  1.81s/it]
 52%|█████▏    | 653/1250 [17:40<17:07,  1.72s/it]
 52%|█████▏    | 654/1250 [17:42<15:52,  1.60s/it]
 52%|█████▏    | 655/1250 [17:43<14:29,  1.46s/it]
 52%|█████▏    | 656/1250 [17:44<13:01,  1.32s/it]
 53%|█████▎    | 657/1250 [17:46<16:01,  1.62s/it]
 53%|█████▎    | 658/1250 [17:48<16:22,  1.66s/it]
 53%|█████▎    | 659/1250 [17:49<15:59,  1.62s/it]
 53%|█████▎    | 660/1250 [17:51<15:17,  1.55s/it]
 53%|█████▎    | 661/1250 [17:52<14:06,  1.44s/it]
 53%|█████▎    | 662/1250 [17:53<12:48,  1.31s/it]
 53%|█████▎    | 663/1250 [17:55<15:51,  1.62s/it]
 53%|█████▎    | 664/1250 [17:57<16:12,  1.66s/it]
 53%|█████▎    | 665/1250 [17:59<15:57,  1.64s/it]
 53%|█████▎    | 666/1250 [18:00<15:16,  1.57s/it]
 53%|█████▎    | 667/1250 [18:01<14:03,  1.45s/it]
 53%|█████▎    | 668/1250 [18:02<12:47,  1.32s/it]
 54%|█████▎    | 669/1250 [18:05<15:36,  1.61s/it]
 54%|█████▎    | 670/1250 [18:06<15:47,  1.63s/it]
 54%|█████▎    | 671/1250 [18:08<15:23,  1.60s/it]
 54%|█████▍    | 672/1250 [18:09<14:38,  1.52s/it]
 54%|█████▍    | 673/1250 [18:10<13:32,  1.41s/it]
 54%|█████▍    | 674/1250 [18:11<12:19,  1.28s/it]
 54%|█████▍    | 675/1250 [18:13<13:59,  1.46s/it]
 54%|█████▍    | 676/1250 [18:16<17:40,  1.85s/it]
 54%|█████▍    | 677/1250 [18:18<17:05,  1.79s/it]
 54%|█████▍    | 678/1250 [18:19<16:09,  1.69s/it]
 54%|█████▍    | 679/1250 [18:20<14:52,  1.56s/it]
 54%|█████▍    | 680/1250 [18:21<13:35,  1.43s/it]
 54%|█████▍    | 681/1250 [18:22<11:55,  1.26s/it]
 55%|█████▍    | 682/1250 [18:25<14:46,  1.56s/it]
 55%|█████▍    | 683/1250 [18:26<15:15,  1.62s/it]
 55%|█████▍    | 684/1250 [18:28<14:52,  1.58s/it]
 55%|█████▍    | 685/1250 [18:29<14:09,  1.50s/it]
 55%|█████▍    | 686/1250 [18:30<13:09,  1.40s/it]
 55%|█████▍    | 687/1250 [18:31<12:00,  1.28s/it]
 55%|█████▌    | 688/1250 [18:34<15:21,  1.64s/it]
 55%|█████▌    | 689/1250 [18:36<15:46,  1.69s/it]
 55%|█████▌    | 690/1250 [18:37<15:26,  1.65s/it]
 55%|█████▌    | 691/1250 [18:39<14:41,  1.58s/it]
 55%|█████▌    | 692/1250 [18:40<13:45,  1.48s/it]
 55%|█████▌    | 693/1250 [18:41<12:26,  1.34s/it]
 56%|█████▌    | 694/1250 [18:43<15:15,  1.65s/it]
 56%|█████▌    | 695/1250 [18:45<15:35,  1.69s/it]
 56%|█████▌    | 696/1250 [18:46<15:05,  1.63s/it]
 56%|█████▌    | 697/1250 [18:48<14:16,  1.55s/it]
 56%|█████▌    | 698/1250 [18:49<13:13,  1.44s/it]
 56%|█████▌    | 699/1250 [18:50<11:53,  1.29s/it]
 56%|█████▌    | 700/1250 [18:52<12:52,  1.41s/it]
                                                  
 56%|█████▌    | 700/1250 [18:52<12:52,  1.41s/it]
 56%|█████▌    | 701/1250 [18:55<17:02,  1.86s/it]
 56%|█████▌    | 702/1250 [18:56<16:45,  1.83s/it]
 56%|█████▌    | 703/1250 [18:58<15:53,  1.74s/it]
 56%|█████▋    | 704/1250 [18:59<14:53,  1.64s/it]
 56%|█████▋    | 705/1250 [19:00<13:30,  1.49s/it]
 56%|█████▋    | 706/1250 [19:01<12:05,  1.33s/it]
 57%|█████▋    | 707/1250 [19:03<14:22,  1.59s/it]
 57%|█████▋    | 708/1250 [19:05<14:43,  1.63s/it]
 57%|█████▋    | 709/1250 [19:07<14:21,  1.59s/it]
 57%|█████▋    | 710/1250 [19:08<13:40,  1.52s/it]
 57%|█████▋    | 711/1250 [19:09<12:45,  1.42s/it]
 57%|█████▋    | 712/1250 [19:10<11:41,  1.30s/it]
 57%|█████▋    | 713/1250 [19:13<14:27,  1.62s/it]
 57%|█████▋    | 714/1250 [19:14<14:40,  1.64s/it]
 57%|█████▋    | 715/1250 [19:16<14:14,  1.60s/it]
 57%|█████▋    | 716/1250 [19:17<13:36,  1.53s/it]
 57%|█████▋    | 717/1250 [19:18<12:39,  1.43s/it]
 57%|█████▋    | 718/1250 [19:19<11:22,  1.28s/it]
 58%|█████▊    | 719/1250 [19:22<14:16,  1.61s/it]
 58%|█████▊    | 720/1250 [19:23<14:39,  1.66s/it]
 58%|█████▊    | 721/1250 [19:25<14:19,  1.62s/it]
 58%|█████▊    | 722/1250 [19:26<13:41,  1.56s/it]
 58%|█████▊    | 723/1250 [19:28<12:43,  1.45s/it]
 58%|█████▊    | 724/1250 [19:29<11:25,  1.30s/it]
 58%|█████▊    | 725/1250 [19:30<12:36,  1.44s/it]
 58%|█████▊    | 726/1250 [19:33<16:06,  1.84s/it]
 58%|█████▊    | 727/1250 [19:35<15:46,  1.81s/it]
 58%|█████▊    | 728/1250 [19:36<14:53,  1.71s/it]
 58%|█████▊    | 729/1250 [19:38<13:55,  1.60s/it]
 58%|█████▊    | 730/1250 [19:39<12:51,  1.48s/it]
 58%|█████▊    | 731/1250 [19:40<11:45,  1.36s/it]
 59%|█████▊    | 732/1250 [19:42<14:18,  1.66s/it]
 59%|█████▊    | 733/1250 [19:44<14:28,  1.68s/it]
 59%|█████▊    | 734/1250 [19:46<14:05,  1.64s/it]
 59%|█████▉    | 735/1250 [19:47<13:24,  1.56s/it]
 59%|█████▉    | 736/1250 [19:48<12:20,  1.44s/it]
 59%|█████▉    | 737/1250 [19:49<10:57,  1.28s/it]
 59%|█████▉    | 738/1250 [19:51<13:46,  1.61s/it]
 59%|█████▉    | 739/1250 [19:53<13:58,  1.64s/it]
 59%|█████▉    | 740/1250 [19:55<13:35,  1.60s/it]
 59%|█████▉    | 741/1250 [19:56<12:54,  1.52s/it]
 59%|█████▉    | 742/1250 [19:57<11:55,  1.41s/it]
 59%|█████▉    | 743/1250 [19:58<10:50,  1.28s/it]
 60%|█████▉    | 744/1250 [20:00<13:23,  1.59s/it]
 60%|█████▉    | 745/1250 [20:02<13:51,  1.65s/it]
 60%|█████▉    | 746/1250 [20:04<13:20,  1.59s/it]
 60%|█████▉    | 747/1250 [20:05<12:29,  1.49s/it]
 60%|█████▉    | 748/1250 [20:06<11:35,  1.38s/it]
 60%|█████▉    | 749/1250 [20:07<10:31,  1.26s/it]
 60%|██████    | 750/1250 [20:09<11:41,  1.40s/it]
 60%|██████    | 751/1250 [20:12<15:16,  1.84s/it]
 60%|██████    | 752/1250 [20:13<15:11,  1.83s/it]
 60%|██████    | 753/1250 [20:15<14:30,  1.75s/it]
 60%|██████    | 754/1250 [20:16<13:36,  1.65s/it]
 60%|██████    | 755/1250 [20:18<12:29,  1.51s/it]
 60%|██████    | 756/1250 [20:19<11:07,  1.35s/it]
 61%|██████    | 757/1250 [20:21<13:17,  1.62s/it]
 61%|██████    | 758/1250 [20:23<13:31,  1.65s/it]
 61%|██████    | 759/1250 [20:24<13:10,  1.61s/it]
 61%|██████    | 760/1250 [20:25<12:28,  1.53s/it]
 61%|██████    | 761/1250 [20:27<11:34,  1.42s/it]
 61%|██████    | 762/1250 [20:28<10:28,  1.29s/it]
 61%|██████    | 763/1250 [20:30<12:59,  1.60s/it]
 61%|██████    | 764/1250 [20:32<13:13,  1.63s/it]
 61%|██████    | 765/1250 [20:33<12:52,  1.59s/it]
 61%|██████▏   | 766/1250 [20:34<12:05,  1.50s/it]
 61%|██████▏   | 767/1250 [20:36<11:13,  1.39s/it]
 61%|██████▏   | 768/1250 [20:36<10:11,  1.27s/it]
 62%|██████▏   | 769/1250 [20:39<12:54,  1.61s/it]
 62%|██████▏   | 770/1250 [20:41<13:05,  1.64s/it]
 62%|██████▏   | 771/1250 [20:42<12:44,  1.60s/it]
 62%|██████▏   | 772/1250 [20:43<12:12,  1.53s/it]
 62%|██████▏   | 773/1250 [20:45<11:18,  1.42s/it]
 62%|██████▏   | 774/1250 [20:46<10:16,  1.29s/it]
 62%|██████▏   | 775/1250 [20:47<11:19,  1.43s/it]
 62%|██████▏   | 776/1250 [20:50<14:32,  1.84s/it]
 62%|██████▏   | 777/1250 [20:52<14:10,  1.80s/it]
 62%|██████▏   | 778/1250 [20:53<13:17,  1.69s/it]
 62%|██████▏   | 779/1250 [20:55<12:15,  1.56s/it]
 62%|██████▏   | 780/1250 [20:56<11:16,  1.44s/it]
 62%|██████▏   | 781/1250 [20:57<10:16,  1.31s/it]
 63%|██████▎   | 782/1250 [20:59<12:23,  1.59s/it]
 63%|██████▎   | 783/1250 [21:01<12:25,  1.60s/it]
 63%|██████▎   | 784/1250 [21:02<12:05,  1.56s/it]
 63%|██████▎   | 785/1250 [21:03<11:45,  1.52s/it]
 63%|██████▎   | 786/1250 [21:05<11:03,  1.43s/it]
 63%|██████▎   | 787/1250 [21:06<10:03,  1.30s/it]
 63%|██████▎   | 788/1250 [21:08<12:27,  1.62s/it]
 63%|██████▎   | 789/1250 [21:10<12:40,  1.65s/it]
 63%|██████▎   | 790/1250 [21:11<12:29,  1.63s/it]
 63%|██████▎   | 791/1250 [21:13<11:53,  1.55s/it]
 63%|██████▎   | 792/1250 [21:14<10:56,  1.43s/it]
 63%|██████▎   | 793/1250 [21:15<09:50,  1.29s/it]
 64%|██████▎   | 794/1250 [21:17<12:23,  1.63s/it]
 64%|██████▎   | 795/1250 [21:19<12:37,  1.66s/it]
 64%|██████▎   | 796/1250 [21:21<12:18,  1.63s/it]
 64%|██████▍   | 797/1250 [21:22<11:42,  1.55s/it]
 64%|██████▍   | 798/1250 [21:23<10:55,  1.45s/it]
 64%|██████▍   | 799/1250 [21:24<09:56,  1.32s/it]
 64%|██████▍   | 800/1250 [21:26<10:45,  1.44s/it]
                                                  
 64%|██████▍   | 800/1250 [21:26<10:45,  1.44s/it]
 64%|██████▍   | 801/1250 [21:29<13:45,  1.84s/it]
 64%|██████▍   | 802/1250 [21:30<13:32,  1.81s/it]
 64%|██████▍   | 803/1250 [21:32<12:51,  1.73s/it]
 64%|██████▍   | 804/1250 [21:33<12:01,  1.62s/it]
 64%|██████▍   | 805/1250 [21:35<11:02,  1.49s/it]
 64%|██████▍   | 806/1250 [21:36<09:58,  1.35s/it]
 65%|██████▍   | 807/1250 [21:38<12:15,  1.66s/it]
 65%|██████▍   | 808/1250 [21:40<12:28,  1.69s/it]
 65%|██████▍   | 809/1250 [21:41<12:08,  1.65s/it]
 65%|██████▍   | 810/1250 [21:43<11:33,  1.58s/it]
 65%|██████▍   | 811/1250 [21:44<10:42,  1.46s/it]
 65%|██████▍   | 812/1250 [21:45<09:37,  1.32s/it]
 65%|██████▌   | 813/1250 [21:47<12:07,  1.67s/it]
 65%|██████▌   | 814/1250 [21:49<12:17,  1.69s/it]
 65%|██████▌   | 815/1250 [21:51<11:49,  1.63s/it]
 65%|██████▌   | 816/1250 [21:52<11:08,  1.54s/it]
 65%|██████▌   | 817/1250 [21:53<10:16,  1.42s/it]
 65%|██████▌   | 818/1250 [21:54<09:19,  1.29s/it]
 66%|██████▌   | 819/1250 [21:56<11:27,  1.59s/it]
 66%|██████▌   | 820/1250 [21:58<11:46,  1.64s/it]
 66%|██████▌   | 821/1250 [22:00<11:23,  1.59s/it]
 66%|██████▌   | 822/1250 [22:01<10:43,  1.50s/it]
 66%|██████▌   | 823/1250 [22:02<09:59,  1.40s/it]
 66%|██████▌   | 824/1250 [22:03<09:13,  1.30s/it]
 66%|██████▌   | 825/1250 [22:05<09:56,  1.40s/it]
 66%|██████▌   | 826/1250 [22:07<12:44,  1.80s/it]
 66%|██████▌   | 827/1250 [22:09<12:37,  1.79s/it]
 66%|██████▌   | 828/1250 [22:11<12:05,  1.72s/it]
 66%|██████▋   | 829/1250 [22:12<11:15,  1.60s/it]
 66%|██████▋   | 830/1250 [22:13<10:13,  1.46s/it]
 66%|██████▋   | 831/1250 [22:14<09:13,  1.32s/it]
 67%|██████▋   | 832/1250 [22:17<11:23,  1.64s/it]
 67%|██████▋   | 833/1250 [22:18<11:33,  1.66s/it]
 67%|██████▋   | 834/1250 [22:20<11:12,  1.62s/it]
 67%|██████▋   | 835/1250 [22:21<10:40,  1.54s/it]
 67%|██████▋   | 836/1250 [22:22<09:52,  1.43s/it]
 67%|██████▋   | 837/1250 [22:23<09:00,  1.31s/it]
 67%|██████▋   | 838/1250 [22:26<11:13,  1.63s/it]
 67%|██████▋   | 839/1250 [22:28<11:32,  1.68s/it]
 67%|██████▋   | 840/1250 [22:29<11:13,  1.64s/it]
 67%|██████▋   | 841/1250 [22:31<10:43,  1.57s/it]
 67%|██████▋   | 842/1250 [22:32<09:58,  1.47s/it]
 67%|██████▋   | 843/1250 [22:33<08:54,  1.31s/it]
 68%|██████▊   | 844/1250 [22:35<11:11,  1.65s/it]
 68%|██████▊   | 845/1250 [22:37<11:19,  1.68s/it]
 68%|██████▊   | 846/1250 [22:38<10:59,  1.63s/it]
 68%|██████▊   | 847/1250 [22:40<10:24,  1.55s/it]
 68%|██████▊   | 848/1250 [22:41<09:36,  1.43s/it]
 68%|██████▊   | 849/1250 [22:42<08:41,  1.30s/it]
 68%|██████▊   | 850/1250 [22:44<09:16,  1.39s/it]
 68%|██████▊   | 851/1250 [22:46<12:23,  1.86s/it]
 68%|██████▊   | 852/1250 [22:48<12:16,  1.85s/it]
 68%|██████▊   | 853/1250 [22:50<11:34,  1.75s/it]
 68%|██████▊   | 854/1250 [22:51<10:46,  1.63s/it]
 68%|██████▊   | 855/1250 [22:52<09:45,  1.48s/it]
 68%|██████▊   | 856/1250 [22:53<08:41,  1.32s/it]
 69%|██████▊   | 857/1250 [22:55<10:23,  1.59s/it]
 69%|██████▊   | 858/1250 [22:57<10:29,  1.61s/it]
 69%|██████▊   | 859/1250 [22:59<10:18,  1.58s/it]
 69%|██████▉   | 860/1250 [23:00<09:50,  1.51s/it]
 69%|██████▉   | 861/1250 [23:01<09:11,  1.42s/it]
 69%|██████▉   | 862/1250 [23:02<08:22,  1.29s/it]
 69%|██████▉   | 863/1250 [23:05<10:28,  1.62s/it]
 69%|██████▉   | 864/1250 [23:06<10:41,  1.66s/it]
 69%|██████▉   | 865/1250 [23:08<10:21,  1.61s/it]
 69%|██████▉   | 866/1250 [23:09<09:53,  1.54s/it]
 69%|██████▉   | 867/1250 [23:10<09:10,  1.44s/it]
 69%|██████▉   | 868/1250 [23:11<08:17,  1.30s/it]
 70%|██████▉   | 869/1250 [23:14<10:13,  1.61s/it]
 70%|██████▉   | 870/1250 [23:15<10:26,  1.65s/it]
 70%|██████▉   | 871/1250 [23:17<10:12,  1.62s/it]
 70%|██████▉   | 872/1250 [23:18<09:40,  1.54s/it]
 70%|██████▉   | 873/1250 [23:20<09:00,  1.43s/it]
 70%|██████▉   | 874/1250 [23:21<08:15,  1.32s/it]
 70%|███████   | 875/1250 [23:22<09:07,  1.46s/it]
 70%|███████   | 876/1250 [23:25<11:37,  1.86s/it]
 70%|███████   | 877/1250 [23:27<11:25,  1.84s/it]
 70%|███████   | 878/1250 [23:28<10:44,  1.73s/it]
 70%|███████   | 879/1250 [23:30<09:57,  1.61s/it]
 70%|███████   | 880/1250 [23:31<09:08,  1.48s/it]
 70%|███████   | 881/1250 [23:32<08:10,  1.33s/it]
 71%|███████   | 882/1250 [23:34<10:07,  1.65s/it]
 71%|███████   | 883/1250 [23:36<10:10,  1.66s/it]
 71%|███████   | 884/1250 [23:38<09:50,  1.61s/it]
 71%|███████   | 885/1250 [23:39<09:23,  1.54s/it]
 71%|███████   | 886/1250 [23:40<08:41,  1.43s/it]
 71%|███████   | 887/1250 [23:41<07:57,  1.32s/it]
 71%|███████   | 888/1250 [23:43<09:50,  1.63s/it]
 71%|███████   | 889/1250 [23:45<10:01,  1.67s/it]
 71%|███████   | 890/1250 [23:47<09:45,  1.63s/it]
 71%|███████▏  | 891/1250 [23:48<09:09,  1.53s/it]
 71%|███████▏  | 892/1250 [23:49<08:20,  1.40s/it]
 71%|███████▏  | 893/1250 [23:50<07:22,  1.24s/it]
 72%|███████▏  | 894/1250 [23:52<09:15,  1.56s/it]
 72%|███████▏  | 895/1250 [23:54<09:33,  1.61s/it]
 72%|███████▏  | 896/1250 [23:56<09:23,  1.59s/it]
 72%|███████▏  | 897/1250 [23:57<08:57,  1.52s/it]
 72%|███���███▏  | 898/1250 [23:58<08:19,  1.42s/it]
 72%|███████▏  | 899/1250 [23:59<07:28,  1.28s/it]
 72%|███████▏  | 900/1250 [24:01<08:27,  1.45s/it]
                                                  
 72%|███████▏  | 900/1250 [24:01<08:27,  1.45s/it]
 72%|███████▏  | 901/1250 [24:04<10:51,  1.87s/it]
 72%|███████▏  | 902/1250 [24:06<10:39,  1.84s/it]
 72%|███████▏  | 903/1250 [24:07<10:00,  1.73s/it]
 72%|███████▏  | 904/1250 [24:08<09:08,  1.59s/it]
 72%|███████▏  | 905/1250 [24:09<08:14,  1.43s/it]
 72%|███████▏  | 906/1250 [24:10<07:16,  1.27s/it]
 73%|███████▎  | 907/1250 [24:13<08:59,  1.57s/it]
 73%|███████▎  | 908/1250 [24:14<09:14,  1.62s/it]
 73%|███████▎  | 909/1250 [24:16<09:03,  1.59s/it]
 73%|███████▎  | 910/1250 [24:17<08:40,  1.53s/it]
 73%|███████▎  | 911/1250 [24:18<08:05,  1.43s/it]
 73%|███████▎  | 912/1250 [24:19<07:20,  1.30s/it]
 73%|███████▎  | 913/1250 [24:22<09:00,  1.60s/it]
 73%|███████▎  | 914/1250 [24:23<09:06,  1.63s/it]
 73%|███████▎  | 915/1250 [24:25<08:50,  1.58s/it]
 73%|███████▎  | 916/1250 [24:26<08:20,  1.50s/it]
 73%|███████▎  | 917/1250 [24:27<07:42,  1.39s/it]
 73%|███████▎  | 918/1250 [24:28<07:01,  1.27s/it]
 74%|███████▎  | 919/1250 [24:31<08:52,  1.61s/it]
 74%|███████▎  | 920/1250 [24:32<09:04,  1.65s/it]
 74%|███████▎  | 921/1250 [24:34<08:46,  1.60s/it]
 74%|███████▍  | 922/1250 [24:35<08:25,  1.54s/it]
 74%|███████▍  | 923/1250 [24:37<07:54,  1.45s/it]
 74%|███████▍  | 924/1250 [24:38<07:06,  1.31s/it]
 74%|███████▍  | 925/1250 [24:39<07:43,  1.42s/it]
 74%|███████▍  | 926/1250 [24:42<09:52,  1.83s/it]
 74%|███████▍  | 927/1250 [24:44<09:41,  1.80s/it]
 74%|███████▍  | 928/1250 [24:45<09:17,  1.73s/it]
 74%|███████▍  | 929/1250 [24:47<08:40,  1.62s/it]
 74%|███████▍  | 930/1250 [24:48<07:59,  1.50s/it]
 74%|███████▍  | 931/1250 [24:49<07:10,  1.35s/it]
 75%|███████▍  | 932/1250 [24:51<08:30,  1.61s/it]
 75%|███████▍  | 933/1250 [24:53<08:39,  1.64s/it]
 75%|███████▍  | 934/1250 [24:54<08:23,  1.59s/it]
 75%|███████▍  | 935/1250 [24:56<07:57,  1.51s/it]
 75%|███████▍  | 936/1250 [24:57<07:22,  1.41s/it]
 75%|███████▍  | 937/1250 [24:58<06:44,  1.29s/it]
 75%|███████▌  | 938/1250 [25:00<08:28,  1.63s/it]
 75%|███████▌  | 939/1250 [25:02<08:36,  1.66s/it]
 75%|███████▌  | 940/1250 [25:03<08:20,  1.61s/it]
 75%|███████▌  | 941/1250 [25:05<07:51,  1.53s/it]
 75%|███████▌  | 942/1250 [25:06<07:16,  1.42s/it]
 75%|███████▌  | 943/1250 [25:07<06:32,  1.28s/it]
 76%|███████▌  | 944/1250 [25:09<08:08,  1.59s/it]
 76%|███████▌  | 945/1250 [25:11<08:16,  1.63s/it]
 76%|███████▌  | 946/1250 [25:12<07:57,  1.57s/it]
 76%|███████▌  | 947/1250 [25:14<07:34,  1.50s/it]
 76%|███████▌  | 948/1250 [25:15<07:06,  1.41s/it]
 76%|███████▌  | 949/1250 [25:16<06:29,  1.29s/it]
 76%|███████▌  | 950/1250 [25:18<07:01,  1.41s/it]
 76%|███████▌  | 951/1250 [25:20<09:10,  1.84s/it]
 76%|███████▌  | 952/1250 [25:22<09:00,  1.81s/it]
 76%|███████▌  | 953/1250 [25:24<08:36,  1.74s/it]
 76%|███████▋  | 954/1250 [25:25<07:59,  1.62s/it]
 76%|███████▋  | 955/1250 [25:26<07:22,  1.50s/it]
 76%|███████▋  | 956/1250 [25:27<06:36,  1.35s/it]
 77%|███████▋  | 957/1250 [25:30<08:12,  1.68s/it]
 77%|███████▋  | 958/1250 [25:32<08:19,  1.71s/it]
 77%|███████▋  | 959/1250 [25:33<08:03,  1.66s/it]
 77%|███████▋  | 960/1250 [25:35<07:39,  1.58s/it]
 77%|███████▋  | 961/1250 [25:36<07:00,  1.45s/it]
 77%|███████▋  | 962/1250 [25:37<06:18,  1.31s/it]
 77%|███████▋  | 963/1250 [25:39<07:38,  1.60s/it]
 77%|███████▋  | 964/1250 [25:41<07:43,  1.62s/it]
 77%|███████▋  | 965/1250 [25:42<07:26,  1.57s/it]
 77%|███████▋  | 966/1250 [25:43<07:02,  1.49s/it]
 77%|███████▋  | 967/1250 [25:45<06:34,  1.39s/it]
 77%|███████▋  | 968/1250 [25:46<06:05,  1.30s/it]
 78%|███████▊  | 969/1250 [25:48<07:25,  1.59s/it]
 78%|███████▊  | 970/1250 [25:50<07:40,  1.65s/it]
 78%|███████▊  | 971/1250 [25:51<07:26,  1.60s/it]
 78%|███████▊  | 972/1250 [25:52<07:03,  1.52s/it]
 78%|███████▊  | 973/1250 [25:54<06:33,  1.42s/it]
 78%|███████▊  | 974/1250 [25:55<05:52,  1.28s/it]
 78%|███████▊  | 975/1250 [25:56<06:38,  1.45s/it]
 78%|███████▊  | 976/1250 [25:59<08:36,  1.88s/it]
 78%|███████▊  | 977/1250 [26:01<08:26,  1.86s/it]
 78%|███████▊  | 978/1250 [26:03<08:00,  1.77s/it]
 78%|███████▊  | 979/1250 [26:04<07:26,  1.65s/it]
 78%|███████▊  | 980/1250 [26:05<06:47,  1.51s/it]
 78%|███████▊  | 981/1250 [26:06<06:06,  1.36s/it]
 79%|███████▊  | 982/1250 [26:09<07:27,  1.67s/it]
 79%|███████▊  | 983/1250 [26:10<07:29,  1.68s/it]
 79%|███████▊  | 984/1250 [26:12<07:11,  1.62s/it]
 79%|███████▉  | 985/1250 [26:13<06:47,  1.54s/it]
 79%|███████▉  | 986/1250 [26:14<06:14,  1.42s/it]
 79%|███████▉  | 987/1250 [26:15<05:37,  1.28s/it]
 79%|███████▉  | 988/1250 [26:18<06:56,  1.59s/it]
 79%|███████▉  | 989/1250 [26:19<07:03,  1.62s/it]
 79%|███████▉  | 990/1250 [26:21<06:53,  1.59s/it]
 79%|███████▉  | 991/1250 [26:22<06:31,  1.51s/it]
 79%|███████▉  | 992/1250 [26:23<06:07,  1.43s/it]
 79%|███████▉  | 993/1250 [26:24<05:32,  1.29s/it]
 80%|███████▉  | 994/1250 [26:27<06:43,  1.57s/it]
 80%|███████▉  | 995/1250 [26:28<06:52,  1.62s/it]
 80%|███████▉  | 996/1250 [26:30<06:43,  1.59s/it]
 80%|███████▉  | 997/1250 [26:31<06:26,  1.53s/it]
 80%|███████▉  | 998/1250 [26:32<05:57,  1.42s/it]
 80%|███████▉  | 999/1250 [26:33<05:22,  1.29s/it]
 80%|████████  | 1000/1250 [26:35<06:04,  1.46s/it]
                                                   
 80%|████████  | 1000/1250 [26:35<06:04,  1.46s/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 = 341
+  Batch size = 8
+{'eval_loss': 4.144110202789307, 'eval_wer': 1.0, 'eval_runtime': 12.9526, 'eval_samples_per_second': 26.327, 'eval_steps_per_second': 3.32, 'epoch': 19.98}
+{'loss': 3.7383, 'learning_rate': 2.2424999999999996e-05, 'epoch': 23.98}
+{'loss': 3.361, 'learning_rate': 2.6174999999999996e-05, 'epoch': 27.98}
+{'loss': 3.2219, 'learning_rate': 2.9925e-05, 'epoch': 31.98}
+{'loss': 3.104, 'learning_rate': 3.3675e-05, 'epoch': 35.98}
+{'loss': 3.0399, 'learning_rate': 3.7424999999999995e-05, 'epoch': 39.98}
+
+
  0%|          | 0/43 [00:00<?, ?it/s]
+
  5%|▍         | 2/43 [00:00<00:04, 10.00it/s]
+
  9%|▉         | 4/43 [00:00<00:08,  4.72it/s]
+
 12%|█▏        | 5/43 [00:01<00:08,  4.42it/s]
+
 14%|█▍        | 6/43 [00:01<00:08,  4.12it/s]
+
 16%|█▋        | 7/43 [00:01<00:09,  3.92it/s]
+
 19%|█▊        | 8/43 [00:01<00:09,  3.73it/s]
+
 21%|██        | 9/43 [00:02<00:09,  3.49it/s]
+
 23%|██▎       | 10/43 [00:02<00:08,  3.74it/s]
+
 26%|██▌       | 11/43 [00:02<00:08,  3.75it/s]
+
 28%|██▊       | 12/43 [00:02<00:08,  3.87it/s]
+
 30%|███       | 13/43 [00:03<00:07,  3.91it/s]
+
 33%|███▎      | 14/43 [00:03<00:08,  3.51it/s]
+
 35%|███▍      | 15/43 [00:03<00:09,  3.08it/s]
+
 37%|███▋      | 16/43 [00:04<00:08,  3.13it/s]
+
 40%|███▉      | 17/43 [00:04<00:08,  3.20it/s]
+
 42%|████▏     | 18/43 [00:04<00:08,  3.10it/s]
+
 44%|████▍     | 19/43 [00:05<00:08,  2.87it/s]
+
 47%|████▋     | 20/43 [00:05<00:08,  2.61it/s]
+
 49%|████▉     | 21/43 [00:06<00:08,  2.71it/s]
+
 51%|█████     | 22/43 [00:06<00:07,  2.72it/s]
+
 53%|█████▎    | 23/43 [00:06<00:07,  2.83it/s]
+
 56%|█████▌    | 24/43 [00:07<00:06,  3.11it/s]
+
 58%|█████▊    | 25/43 [00:07<00:05,  3.22it/s]
+
 60%|██████    | 26/43 [00:07<00:05,  3.27it/s]
+
 63%|██████▎   | 27/43 [00:07<00:04,  3.65it/s]
+
 65%|██████▌   | 28/43 [00:08<00:04,  3.74it/s]
+
 67%|██████▋   | 29/43 [00:08<00:03,  3.75it/s]
+
 70%|██████▉   | 30/43 [00:08<00:03,  3.85it/s]
+
 72%|███████▏  | 31/43 [00:08<00:03,  3.83it/s]
+
 74%|███████▍  | 32/43 [00:09<00:02,  3.87it/s]
+
 77%|███████▋  | 33/43 [00:09<00:02,  3.56it/s]
+
 79%|███████▉  | 34/43 [00:09<00:02,  3.56it/s]
+
 81%|████████▏ | 35/43 [00:10<00:02,  3.56it/s]
+
 84%|████████▎ | 36/43 [00:10<00:02,  3.38it/s]
+
 86%|████████▌ | 37/43 [00:10<00:01,  3.48it/s]
+
 88%|████████▊ | 38/43 [00:10<00:01,  3.22it/s]
+
 91%|█████████ | 39/43 [00:11<00:01,  3.30it/s]
+
 93%|█████████▎| 40/43 [00:11<00:00,  3.17it/s]
+
 95%|█████████▌| 41/43 [00:11<00:00,  3.30it/s]
+
 98%|█████████▊| 42/43 [00:12<00:00,  3.18it/s]
+
                                                   
+
                                               
 80%|████████  | 1000/1250 [26:48<06:04,  1.46s/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 sha256:4b3c7996c48bbce91a11a7b8efbb9dbd48a52cc46b992569ecdef9e54e1180da
+oid sha256:536263acbdad2120d5228cfed7ae298da5b37b0a6eea41daae7d935bf5dc14a6
 size 1262173745