PereLluis13 commited on
Commit
efc51f9
1 Parent(s): e625f94

Add epoch 12 (22500 steps) trained model

Browse files
all_results.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
- "epoch": 6.0,
3
- "eval_loss": 0.27584555745124817,
4
- "eval_runtime": 371.4251,
5
  "eval_samples": 4297,
6
- "eval_samples_per_second": 11.569,
7
- "eval_steps_per_second": 0.363,
8
- "eval_wer": 0.17918264285046293,
9
- "train_loss": 0.5975231319014925,
10
- "train_runtime": 88923.2167,
11
  "train_samples": 240334,
12
- "train_samples_per_second": 16.216,
13
- "train_steps_per_second": 0.127
14
  }
 
1
  {
2
+ "epoch": 12.0,
3
+ "eval_loss": 0.25491979718208313,
4
+ "eval_runtime": 392.0567,
5
  "eval_samples": 4297,
6
+ "eval_samples_per_second": 10.96,
7
+ "eval_steps_per_second": 0.344,
8
+ "eval_wer": 0.15725760362438562,
9
+ "train_loss": 0.5676147035501541,
10
+ "train_runtime": 172546.67,
11
  "train_samples": 240334,
12
+ "train_samples_per_second": 16.714,
13
+ "train_steps_per_second": 0.131
14
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 6.0,
3
- "eval_loss": 0.27584555745124817,
4
- "eval_runtime": 371.4251,
5
  "eval_samples": 4297,
6
- "eval_samples_per_second": 11.569,
7
- "eval_steps_per_second": 0.363,
8
- "eval_wer": 0.17918264285046293
9
  }
 
1
  {
2
+ "epoch": 12.0,
3
+ "eval_loss": 0.25491979718208313,
4
+ "eval_runtime": 392.0567,
5
  "eval_samples": 4297,
6
+ "eval_samples_per_second": 10.96,
7
+ "eval_steps_per_second": 0.344,
8
+ "eval_wer": 0.15725760362438562
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f89ec5de9dd87da4f2a4c2382f07f15a131a2b2c9de36a7ae27f30c07f7e2540
3
  size 1262112241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f9952471847b9dbd693d34fa642974ebb6a016e7677a8ccfb3e3458f45e32a
3
  size 1262112241
run_speech_recognition_ctc.py CHANGED
@@ -795,7 +795,7 @@ def main():
795
  kwargs = {
796
  "finetuned_from": model_args.model_name_or_path,
797
  "tasks": "speech-recognition",
798
- "tags": ["automatic-speech-recognition"]+data_args.dataset_name[0],
799
  "dataset_args": f"Config: {config_name}, Training split: {data_args.train_split_name[0]}, Eval split: {data_args.eval_split_name[0]}",
800
  "dataset": f"{data_args.dataset_name[0].upper()} - {config_name.upper()}",
801
  }
 
795
  kwargs = {
796
  "finetuned_from": model_args.model_name_or_path,
797
  "tasks": "speech-recognition",
798
+ "tags": ["automatic-speech-recognition"]+data_args.dataset_name,
799
  "dataset_args": f"Config: {config_name}, Training split: {data_args.train_split_name[0]}, Eval split: {data_args.eval_split_name[0]}",
800
  "dataset": f"{data_args.dataset_name[0].upper()} - {config_name.upper()}",
801
  }
runs/Jan30_13-38-42_job-336a688f-553a-4e6e-83b3-ad5d10274b51/1643552601.573901/events.out.tfevents.1643552601.job-336a688f-553a-4e6e-83b3-ad5d10274b51.2135399.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de497b3e2912c8bdb4568262999c01c79948f2ece6537c3124bd3b61c876d42
3
+ size 4814
runs/Jan30_13-38-42_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643552601.job-336a688f-553a-4e6e-83b3-ad5d10274b51.2135399.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d2ffd14afa2fe9002da018be9ba7570c3afef91435956aa2d565252f94017e
3
+ size 16148
runs/Jan30_13-38-42_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643725543.job-336a688f-553a-4e6e-83b3-ad5d10274b51.2135399.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454a150fa046a76b31aba582143cc6b1784dda9e4a4190c2b53f77438650e98f
3
+ size 364
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 6.0,
3
- "train_loss": 0.5975231319014925,
4
- "train_runtime": 88923.2167,
5
  "train_samples": 240334,
6
- "train_samples_per_second": 16.216,
7
- "train_steps_per_second": 0.127
8
  }
 
1
  {
2
+ "epoch": 12.0,
3
+ "train_loss": 0.5676147035501541,
4
+ "train_runtime": 172546.67,
5
  "train_samples": 240334,
6
+ "train_samples_per_second": 16.714,
7
+ "train_steps_per_second": 0.131
8
  }
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 5.999600585807483,
5
- "global_step": 11262,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -338,18 +338,363 @@
338
  "step": 11000
339
  },
340
  {
341
- "epoch": 6.0,
342
- "step": 11262,
343
- "total_flos": 3.063803468240281e+20,
344
- "train_loss": 0.5975231319014925,
345
- "train_runtime": 88923.2167,
346
- "train_samples_per_second": 16.216,
347
- "train_steps_per_second": 0.127
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
348
  }
349
  ],
350
- "max_steps": 11262,
351
- "num_train_epochs": 6,
352
- "total_flos": 3.063803468240281e+20,
353
  "trial_name": null,
354
  "trial_params": null
355
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 11.999600585807482,
5
+ "global_step": 22524,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
338
  "step": 11000
339
  },
340
  {
341
+ "epoch": 6.13,
342
+ "learning_rate": 4.029916195673358e-05,
343
+ "loss": 1.1571,
344
+ "step": 11500
345
+ },
346
+ {
347
+ "epoch": 6.13,
348
+ "eval_loss": 0.2807982861995697,
349
+ "eval_runtime": 393.9701,
350
+ "eval_samples_per_second": 10.907,
351
+ "eval_steps_per_second": 0.343,
352
+ "eval_wer": 0.17083865872793208,
353
+ "step": 11500
354
+ },
355
+ {
356
+ "epoch": 6.39,
357
+ "learning_rate": 3.8472032742155524e-05,
358
+ "loss": 1.1505,
359
+ "step": 12000
360
+ },
361
+ {
362
+ "epoch": 6.39,
363
+ "eval_loss": 0.27258625626564026,
364
+ "eval_runtime": 389.5937,
365
+ "eval_samples_per_second": 11.029,
366
+ "eval_steps_per_second": 0.347,
367
+ "eval_wer": 0.16920726955329032,
368
+ "step": 12000
369
+ },
370
+ {
371
+ "epoch": 6.66,
372
+ "learning_rate": 3.6648557786006625e-05,
373
+ "loss": 1.1519,
374
+ "step": 12500
375
+ },
376
+ {
377
+ "epoch": 6.66,
378
+ "eval_loss": 0.2748955190181732,
379
+ "eval_runtime": 387.583,
380
+ "eval_samples_per_second": 11.087,
381
+ "eval_steps_per_second": 0.348,
382
+ "eval_wer": 0.16539376746989204,
383
+ "step": 12500
384
+ },
385
+ {
386
+ "epoch": 6.93,
387
+ "learning_rate": 3.482142857142857e-05,
388
+ "loss": 1.136,
389
+ "step": 13000
390
+ },
391
+ {
392
+ "epoch": 6.93,
393
+ "eval_loss": 0.276467502117157,
394
+ "eval_runtime": 393.6733,
395
+ "eval_samples_per_second": 10.915,
396
+ "eval_steps_per_second": 0.343,
397
+ "eval_wer": 0.16425075594625768,
398
+ "step": 13000
399
+ },
400
+ {
401
+ "epoch": 7.19,
402
+ "learning_rate": 3.299429935685051e-05,
403
+ "loss": 1.1326,
404
+ "step": 13500
405
+ },
406
+ {
407
+ "epoch": 7.19,
408
+ "eval_loss": 0.27056241035461426,
409
+ "eval_runtime": 391.6082,
410
+ "eval_samples_per_second": 10.973,
411
+ "eval_steps_per_second": 0.345,
412
+ "eval_wer": 0.1668277273813606,
413
+ "step": 13500
414
+ },
415
+ {
416
+ "epoch": 7.46,
417
+ "learning_rate": 3.116717014227246e-05,
418
+ "loss": 1.1342,
419
+ "step": 14000
420
+ },
421
+ {
422
+ "epoch": 7.46,
423
+ "eval_loss": 0.26654428243637085,
424
+ "eval_runtime": 388.567,
425
+ "eval_samples_per_second": 11.059,
426
+ "eval_steps_per_second": 0.347,
427
+ "eval_wer": 0.1638247243783576,
428
+ "step": 14000
429
+ },
430
+ {
431
+ "epoch": 7.72,
432
+ "learning_rate": 2.9340040927694404e-05,
433
+ "loss": 1.1286,
434
+ "step": 14500
435
+ },
436
+ {
437
+ "epoch": 7.72,
438
+ "eval_loss": 0.2668865919113159,
439
+ "eval_runtime": 384.4478,
440
+ "eval_samples_per_second": 11.177,
441
+ "eval_steps_per_second": 0.351,
442
+ "eval_wer": 0.1635857310597795,
443
+ "step": 14500
444
+ },
445
+ {
446
+ "epoch": 7.99,
447
+ "learning_rate": 2.7516565971545504e-05,
448
+ "loss": 1.1243,
449
+ "step": 15000
450
+ },
451
+ {
452
+ "epoch": 7.99,
453
+ "eval_loss": 0.2619013488292694,
454
+ "eval_runtime": 392.1143,
455
+ "eval_samples_per_second": 10.959,
456
+ "eval_steps_per_second": 0.344,
457
+ "eval_wer": 0.16234920041148415,
458
+ "step": 15000
459
+ },
460
+ {
461
+ "epoch": 8.26,
462
+ "learning_rate": 2.5689436756967453e-05,
463
+ "loss": 1.1173,
464
+ "step": 15500
465
+ },
466
+ {
467
+ "epoch": 8.26,
468
+ "eval_loss": 0.2651631236076355,
469
+ "eval_runtime": 388.7223,
470
+ "eval_samples_per_second": 11.054,
471
+ "eval_steps_per_second": 0.347,
472
+ "eval_wer": 0.16037490777975208,
473
+ "step": 15500
474
+ },
475
+ {
476
+ "epoch": 8.52,
477
+ "learning_rate": 2.3862307542389395e-05,
478
+ "loss": 1.1129,
479
+ "step": 16000
480
+ },
481
+ {
482
+ "epoch": 8.52,
483
+ "eval_loss": 0.26095372438430786,
484
+ "eval_runtime": 387.1141,
485
+ "eval_samples_per_second": 11.1,
486
+ "eval_steps_per_second": 0.349,
487
+ "eval_wer": 0.1597514469486788,
488
+ "step": 16000
489
+ },
490
+ {
491
+ "epoch": 8.79,
492
+ "learning_rate": 2.203517832781134e-05,
493
+ "loss": 1.1091,
494
+ "step": 16500
495
+ },
496
+ {
497
+ "epoch": 8.79,
498
+ "eval_loss": 0.2608127295970917,
499
+ "eval_runtime": 386.5271,
500
+ "eval_samples_per_second": 11.117,
501
+ "eval_steps_per_second": 0.349,
502
+ "eval_wer": 0.15837983312031756,
503
+ "step": 16500
504
+ },
505
+ {
506
+ "epoch": 9.06,
507
+ "learning_rate": 2.0208049113233286e-05,
508
+ "loss": 1.1053,
509
+ "step": 17000
510
+ },
511
+ {
512
+ "epoch": 9.06,
513
+ "eval_loss": 0.2632738947868347,
514
+ "eval_runtime": 389.2784,
515
+ "eval_samples_per_second": 11.038,
516
+ "eval_steps_per_second": 0.347,
517
+ "eval_wer": 0.1664016958134605,
518
+ "step": 17000
519
+ },
520
+ {
521
+ "epoch": 9.32,
522
+ "learning_rate": 1.8384574157084387e-05,
523
+ "loss": 1.1004,
524
+ "step": 17500
525
+ },
526
+ {
527
+ "epoch": 9.32,
528
+ "eval_loss": 0.2594461441040039,
529
+ "eval_runtime": 388.9349,
530
+ "eval_samples_per_second": 11.048,
531
+ "eval_steps_per_second": 0.347,
532
+ "eval_wer": 0.16618348452258486,
533
+ "step": 17500
534
+ },
535
+ {
536
+ "epoch": 9.59,
537
+ "learning_rate": 1.6557444942506332e-05,
538
+ "loss": 1.0995,
539
+ "step": 18000
540
+ },
541
+ {
542
+ "epoch": 9.59,
543
+ "eval_loss": 0.26234543323516846,
544
+ "eval_runtime": 383.4387,
545
+ "eval_samples_per_second": 11.206,
546
+ "eval_steps_per_second": 0.352,
547
+ "eval_wer": 0.15694587320884898,
548
+ "step": 18000
549
+ },
550
+ {
551
+ "epoch": 9.86,
552
+ "learning_rate": 1.4730315727928276e-05,
553
+ "loss": 1.0964,
554
+ "step": 18500
555
+ },
556
+ {
557
+ "epoch": 9.86,
558
+ "eval_loss": 0.26244357228279114,
559
+ "eval_runtime": 384.9493,
560
+ "eval_samples_per_second": 11.163,
561
+ "eval_steps_per_second": 0.351,
562
+ "eval_wer": 0.15968910086557145,
563
+ "step": 18500
564
+ },
565
+ {
566
+ "epoch": 10.12,
567
+ "learning_rate": 1.2903186513350224e-05,
568
+ "loss": 1.09,
569
+ "step": 19000
570
+ },
571
+ {
572
+ "epoch": 10.12,
573
+ "eval_loss": 0.2576591968536377,
574
+ "eval_runtime": 391.5397,
575
+ "eval_samples_per_second": 10.975,
576
+ "eval_steps_per_second": 0.345,
577
+ "eval_wer": 0.15782910938620281,
578
+ "step": 19000
579
+ },
580
+ {
581
+ "epoch": 10.39,
582
+ "learning_rate": 1.108336581563048e-05,
583
+ "loss": 1.089,
584
+ "step": 19500
585
+ },
586
+ {
587
+ "epoch": 10.39,
588
+ "eval_loss": 0.25744903087615967,
589
+ "eval_runtime": 384.7348,
590
+ "eval_samples_per_second": 11.169,
591
+ "eval_steps_per_second": 0.351,
592
+ "eval_wer": 0.1531219801115995,
593
+ "step": 19500
594
+ },
595
+ {
596
+ "epoch": 10.66,
597
+ "learning_rate": 9.256236601052426e-06,
598
+ "loss": 1.0864,
599
+ "step": 20000
600
+ },
601
+ {
602
+ "epoch": 10.66,
603
+ "eval_loss": 0.2556162476539612,
604
+ "eval_runtime": 391.8515,
605
+ "eval_samples_per_second": 10.966,
606
+ "eval_steps_per_second": 0.345,
607
+ "eval_wer": 0.15464945914772904,
608
+ "step": 20000
609
+ },
610
+ {
611
+ "epoch": 10.92,
612
+ "learning_rate": 7.429107386474371e-06,
613
+ "loss": 1.0806,
614
+ "step": 20500
615
+ },
616
+ {
617
+ "epoch": 10.92,
618
+ "eval_loss": 0.2548317313194275,
619
+ "eval_runtime": 384.3272,
620
+ "eval_samples_per_second": 11.181,
621
+ "eval_steps_per_second": 0.351,
622
+ "eval_wer": 0.1583174870372102,
623
+ "step": 20500
624
+ },
625
+ {
626
+ "epoch": 11.19,
627
+ "learning_rate": 5.6019781718963155e-06,
628
+ "loss": 1.0842,
629
+ "step": 21000
630
+ },
631
+ {
632
+ "epoch": 11.19,
633
+ "eval_loss": 0.25501224398612976,
634
+ "eval_runtime": 383.8764,
635
+ "eval_samples_per_second": 11.194,
636
+ "eval_steps_per_second": 0.352,
637
+ "eval_wer": 0.1542026455521265,
638
+ "step": 21000
639
+ },
640
+ {
641
+ "epoch": 11.45,
642
+ "learning_rate": 3.774848957318261e-06,
643
+ "loss": 1.0805,
644
+ "step": 21500
645
+ },
646
+ {
647
+ "epoch": 11.45,
648
+ "eval_loss": 0.25607678294181824,
649
+ "eval_runtime": 388.7678,
650
+ "eval_samples_per_second": 11.053,
651
+ "eval_steps_per_second": 0.347,
652
+ "eval_wer": 0.15236343610046033,
653
+ "step": 21500
654
+ },
655
+ {
656
+ "epoch": 11.72,
657
+ "learning_rate": 1.9477197427402063e-06,
658
+ "loss": 1.0722,
659
+ "step": 22000
660
+ },
661
+ {
662
+ "epoch": 11.72,
663
+ "eval_loss": 0.25402259826660156,
664
+ "eval_runtime": 385.5053,
665
+ "eval_samples_per_second": 11.146,
666
+ "eval_steps_per_second": 0.35,
667
+ "eval_wer": 0.1565614056963538,
668
+ "step": 22000
669
+ },
670
+ {
671
+ "epoch": 11.99,
672
+ "learning_rate": 1.2059052816215163e-07,
673
+ "loss": 1.0763,
674
+ "step": 22500
675
+ },
676
+ {
677
+ "epoch": 11.99,
678
+ "eval_loss": 0.2549177408218384,
679
+ "eval_runtime": 379.953,
680
+ "eval_samples_per_second": 11.309,
681
+ "eval_steps_per_second": 0.355,
682
+ "eval_wer": 0.15720564855512953,
683
+ "step": 22500
684
+ },
685
+ {
686
+ "epoch": 12.0,
687
+ "step": 22524,
688
+ "total_flos": 6.281601139352125e+20,
689
+ "train_loss": 0.5676147035501541,
690
+ "train_runtime": 172546.67,
691
+ "train_samples_per_second": 16.714,
692
+ "train_steps_per_second": 0.131
693
  }
694
  ],
695
+ "max_steps": 22524,
696
+ "num_train_epochs": 12,
697
+ "total_flos": 6.281601139352125e+20,
698
  "trial_name": null,
699
  "trial_params": null
700
  }