Hugging Face's logo

marinone94
/
xls-r-300m-sv-robust

Automatic Speech Recognition
Transformers
PyTorch
Swedish
wav2vec2
mozilla-foundation/common_voice_9_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
marinone94 commited on
Commit
f625d5e
·
1 Parent(s): c81fe7e

Training in progress, step 9000

Browse files
Files changed (10) hide show
  1. {checkpoint-6000 → checkpoint-9000}/config.json +0 -0
  2. {checkpoint-6000 → checkpoint-9000}/optimizer.pt +1 -1
  3. {checkpoint-6000 → checkpoint-9000}/preprocessor_config.json +0 -0
  4. {checkpoint-6000 → checkpoint-9000}/pytorch_model.bin +1 -1
  5. {checkpoint-6000 → checkpoint-9000}/rng_state.pth +1 -1
  6. {checkpoint-6000 → checkpoint-9000}/scaler.pt +1 -1
  7. {checkpoint-6000 → checkpoint-9000}/scheduler.pt +1 -1
  8. {checkpoint-6000 → checkpoint-9000}/trainer_state.json +210 -3
  9. {checkpoint-6000 → checkpoint-9000}/training_args.bin +0 -0
  10. pytorch_model.bin +1 -1
{checkpoint-6000 → checkpoint-9000}/config.json RENAMED
File without changes
{checkpoint-6000 → checkpoint-9000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57a02e3f0c79bd1e97834af9735ae9ea2c51e986a0e4aebe78745ac090bd29bf
3
  size 2490337809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6a25135607878564d23676b93d3f4389e9142723c5aa358874bbbe694e1865
3
  size 2490337809
{checkpoint-6000 → checkpoint-9000}/preprocessor_config.json RENAMED
File without changes
{checkpoint-6000 → checkpoint-9000}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c14c1a98519a72a2d3a4339ab78f6a4b41d391852271790078767a444fe87beb
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60167f2a48ceb8fe506a6fc5fadb34f674f92a0e6fbe059beb8b59920c10081b
3
  size 1262063089
{checkpoint-6000 → checkpoint-9000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7855b43fb50533e2e01cf47c566be51da5a7cd11b3be55d9d7c0c79407094c18
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e96a02656084c27e5355ae600e92f7ba16d5ba89c035e7e41177dd5ca14ef0
3
  size 14567
{checkpoint-6000 → checkpoint-9000}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d156164b5a9269c6c2ad987484964bc9fa0a7b461cee526f820c65c9c09e374a
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f2112253674fa8e9f42754533bdf95c2eb4295f47b03bdedc1e3c171d21748
3
  size 559
{checkpoint-6000 → checkpoint-9000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48b52dcc81c772638b05def04e150569a1ebe5930008f73931aa734959b1a983
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:274e525d3dd45c03d813604b39b3c9c988772a76a04bf332683348376d00e7d1
3
  size 623
{checkpoint-6000 → checkpoint-9000}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 62.4987012987013,
5
- "global_step": 6000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -420,11 +420,218 @@
420
  "eval_steps_per_second": 0.761,
421
  "eval_wer": 0.11913406307575593,
422
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
423
  }
424
  ],
425
  "max_steps": 9600,
426
  "num_train_epochs": 100,
427
- "total_flos": 9.319334032985827e+19,
428
  "trial_name": null,
429
  "trial_params": null
430
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 93.74805194805195,
5
+ "global_step": 9000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
420
  "eval_steps_per_second": 0.761,
421
  "eval_wer": 0.11913406307575593,
422
  "step": 6000
423
+ },
424
+ {
425
+ "epoch": 63.54,
426
+ "learning_rate": 3.4208984375e-05,
427
+ "loss": 0.8004,
428
+ "step": 6100
429
+ },
430
+ {
431
+ "epoch": 64.58,
432
+ "learning_rate": 3.32421875e-05,
433
+ "loss": 0.7904,
434
+ "step": 6200
435
+ },
436
+ {
437
+ "epoch": 65.62,
438
+ "learning_rate": 3.2265625e-05,
439
+ "loss": 0.7947,
440
+ "step": 6300
441
+ },
442
+ {
443
+ "epoch": 66.66,
444
+ "learning_rate": 3.12890625e-05,
445
+ "loss": 0.7981,
446
+ "step": 6400
447
+ },
448
+ {
449
+ "epoch": 67.71,
450
+ "learning_rate": 3.0312499999999998e-05,
451
+ "loss": 0.8018,
452
+ "step": 6500
453
+ },
454
+ {
455
+ "epoch": 68.75,
456
+ "learning_rate": 2.93359375e-05,
457
+ "loss": 0.7922,
458
+ "step": 6600
459
+ },
460
+ {
461
+ "epoch": 69.79,
462
+ "learning_rate": 2.8359374999999996e-05,
463
+ "loss": 0.796,
464
+ "step": 6700
465
+ },
466
+ {
467
+ "epoch": 70.83,
468
+ "learning_rate": 2.73828125e-05,
469
+ "loss": 0.7887,
470
+ "step": 6800
471
+ },
472
+ {
473
+ "epoch": 71.87,
474
+ "learning_rate": 2.6406249999999998e-05,
475
+ "loss": 0.7796,
476
+ "step": 6900
477
+ },
478
+ {
479
+ "epoch": 72.91,
480
+ "learning_rate": 2.5429687499999997e-05,
481
+ "loss": 0.7822,
482
+ "step": 7000
483
+ },
484
+ {
485
+ "epoch": 72.91,
486
+ "eval_loss": 0.1346774846315384,
487
+ "eval_runtime": 195.6804,
488
+ "eval_samples_per_second": 25.782,
489
+ "eval_steps_per_second": 0.807,
490
+ "eval_wer": 0.11550341389400672,
491
+ "step": 7000
492
+ },
493
+ {
494
+ "epoch": 73.96,
495
+ "learning_rate": 2.4453125e-05,
496
+ "loss": 0.7882,
497
+ "step": 7100
498
+ },
499
+ {
500
+ "epoch": 75.0,
501
+ "learning_rate": 2.34765625e-05,
502
+ "loss": 0.7821,
503
+ "step": 7200
504
+ },
505
+ {
506
+ "epoch": 76.04,
507
+ "learning_rate": 2.2499999999999998e-05,
508
+ "loss": 0.7814,
509
+ "step": 7300
510
+ },
511
+ {
512
+ "epoch": 77.08,
513
+ "learning_rate": 2.1523437499999997e-05,
514
+ "loss": 0.784,
515
+ "step": 7400
516
+ },
517
+ {
518
+ "epoch": 78.12,
519
+ "learning_rate": 2.0546875e-05,
520
+ "loss": 0.7772,
521
+ "step": 7500
522
+ },
523
+ {
524
+ "epoch": 79.17,
525
+ "learning_rate": 1.95703125e-05,
526
+ "loss": 0.7785,
527
+ "step": 7600
528
+ },
529
+ {
530
+ "epoch": 80.21,
531
+ "learning_rate": 1.8593749999999998e-05,
532
+ "loss": 0.7731,
533
+ "step": 7700
534
+ },
535
+ {
536
+ "epoch": 81.25,
537
+ "learning_rate": 1.7617187499999997e-05,
538
+ "loss": 0.7726,
539
+ "step": 7800
540
+ },
541
+ {
542
+ "epoch": 82.29,
543
+ "learning_rate": 1.6640624999999996e-05,
544
+ "loss": 0.7765,
545
+ "step": 7900
546
+ },
547
+ {
548
+ "epoch": 83.33,
549
+ "learning_rate": 1.56640625e-05,
550
+ "loss": 0.7769,
551
+ "step": 8000
552
+ },
553
+ {
554
+ "epoch": 83.33,
555
+ "eval_loss": 0.1320926398038864,
556
+ "eval_runtime": 197.3103,
557
+ "eval_samples_per_second": 25.569,
558
+ "eval_steps_per_second": 0.801,
559
+ "eval_wer": 0.11306491817492142,
560
+ "step": 8000
561
+ },
562
+ {
563
+ "epoch": 84.37,
564
+ "learning_rate": 1.4687499999999998e-05,
565
+ "loss": 0.7713,
566
+ "step": 8100
567
+ },
568
+ {
569
+ "epoch": 85.42,
570
+ "learning_rate": 1.3710937499999999e-05,
571
+ "loss": 0.773,
572
+ "step": 8200
573
+ },
574
+ {
575
+ "epoch": 86.46,
576
+ "learning_rate": 1.2734375e-05,
577
+ "loss": 0.7668,
578
+ "step": 8300
579
+ },
580
+ {
581
+ "epoch": 87.5,
582
+ "learning_rate": 1.1757812499999999e-05,
583
+ "loss": 0.7766,
584
+ "step": 8400
585
+ },
586
+ {
587
+ "epoch": 88.54,
588
+ "learning_rate": 1.0781249999999998e-05,
589
+ "loss": 0.7596,
590
+ "step": 8500
591
+ },
592
+ {
593
+ "epoch": 89.58,
594
+ "learning_rate": 9.8046875e-06,
595
+ "loss": 0.7561,
596
+ "step": 8600
597
+ },
598
+ {
599
+ "epoch": 90.62,
600
+ "learning_rate": 8.837890624999999e-06,
601
+ "loss": 0.7585,
602
+ "step": 8700
603
+ },
604
+ {
605
+ "epoch": 91.66,
606
+ "learning_rate": 7.861328124999998e-06,
607
+ "loss": 0.7524,
608
+ "step": 8800
609
+ },
610
+ {
611
+ "epoch": 92.71,
612
+ "learning_rate": 6.884765624999999e-06,
613
+ "loss": 0.7591,
614
+ "step": 8900
615
+ },
616
+ {
617
+ "epoch": 93.75,
618
+ "learning_rate": 5.908203125e-06,
619
+ "loss": 0.7678,
620
+ "step": 9000
621
+ },
622
+ {
623
+ "epoch": 93.75,
624
+ "eval_loss": 0.13205420970916748,
625
+ "eval_runtime": 199.4472,
626
+ "eval_samples_per_second": 25.295,
627
+ "eval_steps_per_second": 0.792,
628
+ "eval_wer": 0.11146634875907663,
629
+ "step": 9000
630
  }
631
  ],
632
  "max_steps": 9600,
633
  "num_train_epochs": 100,
634
+ "total_flos": 1.397913952067139e+20,
635
  "trial_name": null,
636
  "trial_params": null
637
  }
{checkpoint-6000 → checkpoint-9000}/training_args.bin RENAMED
File without changes
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e03974019e7bfaa10bfd153daa4001f4cabd730e7b038f7b98a07fecd285577
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60167f2a48ceb8fe506a6fc5fadb34f674f92a0e6fbe059beb8b59920c10081b
3
  size 1262063089