Hugging Face's logo

JRHuy
/
whisper-small-vietnamese

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JRHuy commited on
Commit
f00b6c0
•
1 Parent(s): b7e39b2

Training in progress, step 3000

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +255 -5
  6. pytorch_model.bin +1 -1
  7. runs/Aug21_16-43-21_8bad39564bfa/events.out.tfevents.1692636213.8bad39564bfa.55.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06d9f310e7215fa53772a26e73c8bfe99258430f637a0e7c6a57b1411a3fc046
3
  size 1934161157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7cf542d1162861a412322de0843a71f9b7d2a2491fed87f740beafd324feb87
3
  size 1934161157
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08268c9356743b28c4219f4829b0833b9e174958fd62a1cb1e2061f4cf025441
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aed36cd0774277c3bc7d2577938faa840a081b7219a5939e6d8e3f7908a9e51
3
  size 967102729
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11dbcedeb462d624e874b21e47f755022f531a9db8eea64f2e44191aab46241b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85dcd9588829e28a34b471fbefe47c5b729c37261cb017e050a2c52e69019df0
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cd37dd530bd467817ba99df096031e0ec04862523fd363efae5f40294a6a156
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f375f0ec2d81d3bc0adbea21cfba80dd771ec303d1e16586405d497868a3b309
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 16.120763315294788,
3
- "best_model_checkpoint": "./whisper-small-vietnamese/checkpoint-1000",
4
- "epoch": 5.730659025787966,
5
- "global_step": 2000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -506,11 +506,261 @@
506
  "eval_steps_per_second": 0.097,
507
  "eval_wer": 16.708526449341033,
508
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
509
  }
510
  ],
511
  "max_steps": 4000,
512
  "num_train_epochs": 12,
513
- "total_flos": 9.2174176862208e+18,
514
  "trial_name": null,
515
  "trial_params": null
516
  }
 
1
  {
2
+ "best_metric": 15.545946505787006,
3
+ "best_model_checkpoint": "./whisper-small-vietnamese/checkpoint-3000",
4
+ "epoch": 8.595988538681949,
5
+ "global_step": 3000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
506
  "eval_steps_per_second": 0.097,
507
  "eval_wer": 16.708526449341033,
508
  "step": 2000
509
+ },
510
+ {
511
+ "epoch": 5.8,
512
+ "learning_rate": 1e-05,
513
+ "loss": 0.0201,
514
+ "step": 2025
515
+ },
516
+ {
517
+ "epoch": 5.87,
518
+ "learning_rate": 1e-05,
519
+ "loss": 0.0236,
520
+ "step": 2050
521
+ },
522
+ {
523
+ "epoch": 5.95,
524
+ "learning_rate": 1e-05,
525
+ "loss": 0.0199,
526
+ "step": 2075
527
+ },
528
+ {
529
+ "epoch": 6.02,
530
+ "learning_rate": 1e-05,
531
+ "loss": 0.0175,
532
+ "step": 2100
533
+ },
534
+ {
535
+ "epoch": 6.09,
536
+ "learning_rate": 1e-05,
537
+ "loss": 0.0115,
538
+ "step": 2125
539
+ },
540
+ {
541
+ "epoch": 6.16,
542
+ "learning_rate": 1e-05,
543
+ "loss": 0.0111,
544
+ "step": 2150
545
+ },
546
+ {
547
+ "epoch": 6.23,
548
+ "learning_rate": 1e-05,
549
+ "loss": 0.011,
550
+ "step": 2175
551
+ },
552
+ {
553
+ "epoch": 6.3,
554
+ "learning_rate": 1e-05,
555
+ "loss": 0.0108,
556
+ "step": 2200
557
+ },
558
+ {
559
+ "epoch": 6.38,
560
+ "learning_rate": 1e-05,
561
+ "loss": 0.0133,
562
+ "step": 2225
563
+ },
564
+ {
565
+ "epoch": 6.45,
566
+ "learning_rate": 1e-05,
567
+ "loss": 0.0093,
568
+ "step": 2250
569
+ },
570
+ {
571
+ "epoch": 6.52,
572
+ "learning_rate": 1e-05,
573
+ "loss": 0.0114,
574
+ "step": 2275
575
+ },
576
+ {
577
+ "epoch": 6.59,
578
+ "learning_rate": 1e-05,
579
+ "loss": 0.012,
580
+ "step": 2300
581
+ },
582
+ {
583
+ "epoch": 6.66,
584
+ "learning_rate": 1e-05,
585
+ "loss": 0.0103,
586
+ "step": 2325
587
+ },
588
+ {
589
+ "epoch": 6.73,
590
+ "learning_rate": 1e-05,
591
+ "loss": 0.0142,
592
+ "step": 2350
593
+ },
594
+ {
595
+ "epoch": 6.81,
596
+ "learning_rate": 1e-05,
597
+ "loss": 0.0115,
598
+ "step": 2375
599
+ },
600
+ {
601
+ "epoch": 6.88,
602
+ "learning_rate": 1e-05,
603
+ "loss": 0.0117,
604
+ "step": 2400
605
+ },
606
+ {
607
+ "epoch": 6.95,
608
+ "learning_rate": 1e-05,
609
+ "loss": 0.0156,
610
+ "step": 2425
611
+ },
612
+ {
613
+ "epoch": 7.02,
614
+ "learning_rate": 1e-05,
615
+ "loss": 0.0124,
616
+ "step": 2450
617
+ },
618
+ {
619
+ "epoch": 7.09,
620
+ "learning_rate": 1e-05,
621
+ "loss": 0.0077,
622
+ "step": 2475
623
+ },
624
+ {
625
+ "epoch": 7.16,
626
+ "learning_rate": 1e-05,
627
+ "loss": 0.0075,
628
+ "step": 2500
629
+ },
630
+ {
631
+ "epoch": 7.23,
632
+ "learning_rate": 1e-05,
633
+ "loss": 0.0097,
634
+ "step": 2525
635
+ },
636
+ {
637
+ "epoch": 7.31,
638
+ "learning_rate": 1e-05,
639
+ "loss": 0.009,
640
+ "step": 2550
641
+ },
642
+ {
643
+ "epoch": 7.38,
644
+ "learning_rate": 1e-05,
645
+ "loss": 0.0081,
646
+ "step": 2575
647
+ },
648
+ {
649
+ "epoch": 7.45,
650
+ "learning_rate": 1e-05,
651
+ "loss": 0.0076,
652
+ "step": 2600
653
+ },
654
+ {
655
+ "epoch": 7.52,
656
+ "learning_rate": 1e-05,
657
+ "loss": 0.0079,
658
+ "step": 2625
659
+ },
660
+ {
661
+ "epoch": 7.59,
662
+ "learning_rate": 1e-05,
663
+ "loss": 0.0093,
664
+ "step": 2650
665
+ },
666
+ {
667
+ "epoch": 7.66,
668
+ "learning_rate": 1e-05,
669
+ "loss": 0.0086,
670
+ "step": 2675
671
+ },
672
+ {
673
+ "epoch": 7.74,
674
+ "learning_rate": 1e-05,
675
+ "loss": 0.0093,
676
+ "step": 2700
677
+ },
678
+ {
679
+ "epoch": 7.81,
680
+ "learning_rate": 1e-05,
681
+ "loss": 0.009,
682
+ "step": 2725
683
+ },
684
+ {
685
+ "epoch": 7.88,
686
+ "learning_rate": 1e-05,
687
+ "loss": 0.0093,
688
+ "step": 2750
689
+ },
690
+ {
691
+ "epoch": 7.95,
692
+ "learning_rate": 1e-05,
693
+ "loss": 0.0085,
694
+ "step": 2775
695
+ },
696
+ {
697
+ "epoch": 8.02,
698
+ "learning_rate": 1e-05,
699
+ "loss": 0.0076,
700
+ "step": 2800
701
+ },
702
+ {
703
+ "epoch": 8.09,
704
+ "learning_rate": 1e-05,
705
+ "loss": 0.0055,
706
+ "step": 2825
707
+ },
708
+ {
709
+ "epoch": 8.17,
710
+ "learning_rate": 1e-05,
711
+ "loss": 0.0049,
712
+ "step": 2850
713
+ },
714
+ {
715
+ "epoch": 8.24,
716
+ "learning_rate": 1e-05,
717
+ "loss": 0.0055,
718
+ "step": 2875
719
+ },
720
+ {
721
+ "epoch": 8.31,
722
+ "learning_rate": 1e-05,
723
+ "loss": 0.0063,
724
+ "step": 2900
725
+ },
726
+ {
727
+ "epoch": 8.38,
728
+ "learning_rate": 1e-05,
729
+ "loss": 0.0078,
730
+ "step": 2925
731
+ },
732
+ {
733
+ "epoch": 8.45,
734
+ "learning_rate": 1e-05,
735
+ "loss": 0.0069,
736
+ "step": 2950
737
+ },
738
+ {
739
+ "epoch": 8.52,
740
+ "learning_rate": 1e-05,
741
+ "loss": 0.0063,
742
+ "step": 2975
743
+ },
744
+ {
745
+ "epoch": 8.6,
746
+ "learning_rate": 1e-05,
747
+ "loss": 0.0059,
748
+ "step": 3000
749
+ },
750
+ {
751
+ "epoch": 8.6,
752
+ "eval_cer": 8.218942932064238,
753
+ "eval_loss": 0.4233042001724243,
754
+ "eval_runtime": 697.1158,
755
+ "eval_samples_per_second": 1.584,
756
+ "eval_steps_per_second": 0.099,
757
+ "eval_wer": 15.545946505787006,
758
+ "step": 3000
759
  }
760
  ],
761
  "max_steps": 4000,
762
  "num_train_epochs": 12,
763
+ "total_flos": 1.382439501692928e+19,
764
  "trial_name": null,
765
  "trial_params": null
766
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08268c9356743b28c4219f4829b0833b9e174958fd62a1cb1e2061f4cf025441
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aed36cd0774277c3bc7d2577938faa840a081b7219a5939e6d8e3f7908a9e51
3
  size 967102729
runs/Aug21_16-43-21_8bad39564bfa/events.out.tfevents.1692636213.8bad39564bfa.55.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd7e56f2ee548b2300e461b19266ec105f9ed5c6c75687d5ded64b101777e0c
3
- size 19139
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234771433c64a48dbfa61992972eca3ff4220b661982fa138194e7c8a3af2d0e
3
+ size 25784