Hugging Face's logo

JRHuy
/
whisper-small-vivos

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JRHuy commited on
Commit
e8d940c
•
1 Parent(s): 6ed888a

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/Aug20_17-07-13_713cba38a708/events.out.tfevents.1692551245.713cba38a708.95.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9345b866ebc9159328815b3ecdcc308b8a2e853a3e173aee675d508068a92b2d
3
  size 1934161157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145802247f511f2db8a6588be1fa1b29d0b032879310d24beb32ffec60f6d996
3
  size 1934161157
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65503e2d287eeb93231cc3f6e123f111f05e00b5886775a96c9f0f3234a9cb60
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da96b2ae6e5559d7f78e7908472ddf37a9adc97bc0dfa1983148ab68e5b3eb9
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:def05a477428754b4320528e52a0b3ae385799f784ed0d816af6d7b633b37a5a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1b5c1b07a03db7d365bf63cf3eae9ed5e22033102108fc6ba233d19973a74e
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": 19.08831908831909,
3
- "best_model_checkpoint": "./whisper-small-vivos/checkpoint-2000",
4
- "epoch": 2.7434842249657065,
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": 0.122,
507
  "eval_wer": 19.08831908831909,
508
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
509
  }
510
  ],
511
  "max_steps": 4000,
512
  "num_train_epochs": 6,
513
- "total_flos": 9.23242412703744e+18,
514
  "trial_name": null,
515
  "trial_params": null
516
  }
 
1
  {
2
+ "best_metric": 17.98756798756799,
3
+ "best_model_checkpoint": "./whisper-small-vivos/checkpoint-3000",
4
+ "epoch": 4.11522633744856,
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": 0.122,
507
  "eval_wer": 19.08831908831909,
508
  "step": 2000
509
+ },
510
+ {
511
+ "epoch": 2.78,
512
+ "learning_rate": 1e-05,
513
+ "loss": 0.0816,
514
+ "step": 2025
515
+ },
516
+ {
517
+ "epoch": 2.81,
518
+ "learning_rate": 1e-05,
519
+ "loss": 0.0796,
520
+ "step": 2050
521
+ },
522
+ {
523
+ "epoch": 2.85,
524
+ "learning_rate": 1e-05,
525
+ "loss": 0.0721,
526
+ "step": 2075
527
+ },
528
+ {
529
+ "epoch": 2.88,
530
+ "learning_rate": 1e-05,
531
+ "loss": 0.0716,
532
+ "step": 2100
533
+ },
534
+ {
535
+ "epoch": 2.91,
536
+ "learning_rate": 1e-05,
537
+ "loss": 0.0659,
538
+ "step": 2125
539
+ },
540
+ {
541
+ "epoch": 2.95,
542
+ "learning_rate": 1e-05,
543
+ "loss": 0.0644,
544
+ "step": 2150
545
+ },
546
+ {
547
+ "epoch": 2.98,
548
+ "learning_rate": 1e-05,
549
+ "loss": 0.0653,
550
+ "step": 2175
551
+ },
552
+ {
553
+ "epoch": 3.02,
554
+ "learning_rate": 1e-05,
555
+ "loss": 0.0558,
556
+ "step": 2200
557
+ },
558
+ {
559
+ "epoch": 3.05,
560
+ "learning_rate": 1e-05,
561
+ "loss": 0.043,
562
+ "step": 2225
563
+ },
564
+ {
565
+ "epoch": 3.09,
566
+ "learning_rate": 1e-05,
567
+ "loss": 0.047,
568
+ "step": 2250
569
+ },
570
+ {
571
+ "epoch": 3.12,
572
+ "learning_rate": 1e-05,
573
+ "loss": 0.0355,
574
+ "step": 2275
575
+ },
576
+ {
577
+ "epoch": 3.16,
578
+ "learning_rate": 1e-05,
579
+ "loss": 0.033,
580
+ "step": 2300
581
+ },
582
+ {
583
+ "epoch": 3.19,
584
+ "learning_rate": 1e-05,
585
+ "loss": 0.0357,
586
+ "step": 2325
587
+ },
588
+ {
589
+ "epoch": 3.22,
590
+ "learning_rate": 1e-05,
591
+ "loss": 0.0364,
592
+ "step": 2350
593
+ },
594
+ {
595
+ "epoch": 3.26,
596
+ "learning_rate": 1e-05,
597
+ "loss": 0.0425,
598
+ "step": 2375
599
+ },
600
+ {
601
+ "epoch": 3.29,
602
+ "learning_rate": 1e-05,
603
+ "loss": 0.0398,
604
+ "step": 2400
605
+ },
606
+ {
607
+ "epoch": 3.33,
608
+ "learning_rate": 1e-05,
609
+ "loss": 0.0376,
610
+ "step": 2425
611
+ },
612
+ {
613
+ "epoch": 3.36,
614
+ "learning_rate": 1e-05,
615
+ "loss": 0.0413,
616
+ "step": 2450
617
+ },
618
+ {
619
+ "epoch": 3.4,
620
+ "learning_rate": 1e-05,
621
+ "loss": 0.0374,
622
+ "step": 2475
623
+ },
624
+ {
625
+ "epoch": 3.43,
626
+ "learning_rate": 1e-05,
627
+ "loss": 0.0383,
628
+ "step": 2500
629
+ },
630
+ {
631
+ "epoch": 3.46,
632
+ "learning_rate": 1e-05,
633
+ "loss": 0.0381,
634
+ "step": 2525
635
+ },
636
+ {
637
+ "epoch": 3.5,
638
+ "learning_rate": 1e-05,
639
+ "loss": 0.0466,
640
+ "step": 2550
641
+ },
642
+ {
643
+ "epoch": 3.53,
644
+ "learning_rate": 1e-05,
645
+ "loss": 0.04,
646
+ "step": 2575
647
+ },
648
+ {
649
+ "epoch": 3.57,
650
+ "learning_rate": 1e-05,
651
+ "loss": 0.0452,
652
+ "step": 2600
653
+ },
654
+ {
655
+ "epoch": 3.6,
656
+ "learning_rate": 1e-05,
657
+ "loss": 0.0393,
658
+ "step": 2625
659
+ },
660
+ {
661
+ "epoch": 3.64,
662
+ "learning_rate": 1e-05,
663
+ "loss": 0.0461,
664
+ "step": 2650
665
+ },
666
+ {
667
+ "epoch": 3.67,
668
+ "learning_rate": 1e-05,
669
+ "loss": 0.0403,
670
+ "step": 2675
671
+ },
672
+ {
673
+ "epoch": 3.7,
674
+ "learning_rate": 1e-05,
675
+ "loss": 0.0489,
676
+ "step": 2700
677
+ },
678
+ {
679
+ "epoch": 3.74,
680
+ "learning_rate": 1e-05,
681
+ "loss": 0.0418,
682
+ "step": 2725
683
+ },
684
+ {
685
+ "epoch": 3.77,
686
+ "learning_rate": 1e-05,
687
+ "loss": 0.0389,
688
+ "step": 2750
689
+ },
690
+ {
691
+ "epoch": 3.81,
692
+ "learning_rate": 1e-05,
693
+ "loss": 0.041,
694
+ "step": 2775
695
+ },
696
+ {
697
+ "epoch": 3.84,
698
+ "learning_rate": 1e-05,
699
+ "loss": 0.0394,
700
+ "step": 2800
701
+ },
702
+ {
703
+ "epoch": 3.88,
704
+ "learning_rate": 1e-05,
705
+ "loss": 0.0485,
706
+ "step": 2825
707
+ },
708
+ {
709
+ "epoch": 3.91,
710
+ "learning_rate": 1e-05,
711
+ "loss": 0.0416,
712
+ "step": 2850
713
+ },
714
+ {
715
+ "epoch": 3.94,
716
+ "learning_rate": 1e-05,
717
+ "loss": 0.0501,
718
+ "step": 2875
719
+ },
720
+ {
721
+ "epoch": 3.98,
722
+ "learning_rate": 1e-05,
723
+ "loss": 0.0393,
724
+ "step": 2900
725
+ },
726
+ {
727
+ "epoch": 4.01,
728
+ "learning_rate": 1e-05,
729
+ "loss": 0.0306,
730
+ "step": 2925
731
+ },
732
+ {
733
+ "epoch": 4.05,
734
+ "learning_rate": 1e-05,
735
+ "loss": 0.0265,
736
+ "step": 2950
737
+ },
738
+ {
739
+ "epoch": 4.08,
740
+ "learning_rate": 1e-05,
741
+ "loss": 0.0223,
742
+ "step": 2975
743
+ },
744
+ {
745
+ "epoch": 4.12,
746
+ "learning_rate": 1e-05,
747
+ "loss": 0.0215,
748
+ "step": 3000
749
+ },
750
+ {
751
+ "epoch": 4.12,
752
+ "eval_cer": 7.079429983827164,
753
+ "eval_loss": 0.24198034405708313,
754
+ "eval_runtime": 393.3959,
755
+ "eval_samples_per_second": 1.932,
756
+ "eval_steps_per_second": 0.122,
757
+ "eval_wer": 17.98756798756799,
758
+ "step": 3000
759
  }
760
  ],
761
  "max_steps": 4000,
762
  "num_train_epochs": 6,
763
+ "total_flos": 1.384748184895488e+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 sha256:65503e2d287eeb93231cc3f6e123f111f05e00b5886775a96c9f0f3234a9cb60
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da96b2ae6e5559d7f78e7908472ddf37a9adc97bc0dfa1983148ab68e5b3eb9
3
  size 967102729
runs/Aug20_17-07-13_713cba38a708/events.out.tfevents.1692551245.713cba38a708.95.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7badd4eee194eccbbca23d4b453d756dca52d0772c6e2718bb059f9da62b8d29
3
- size 19119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:667db5d350222a235eac237786b548d21eb5511ddfd0c40292cd8517321f5b71
3
+ size 25764