elsayedissa
commited on
Commit
•
5cf3888
1
Parent(s):
7412490
Training in progress, step 3000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +254 -5
- pytorch_model.bin +1 -1
- runs/Jan28_23-42-14_gpu07.cyverse.org/events.out.tfevents.1674974582.gpu07.cyverse.org.94170.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12347192855
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43b529b6527a55ecb1b2908bd5bb21af352a338f256021a3435cb4e37cb0e7d9
|
3 |
size 12347192855
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6173655480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:754a96c8f6aa3da0eed380bf4de66f9ac5838d1ecc89aec3728052ea541b779a
|
3 |
size 6173655480
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a86cb34862aab94736a5ade9f79f8059219434eb9b4a3f6f63ad15faca3b737
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dbbd96826db496f861eb18e5267b27126c9f62d91eb523417dba169a922dd12
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c7ac18b548a5f57b43479491efeef75333701321d878addd7822f27ec30f6d9
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-japanese-24h/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -504,11 +504,260 @@
|
|
504 |
"eval_steps_per_second": 0.164,
|
505 |
"eval_wer": 0.7478299577119965,
|
506 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
507 |
}
|
508 |
],
|
509 |
"max_steps": 5000,
|
510 |
"num_train_epochs": 39,
|
511 |
-
"total_flos":
|
512 |
"trial_name": null,
|
513 |
"trial_params": null
|
514 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7431560204762965,
|
3 |
+
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-japanese-24h/checkpoint-3000",
|
4 |
+
"epoch": 22.900763358778626,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
504 |
"eval_steps_per_second": 0.164,
|
505 |
"eval_wer": 0.7478299577119965,
|
506 |
"step": 2000
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 15.46,
|
510 |
+
"learning_rate": 6.620000000000001e-06,
|
511 |
+
"loss": 0.0007,
|
512 |
+
"step": 2025
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 15.65,
|
516 |
+
"learning_rate": 6.564444444444446e-06,
|
517 |
+
"loss": 0.0006,
|
518 |
+
"step": 2050
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 15.84,
|
522 |
+
"learning_rate": 6.508888888888889e-06,
|
523 |
+
"loss": 0.0005,
|
524 |
+
"step": 2075
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 16.03,
|
528 |
+
"learning_rate": 6.453333333333334e-06,
|
529 |
+
"loss": 0.0005,
|
530 |
+
"step": 2100
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 16.22,
|
534 |
+
"learning_rate": 6.397777777777778e-06,
|
535 |
+
"loss": 0.0005,
|
536 |
+
"step": 2125
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 16.41,
|
540 |
+
"learning_rate": 6.342222222222223e-06,
|
541 |
+
"loss": 0.0005,
|
542 |
+
"step": 2150
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 16.6,
|
546 |
+
"learning_rate": 6.286666666666668e-06,
|
547 |
+
"loss": 0.0004,
|
548 |
+
"step": 2175
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 16.79,
|
552 |
+
"learning_rate": 6.231111111111111e-06,
|
553 |
+
"loss": 0.0004,
|
554 |
+
"step": 2200
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 16.98,
|
558 |
+
"learning_rate": 6.175555555555556e-06,
|
559 |
+
"loss": 0.0004,
|
560 |
+
"step": 2225
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 17.18,
|
564 |
+
"learning_rate": 6.120000000000001e-06,
|
565 |
+
"loss": 0.0004,
|
566 |
+
"step": 2250
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 17.37,
|
570 |
+
"learning_rate": 6.064444444444445e-06,
|
571 |
+
"loss": 0.0004,
|
572 |
+
"step": 2275
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 17.56,
|
576 |
+
"learning_rate": 6.00888888888889e-06,
|
577 |
+
"loss": 0.0004,
|
578 |
+
"step": 2300
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 17.75,
|
582 |
+
"learning_rate": 5.9533333333333345e-06,
|
583 |
+
"loss": 0.0004,
|
584 |
+
"step": 2325
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 17.94,
|
588 |
+
"learning_rate": 5.897777777777778e-06,
|
589 |
+
"loss": 0.0004,
|
590 |
+
"step": 2350
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 18.13,
|
594 |
+
"learning_rate": 5.8422222222222226e-06,
|
595 |
+
"loss": 0.0004,
|
596 |
+
"step": 2375
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 18.32,
|
600 |
+
"learning_rate": 5.7866666666666674e-06,
|
601 |
+
"loss": 0.0003,
|
602 |
+
"step": 2400
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 18.51,
|
606 |
+
"learning_rate": 5.7311111111111115e-06,
|
607 |
+
"loss": 0.0003,
|
608 |
+
"step": 2425
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 18.7,
|
612 |
+
"learning_rate": 5.675555555555556e-06,
|
613 |
+
"loss": 0.0003,
|
614 |
+
"step": 2450
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 18.89,
|
618 |
+
"learning_rate": 5.620000000000001e-06,
|
619 |
+
"loss": 0.0004,
|
620 |
+
"step": 2475
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 19.08,
|
624 |
+
"learning_rate": 5.5644444444444444e-06,
|
625 |
+
"loss": 0.0003,
|
626 |
+
"step": 2500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 19.27,
|
630 |
+
"learning_rate": 5.508888888888889e-06,
|
631 |
+
"loss": 0.0003,
|
632 |
+
"step": 2525
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 19.47,
|
636 |
+
"learning_rate": 5.453333333333334e-06,
|
637 |
+
"loss": 0.0003,
|
638 |
+
"step": 2550
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 19.66,
|
642 |
+
"learning_rate": 5.397777777777778e-06,
|
643 |
+
"loss": 0.0003,
|
644 |
+
"step": 2575
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 19.85,
|
648 |
+
"learning_rate": 5.342222222222223e-06,
|
649 |
+
"loss": 0.0003,
|
650 |
+
"step": 2600
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 20.04,
|
654 |
+
"learning_rate": 5.286666666666666e-06,
|
655 |
+
"loss": 0.0003,
|
656 |
+
"step": 2625
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 20.23,
|
660 |
+
"learning_rate": 5.231111111111111e-06,
|
661 |
+
"loss": 0.0003,
|
662 |
+
"step": 2650
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 20.42,
|
666 |
+
"learning_rate": 5.175555555555556e-06,
|
667 |
+
"loss": 0.0003,
|
668 |
+
"step": 2675
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 20.61,
|
672 |
+
"learning_rate": 5.12e-06,
|
673 |
+
"loss": 0.0003,
|
674 |
+
"step": 2700
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 20.8,
|
678 |
+
"learning_rate": 5.064444444444445e-06,
|
679 |
+
"loss": 0.0003,
|
680 |
+
"step": 2725
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 20.99,
|
684 |
+
"learning_rate": 5.00888888888889e-06,
|
685 |
+
"loss": 0.0003,
|
686 |
+
"step": 2750
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 21.18,
|
690 |
+
"learning_rate": 4.953333333333334e-06,
|
691 |
+
"loss": 0.0003,
|
692 |
+
"step": 2775
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 21.37,
|
696 |
+
"learning_rate": 4.897777777777778e-06,
|
697 |
+
"loss": 0.0003,
|
698 |
+
"step": 2800
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 21.56,
|
702 |
+
"learning_rate": 4.842222222222223e-06,
|
703 |
+
"loss": 0.0003,
|
704 |
+
"step": 2825
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 21.76,
|
708 |
+
"learning_rate": 4.786666666666667e-06,
|
709 |
+
"loss": 0.0003,
|
710 |
+
"step": 2850
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 21.95,
|
714 |
+
"learning_rate": 4.731111111111112e-06,
|
715 |
+
"loss": 0.0003,
|
716 |
+
"step": 2875
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 22.14,
|
720 |
+
"learning_rate": 4.675555555555556e-06,
|
721 |
+
"loss": 0.0003,
|
722 |
+
"step": 2900
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 22.33,
|
726 |
+
"learning_rate": 4.620000000000001e-06,
|
727 |
+
"loss": 0.0002,
|
728 |
+
"step": 2925
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 22.52,
|
732 |
+
"learning_rate": 4.564444444444445e-06,
|
733 |
+
"loss": 0.0002,
|
734 |
+
"step": 2950
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 22.71,
|
738 |
+
"learning_rate": 4.50888888888889e-06,
|
739 |
+
"loss": 0.0002,
|
740 |
+
"step": 2975
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 22.9,
|
744 |
+
"learning_rate": 4.453333333333334e-06,
|
745 |
+
"loss": 0.0003,
|
746 |
+
"step": 3000
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 22.9,
|
750 |
+
"eval_loss": 0.3937181532382965,
|
751 |
+
"eval_runtime": 1714.4778,
|
752 |
+
"eval_samples_per_second": 2.616,
|
753 |
+
"eval_steps_per_second": 0.164,
|
754 |
+
"eval_wer": 0.7431560204762965,
|
755 |
+
"step": 3000
|
756 |
}
|
757 |
],
|
758 |
"max_steps": 5000,
|
759 |
"num_train_epochs": 39,
|
760 |
+
"total_flos": 3.16373713809408e+20,
|
761 |
"trial_name": null,
|
762 |
"trial_params": null
|
763 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6173655480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:754a96c8f6aa3da0eed380bf4de66f9ac5838d1ecc89aec3728052ea541b779a
|
3 |
size 6173655480
|
runs/Jan28_23-42-14_gpu07.cyverse.org/events.out.tfevents.1674974582.gpu07.cyverse.org.94170.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c793cf7ac753d6045f2e0aff18181a1aa802d07daa76157c9eea31d897ec8e
|
3 |
+
size 24198
|