elsayedissa
commited on
Commit
•
214ecc9
1
Parent(s):
38f73f2
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 +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +254 -5
- pytorch_model.bin +1 -1
- runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 +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 2524414853
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d663f5f146d9e8f297bc578554bd7042672ed6047e1f155a177a7a2f277f077
|
3 |
size 2524414853
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262229869
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5258a25b9c74c3d9d5b375fb7669f896562d55ca5085300312146eb59f59737e
|
3 |
size 1262229869
|
last-checkpoint/rng_state.pth
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:cfa739ad5003b32689d1be9cfc41058f1ee1620e0b3d1c54f70c056c125f5219
|
3 |
+
size 14575
|
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 sha256:52b81cce263ca1a87119e3db86ee6c4352a4b53f0c600c4f6eca5921e2e70890
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/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": 1.176,
|
505 |
"eval_wer": 0.08071266292000479,
|
506 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
507 |
}
|
508 |
],
|
509 |
"max_steps": 10000,
|
510 |
"num_train_epochs": 89,
|
511 |
-
"total_flos":
|
512 |
"trial_name": null,
|
513 |
"trial_params": null
|
514 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.0693531029534856,
|
3 |
+
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-3000",
|
4 |
+
"epoch": 26.548672566371682,
|
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": 1.176,
|
505 |
"eval_wer": 0.08071266292000479,
|
506 |
"step": 2000
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 17.92,
|
510 |
+
"learning_rate": 0.00025184210526315784,
|
511 |
+
"loss": 0.0406,
|
512 |
+
"step": 2025
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 18.14,
|
516 |
+
"learning_rate": 0.0002510526315789474,
|
517 |
+
"loss": 0.0322,
|
518 |
+
"step": 2050
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 18.36,
|
522 |
+
"learning_rate": 0.0002502631578947368,
|
523 |
+
"loss": 0.0393,
|
524 |
+
"step": 2075
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 18.58,
|
528 |
+
"learning_rate": 0.0002494736842105263,
|
529 |
+
"loss": 0.0438,
|
530 |
+
"step": 2100
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 18.81,
|
534 |
+
"learning_rate": 0.0002486842105263158,
|
535 |
+
"loss": 0.0372,
|
536 |
+
"step": 2125
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 19.03,
|
540 |
+
"learning_rate": 0.00024789473684210526,
|
541 |
+
"loss": 0.0335,
|
542 |
+
"step": 2150
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 19.25,
|
546 |
+
"learning_rate": 0.00024710526315789474,
|
547 |
+
"loss": 0.0327,
|
548 |
+
"step": 2175
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 19.47,
|
552 |
+
"learning_rate": 0.00024631578947368417,
|
553 |
+
"loss": 0.0307,
|
554 |
+
"step": 2200
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 19.69,
|
558 |
+
"learning_rate": 0.00024552631578947365,
|
559 |
+
"loss": 0.0374,
|
560 |
+
"step": 2225
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 19.91,
|
564 |
+
"learning_rate": 0.00024473684210526314,
|
565 |
+
"loss": 0.035,
|
566 |
+
"step": 2250
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 20.13,
|
570 |
+
"learning_rate": 0.0002439473684210526,
|
571 |
+
"loss": 0.0336,
|
572 |
+
"step": 2275
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 20.35,
|
576 |
+
"learning_rate": 0.00024315789473684207,
|
577 |
+
"loss": 0.0426,
|
578 |
+
"step": 2300
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 20.58,
|
582 |
+
"learning_rate": 0.00024236842105263156,
|
583 |
+
"loss": 0.0375,
|
584 |
+
"step": 2325
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 20.8,
|
588 |
+
"learning_rate": 0.000241578947368421,
|
589 |
+
"loss": 0.0352,
|
590 |
+
"step": 2350
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 21.02,
|
594 |
+
"learning_rate": 0.00024078947368421052,
|
595 |
+
"loss": 0.0319,
|
596 |
+
"step": 2375
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 21.24,
|
600 |
+
"learning_rate": 0.00023999999999999998,
|
601 |
+
"loss": 0.0339,
|
602 |
+
"step": 2400
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 21.46,
|
606 |
+
"learning_rate": 0.00023921052631578946,
|
607 |
+
"loss": 0.0335,
|
608 |
+
"step": 2425
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 21.68,
|
612 |
+
"learning_rate": 0.00023842105263157895,
|
613 |
+
"loss": 0.0329,
|
614 |
+
"step": 2450
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 21.9,
|
618 |
+
"learning_rate": 0.0002376315789473684,
|
619 |
+
"loss": 0.0373,
|
620 |
+
"step": 2475
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 22.12,
|
624 |
+
"learning_rate": 0.00023684210526315788,
|
625 |
+
"loss": 0.0371,
|
626 |
+
"step": 2500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 22.35,
|
630 |
+
"learning_rate": 0.00023605263157894734,
|
631 |
+
"loss": 0.0273,
|
632 |
+
"step": 2525
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 22.57,
|
636 |
+
"learning_rate": 0.00023526315789473682,
|
637 |
+
"loss": 0.0361,
|
638 |
+
"step": 2550
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 22.79,
|
642 |
+
"learning_rate": 0.00023447368421052628,
|
643 |
+
"loss": 0.0367,
|
644 |
+
"step": 2575
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 23.01,
|
648 |
+
"learning_rate": 0.00023368421052631576,
|
649 |
+
"loss": 0.0374,
|
650 |
+
"step": 2600
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 23.23,
|
654 |
+
"learning_rate": 0.00023289473684210524,
|
655 |
+
"loss": 0.0264,
|
656 |
+
"step": 2625
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 23.45,
|
660 |
+
"learning_rate": 0.0002321052631578947,
|
661 |
+
"loss": 0.0331,
|
662 |
+
"step": 2650
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 23.67,
|
666 |
+
"learning_rate": 0.00023131578947368418,
|
667 |
+
"loss": 0.0407,
|
668 |
+
"step": 2675
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 23.89,
|
672 |
+
"learning_rate": 0.00023052631578947364,
|
673 |
+
"loss": 0.031,
|
674 |
+
"step": 2700
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 24.12,
|
678 |
+
"learning_rate": 0.00022973684210526315,
|
679 |
+
"loss": 0.0294,
|
680 |
+
"step": 2725
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 24.34,
|
684 |
+
"learning_rate": 0.00022894736842105263,
|
685 |
+
"loss": 0.0345,
|
686 |
+
"step": 2750
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 24.56,
|
690 |
+
"learning_rate": 0.0002281578947368421,
|
691 |
+
"loss": 0.027,
|
692 |
+
"step": 2775
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 24.78,
|
696 |
+
"learning_rate": 0.00022736842105263157,
|
697 |
+
"loss": 0.0241,
|
698 |
+
"step": 2800
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 25.0,
|
702 |
+
"learning_rate": 0.00022657894736842103,
|
703 |
+
"loss": 0.0304,
|
704 |
+
"step": 2825
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 25.22,
|
708 |
+
"learning_rate": 0.0002257894736842105,
|
709 |
+
"loss": 0.026,
|
710 |
+
"step": 2850
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 25.44,
|
714 |
+
"learning_rate": 0.000225,
|
715 |
+
"loss": 0.0325,
|
716 |
+
"step": 2875
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 25.66,
|
720 |
+
"learning_rate": 0.00022421052631578945,
|
721 |
+
"loss": 0.0374,
|
722 |
+
"step": 2900
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 25.88,
|
726 |
+
"learning_rate": 0.00022342105263157893,
|
727 |
+
"loss": 0.036,
|
728 |
+
"step": 2925
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 26.11,
|
732 |
+
"learning_rate": 0.0002226315789473684,
|
733 |
+
"loss": 0.0339,
|
734 |
+
"step": 2950
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 26.33,
|
738 |
+
"learning_rate": 0.00022184210526315787,
|
739 |
+
"loss": 0.0312,
|
740 |
+
"step": 2975
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 26.55,
|
744 |
+
"learning_rate": 0.00022105263157894733,
|
745 |
+
"loss": 0.0285,
|
746 |
+
"step": 3000
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 26.55,
|
750 |
+
"eval_loss": 0.22891539335250854,
|
751 |
+
"eval_runtime": 10.8646,
|
752 |
+
"eval_samples_per_second": 9.204,
|
753 |
+
"eval_steps_per_second": 1.197,
|
754 |
+
"eval_wer": 0.0693531029534856,
|
755 |
+
"step": 3000
|
756 |
}
|
757 |
],
|
758 |
"max_steps": 10000,
|
759 |
"num_train_epochs": 89,
|
760 |
+
"total_flos": 1.1850399847250571e+19,
|
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 1262229869
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5258a25b9c74c3d9d5b375fb7669f896562d55ca5085300312146eb59f59737e
|
3 |
size 1262229869
|
runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0
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 sha256:45e79a3318aae7f7e3793092d9c72a265dbb46e733875d98b4217ffa7542a1bb
|
3 |
+
size 25176
|