Training in progress, step 3000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13f8f2b474fa2b6284d59b3ee18ee12fa7507a2433ee4f0ba97cf2ecdc3c35c1
|
| 3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1925064044
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0ef1069b97fed6b2293215f8c989c7a0784d96706a1ee18b58bab201b4fc6d0
|
| 3 |
size 1925064044
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27cdf2edd39f57a70573d9ff0027b58248741fcc4a77b968063bd6a9c61fd866
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17af6a83bb1cb19cd0edadcdd8667775ae13ecbc6438dd8bbc5fbd929a74874b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 51.77491557370612,
|
| 3 |
"best_model_checkpoint": "./whisper-small-taiwanese/checkpoint-2000",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -585,6 +585,295 @@
|
|
| 585 |
"eval_samples_per_second": 2.264,
|
| 586 |
"eval_steps_per_second": 0.283,
|
| 587 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 588 |
}
|
| 589 |
],
|
| 590 |
"logging_steps": 25,
|
|
@@ -592,7 +881,7 @@
|
|
| 592 |
"num_input_tokens_seen": 0,
|
| 593 |
"num_train_epochs": 2,
|
| 594 |
"save_steps": 1000,
|
| 595 |
-
"total_flos":
|
| 596 |
"train_batch_size": 8,
|
| 597 |
"trial_name": null,
|
| 598 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 51.77491557370612,
|
| 3 |
"best_model_checkpoint": "./whisper-small-taiwanese/checkpoint-2000",
|
| 4 |
+
"epoch": 1.2,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 585 |
"eval_samples_per_second": 2.264,
|
| 586 |
"eval_steps_per_second": 0.283,
|
| 587 |
"step": 2000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.81,
|
| 591 |
+
"grad_norm": 15.01921272277832,
|
| 592 |
+
"learning_rate": 6.6111111111111115e-06,
|
| 593 |
+
"loss": 1.0203,
|
| 594 |
+
"step": 2025
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.82,
|
| 598 |
+
"grad_norm": 12.810806274414062,
|
| 599 |
+
"learning_rate": 6.555555555555556e-06,
|
| 600 |
+
"loss": 1.0426,
|
| 601 |
+
"step": 2050
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.83,
|
| 605 |
+
"grad_norm": 12.653311729431152,
|
| 606 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 607 |
+
"loss": 1.0451,
|
| 608 |
+
"step": 2075
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.84,
|
| 612 |
+
"grad_norm": 14.353548049926758,
|
| 613 |
+
"learning_rate": 6.444444444444445e-06,
|
| 614 |
+
"loss": 1.0853,
|
| 615 |
+
"step": 2100
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.85,
|
| 619 |
+
"grad_norm": 12.075662612915039,
|
| 620 |
+
"learning_rate": 6.3888888888888885e-06,
|
| 621 |
+
"loss": 1.0124,
|
| 622 |
+
"step": 2125
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.86,
|
| 626 |
+
"grad_norm": 14.976198196411133,
|
| 627 |
+
"learning_rate": 6.333333333333333e-06,
|
| 628 |
+
"loss": 1.0461,
|
| 629 |
+
"step": 2150
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.87,
|
| 633 |
+
"grad_norm": 12.702341079711914,
|
| 634 |
+
"learning_rate": 6.277777777777778e-06,
|
| 635 |
+
"loss": 1.0319,
|
| 636 |
+
"step": 2175
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.88,
|
| 640 |
+
"grad_norm": 14.232624053955078,
|
| 641 |
+
"learning_rate": 6.222222222222223e-06,
|
| 642 |
+
"loss": 1.0174,
|
| 643 |
+
"step": 2200
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.89,
|
| 647 |
+
"grad_norm": 12.84585189819336,
|
| 648 |
+
"learning_rate": 6.166666666666667e-06,
|
| 649 |
+
"loss": 1.0275,
|
| 650 |
+
"step": 2225
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.9,
|
| 654 |
+
"grad_norm": 17.438783645629883,
|
| 655 |
+
"learning_rate": 6.111111111111112e-06,
|
| 656 |
+
"loss": 0.9808,
|
| 657 |
+
"step": 2250
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.91,
|
| 661 |
+
"grad_norm": 13.450716018676758,
|
| 662 |
+
"learning_rate": 6.055555555555555e-06,
|
| 663 |
+
"loss": 1.0239,
|
| 664 |
+
"step": 2275
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.92,
|
| 668 |
+
"grad_norm": 14.077709197998047,
|
| 669 |
+
"learning_rate": 6e-06,
|
| 670 |
+
"loss": 1.0151,
|
| 671 |
+
"step": 2300
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.93,
|
| 675 |
+
"grad_norm": 10.755902290344238,
|
| 676 |
+
"learning_rate": 5.944444444444445e-06,
|
| 677 |
+
"loss": 0.9994,
|
| 678 |
+
"step": 2325
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.94,
|
| 682 |
+
"grad_norm": 13.025961875915527,
|
| 683 |
+
"learning_rate": 5.88888888888889e-06,
|
| 684 |
+
"loss": 1.0136,
|
| 685 |
+
"step": 2350
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.95,
|
| 689 |
+
"grad_norm": 13.124420166015625,
|
| 690 |
+
"learning_rate": 5.833333333333334e-06,
|
| 691 |
+
"loss": 0.9732,
|
| 692 |
+
"step": 2375
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.96,
|
| 696 |
+
"grad_norm": 13.470574378967285,
|
| 697 |
+
"learning_rate": 5.777777777777778e-06,
|
| 698 |
+
"loss": 0.9919,
|
| 699 |
+
"step": 2400
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.97,
|
| 703 |
+
"grad_norm": 13.073882102966309,
|
| 704 |
+
"learning_rate": 5.722222222222222e-06,
|
| 705 |
+
"loss": 0.9791,
|
| 706 |
+
"step": 2425
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.98,
|
| 710 |
+
"grad_norm": 12.156904220581055,
|
| 711 |
+
"learning_rate": 5.666666666666667e-06,
|
| 712 |
+
"loss": 0.9761,
|
| 713 |
+
"step": 2450
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.99,
|
| 717 |
+
"grad_norm": 14.560174942016602,
|
| 718 |
+
"learning_rate": 5.611111111111112e-06,
|
| 719 |
+
"loss": 0.9478,
|
| 720 |
+
"step": 2475
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.0,
|
| 724 |
+
"grad_norm": 13.365988731384277,
|
| 725 |
+
"learning_rate": 5.555555555555557e-06,
|
| 726 |
+
"loss": 0.9439,
|
| 727 |
+
"step": 2500
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.01,
|
| 731 |
+
"grad_norm": 11.116703987121582,
|
| 732 |
+
"learning_rate": 5.500000000000001e-06,
|
| 733 |
+
"loss": 0.8144,
|
| 734 |
+
"step": 2525
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.02,
|
| 738 |
+
"grad_norm": 11.22291088104248,
|
| 739 |
+
"learning_rate": 5.444444444444445e-06,
|
| 740 |
+
"loss": 0.7626,
|
| 741 |
+
"step": 2550
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.03,
|
| 745 |
+
"grad_norm": 10.895951271057129,
|
| 746 |
+
"learning_rate": 5.388888888888889e-06,
|
| 747 |
+
"loss": 0.7443,
|
| 748 |
+
"step": 2575
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.04,
|
| 752 |
+
"grad_norm": 10.497587203979492,
|
| 753 |
+
"learning_rate": 5.333333333333334e-06,
|
| 754 |
+
"loss": 0.7348,
|
| 755 |
+
"step": 2600
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.05,
|
| 759 |
+
"grad_norm": 10.018071174621582,
|
| 760 |
+
"learning_rate": 5.2777777777777785e-06,
|
| 761 |
+
"loss": 0.7096,
|
| 762 |
+
"step": 2625
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.06,
|
| 766 |
+
"grad_norm": 11.595548629760742,
|
| 767 |
+
"learning_rate": 5.2222222222222226e-06,
|
| 768 |
+
"loss": 0.7527,
|
| 769 |
+
"step": 2650
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.07,
|
| 773 |
+
"grad_norm": 9.90001106262207,
|
| 774 |
+
"learning_rate": 5.1666666666666675e-06,
|
| 775 |
+
"loss": 0.7502,
|
| 776 |
+
"step": 2675
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.08,
|
| 780 |
+
"grad_norm": 14.49976921081543,
|
| 781 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 782 |
+
"loss": 0.7253,
|
| 783 |
+
"step": 2700
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.09,
|
| 787 |
+
"grad_norm": 10.992387771606445,
|
| 788 |
+
"learning_rate": 5.0555555555555555e-06,
|
| 789 |
+
"loss": 0.759,
|
| 790 |
+
"step": 2725
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.1,
|
| 794 |
+
"grad_norm": 11.267956733703613,
|
| 795 |
+
"learning_rate": 5e-06,
|
| 796 |
+
"loss": 0.7174,
|
| 797 |
+
"step": 2750
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.11,
|
| 801 |
+
"grad_norm": 12.558463096618652,
|
| 802 |
+
"learning_rate": 4.944444444444445e-06,
|
| 803 |
+
"loss": 0.7936,
|
| 804 |
+
"step": 2775
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.12,
|
| 808 |
+
"grad_norm": 10.136383056640625,
|
| 809 |
+
"learning_rate": 4.888888888888889e-06,
|
| 810 |
+
"loss": 0.7573,
|
| 811 |
+
"step": 2800
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.13,
|
| 815 |
+
"grad_norm": 10.183345794677734,
|
| 816 |
+
"learning_rate": 4.833333333333333e-06,
|
| 817 |
+
"loss": 0.7704,
|
| 818 |
+
"step": 2825
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.1400000000000001,
|
| 822 |
+
"grad_norm": 10.488049507141113,
|
| 823 |
+
"learning_rate": 4.777777777777778e-06,
|
| 824 |
+
"loss": 0.7343,
|
| 825 |
+
"step": 2850
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.15,
|
| 829 |
+
"grad_norm": 12.607866287231445,
|
| 830 |
+
"learning_rate": 4.722222222222222e-06,
|
| 831 |
+
"loss": 0.7247,
|
| 832 |
+
"step": 2875
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.16,
|
| 836 |
+
"grad_norm": 10.342514991760254,
|
| 837 |
+
"learning_rate": 4.666666666666667e-06,
|
| 838 |
+
"loss": 0.7618,
|
| 839 |
+
"step": 2900
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.17,
|
| 843 |
+
"grad_norm": 10.273557662963867,
|
| 844 |
+
"learning_rate": 4.611111111111112e-06,
|
| 845 |
+
"loss": 0.805,
|
| 846 |
+
"step": 2925
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.18,
|
| 850 |
+
"grad_norm": 11.328307151794434,
|
| 851 |
+
"learning_rate": 4.555555555555556e-06,
|
| 852 |
+
"loss": 0.6998,
|
| 853 |
+
"step": 2950
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.19,
|
| 857 |
+
"grad_norm": 13.699926376342773,
|
| 858 |
+
"learning_rate": 4.5e-06,
|
| 859 |
+
"loss": 0.7924,
|
| 860 |
+
"step": 2975
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.2,
|
| 864 |
+
"grad_norm": 10.797248840332031,
|
| 865 |
+
"learning_rate": 4.444444444444444e-06,
|
| 866 |
+
"loss": 0.7837,
|
| 867 |
+
"step": 3000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.2,
|
| 871 |
+
"eval_cer": 54.1977538679023,
|
| 872 |
+
"eval_loss": 0.9572013020515442,
|
| 873 |
+
"eval_runtime": 1756.4904,
|
| 874 |
+
"eval_samples_per_second": 2.241,
|
| 875 |
+
"eval_steps_per_second": 0.28,
|
| 876 |
+
"step": 3000
|
| 877 |
}
|
| 878 |
],
|
| 879 |
"logging_steps": 25,
|
|
|
|
| 881 |
"num_input_tokens_seen": 0,
|
| 882 |
"num_train_epochs": 2,
|
| 883 |
"save_steps": 1000,
|
| 884 |
+
"total_flos": 1.385209921536e+19,
|
| 885 |
"train_batch_size": 8,
|
| 886 |
"trial_name": null,
|
| 887 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c3e5a033637a03b3c288e7f28b5f4eb2b2c22389eb467e77f64839f3948fe5f
|
| 3 |
size 5176
|