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 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98a40d1f879e92b1250c6ce6814b61dc6d1fca0c70ebd417d8ead38a7dce3f4e
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440235130
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77c69b1b51235eeb3ea13d92f8c6dcf9f655d0d2d123b4b47cd7aef8a879fb06
|
| 3 |
size 440235130
|
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 sha256:4bf29b98658cbaec0d62f4ead6c42ba9b88966fa3b2ce6348ec1b4bf21ab3255
|
| 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 sha256:767f5d686c361afdbfc4427661911446768c0b14e80b00b46139bfc4c493d9cb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./iteboshi_temp/checkpoint-
|
| 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,
|
|
@@ -587,6 +587,296 @@
|
|
| 587 |
"eval_steps_per_second": 1.195,
|
| 588 |
"eval_wer": 97.35030645921735,
|
| 589 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 590 |
}
|
| 591 |
],
|
| 592 |
"logging_steps": 25,
|
|
@@ -606,7 +896,7 @@
|
|
| 606 |
"attributes": {}
|
| 607 |
}
|
| 608 |
},
|
| 609 |
-
"total_flos":
|
| 610 |
"train_batch_size": 12,
|
| 611 |
"trial_name": null,
|
| 612 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 96.64309288071664,
|
| 3 |
+
"best_model_checkpoint": "./iteboshi_temp/checkpoint-3000",
|
| 4 |
+
"epoch": 4.951279933938894,
|
| 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,
|
|
|
|
| 587 |
"eval_steps_per_second": 1.195,
|
| 588 |
"eval_wer": 97.35030645921735,
|
| 589 |
"step": 2000
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.34186622625929,
|
| 593 |
+
"grad_norm": 7.776848793029785,
|
| 594 |
+
"learning_rate": 1.6791578947368425e-05,
|
| 595 |
+
"loss": 0.9834,
|
| 596 |
+
"step": 2025
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.383154417836499,
|
| 600 |
+
"grad_norm": 8.306714057922363,
|
| 601 |
+
"learning_rate": 1.6738947368421055e-05,
|
| 602 |
+
"loss": 1.0036,
|
| 603 |
+
"step": 2050
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.424442609413708,
|
| 607 |
+
"grad_norm": 9.474985122680664,
|
| 608 |
+
"learning_rate": 1.6686315789473685e-05,
|
| 609 |
+
"loss": 1.0534,
|
| 610 |
+
"step": 2075
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.4657308009909165,
|
| 614 |
+
"grad_norm": 7.486320972442627,
|
| 615 |
+
"learning_rate": 1.6633684210526318e-05,
|
| 616 |
+
"loss": 0.9673,
|
| 617 |
+
"step": 2100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.5070189925681254,
|
| 621 |
+
"grad_norm": 8.373710632324219,
|
| 622 |
+
"learning_rate": 1.6581052631578948e-05,
|
| 623 |
+
"loss": 1.0009,
|
| 624 |
+
"step": 2125
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.5483071841453344,
|
| 628 |
+
"grad_norm": 8.073158264160156,
|
| 629 |
+
"learning_rate": 1.652842105263158e-05,
|
| 630 |
+
"loss": 1.0142,
|
| 631 |
+
"step": 2150
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 3.5895953757225434,
|
| 635 |
+
"grad_norm": 8.070113182067871,
|
| 636 |
+
"learning_rate": 1.647578947368421e-05,
|
| 637 |
+
"loss": 0.9742,
|
| 638 |
+
"step": 2175
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.6308835672997524,
|
| 642 |
+
"grad_norm": 7.891678333282471,
|
| 643 |
+
"learning_rate": 1.6423157894736845e-05,
|
| 644 |
+
"loss": 1.0163,
|
| 645 |
+
"step": 2200
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.6721717588769613,
|
| 649 |
+
"grad_norm": 7.933286666870117,
|
| 650 |
+
"learning_rate": 1.6370526315789475e-05,
|
| 651 |
+
"loss": 0.9442,
|
| 652 |
+
"step": 2225
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.71345995045417,
|
| 656 |
+
"grad_norm": 8.791912078857422,
|
| 657 |
+
"learning_rate": 1.6317894736842105e-05,
|
| 658 |
+
"loss": 0.9295,
|
| 659 |
+
"step": 2250
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.754748142031379,
|
| 663 |
+
"grad_norm": 7.6395583152771,
|
| 664 |
+
"learning_rate": 1.6265263157894738e-05,
|
| 665 |
+
"loss": 0.9328,
|
| 666 |
+
"step": 2275
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.796036333608588,
|
| 670 |
+
"grad_norm": 8.580839157104492,
|
| 671 |
+
"learning_rate": 1.6212631578947368e-05,
|
| 672 |
+
"loss": 0.9779,
|
| 673 |
+
"step": 2300
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 3.837324525185797,
|
| 677 |
+
"grad_norm": 8.464973449707031,
|
| 678 |
+
"learning_rate": 1.616e-05,
|
| 679 |
+
"loss": 0.923,
|
| 680 |
+
"step": 2325
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.878612716763006,
|
| 684 |
+
"grad_norm": 8.684146881103516,
|
| 685 |
+
"learning_rate": 1.6107368421052634e-05,
|
| 686 |
+
"loss": 0.9842,
|
| 687 |
+
"step": 2350
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.9199009083402148,
|
| 691 |
+
"grad_norm": 8.286194801330566,
|
| 692 |
+
"learning_rate": 1.6054736842105264e-05,
|
| 693 |
+
"loss": 0.9283,
|
| 694 |
+
"step": 2375
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 3.9611890999174237,
|
| 698 |
+
"grad_norm": 8.621734619140625,
|
| 699 |
+
"learning_rate": 1.6002105263157898e-05,
|
| 700 |
+
"loss": 0.9424,
|
| 701 |
+
"step": 2400
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 4.001651527663088,
|
| 705 |
+
"grad_norm": 7.654041767120361,
|
| 706 |
+
"learning_rate": 1.5949473684210528e-05,
|
| 707 |
+
"loss": 0.9083,
|
| 708 |
+
"step": 2425
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 4.042939719240297,
|
| 712 |
+
"grad_norm": 8.66199016571045,
|
| 713 |
+
"learning_rate": 1.589684210526316e-05,
|
| 714 |
+
"loss": 0.8082,
|
| 715 |
+
"step": 2450
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 4.084227910817506,
|
| 719 |
+
"grad_norm": 7.401526927947998,
|
| 720 |
+
"learning_rate": 1.584421052631579e-05,
|
| 721 |
+
"loss": 0.7986,
|
| 722 |
+
"step": 2475
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 4.125516102394715,
|
| 726 |
+
"grad_norm": 6.765837669372559,
|
| 727 |
+
"learning_rate": 1.579157894736842e-05,
|
| 728 |
+
"loss": 0.8111,
|
| 729 |
+
"step": 2500
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 4.166804293971924,
|
| 733 |
+
"grad_norm": 7.28730583190918,
|
| 734 |
+
"learning_rate": 1.5738947368421054e-05,
|
| 735 |
+
"loss": 0.8089,
|
| 736 |
+
"step": 2525
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 4.208092485549133,
|
| 740 |
+
"grad_norm": 7.018956661224365,
|
| 741 |
+
"learning_rate": 1.5686315789473684e-05,
|
| 742 |
+
"loss": 0.7773,
|
| 743 |
+
"step": 2550
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 4.249380677126342,
|
| 747 |
+
"grad_norm": 8.369226455688477,
|
| 748 |
+
"learning_rate": 1.5633684210526318e-05,
|
| 749 |
+
"loss": 0.7895,
|
| 750 |
+
"step": 2575
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 4.290668868703551,
|
| 754 |
+
"grad_norm": 8.268858909606934,
|
| 755 |
+
"learning_rate": 1.5581052631578947e-05,
|
| 756 |
+
"loss": 0.857,
|
| 757 |
+
"step": 2600
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 4.33195706028076,
|
| 761 |
+
"grad_norm": 7.69369649887085,
|
| 762 |
+
"learning_rate": 1.552842105263158e-05,
|
| 763 |
+
"loss": 0.807,
|
| 764 |
+
"step": 2625
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 4.373245251857969,
|
| 768 |
+
"grad_norm": 8.12571907043457,
|
| 769 |
+
"learning_rate": 1.547578947368421e-05,
|
| 770 |
+
"loss": 0.8066,
|
| 771 |
+
"step": 2650
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 4.414533443435178,
|
| 775 |
+
"grad_norm": 9.947578430175781,
|
| 776 |
+
"learning_rate": 1.5423157894736844e-05,
|
| 777 |
+
"loss": 0.8245,
|
| 778 |
+
"step": 2675
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 4.455821635012386,
|
| 782 |
+
"grad_norm": 7.1731791496276855,
|
| 783 |
+
"learning_rate": 1.5370526315789477e-05,
|
| 784 |
+
"loss": 0.809,
|
| 785 |
+
"step": 2700
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 4.497109826589595,
|
| 789 |
+
"grad_norm": 8.121570587158203,
|
| 790 |
+
"learning_rate": 1.5317894736842107e-05,
|
| 791 |
+
"loss": 0.8382,
|
| 792 |
+
"step": 2725
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 4.538398018166804,
|
| 796 |
+
"grad_norm": 8.422553062438965,
|
| 797 |
+
"learning_rate": 1.5265263157894737e-05,
|
| 798 |
+
"loss": 0.8017,
|
| 799 |
+
"step": 2750
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 4.579686209744013,
|
| 803 |
+
"grad_norm": 9.263009071350098,
|
| 804 |
+
"learning_rate": 1.521263157894737e-05,
|
| 805 |
+
"loss": 0.805,
|
| 806 |
+
"step": 2775
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.620974401321222,
|
| 810 |
+
"grad_norm": 8.761811256408691,
|
| 811 |
+
"learning_rate": 1.516e-05,
|
| 812 |
+
"loss": 0.7896,
|
| 813 |
+
"step": 2800
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.662262592898431,
|
| 817 |
+
"grad_norm": 7.018781661987305,
|
| 818 |
+
"learning_rate": 1.5107368421052632e-05,
|
| 819 |
+
"loss": 0.764,
|
| 820 |
+
"step": 2825
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 4.70355078447564,
|
| 824 |
+
"grad_norm": 8.710026741027832,
|
| 825 |
+
"learning_rate": 1.5054736842105264e-05,
|
| 826 |
+
"loss": 0.7673,
|
| 827 |
+
"step": 2850
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 4.744838976052849,
|
| 831 |
+
"grad_norm": 7.182971954345703,
|
| 832 |
+
"learning_rate": 1.5002105263157895e-05,
|
| 833 |
+
"loss": 0.7649,
|
| 834 |
+
"step": 2875
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 4.786127167630058,
|
| 838 |
+
"grad_norm": 8.922381401062012,
|
| 839 |
+
"learning_rate": 1.4949473684210527e-05,
|
| 840 |
+
"loss": 0.8047,
|
| 841 |
+
"step": 2900
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 4.827415359207267,
|
| 845 |
+
"grad_norm": 7.456427097320557,
|
| 846 |
+
"learning_rate": 1.4896842105263159e-05,
|
| 847 |
+
"loss": 0.7793,
|
| 848 |
+
"step": 2925
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.868703550784476,
|
| 852 |
+
"grad_norm": 8.16557502746582,
|
| 853 |
+
"learning_rate": 1.484421052631579e-05,
|
| 854 |
+
"loss": 0.7642,
|
| 855 |
+
"step": 2950
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 4.909991742361685,
|
| 859 |
+
"grad_norm": 7.600188255310059,
|
| 860 |
+
"learning_rate": 1.4791578947368422e-05,
|
| 861 |
+
"loss": 0.7719,
|
| 862 |
+
"step": 2975
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 4.951279933938894,
|
| 866 |
+
"grad_norm": 7.850863456726074,
|
| 867 |
+
"learning_rate": 1.4738947368421055e-05,
|
| 868 |
+
"loss": 0.7577,
|
| 869 |
+
"step": 3000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 4.951279933938894,
|
| 873 |
+
"eval_cer": 53.34678390058808,
|
| 874 |
+
"eval_loss": 1.1084543466567993,
|
| 875 |
+
"eval_runtime": 754.0137,
|
| 876 |
+
"eval_samples_per_second": 14.033,
|
| 877 |
+
"eval_steps_per_second": 1.17,
|
| 878 |
+
"eval_wer": 96.64309288071664,
|
| 879 |
+
"step": 3000
|
| 880 |
}
|
| 881 |
],
|
| 882 |
"logging_steps": 25,
|
|
|
|
| 896 |
"attributes": {}
|
| 897 |
}
|
| 898 |
},
|
| 899 |
+
"total_flos": 5.84849320574976e+18,
|
| 900 |
"train_batch_size": 12,
|
| 901 |
"trial_name": null,
|
| 902 |
"trial_params": null
|