Training in progress, epoch 99, 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 56862772
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:594ed2c8f0bb4f3ff612a4d6690cd0ea9d181c24a0784d1d908297ba826b6170
|
| 3 |
size 56862772
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 113744007
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd80a819cfcb97bd05ace5efd7019407db4c099d4f769f4ba75c086a7ef96d8c
|
| 3 |
size 113744007
|
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 sha256:9688ecbaaabe6dd2631b971e0ac049ec8c0a81e254a5a8c4146f3739c589121a
|
| 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 sha256:08ca5b03dc7d99ca80c2974df07874d742f8195d77d13c5aa897314a6ac0e7cf
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 19,
|
| 3 |
"best_metric": 0.07475842535495758,
|
| 4 |
"best_model_checkpoint": "./results/checkpoint-19",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -570,6 +570,299 @@
|
|
| 570 |
"eval_samples_per_second": 617.163,
|
| 571 |
"eval_steps_per_second": 123.433,
|
| 572 |
"step": 65
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 573 |
}
|
| 574 |
],
|
| 575 |
"logging_steps": 10,
|
|
|
|
| 2 |
"best_global_step": 19,
|
| 3 |
"best_metric": 0.07475842535495758,
|
| 4 |
"best_model_checkpoint": "./results/checkpoint-19",
|
| 5 |
+
"epoch": 99.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 99,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 570 |
"eval_samples_per_second": 617.163,
|
| 571 |
"eval_steps_per_second": 123.433,
|
| 572 |
"step": 65
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 66.0,
|
| 576 |
+
"eval_loss": 0.1179947480559349,
|
| 577 |
+
"eval_runtime": 0.0163,
|
| 578 |
+
"eval_samples_per_second": 614.946,
|
| 579 |
+
"eval_steps_per_second": 122.989,
|
| 580 |
+
"step": 66
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 67.0,
|
| 584 |
+
"eval_loss": 0.07585181295871735,
|
| 585 |
+
"eval_runtime": 0.0255,
|
| 586 |
+
"eval_samples_per_second": 391.574,
|
| 587 |
+
"eval_steps_per_second": 78.315,
|
| 588 |
+
"step": 67
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 68.0,
|
| 592 |
+
"eval_loss": 0.09531017392873764,
|
| 593 |
+
"eval_runtime": 0.0206,
|
| 594 |
+
"eval_samples_per_second": 486.415,
|
| 595 |
+
"eval_steps_per_second": 97.283,
|
| 596 |
+
"step": 68
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 69.0,
|
| 600 |
+
"eval_loss": 0.14820639789104462,
|
| 601 |
+
"eval_runtime": 0.0208,
|
| 602 |
+
"eval_samples_per_second": 480.227,
|
| 603 |
+
"eval_steps_per_second": 96.045,
|
| 604 |
+
"step": 69
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 70.0,
|
| 608 |
+
"grad_norm": 5.213359355926514,
|
| 609 |
+
"learning_rate": 0.0031,
|
| 610 |
+
"loss": 0.1041,
|
| 611 |
+
"step": 70
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 70.0,
|
| 615 |
+
"eval_loss": 0.09258551150560379,
|
| 616 |
+
"eval_runtime": 0.0168,
|
| 617 |
+
"eval_samples_per_second": 596.044,
|
| 618 |
+
"eval_steps_per_second": 119.209,
|
| 619 |
+
"step": 70
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 71.0,
|
| 623 |
+
"eval_loss": 0.12545828521251678,
|
| 624 |
+
"eval_runtime": 0.029,
|
| 625 |
+
"eval_samples_per_second": 344.343,
|
| 626 |
+
"eval_steps_per_second": 68.869,
|
| 627 |
+
"step": 71
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 72.0,
|
| 631 |
+
"eval_loss": 0.07994948327541351,
|
| 632 |
+
"eval_runtime": 0.0264,
|
| 633 |
+
"eval_samples_per_second": 378.342,
|
| 634 |
+
"eval_steps_per_second": 75.668,
|
| 635 |
+
"step": 72
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 73.0,
|
| 639 |
+
"eval_loss": 0.10161998122930527,
|
| 640 |
+
"eval_runtime": 0.0164,
|
| 641 |
+
"eval_samples_per_second": 611.317,
|
| 642 |
+
"eval_steps_per_second": 122.263,
|
| 643 |
+
"step": 73
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 74.0,
|
| 647 |
+
"eval_loss": 0.08442724496126175,
|
| 648 |
+
"eval_runtime": 0.0172,
|
| 649 |
+
"eval_samples_per_second": 579.764,
|
| 650 |
+
"eval_steps_per_second": 115.953,
|
| 651 |
+
"step": 74
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 75.0,
|
| 655 |
+
"eval_loss": 0.13757655024528503,
|
| 656 |
+
"eval_runtime": 0.0159,
|
| 657 |
+
"eval_samples_per_second": 628.097,
|
| 658 |
+
"eval_steps_per_second": 125.619,
|
| 659 |
+
"step": 75
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 76.0,
|
| 663 |
+
"eval_loss": 0.10746718943119049,
|
| 664 |
+
"eval_runtime": 0.016,
|
| 665 |
+
"eval_samples_per_second": 623.336,
|
| 666 |
+
"eval_steps_per_second": 124.667,
|
| 667 |
+
"step": 76
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 77.0,
|
| 671 |
+
"eval_loss": 0.07997341454029083,
|
| 672 |
+
"eval_runtime": 0.0163,
|
| 673 |
+
"eval_samples_per_second": 613.337,
|
| 674 |
+
"eval_steps_per_second": 122.667,
|
| 675 |
+
"step": 77
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 78.0,
|
| 679 |
+
"eval_loss": 0.08581076562404633,
|
| 680 |
+
"eval_runtime": 0.0225,
|
| 681 |
+
"eval_samples_per_second": 444.59,
|
| 682 |
+
"eval_steps_per_second": 88.918,
|
| 683 |
+
"step": 78
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 79.0,
|
| 687 |
+
"eval_loss": 0.07667073607444763,
|
| 688 |
+
"eval_runtime": 0.0173,
|
| 689 |
+
"eval_samples_per_second": 578.748,
|
| 690 |
+
"eval_steps_per_second": 115.75,
|
| 691 |
+
"step": 79
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 80.0,
|
| 695 |
+
"grad_norm": 4.289701461791992,
|
| 696 |
+
"learning_rate": 0.0021,
|
| 697 |
+
"loss": 0.0468,
|
| 698 |
+
"step": 80
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 80.0,
|
| 702 |
+
"eval_loss": 0.1910361349582672,
|
| 703 |
+
"eval_runtime": 0.0156,
|
| 704 |
+
"eval_samples_per_second": 639.015,
|
| 705 |
+
"eval_steps_per_second": 127.803,
|
| 706 |
+
"step": 80
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 81.0,
|
| 710 |
+
"eval_loss": 0.2634718120098114,
|
| 711 |
+
"eval_runtime": 0.0162,
|
| 712 |
+
"eval_samples_per_second": 617.854,
|
| 713 |
+
"eval_steps_per_second": 123.571,
|
| 714 |
+
"step": 81
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 82.0,
|
| 718 |
+
"eval_loss": 0.20500917732715607,
|
| 719 |
+
"eval_runtime": 0.0159,
|
| 720 |
+
"eval_samples_per_second": 627.542,
|
| 721 |
+
"eval_steps_per_second": 125.508,
|
| 722 |
+
"step": 82
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 83.0,
|
| 726 |
+
"eval_loss": 0.09815473854541779,
|
| 727 |
+
"eval_runtime": 0.0159,
|
| 728 |
+
"eval_samples_per_second": 627.871,
|
| 729 |
+
"eval_steps_per_second": 125.574,
|
| 730 |
+
"step": 83
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 84.0,
|
| 734 |
+
"eval_loss": 0.08160002529621124,
|
| 735 |
+
"eval_runtime": 0.0256,
|
| 736 |
+
"eval_samples_per_second": 390.746,
|
| 737 |
+
"eval_steps_per_second": 78.149,
|
| 738 |
+
"step": 84
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 85.0,
|
| 742 |
+
"eval_loss": 0.0980997309088707,
|
| 743 |
+
"eval_runtime": 0.0163,
|
| 744 |
+
"eval_samples_per_second": 613.005,
|
| 745 |
+
"eval_steps_per_second": 122.601,
|
| 746 |
+
"step": 85
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 86.0,
|
| 750 |
+
"eval_loss": 0.08293064683675766,
|
| 751 |
+
"eval_runtime": 0.016,
|
| 752 |
+
"eval_samples_per_second": 625.409,
|
| 753 |
+
"eval_steps_per_second": 125.082,
|
| 754 |
+
"step": 86
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 87.0,
|
| 758 |
+
"eval_loss": 0.08042607456445694,
|
| 759 |
+
"eval_runtime": 0.0166,
|
| 760 |
+
"eval_samples_per_second": 602.82,
|
| 761 |
+
"eval_steps_per_second": 120.564,
|
| 762 |
+
"step": 87
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 88.0,
|
| 766 |
+
"eval_loss": 0.17653095722198486,
|
| 767 |
+
"eval_runtime": 0.0166,
|
| 768 |
+
"eval_samples_per_second": 600.671,
|
| 769 |
+
"eval_steps_per_second": 120.134,
|
| 770 |
+
"step": 88
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 89.0,
|
| 774 |
+
"eval_loss": 0.2547139525413513,
|
| 775 |
+
"eval_runtime": 0.016,
|
| 776 |
+
"eval_samples_per_second": 624.729,
|
| 777 |
+
"eval_steps_per_second": 124.946,
|
| 778 |
+
"step": 89
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 90.0,
|
| 782 |
+
"grad_norm": 12.196877479553223,
|
| 783 |
+
"learning_rate": 0.0011,
|
| 784 |
+
"loss": 0.0779,
|
| 785 |
+
"step": 90
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 90.0,
|
| 789 |
+
"eval_loss": 0.2526191473007202,
|
| 790 |
+
"eval_runtime": 0.0164,
|
| 791 |
+
"eval_samples_per_second": 609.602,
|
| 792 |
+
"eval_steps_per_second": 121.92,
|
| 793 |
+
"step": 90
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 91.0,
|
| 797 |
+
"eval_loss": 0.1893763244152069,
|
| 798 |
+
"eval_runtime": 0.0275,
|
| 799 |
+
"eval_samples_per_second": 363.89,
|
| 800 |
+
"eval_steps_per_second": 72.778,
|
| 801 |
+
"step": 91
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 92.0,
|
| 805 |
+
"eval_loss": 0.11402726173400879,
|
| 806 |
+
"eval_runtime": 0.0165,
|
| 807 |
+
"eval_samples_per_second": 604.506,
|
| 808 |
+
"eval_steps_per_second": 120.901,
|
| 809 |
+
"step": 92
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 93.0,
|
| 813 |
+
"eval_loss": 0.0751984640955925,
|
| 814 |
+
"eval_runtime": 0.0174,
|
| 815 |
+
"eval_samples_per_second": 575.516,
|
| 816 |
+
"eval_steps_per_second": 115.103,
|
| 817 |
+
"step": 93
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 94.0,
|
| 821 |
+
"eval_loss": 0.0785483792424202,
|
| 822 |
+
"eval_runtime": 0.0162,
|
| 823 |
+
"eval_samples_per_second": 618.592,
|
| 824 |
+
"eval_steps_per_second": 123.718,
|
| 825 |
+
"step": 94
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 95.0,
|
| 829 |
+
"eval_loss": 0.08064951747655869,
|
| 830 |
+
"eval_runtime": 0.0174,
|
| 831 |
+
"eval_samples_per_second": 575.698,
|
| 832 |
+
"eval_steps_per_second": 115.14,
|
| 833 |
+
"step": 95
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 96.0,
|
| 837 |
+
"eval_loss": 0.07702342420816422,
|
| 838 |
+
"eval_runtime": 0.0179,
|
| 839 |
+
"eval_samples_per_second": 559.129,
|
| 840 |
+
"eval_steps_per_second": 111.826,
|
| 841 |
+
"step": 96
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 97.0,
|
| 845 |
+
"eval_loss": 0.07478635758161545,
|
| 846 |
+
"eval_runtime": 0.0293,
|
| 847 |
+
"eval_samples_per_second": 341.431,
|
| 848 |
+
"eval_steps_per_second": 68.286,
|
| 849 |
+
"step": 97
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 98.0,
|
| 853 |
+
"eval_loss": 0.07912726700305939,
|
| 854 |
+
"eval_runtime": 0.0202,
|
| 855 |
+
"eval_samples_per_second": 495.289,
|
| 856 |
+
"eval_steps_per_second": 99.058,
|
| 857 |
+
"step": 98
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 99.0,
|
| 861 |
+
"eval_loss": 0.0888177827000618,
|
| 862 |
+
"eval_runtime": 0.0291,
|
| 863 |
+
"eval_samples_per_second": 343.866,
|
| 864 |
+
"eval_steps_per_second": 68.773,
|
| 865 |
+
"step": 99
|
| 866 |
}
|
| 867 |
],
|
| 868 |
"logging_steps": 10,
|