Training in progress, step 114, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 37134420
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19356eacb8c37217669fb12ba13fb0bbf5cd120c48b40980f67b739cf2b59277
|
| 3 |
size 37134420
|
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 sha256:220dee27a26b361841ca6ec77a0d465a152c866c9f9c78f0bc6701760d02f1d7
|
| 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:d35a71cd96ab153cf58aa68810dc4405b5e1a7fbfef5501d233ae84e34aa51c4
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 38,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -563,6 +563,280 @@
|
|
| 563 |
"eval_samples_per_second": 11.343,
|
| 564 |
"eval_steps_per_second": 5.671,
|
| 565 |
"step": 76
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 566 |
}
|
| 567 |
],
|
| 568 |
"logging_steps": 1,
|
|
@@ -582,7 +856,7 @@
|
|
| 582 |
"attributes": {}
|
| 583 |
}
|
| 584 |
},
|
| 585 |
-
"total_flos":
|
| 586 |
"train_batch_size": 2,
|
| 587 |
"trial_name": null,
|
| 588 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.30039525691699603,
|
| 5 |
"eval_steps": 38,
|
| 6 |
+
"global_step": 114,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 563 |
"eval_samples_per_second": 11.343,
|
| 564 |
"eval_steps_per_second": 5.671,
|
| 565 |
"step": 76
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.2028985507246377,
|
| 569 |
+
"grad_norm": NaN,
|
| 570 |
+
"learning_rate": 0.00021345380112240797,
|
| 571 |
+
"loss": 0.0,
|
| 572 |
+
"step": 77
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.20553359683794467,
|
| 576 |
+
"grad_norm": NaN,
|
| 577 |
+
"learning_rate": 0.00020897296607010301,
|
| 578 |
+
"loss": 0.0,
|
| 579 |
+
"step": 78
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.20816864295125165,
|
| 583 |
+
"grad_norm": NaN,
|
| 584 |
+
"learning_rate": 0.00020448761285916104,
|
| 585 |
+
"loss": 0.0,
|
| 586 |
+
"step": 79
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.21080368906455862,
|
| 590 |
+
"grad_norm": NaN,
|
| 591 |
+
"learning_rate": 0.0002,
|
| 592 |
+
"loss": 0.0,
|
| 593 |
+
"step": 80
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.2134387351778656,
|
| 597 |
+
"grad_norm": NaN,
|
| 598 |
+
"learning_rate": 0.00019551238714083903,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"step": 81
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.2160737812911726,
|
| 604 |
+
"grad_norm": NaN,
|
| 605 |
+
"learning_rate": 0.00019102703392989709,
|
| 606 |
+
"loss": 0.0,
|
| 607 |
+
"step": 82
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.21870882740447958,
|
| 611 |
+
"grad_norm": NaN,
|
| 612 |
+
"learning_rate": 0.00018654619887759207,
|
| 613 |
+
"loss": 0.0,
|
| 614 |
+
"step": 83
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.22134387351778656,
|
| 618 |
+
"grad_norm": NaN,
|
| 619 |
+
"learning_rate": 0.00018207213821931333,
|
| 620 |
+
"loss": 0.0,
|
| 621 |
+
"step": 84
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.22397891963109354,
|
| 625 |
+
"grad_norm": NaN,
|
| 626 |
+
"learning_rate": 0.00017760710477933845,
|
| 627 |
+
"loss": 0.0,
|
| 628 |
+
"step": 85
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.22661396574440051,
|
| 632 |
+
"grad_norm": NaN,
|
| 633 |
+
"learning_rate": 0.00017315334683646897,
|
| 634 |
+
"loss": 0.0,
|
| 635 |
+
"step": 86
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.22924901185770752,
|
| 639 |
+
"grad_norm": NaN,
|
| 640 |
+
"learning_rate": 0.00016871310699195379,
|
| 641 |
+
"loss": 0.0,
|
| 642 |
+
"step": 87
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.2318840579710145,
|
| 646 |
+
"grad_norm": NaN,
|
| 647 |
+
"learning_rate": 0.00016428862104027268,
|
| 648 |
+
"loss": 0.0,
|
| 649 |
+
"step": 88
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.23451910408432147,
|
| 653 |
+
"grad_norm": NaN,
|
| 654 |
+
"learning_rate": 0.00015988211684334546,
|
| 655 |
+
"loss": 0.0,
|
| 656 |
+
"step": 89
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.23715415019762845,
|
| 660 |
+
"grad_norm": NaN,
|
| 661 |
+
"learning_rate": 0.00015549581320873715,
|
| 662 |
+
"loss": 0.0,
|
| 663 |
+
"step": 90
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.23978919631093545,
|
| 667 |
+
"grad_norm": NaN,
|
| 668 |
+
"learning_rate": 0.00015113191877242117,
|
| 669 |
+
"loss": 0.0,
|
| 670 |
+
"step": 91
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.24242424242424243,
|
| 674 |
+
"grad_norm": NaN,
|
| 675 |
+
"learning_rate": 0.00014679263088666499,
|
| 676 |
+
"loss": 0.0,
|
| 677 |
+
"step": 92
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.2450592885375494,
|
| 681 |
+
"grad_norm": NaN,
|
| 682 |
+
"learning_rate": 0.00014248013451359656,
|
| 683 |
+
"loss": 0.0,
|
| 684 |
+
"step": 93
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.24769433465085638,
|
| 688 |
+
"grad_norm": NaN,
|
| 689 |
+
"learning_rate": 0.00013819660112501054,
|
| 690 |
+
"loss": 0.0,
|
| 691 |
+
"step": 94
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.2503293807641634,
|
| 695 |
+
"grad_norm": NaN,
|
| 696 |
+
"learning_rate": 0.00013394418760896666,
|
| 697 |
+
"loss": 0.0,
|
| 698 |
+
"step": 95
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.25296442687747034,
|
| 702 |
+
"grad_norm": NaN,
|
| 703 |
+
"learning_rate": 0.00012972503518373144,
|
| 704 |
+
"loss": 0.0,
|
| 705 |
+
"step": 96
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.25559947299077734,
|
| 709 |
+
"grad_norm": NaN,
|
| 710 |
+
"learning_rate": 0.00012554126831961098,
|
| 711 |
+
"loss": 0.0,
|
| 712 |
+
"step": 97
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.25823451910408435,
|
| 716 |
+
"grad_norm": NaN,
|
| 717 |
+
"learning_rate": 0.0001213949936692153,
|
| 718 |
+
"loss": 0.0,
|
| 719 |
+
"step": 98
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.2608695652173913,
|
| 723 |
+
"grad_norm": NaN,
|
| 724 |
+
"learning_rate": 0.00011728829900669591,
|
| 725 |
+
"loss": 0.0,
|
| 726 |
+
"step": 99
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.2635046113306983,
|
| 730 |
+
"grad_norm": NaN,
|
| 731 |
+
"learning_rate": 0.00011322325217648839,
|
| 732 |
+
"loss": 0.0,
|
| 733 |
+
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.26613965744400525,
|
| 737 |
+
"grad_norm": NaN,
|
| 738 |
+
"learning_rate": 0.00010920190005209065,
|
| 739 |
+
"loss": 0.0,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.26877470355731226,
|
| 744 |
+
"grad_norm": NaN,
|
| 745 |
+
"learning_rate": 0.00010522626750540028,
|
| 746 |
+
"loss": 0.0,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.27140974967061926,
|
| 751 |
+
"grad_norm": NaN,
|
| 752 |
+
"learning_rate": 0.00010129835638713063,
|
| 753 |
+
"loss": 0.0,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.2740447957839262,
|
| 758 |
+
"grad_norm": NaN,
|
| 759 |
+
"learning_rate": 9.74201445188188e-05,
|
| 760 |
+
"loss": 0.0,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.2766798418972332,
|
| 765 |
+
"grad_norm": NaN,
|
| 766 |
+
"learning_rate": 9.359358469693271e-05,
|
| 767 |
+
"loss": 0.0,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.27931488801054016,
|
| 772 |
+
"grad_norm": NaN,
|
| 773 |
+
"learning_rate": 8.982060370957952e-05,
|
| 774 |
+
"loss": 0.0,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.28194993412384717,
|
| 779 |
+
"grad_norm": NaN,
|
| 780 |
+
"learning_rate": 8.610310136630962e-05,
|
| 781 |
+
"loss": 0.0,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.2845849802371542,
|
| 786 |
+
"grad_norm": NaN,
|
| 787 |
+
"learning_rate": 8.24429495415054e-05,
|
| 788 |
+
"loss": 0.0,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.2872200263504611,
|
| 793 |
+
"grad_norm": NaN,
|
| 794 |
+
"learning_rate": 7.884199123183605e-05,
|
| 795 |
+
"loss": 0.0,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.2898550724637681,
|
| 800 |
+
"grad_norm": NaN,
|
| 801 |
+
"learning_rate": 7.530203962825331e-05,
|
| 802 |
+
"loss": 0.0,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.2924901185770751,
|
| 807 |
+
"grad_norm": NaN,
|
| 808 |
+
"learning_rate": 7.182487720299517e-05,
|
| 809 |
+
"loss": 0.0,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.2951251646903821,
|
| 814 |
+
"grad_norm": NaN,
|
| 815 |
+
"learning_rate": 6.841225481205749e-05,
|
| 816 |
+
"loss": 0.0,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.2977602108036891,
|
| 821 |
+
"grad_norm": NaN,
|
| 822 |
+
"learning_rate": 6.506589081358514e-05,
|
| 823 |
+
"loss": 0.0,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.30039525691699603,
|
| 828 |
+
"grad_norm": NaN,
|
| 829 |
+
"learning_rate": 6.178747020262707e-05,
|
| 830 |
+
"loss": 0.0,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.30039525691699603,
|
| 835 |
+
"eval_loss": NaN,
|
| 836 |
+
"eval_runtime": 14.1098,
|
| 837 |
+
"eval_samples_per_second": 11.34,
|
| 838 |
+
"eval_steps_per_second": 5.67,
|
| 839 |
+
"step": 114
|
| 840 |
}
|
| 841 |
],
|
| 842 |
"logging_steps": 1,
|
|
|
|
| 856 |
"attributes": {}
|
| 857 |
}
|
| 858 |
},
|
| 859 |
+
"total_flos": 6534801829920768.0,
|
| 860 |
"train_batch_size": 2,
|
| 861 |
"trial_name": null,
|
| 862 |
"trial_params": null
|