Training in progress, step 100, 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 90365754
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c96e32b039f32c63ecedd4e4254822f50a9a2344ff2aae636216425712ce36ac
|
| 3 |
size 90365754
|
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:c659e4505005131eab7ea0ee74ff9e2fee448c1f7e5a9dc766af93a6f64c72a6
|
| 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 sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
| 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": 9,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -604,6 +604,205 @@
|
|
| 604 |
"learning_rate": 1.7860619515673033e-05,
|
| 605 |
"loss": 0.0,
|
| 606 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 607 |
}
|
| 608 |
],
|
| 609 |
"logging_steps": 1,
|
|
@@ -618,12 +817,12 @@
|
|
| 618 |
"should_evaluate": false,
|
| 619 |
"should_log": false,
|
| 620 |
"should_save": true,
|
| 621 |
-
"should_training_stop":
|
| 622 |
},
|
| 623 |
"attributes": {}
|
| 624 |
}
|
| 625 |
},
|
| 626 |
-
"total_flos":
|
| 627 |
"train_batch_size": 8,
|
| 628 |
"trial_name": null,
|
| 629 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.01258890917102033,
|
| 5 |
"eval_steps": 9,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 604 |
"learning_rate": 1.7860619515673033e-05,
|
| 605 |
"loss": 0.0,
|
| 606 |
"step": 75
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.009567570969975452,
|
| 610 |
+
"grad_norm": NaN,
|
| 611 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 612 |
+
"loss": 0.0,
|
| 613 |
+
"step": 76
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.009693460061685654,
|
| 617 |
+
"grad_norm": NaN,
|
| 618 |
+
"learning_rate": 1.526708147705013e-05,
|
| 619 |
+
"loss": 0.0,
|
| 620 |
+
"step": 77
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.009819349153395858,
|
| 624 |
+
"grad_norm": NaN,
|
| 625 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 626 |
+
"loss": 0.0,
|
| 627 |
+
"step": 78
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.00994523824510606,
|
| 631 |
+
"grad_norm": NaN,
|
| 632 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 633 |
+
"loss": 0.0,
|
| 634 |
+
"step": 79
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.010071127336816265,
|
| 638 |
+
"grad_norm": NaN,
|
| 639 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 640 |
+
"loss": 0.0,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.010197016428526468,
|
| 645 |
+
"grad_norm": NaN,
|
| 646 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 647 |
+
"loss": 0.0,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.010197016428526468,
|
| 652 |
+
"eval_loss": NaN,
|
| 653 |
+
"eval_runtime": 204.6403,
|
| 654 |
+
"eval_samples_per_second": 32.692,
|
| 655 |
+
"eval_steps_per_second": 4.09,
|
| 656 |
+
"step": 81
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.010322905520236672,
|
| 660 |
+
"grad_norm": NaN,
|
| 661 |
+
"learning_rate": 9.549150281252633e-06,
|
| 662 |
+
"loss": 0.0,
|
| 663 |
+
"step": 82
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.010448794611946874,
|
| 667 |
+
"grad_norm": NaN,
|
| 668 |
+
"learning_rate": 8.548121372247918e-06,
|
| 669 |
+
"loss": 0.0,
|
| 670 |
+
"step": 83
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.010574683703657078,
|
| 674 |
+
"grad_norm": NaN,
|
| 675 |
+
"learning_rate": 7.597595192178702e-06,
|
| 676 |
+
"loss": 0.0,
|
| 677 |
+
"step": 84
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.010700572795367281,
|
| 681 |
+
"grad_norm": NaN,
|
| 682 |
+
"learning_rate": 6.698729810778065e-06,
|
| 683 |
+
"loss": 0.0,
|
| 684 |
+
"step": 85
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.010826461887077485,
|
| 688 |
+
"grad_norm": NaN,
|
| 689 |
+
"learning_rate": 5.852620357053651e-06,
|
| 690 |
+
"loss": 0.0,
|
| 691 |
+
"step": 86
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.010952350978787688,
|
| 695 |
+
"grad_norm": NaN,
|
| 696 |
+
"learning_rate": 5.060297685041659e-06,
|
| 697 |
+
"loss": 0.0,
|
| 698 |
+
"step": 87
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.011078240070497892,
|
| 702 |
+
"grad_norm": NaN,
|
| 703 |
+
"learning_rate": 4.322727117869951e-06,
|
| 704 |
+
"loss": 0.0,
|
| 705 |
+
"step": 88
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.011204129162208094,
|
| 709 |
+
"grad_norm": NaN,
|
| 710 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 711 |
+
"loss": 0.0,
|
| 712 |
+
"step": 89
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.011330018253918299,
|
| 716 |
+
"grad_norm": NaN,
|
| 717 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 718 |
+
"loss": 0.0,
|
| 719 |
+
"step": 90
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.011330018253918299,
|
| 723 |
+
"eval_loss": NaN,
|
| 724 |
+
"eval_runtime": 204.5523,
|
| 725 |
+
"eval_samples_per_second": 32.706,
|
| 726 |
+
"eval_steps_per_second": 4.092,
|
| 727 |
+
"step": 90
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.011455907345628501,
|
| 731 |
+
"grad_norm": NaN,
|
| 732 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 733 |
+
"loss": 0.0,
|
| 734 |
+
"step": 91
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.011581796437338705,
|
| 738 |
+
"grad_norm": NaN,
|
| 739 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 740 |
+
"loss": 0.0,
|
| 741 |
+
"step": 92
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.011707685529048908,
|
| 745 |
+
"grad_norm": NaN,
|
| 746 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 747 |
+
"loss": 0.0,
|
| 748 |
+
"step": 93
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.011833574620759112,
|
| 752 |
+
"grad_norm": NaN,
|
| 753 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 754 |
+
"loss": 0.0,
|
| 755 |
+
"step": 94
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.011959463712469314,
|
| 759 |
+
"grad_norm": NaN,
|
| 760 |
+
"learning_rate": 7.596123493895991e-07,
|
| 761 |
+
"loss": 0.0,
|
| 762 |
+
"step": 95
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.012085352804179519,
|
| 766 |
+
"grad_norm": NaN,
|
| 767 |
+
"learning_rate": 4.865965629214819e-07,
|
| 768 |
+
"loss": 0.0,
|
| 769 |
+
"step": 96
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.012211241895889721,
|
| 773 |
+
"grad_norm": NaN,
|
| 774 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 775 |
+
"loss": 0.0,
|
| 776 |
+
"step": 97
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.012337130987599924,
|
| 780 |
+
"grad_norm": NaN,
|
| 781 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 782 |
+
"loss": 0.0,
|
| 783 |
+
"step": 98
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.012463020079310128,
|
| 787 |
+
"grad_norm": NaN,
|
| 788 |
+
"learning_rate": 3.04586490452119e-08,
|
| 789 |
+
"loss": 0.0,
|
| 790 |
+
"step": 99
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.012463020079310128,
|
| 794 |
+
"eval_loss": NaN,
|
| 795 |
+
"eval_runtime": 204.5252,
|
| 796 |
+
"eval_samples_per_second": 32.71,
|
| 797 |
+
"eval_steps_per_second": 4.092,
|
| 798 |
+
"step": 99
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.01258890917102033,
|
| 802 |
+
"grad_norm": NaN,
|
| 803 |
+
"learning_rate": 0.0,
|
| 804 |
+
"loss": 0.0,
|
| 805 |
+
"step": 100
|
| 806 |
}
|
| 807 |
],
|
| 808 |
"logging_steps": 1,
|
|
|
|
| 817 |
"should_evaluate": false,
|
| 818 |
"should_log": false,
|
| 819 |
"should_save": true,
|
| 820 |
+
"should_training_stop": true
|
| 821 |
},
|
| 822 |
"attributes": {}
|
| 823 |
}
|
| 824 |
},
|
| 825 |
+
"total_flos": 9677225695641600.0,
|
| 826 |
"train_batch_size": 8,
|
| 827 |
"trial_name": null,
|
| 828 |
"trial_params": null
|