Training in progress, step 50000, checkpoint
Browse files
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:fe277dbde909ce16e9054dbf8ac1ad267160f46c626a6a71f787776dd954b9bf
|
| 3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 5000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -632,6 +632,162 @@
|
|
| 632 |
"eval_samples_per_second": 378.597,
|
| 633 |
"eval_steps_per_second": 11.831,
|
| 634 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 635 |
}
|
| 636 |
],
|
| 637 |
"logging_steps": 500,
|
|
@@ -651,7 +807,7 @@
|
|
| 651 |
"attributes": {}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
-
"total_flos":
|
| 655 |
"train_batch_size": 32,
|
| 656 |
"trial_name": null,
|
| 657 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.2415574096146207,
|
| 6 |
"eval_steps": 5000,
|
| 7 |
+
"global_step": 50000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 632 |
"eval_samples_per_second": 378.597,
|
| 633 |
"eval_steps_per_second": 11.831,
|
| 634 |
"step": 40000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.0056615017878427,
|
| 638 |
+
"grad_norm": NaN,
|
| 639 |
+
"learning_rate": 0.0004900742091849483,
|
| 640 |
+
"loss": 0.0,
|
| 641 |
+
"step": 40500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.0180770758839888,
|
| 645 |
+
"grad_norm": NaN,
|
| 646 |
+
"learning_rate": 0.0004900742091849483,
|
| 647 |
+
"loss": 0.0,
|
| 648 |
+
"step": 41000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.030492649980135,
|
| 652 |
+
"grad_norm": NaN,
|
| 653 |
+
"learning_rate": 0.0004900742091849483,
|
| 654 |
+
"loss": 0.0,
|
| 655 |
+
"step": 41500
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.0429082240762813,
|
| 659 |
+
"grad_norm": NaN,
|
| 660 |
+
"learning_rate": 0.0004900742091849483,
|
| 661 |
+
"loss": 0.0,
|
| 662 |
+
"step": 42000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.0553237981724275,
|
| 666 |
+
"grad_norm": NaN,
|
| 667 |
+
"learning_rate": 0.0004900742091849483,
|
| 668 |
+
"loss": 0.0,
|
| 669 |
+
"step": 42500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.0677393722685737,
|
| 673 |
+
"grad_norm": NaN,
|
| 674 |
+
"learning_rate": 0.0004900742091849483,
|
| 675 |
+
"loss": 0.0,
|
| 676 |
+
"step": 43000
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.08015494636472,
|
| 680 |
+
"grad_norm": NaN,
|
| 681 |
+
"learning_rate": 0.0004900742091849483,
|
| 682 |
+
"loss": 0.0,
|
| 683 |
+
"step": 43500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.0925705204608662,
|
| 687 |
+
"grad_norm": NaN,
|
| 688 |
+
"learning_rate": 0.0004900742091849483,
|
| 689 |
+
"loss": 0.0,
|
| 690 |
+
"step": 44000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.1049860945570122,
|
| 694 |
+
"grad_norm": NaN,
|
| 695 |
+
"learning_rate": 0.0004900742091849483,
|
| 696 |
+
"loss": 0.0,
|
| 697 |
+
"step": 44500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.1174016686531585,
|
| 701 |
+
"grad_norm": NaN,
|
| 702 |
+
"learning_rate": 0.0004900742091849483,
|
| 703 |
+
"loss": 0.0,
|
| 704 |
+
"step": 45000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.1174016686531585,
|
| 708 |
+
"eval_loss": NaN,
|
| 709 |
+
"eval_runtime": 3327.025,
|
| 710 |
+
"eval_samples_per_second": 387.34,
|
| 711 |
+
"eval_steps_per_second": 12.105,
|
| 712 |
+
"step": 45000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.1298172427493047,
|
| 716 |
+
"grad_norm": NaN,
|
| 717 |
+
"learning_rate": 0.0004900742091849483,
|
| 718 |
+
"loss": 0.0,
|
| 719 |
+
"step": 45500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.142232816845451,
|
| 723 |
+
"grad_norm": NaN,
|
| 724 |
+
"learning_rate": 0.0004900742091849483,
|
| 725 |
+
"loss": 0.0,
|
| 726 |
+
"step": 46000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.1546483909415972,
|
| 730 |
+
"grad_norm": NaN,
|
| 731 |
+
"learning_rate": 0.0004900742091849483,
|
| 732 |
+
"loss": 0.0,
|
| 733 |
+
"step": 46500
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.1670639650377432,
|
| 737 |
+
"grad_norm": NaN,
|
| 738 |
+
"learning_rate": 0.0004900742091849483,
|
| 739 |
+
"loss": 0.0,
|
| 740 |
+
"step": 47000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.1794795391338895,
|
| 744 |
+
"grad_norm": NaN,
|
| 745 |
+
"learning_rate": 0.0004900742091849483,
|
| 746 |
+
"loss": 0.0,
|
| 747 |
+
"step": 47500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.1918951132300357,
|
| 751 |
+
"grad_norm": NaN,
|
| 752 |
+
"learning_rate": 0.0004900742091849483,
|
| 753 |
+
"loss": 0.0,
|
| 754 |
+
"step": 48000
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.204310687326182,
|
| 758 |
+
"grad_norm": NaN,
|
| 759 |
+
"learning_rate": 0.0004900742091849483,
|
| 760 |
+
"loss": 0.0,
|
| 761 |
+
"step": 48500
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.2167262614223282,
|
| 765 |
+
"grad_norm": NaN,
|
| 766 |
+
"learning_rate": 0.0004900742091849483,
|
| 767 |
+
"loss": 0.0,
|
| 768 |
+
"step": 49000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.2291418355184744,
|
| 772 |
+
"grad_norm": NaN,
|
| 773 |
+
"learning_rate": 0.0004900742091849483,
|
| 774 |
+
"loss": 0.0,
|
| 775 |
+
"step": 49500
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.2415574096146207,
|
| 779 |
+
"grad_norm": NaN,
|
| 780 |
+
"learning_rate": 0.0004900742091849483,
|
| 781 |
+
"loss": 0.0,
|
| 782 |
+
"step": 50000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.2415574096146207,
|
| 786 |
+
"eval_loss": NaN,
|
| 787 |
+
"eval_runtime": 3219.2453,
|
| 788 |
+
"eval_samples_per_second": 400.308,
|
| 789 |
+
"eval_steps_per_second": 12.51,
|
| 790 |
+
"step": 50000
|
| 791 |
}
|
| 792 |
],
|
| 793 |
"logging_steps": 500,
|
|
|
|
| 807 |
"attributes": {}
|
| 808 |
}
|
| 809 |
},
|
| 810 |
+
"total_flos": 1.0618239799723622e+17,
|
| 811 |
"train_batch_size": 32,
|
| 812 |
"trial_name": null,
|
| 813 |
"trial_params": null
|