Training in progress, epoch 2, 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 671473298
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59d2eed6ad7b6c61be9559b52cf752c4381844a3d89151424a37f1507db2acf9
|
| 3 |
size 671473298
|
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 sha256:04390ef383ebb7ff8fcc9c2f0afceb13e51241963799c3a3c244c987cb70b4d8
|
| 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:c0ab4b5576cffbfe1e9f6fc42d7fb34658a6fda81c06eb0c633b50cbe234b60f
|
| 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":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -637,6 +637,643 @@
|
|
| 637 |
"learning_rate": 6.861468292009727e-05,
|
| 638 |
"loss": 0.0,
|
| 639 |
"step": 630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 640 |
}
|
| 641 |
],
|
| 642 |
"logging_steps": 7,
|
|
@@ -656,7 +1293,7 @@
|
|
| 656 |
"attributes": {}
|
| 657 |
}
|
| 658 |
},
|
| 659 |
-
"total_flos":
|
| 660 |
"train_batch_size": 2,
|
| 661 |
"trial_name": null,
|
| 662 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1271,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 637 |
"learning_rate": 6.861468292009727e-05,
|
| 638 |
"loss": 0.0,
|
| 639 |
"step": 630
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.002360346184107,
|
| 643 |
+
"grad_norm": NaN,
|
| 644 |
+
"learning_rate": 6.788347664153447e-05,
|
| 645 |
+
"loss": 0.0,
|
| 646 |
+
"step": 637
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.013375295043273,
|
| 650 |
+
"grad_norm": NaN,
|
| 651 |
+
"learning_rate": 6.714785788270658e-05,
|
| 652 |
+
"loss": 0.0,
|
| 653 |
+
"step": 644
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.024390243902439,
|
| 657 |
+
"grad_norm": NaN,
|
| 658 |
+
"learning_rate": 6.640800814653503e-05,
|
| 659 |
+
"loss": 0.0,
|
| 660 |
+
"step": 651
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.035405192761605,
|
| 664 |
+
"grad_norm": NaN,
|
| 665 |
+
"learning_rate": 6.566410997987163e-05,
|
| 666 |
+
"loss": 0.0,
|
| 667 |
+
"step": 658
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.046420141620771,
|
| 671 |
+
"grad_norm": NaN,
|
| 672 |
+
"learning_rate": 6.49163469284578e-05,
|
| 673 |
+
"loss": 0.0,
|
| 674 |
+
"step": 665
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.057435090479937,
|
| 678 |
+
"grad_norm": NaN,
|
| 679 |
+
"learning_rate": 6.416490349163748e-05,
|
| 680 |
+
"loss": 0.0,
|
| 681 |
+
"step": 672
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.068450039339103,
|
| 685 |
+
"grad_norm": NaN,
|
| 686 |
+
"learning_rate": 6.340996507683458e-05,
|
| 687 |
+
"loss": 0.0,
|
| 688 |
+
"step": 679
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.0794649881982692,
|
| 692 |
+
"grad_norm": NaN,
|
| 693 |
+
"learning_rate": 6.265171795380659e-05,
|
| 694 |
+
"loss": 0.0,
|
| 695 |
+
"step": 686
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.0904799370574352,
|
| 699 |
+
"grad_norm": NaN,
|
| 700 |
+
"learning_rate": 6.189034920868522e-05,
|
| 701 |
+
"loss": 0.0,
|
| 702 |
+
"step": 693
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.1014948859166012,
|
| 706 |
+
"grad_norm": NaN,
|
| 707 |
+
"learning_rate": 6.112604669781572e-05,
|
| 708 |
+
"loss": 0.0,
|
| 709 |
+
"step": 700
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.1125098347757671,
|
| 713 |
+
"grad_norm": NaN,
|
| 714 |
+
"learning_rate": 6.0358999001406156e-05,
|
| 715 |
+
"loss": 0.0,
|
| 716 |
+
"step": 707
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.1235247836349331,
|
| 720 |
+
"grad_norm": NaN,
|
| 721 |
+
"learning_rate": 5.9589395376998e-05,
|
| 722 |
+
"loss": 0.0,
|
| 723 |
+
"step": 714
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.1345397324940991,
|
| 727 |
+
"grad_norm": NaN,
|
| 728 |
+
"learning_rate": 5.8817425712769794e-05,
|
| 729 |
+
"loss": 0.0,
|
| 730 |
+
"step": 721
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.145554681353265,
|
| 734 |
+
"grad_norm": NaN,
|
| 735 |
+
"learning_rate": 5.804328048068492e-05,
|
| 736 |
+
"loss": 0.0,
|
| 737 |
+
"step": 728
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.156569630212431,
|
| 741 |
+
"grad_norm": NaN,
|
| 742 |
+
"learning_rate": 5.7267150689495644e-05,
|
| 743 |
+
"loss": 0.0,
|
| 744 |
+
"step": 735
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.167584579071597,
|
| 748 |
+
"grad_norm": NaN,
|
| 749 |
+
"learning_rate": 5.648922783761443e-05,
|
| 750 |
+
"loss": 0.0,
|
| 751 |
+
"step": 742
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.1785995279307633,
|
| 755 |
+
"grad_norm": NaN,
|
| 756 |
+
"learning_rate": 5.570970386586469e-05,
|
| 757 |
+
"loss": 0.0,
|
| 758 |
+
"step": 749
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.1896144767899293,
|
| 762 |
+
"grad_norm": NaN,
|
| 763 |
+
"learning_rate": 5.492877111012218e-05,
|
| 764 |
+
"loss": 0.0,
|
| 765 |
+
"step": 756
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.2006294256490952,
|
| 769 |
+
"grad_norm": NaN,
|
| 770 |
+
"learning_rate": 5.414662225385903e-05,
|
| 771 |
+
"loss": 0.0,
|
| 772 |
+
"step": 763
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.2116443745082612,
|
| 776 |
+
"grad_norm": NaN,
|
| 777 |
+
"learning_rate": 5.336345028060199e-05,
|
| 778 |
+
"loss": 0.0,
|
| 779 |
+
"step": 770
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.2226593233674272,
|
| 783 |
+
"grad_norm": NaN,
|
| 784 |
+
"learning_rate": 5.257944842631658e-05,
|
| 785 |
+
"loss": 0.0,
|
| 786 |
+
"step": 777
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.2336742722265932,
|
| 790 |
+
"grad_norm": NaN,
|
| 791 |
+
"learning_rate": 5.179481013172912e-05,
|
| 792 |
+
"loss": 0.0,
|
| 793 |
+
"step": 784
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.2446892210857592,
|
| 797 |
+
"grad_norm": NaN,
|
| 798 |
+
"learning_rate": 5.100972899459796e-05,
|
| 799 |
+
"loss": 0.0,
|
| 800 |
+
"step": 791
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.2557041699449252,
|
| 804 |
+
"grad_norm": NaN,
|
| 805 |
+
"learning_rate": 5.022439872194629e-05,
|
| 806 |
+
"loss": 0.0,
|
| 807 |
+
"step": 798
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.2667191188040912,
|
| 811 |
+
"grad_norm": NaN,
|
| 812 |
+
"learning_rate": 4.943901308226771e-05,
|
| 813 |
+
"loss": 0.0,
|
| 814 |
+
"step": 805
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.2777340676632574,
|
| 818 |
+
"grad_norm": NaN,
|
| 819 |
+
"learning_rate": 4.865376585771687e-05,
|
| 820 |
+
"loss": 0.0,
|
| 821 |
+
"step": 812
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.2887490165224234,
|
| 825 |
+
"grad_norm": NaN,
|
| 826 |
+
"learning_rate": 4.7868850796296495e-05,
|
| 827 |
+
"loss": 0.0,
|
| 828 |
+
"step": 819
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.2997639653815893,
|
| 832 |
+
"grad_norm": NaN,
|
| 833 |
+
"learning_rate": 4.708446156405307e-05,
|
| 834 |
+
"loss": 0.0,
|
| 835 |
+
"step": 826
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.3107789142407553,
|
| 839 |
+
"grad_norm": NaN,
|
| 840 |
+
"learning_rate": 4.630079169729257e-05,
|
| 841 |
+
"loss": 0.0,
|
| 842 |
+
"step": 833
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.3217938630999213,
|
| 846 |
+
"grad_norm": NaN,
|
| 847 |
+
"learning_rate": 4.551803455482833e-05,
|
| 848 |
+
"loss": 0.0,
|
| 849 |
+
"step": 840
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.3328088119590873,
|
| 853 |
+
"grad_norm": NaN,
|
| 854 |
+
"learning_rate": 4.473638327027259e-05,
|
| 855 |
+
"loss": 0.0,
|
| 856 |
+
"step": 847
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.3438237608182533,
|
| 860 |
+
"grad_norm": NaN,
|
| 861 |
+
"learning_rate": 4.395603070438373e-05,
|
| 862 |
+
"loss": 0.0,
|
| 863 |
+
"step": 854
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.3548387096774195,
|
| 867 |
+
"grad_norm": NaN,
|
| 868 |
+
"learning_rate": 4.31771693974807e-05,
|
| 869 |
+
"loss": 0.0,
|
| 870 |
+
"step": 861
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.3658536585365852,
|
| 874 |
+
"grad_norm": NaN,
|
| 875 |
+
"learning_rate": 4.239999152193664e-05,
|
| 876 |
+
"loss": 0.0,
|
| 877 |
+
"step": 868
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.3768686073957515,
|
| 881 |
+
"grad_norm": NaN,
|
| 882 |
+
"learning_rate": 4.162468883476319e-05,
|
| 883 |
+
"loss": 0.0,
|
| 884 |
+
"step": 875
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.3878835562549174,
|
| 888 |
+
"grad_norm": NaN,
|
| 889 |
+
"learning_rate": 4.085145263029726e-05,
|
| 890 |
+
"loss": 0.0,
|
| 891 |
+
"step": 882
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.3988985051140834,
|
| 895 |
+
"grad_norm": NaN,
|
| 896 |
+
"learning_rate": 4.008047369300218e-05,
|
| 897 |
+
"loss": 0.0,
|
| 898 |
+
"step": 889
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.4099134539732494,
|
| 902 |
+
"grad_norm": NaN,
|
| 903 |
+
"learning_rate": 3.9311942250394276e-05,
|
| 904 |
+
"loss": 0.0,
|
| 905 |
+
"step": 896
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.4209284028324154,
|
| 909 |
+
"grad_norm": NaN,
|
| 910 |
+
"learning_rate": 3.8546047926107256e-05,
|
| 911 |
+
"loss": 0.0,
|
| 912 |
+
"step": 903
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.4319433516915814,
|
| 916 |
+
"grad_norm": NaN,
|
| 917 |
+
"learning_rate": 3.778297969310529e-05,
|
| 918 |
+
"loss": 0.0,
|
| 919 |
+
"step": 910
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.4429583005507474,
|
| 923 |
+
"grad_norm": NaN,
|
| 924 |
+
"learning_rate": 3.7022925827056884e-05,
|
| 925 |
+
"loss": 0.0,
|
| 926 |
+
"step": 917
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.4539732494099136,
|
| 930 |
+
"grad_norm": NaN,
|
| 931 |
+
"learning_rate": 3.62660738598805e-05,
|
| 932 |
+
"loss": 0.0,
|
| 933 |
+
"step": 924
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.4649881982690793,
|
| 937 |
+
"grad_norm": NaN,
|
| 938 |
+
"learning_rate": 3.551261053347404e-05,
|
| 939 |
+
"loss": 0.0,
|
| 940 |
+
"step": 931
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.4760031471282455,
|
| 944 |
+
"grad_norm": NaN,
|
| 945 |
+
"learning_rate": 3.4762721753638995e-05,
|
| 946 |
+
"loss": 0.0,
|
| 947 |
+
"step": 938
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.4870180959874115,
|
| 951 |
+
"grad_norm": NaN,
|
| 952 |
+
"learning_rate": 3.401659254421094e-05,
|
| 953 |
+
"loss": 0.0,
|
| 954 |
+
"step": 945
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.4980330448465775,
|
| 958 |
+
"grad_norm": NaN,
|
| 959 |
+
"learning_rate": 3.3274407001407735e-05,
|
| 960 |
+
"loss": 0.0,
|
| 961 |
+
"step": 952
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.5090479937057435,
|
| 965 |
+
"grad_norm": NaN,
|
| 966 |
+
"learning_rate": 3.2536348248406534e-05,
|
| 967 |
+
"loss": 0.0,
|
| 968 |
+
"step": 959
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.5200629425649095,
|
| 972 |
+
"grad_norm": NaN,
|
| 973 |
+
"learning_rate": 3.1802598390160784e-05,
|
| 974 |
+
"loss": 0.0,
|
| 975 |
+
"step": 966
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.5310778914240757,
|
| 979 |
+
"grad_norm": NaN,
|
| 980 |
+
"learning_rate": 3.107333846846872e-05,
|
| 981 |
+
"loss": 0.0,
|
| 982 |
+
"step": 973
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.5420928402832415,
|
| 986 |
+
"grad_norm": NaN,
|
| 987 |
+
"learning_rate": 3.0348748417303823e-05,
|
| 988 |
+
"loss": 0.0,
|
| 989 |
+
"step": 980
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.5531077891424077,
|
| 993 |
+
"grad_norm": NaN,
|
| 994 |
+
"learning_rate": 2.9629007018418985e-05,
|
| 995 |
+
"loss": 0.0,
|
| 996 |
+
"step": 987
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.5641227380015734,
|
| 1000 |
+
"grad_norm": NaN,
|
| 1001 |
+
"learning_rate": 2.8914291857234636e-05,
|
| 1002 |
+
"loss": 0.0,
|
| 1003 |
+
"step": 994
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.5751376868607396,
|
| 1007 |
+
"grad_norm": NaN,
|
| 1008 |
+
"learning_rate": 2.8204779279022276e-05,
|
| 1009 |
+
"loss": 0.0,
|
| 1010 |
+
"step": 1001
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.5861526357199056,
|
| 1014 |
+
"grad_norm": NaN,
|
| 1015 |
+
"learning_rate": 2.7500644345393943e-05,
|
| 1016 |
+
"loss": 0.0,
|
| 1017 |
+
"step": 1008
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.5971675845790716,
|
| 1021 |
+
"grad_norm": NaN,
|
| 1022 |
+
"learning_rate": 2.68020607911083e-05,
|
| 1023 |
+
"loss": 0.0,
|
| 1024 |
+
"step": 1015
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.6081825334382376,
|
| 1028 |
+
"grad_norm": NaN,
|
| 1029 |
+
"learning_rate": 2.610920098120424e-05,
|
| 1030 |
+
"loss": 0.0,
|
| 1031 |
+
"step": 1022
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.6191974822974036,
|
| 1035 |
+
"grad_norm": NaN,
|
| 1036 |
+
"learning_rate": 2.5422235868472345e-05,
|
| 1037 |
+
"loss": 0.0,
|
| 1038 |
+
"step": 1029
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.6302124311565698,
|
| 1042 |
+
"grad_norm": NaN,
|
| 1043 |
+
"learning_rate": 2.4741334951274947e-05,
|
| 1044 |
+
"loss": 0.0,
|
| 1045 |
+
"step": 1036
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.6412273800157355,
|
| 1049 |
+
"grad_norm": NaN,
|
| 1050 |
+
"learning_rate": 2.40666662317248e-05,
|
| 1051 |
+
"loss": 0.0,
|
| 1052 |
+
"step": 1043
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.6522423288749017,
|
| 1056 |
+
"grad_norm": NaN,
|
| 1057 |
+
"learning_rate": 2.3398396174233178e-05,
|
| 1058 |
+
"loss": 0.0,
|
| 1059 |
+
"step": 1050
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.6632572777340675,
|
| 1063 |
+
"grad_norm": NaN,
|
| 1064 |
+
"learning_rate": 2.2736689664437217e-05,
|
| 1065 |
+
"loss": 0.0,
|
| 1066 |
+
"step": 1057
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.6742722265932337,
|
| 1070 |
+
"grad_norm": NaN,
|
| 1071 |
+
"learning_rate": 2.2081709968516866e-05,
|
| 1072 |
+
"loss": 0.0,
|
| 1073 |
+
"step": 1064
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.6852871754523997,
|
| 1077 |
+
"grad_norm": NaN,
|
| 1078 |
+
"learning_rate": 2.1433618692911467e-05,
|
| 1079 |
+
"loss": 0.0,
|
| 1080 |
+
"step": 1071
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.6963021243115657,
|
| 1084 |
+
"grad_norm": NaN,
|
| 1085 |
+
"learning_rate": 2.0792575744445653e-05,
|
| 1086 |
+
"loss": 0.0,
|
| 1087 |
+
"step": 1078
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.7073170731707317,
|
| 1091 |
+
"grad_norm": NaN,
|
| 1092 |
+
"learning_rate": 2.015873929087482e-05,
|
| 1093 |
+
"loss": 0.0,
|
| 1094 |
+
"step": 1085
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.7183320220298977,
|
| 1098 |
+
"grad_norm": NaN,
|
| 1099 |
+
"learning_rate": 1.95322657218596e-05,
|
| 1100 |
+
"loss": 0.0,
|
| 1101 |
+
"step": 1092
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.7293469708890639,
|
| 1105 |
+
"grad_norm": NaN,
|
| 1106 |
+
"learning_rate": 1.8913309610379015e-05,
|
| 1107 |
+
"loss": 0.0,
|
| 1108 |
+
"step": 1099
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.7403619197482296,
|
| 1112 |
+
"grad_norm": NaN,
|
| 1113 |
+
"learning_rate": 1.8302023674591935e-05,
|
| 1114 |
+
"loss": 0.0,
|
| 1115 |
+
"step": 1106
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.7513768686073958,
|
| 1119 |
+
"grad_norm": NaN,
|
| 1120 |
+
"learning_rate": 1.7698558740156135e-05,
|
| 1121 |
+
"loss": 0.0,
|
| 1122 |
+
"step": 1113
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.7623918174665618,
|
| 1126 |
+
"grad_norm": NaN,
|
| 1127 |
+
"learning_rate": 1.7103063703014372e-05,
|
| 1128 |
+
"loss": 0.0,
|
| 1129 |
+
"step": 1120
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.7734067663257278,
|
| 1133 |
+
"grad_norm": NaN,
|
| 1134 |
+
"learning_rate": 1.6515685492656467e-05,
|
| 1135 |
+
"loss": 0.0,
|
| 1136 |
+
"step": 1127
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.7844217151848938,
|
| 1140 |
+
"grad_norm": NaN,
|
| 1141 |
+
"learning_rate": 1.59365690358667e-05,
|
| 1142 |
+
"loss": 0.0,
|
| 1143 |
+
"step": 1134
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.7954366640440598,
|
| 1147 |
+
"grad_norm": NaN,
|
| 1148 |
+
"learning_rate": 1.5365857220965275e-05,
|
| 1149 |
+
"loss": 0.0,
|
| 1150 |
+
"step": 1141
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.8064516129032258,
|
| 1154 |
+
"grad_norm": NaN,
|
| 1155 |
+
"learning_rate": 1.4803690862552755e-05,
|
| 1156 |
+
"loss": 0.0,
|
| 1157 |
+
"step": 1148
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.8174665617623917,
|
| 1161 |
+
"grad_norm": NaN,
|
| 1162 |
+
"learning_rate": 1.4250208666766235e-05,
|
| 1163 |
+
"loss": 0.0,
|
| 1164 |
+
"step": 1155
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.828481510621558,
|
| 1168 |
+
"grad_norm": NaN,
|
| 1169 |
+
"learning_rate": 1.3705547197055584e-05,
|
| 1170 |
+
"loss": 0.0,
|
| 1171 |
+
"step": 1162
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.8394964594807237,
|
| 1175 |
+
"grad_norm": NaN,
|
| 1176 |
+
"learning_rate": 1.3169840840488501e-05,
|
| 1177 |
+
"loss": 0.0,
|
| 1178 |
+
"step": 1169
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.85051140833989,
|
| 1182 |
+
"grad_norm": NaN,
|
| 1183 |
+
"learning_rate": 1.2643221774592518e-05,
|
| 1184 |
+
"loss": 0.0,
|
| 1185 |
+
"step": 1176
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.861526357199056,
|
| 1189 |
+
"grad_norm": NaN,
|
| 1190 |
+
"learning_rate": 1.2125819934742188e-05,
|
| 1191 |
+
"loss": 0.0,
|
| 1192 |
+
"step": 1183
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.8725413060582219,
|
| 1196 |
+
"grad_norm": NaN,
|
| 1197 |
+
"learning_rate": 1.1617762982099446e-05,
|
| 1198 |
+
"loss": 0.0,
|
| 1199 |
+
"step": 1190
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.8835562549173879,
|
| 1203 |
+
"grad_norm": NaN,
|
| 1204 |
+
"learning_rate": 1.1119176272115128e-05,
|
| 1205 |
+
"loss": 0.0,
|
| 1206 |
+
"step": 1197
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.8945712037765539,
|
| 1210 |
+
"grad_norm": NaN,
|
| 1211 |
+
"learning_rate": 1.0630182823599399e-05,
|
| 1212 |
+
"loss": 0.0,
|
| 1213 |
+
"step": 1204
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.90558615263572,
|
| 1217 |
+
"grad_norm": NaN,
|
| 1218 |
+
"learning_rate": 1.0150903288368741e-05,
|
| 1219 |
+
"loss": 0.0,
|
| 1220 |
+
"step": 1211
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.9166011014948858,
|
| 1224 |
+
"grad_norm": NaN,
|
| 1225 |
+
"learning_rate": 9.681455921476839e-06,
|
| 1226 |
+
"loss": 0.0,
|
| 1227 |
+
"step": 1218
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.927616050354052,
|
| 1231 |
+
"grad_norm": NaN,
|
| 1232 |
+
"learning_rate": 9.221956552036992e-06,
|
| 1233 |
+
"loss": 0.0,
|
| 1234 |
+
"step": 1225
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.9386309992132178,
|
| 1238 |
+
"grad_norm": NaN,
|
| 1239 |
+
"learning_rate": 8.772518554642973e-06,
|
| 1240 |
+
"loss": 0.0,
|
| 1241 |
+
"step": 1232
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.949645948072384,
|
| 1245 |
+
"grad_norm": NaN,
|
| 1246 |
+
"learning_rate": 8.333252821395526e-06,
|
| 1247 |
+
"loss": 0.0,
|
| 1248 |
+
"step": 1239
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.96066089693155,
|
| 1252 |
+
"grad_norm": NaN,
|
| 1253 |
+
"learning_rate": 7.904267734541498e-06,
|
| 1254 |
+
"loss": 0.0,
|
| 1255 |
+
"step": 1246
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.971675845790716,
|
| 1259 |
+
"grad_norm": NaN,
|
| 1260 |
+
"learning_rate": 7.485669139732004e-06,
|
| 1261 |
+
"loss": 0.0,
|
| 1262 |
+
"step": 1253
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.982690794649882,
|
| 1266 |
+
"grad_norm": NaN,
|
| 1267 |
+
"learning_rate": 7.077560319906695e-06,
|
| 1268 |
+
"loss": 0.0,
|
| 1269 |
+
"step": 1260
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.993705743509048,
|
| 1273 |
+
"grad_norm": NaN,
|
| 1274 |
+
"learning_rate": 6.680041969810203e-06,
|
| 1275 |
+
"loss": 0.0,
|
| 1276 |
+
"step": 1267
|
| 1277 |
}
|
| 1278 |
],
|
| 1279 |
"logging_steps": 7,
|
|
|
|
| 1293 |
"attributes": {}
|
| 1294 |
}
|
| 1295 |
},
|
| 1296 |
+
"total_flos": 9.064492133221663e+17,
|
| 1297 |
"train_batch_size": 2,
|
| 1298 |
"trial_name": null,
|
| 1299 |
"trial_params": null
|