Training in progress, step 30000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100170757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ef929787429c88c576570a6fdf928468aedd3cf5c685150c4d00c23ed2574b5
|
| 3 |
size 100170757
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b649041f4e942a1c71886ca3f83f11fc846bb4752950f41b84cd207e3cc556c
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e521fc0b39ea1a8ce6e0a681bc8a834da87e83fd7cd3754aacc6c4b558e0937
|
| 3 |
size 14439
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246897640
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:677543783c6139b35f47c70ebab6ad516807591d9ad24cec274ace85b8305217
|
| 3 |
size 246897640
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -606,11 +606,311 @@
|
|
| 606 |
"learning_rate": 0.0008149872553192515,
|
| 607 |
"loss": 4.2065,
|
| 608 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 609 |
}
|
| 610 |
],
|
| 611 |
"max_steps": 500000,
|
| 612 |
"num_train_epochs": 3,
|
| 613 |
-
"total_flos":
|
| 614 |
"trial_name": null,
|
| 615 |
"trial_params": null
|
| 616 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1289213579716373,
|
| 5 |
+
"global_step": 30000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 606 |
"learning_rate": 0.0008149872553192515,
|
| 607 |
"loss": 4.2065,
|
| 608 |
"step": 20000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.09,
|
| 612 |
+
"learning_rate": 0.0008232037327492777,
|
| 613 |
+
"loss": 4.1773,
|
| 614 |
+
"step": 20200
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.09,
|
| 618 |
+
"learning_rate": 0.0008314970061979818,
|
| 619 |
+
"loss": 4.1904,
|
| 620 |
+
"step": 20400
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.09,
|
| 624 |
+
"learning_rate": 0.0008398669301501703,
|
| 625 |
+
"loss": 4.1868,
|
| 626 |
+
"step": 20600
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.09,
|
| 630 |
+
"learning_rate": 0.0008483133577457148,
|
| 631 |
+
"loss": 4.2006,
|
| 632 |
+
"step": 20800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.09,
|
| 636 |
+
"learning_rate": 0.0008568361407821495,
|
| 637 |
+
"loss": 4.1467,
|
| 638 |
+
"step": 21000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.09,
|
| 642 |
+
"learning_rate": 0.0008654351297172607,
|
| 643 |
+
"loss": 4.1585,
|
| 644 |
+
"step": 21200
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.09,
|
| 648 |
+
"learning_rate": 0.0008741101736717116,
|
| 649 |
+
"loss": 4.1547,
|
| 650 |
+
"step": 21400
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.09,
|
| 654 |
+
"learning_rate": 0.0008828611204316911,
|
| 655 |
+
"loss": 4.1557,
|
| 656 |
+
"step": 21600
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.09,
|
| 660 |
+
"learning_rate": 0.0008916878164515838,
|
| 661 |
+
"loss": 4.1496,
|
| 662 |
+
"step": 21800
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.09,
|
| 666 |
+
"learning_rate": 0.0009005901068566691,
|
| 667 |
+
"loss": 4.1434,
|
| 668 |
+
"step": 22000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.1,
|
| 672 |
+
"learning_rate": 0.0009095678354458306,
|
| 673 |
+
"loss": 4.1173,
|
| 674 |
+
"step": 22200
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.1,
|
| 678 |
+
"learning_rate": 0.0009186208446943008,
|
| 679 |
+
"loss": 4.1364,
|
| 680 |
+
"step": 22400
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.1,
|
| 684 |
+
"learning_rate": 0.0009277489757564244,
|
| 685 |
+
"loss": 4.1445,
|
| 686 |
+
"step": 22600
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.1,
|
| 690 |
+
"learning_rate": 0.0009369520684684475,
|
| 691 |
+
"loss": 4.1156,
|
| 692 |
+
"step": 22800
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.1,
|
| 696 |
+
"learning_rate": 0.0009462299613513248,
|
| 697 |
+
"loss": 4.1033,
|
| 698 |
+
"step": 23000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.1,
|
| 702 |
+
"learning_rate": 0.0009555824916135536,
|
| 703 |
+
"loss": 4.1187,
|
| 704 |
+
"step": 23200
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.1,
|
| 708 |
+
"learning_rate": 0.0009650094951540386,
|
| 709 |
+
"loss": 4.0823,
|
| 710 |
+
"step": 23400
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.1,
|
| 714 |
+
"learning_rate": 0.0009745108065649499,
|
| 715 |
+
"loss": 4.0624,
|
| 716 |
+
"step": 23600
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.1,
|
| 720 |
+
"learning_rate": 0.0009840862591346498,
|
| 721 |
+
"loss": 4.0845,
|
| 722 |
+
"step": 23800
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.1,
|
| 726 |
+
"learning_rate": 0.0009937356848506058,
|
| 727 |
+
"loss": 4.0483,
|
| 728 |
+
"step": 24000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.1,
|
| 732 |
+
"learning_rate": 0.001003458914402332,
|
| 733 |
+
"loss": 4.0512,
|
| 734 |
+
"step": 24200
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.1,
|
| 738 |
+
"learning_rate": 0.0010132557771843787,
|
| 739 |
+
"loss": 4.0606,
|
| 740 |
+
"step": 24400
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.11,
|
| 744 |
+
"learning_rate": 0.0010231261012993067,
|
| 745 |
+
"loss": 4.046,
|
| 746 |
+
"step": 24600
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.11,
|
| 750 |
+
"learning_rate": 0.0010330697135607168,
|
| 751 |
+
"loss": 4.0315,
|
| 752 |
+
"step": 24800
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.11,
|
| 756 |
+
"learning_rate": 0.00104308643949628,
|
| 757 |
+
"loss": 4.0179,
|
| 758 |
+
"step": 25000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.11,
|
| 762 |
+
"learning_rate": 0.001053176103350803,
|
| 763 |
+
"loss": 4.0351,
|
| 764 |
+
"step": 25200
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.11,
|
| 768 |
+
"learning_rate": 0.0010633385280893123,
|
| 769 |
+
"loss": 4.02,
|
| 770 |
+
"step": 25400
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.11,
|
| 774 |
+
"learning_rate": 0.0010735735354001595,
|
| 775 |
+
"loss": 4.0201,
|
| 776 |
+
"step": 25600
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.11,
|
| 780 |
+
"learning_rate": 0.0010838809456981471,
|
| 781 |
+
"loss": 4.0044,
|
| 782 |
+
"step": 25800
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.11,
|
| 786 |
+
"learning_rate": 0.001094260578127686,
|
| 787 |
+
"loss": 3.9914,
|
| 788 |
+
"step": 26000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.11,
|
| 792 |
+
"learning_rate": 0.0011047122505659646,
|
| 793 |
+
"loss": 3.9991,
|
| 794 |
+
"step": 26200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.11,
|
| 798 |
+
"learning_rate": 0.0011152357796261423,
|
| 799 |
+
"loss": 4.0109,
|
| 800 |
+
"step": 26400
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.11,
|
| 804 |
+
"learning_rate": 0.0011258309806605731,
|
| 805 |
+
"loss": 4.0405,
|
| 806 |
+
"step": 26600
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.12,
|
| 810 |
+
"learning_rate": 0.0011364976677640387,
|
| 811 |
+
"loss": 4.0349,
|
| 812 |
+
"step": 26800
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.12,
|
| 816 |
+
"learning_rate": 0.0011472356537770186,
|
| 817 |
+
"loss": 4.0312,
|
| 818 |
+
"step": 27000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.12,
|
| 822 |
+
"learning_rate": 0.0011580447502889633,
|
| 823 |
+
"loss": 4.0185,
|
| 824 |
+
"step": 27200
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.12,
|
| 828 |
+
"learning_rate": 0.0011689247676416152,
|
| 829 |
+
"loss": 4.011,
|
| 830 |
+
"step": 27400
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.12,
|
| 834 |
+
"learning_rate": 0.0011798755149323176,
|
| 835 |
+
"loss": 3.9898,
|
| 836 |
+
"step": 27600
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.12,
|
| 840 |
+
"learning_rate": 0.001190896800017379,
|
| 841 |
+
"loss": 3.981,
|
| 842 |
+
"step": 27800
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.12,
|
| 846 |
+
"learning_rate": 0.0012019884295154416,
|
| 847 |
+
"loss": 3.949,
|
| 848 |
+
"step": 28000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.12,
|
| 852 |
+
"learning_rate": 0.0012131502088108658,
|
| 853 |
+
"loss": 3.9896,
|
| 854 |
+
"step": 28200
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.12,
|
| 858 |
+
"learning_rate": 0.0012243819420571598,
|
| 859 |
+
"loss": 3.9951,
|
| 860 |
+
"step": 28400
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.12,
|
| 864 |
+
"learning_rate": 0.0012356834321804039,
|
| 865 |
+
"loss": 4.0361,
|
| 866 |
+
"step": 28600
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.12,
|
| 870 |
+
"learning_rate": 0.0012470544808827113,
|
| 871 |
+
"loss": 4.1212,
|
| 872 |
+
"step": 28800
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.12,
|
| 876 |
+
"learning_rate": 0.001258494888645708,
|
| 877 |
+
"loss": 4.0721,
|
| 878 |
+
"step": 29000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.13,
|
| 882 |
+
"learning_rate": 0.0012700044547340368,
|
| 883 |
+
"loss": 4.0311,
|
| 884 |
+
"step": 29200
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.13,
|
| 888 |
+
"learning_rate": 0.0012815829771988738,
|
| 889 |
+
"loss": 4.0114,
|
| 890 |
+
"step": 29400
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.13,
|
| 894 |
+
"learning_rate": 0.001293230252881479,
|
| 895 |
+
"loss": 3.9868,
|
| 896 |
+
"step": 29600
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.13,
|
| 900 |
+
"learning_rate": 0.0013049460774167514,
|
| 901 |
+
"loss": 3.9881,
|
| 902 |
+
"step": 29800
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.13,
|
| 906 |
+
"learning_rate": 0.0013167302452368242,
|
| 907 |
+
"loss": 3.9705,
|
| 908 |
+
"step": 30000
|
| 909 |
}
|
| 910 |
],
|
| 911 |
"max_steps": 500000,
|
| 912 |
"num_train_epochs": 3,
|
| 913 |
+
"total_flos": 4.781489946624e+16,
|
| 914 |
"trial_name": null,
|
| 915 |
"trial_params": null
|
| 916 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b649041f4e942a1c71886ca3f83f11fc846bb4752950f41b84cd207e3cc556c
|
| 3 |
size 146774203
|