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 sha256:991640a131f2a0a32a17ba1af542f31b7776932281bd0a73639dd3a4960e3a40
|
| 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:c10b0dd9b3e24c2c1ca2db9a9e924f901a4d183202a5c32479436a975f462f9d
|
| 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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f754532050c5b1775c36eee5da06c337e5bc03296f22630efbd5a1c263b25446
|
| 3 |
size 14503
|
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:dd2f5c3de2046b6ec35a993f60879cf7288b2cb7906fdbd23f2869d9429fbe1b
|
| 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": 8.149872553192528e-05,
|
| 607 |
"loss": 3.606,
|
| 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": 8.149872553192528e-05,
|
| 607 |
"loss": 3.606,
|
| 608 |
"step": 20000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.09,
|
| 612 |
+
"learning_rate": 8.232037327492777e-05,
|
| 613 |
+
"loss": 3.6232,
|
| 614 |
+
"step": 20200
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.09,
|
| 618 |
+
"learning_rate": 8.314970061979832e-05,
|
| 619 |
+
"loss": 3.6182,
|
| 620 |
+
"step": 20400
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.09,
|
| 624 |
+
"learning_rate": 8.398669301501699e-05,
|
| 625 |
+
"loss": 3.5904,
|
| 626 |
+
"step": 20600
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.09,
|
| 630 |
+
"learning_rate": 8.483133577457161e-05,
|
| 631 |
+
"loss": 3.6162,
|
| 632 |
+
"step": 20800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.09,
|
| 636 |
+
"learning_rate": 8.568361407821506e-05,
|
| 637 |
+
"loss": 3.6084,
|
| 638 |
+
"step": 21000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.09,
|
| 642 |
+
"learning_rate": 8.65435129717262e-05,
|
| 643 |
+
"loss": 3.598,
|
| 644 |
+
"step": 21200
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.09,
|
| 648 |
+
"learning_rate": 8.74110173671712e-05,
|
| 649 |
+
"loss": 3.6229,
|
| 650 |
+
"step": 21400
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.09,
|
| 654 |
+
"learning_rate": 8.828611204316915e-05,
|
| 655 |
+
"loss": 3.6101,
|
| 656 |
+
"step": 21600
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.09,
|
| 660 |
+
"learning_rate": 8.916878164515847e-05,
|
| 661 |
+
"loss": 3.5859,
|
| 662 |
+
"step": 21800
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.09,
|
| 666 |
+
"learning_rate": 9.005901068566706e-05,
|
| 667 |
+
"loss": 3.6207,
|
| 668 |
+
"step": 22000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.1,
|
| 672 |
+
"learning_rate": 9.095678354458317e-05,
|
| 673 |
+
"loss": 3.6058,
|
| 674 |
+
"step": 22200
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.1,
|
| 678 |
+
"learning_rate": 9.18620844694301e-05,
|
| 679 |
+
"loss": 3.5935,
|
| 680 |
+
"step": 22400
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.1,
|
| 684 |
+
"learning_rate": 9.27748975756424e-05,
|
| 685 |
+
"loss": 3.5917,
|
| 686 |
+
"step": 22600
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.1,
|
| 690 |
+
"learning_rate": 9.369520684684475e-05,
|
| 691 |
+
"loss": 3.5861,
|
| 692 |
+
"step": 22800
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.1,
|
| 696 |
+
"learning_rate": 9.462299613513243e-05,
|
| 697 |
+
"loss": 3.5976,
|
| 698 |
+
"step": 23000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.1,
|
| 702 |
+
"learning_rate": 9.555824916135554e-05,
|
| 703 |
+
"loss": 3.5914,
|
| 704 |
+
"step": 23200
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.1,
|
| 708 |
+
"learning_rate": 9.650094951540393e-05,
|
| 709 |
+
"loss": 3.5778,
|
| 710 |
+
"step": 23400
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.1,
|
| 714 |
+
"learning_rate": 9.745108065649507e-05,
|
| 715 |
+
"loss": 3.6049,
|
| 716 |
+
"step": 23600
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.1,
|
| 720 |
+
"learning_rate": 9.840862591346507e-05,
|
| 721 |
+
"loss": 3.5878,
|
| 722 |
+
"step": 23800
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.1,
|
| 726 |
+
"learning_rate": 9.93735684850606e-05,
|
| 727 |
+
"loss": 3.5918,
|
| 728 |
+
"step": 24000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.1,
|
| 732 |
+
"learning_rate": 0.00010034589144023332,
|
| 733 |
+
"loss": 3.59,
|
| 734 |
+
"step": 24200
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.1,
|
| 738 |
+
"learning_rate": 0.00010132557771843796,
|
| 739 |
+
"loss": 3.5815,
|
| 740 |
+
"step": 24400
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.11,
|
| 744 |
+
"learning_rate": 0.00010231261012993076,
|
| 745 |
+
"loss": 3.5806,
|
| 746 |
+
"step": 24600
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.11,
|
| 750 |
+
"learning_rate": 0.0001033069713560718,
|
| 751 |
+
"loss": 3.5927,
|
| 752 |
+
"step": 24800
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.11,
|
| 756 |
+
"learning_rate": 0.00010430864394962811,
|
| 757 |
+
"loss": 3.595,
|
| 758 |
+
"step": 25000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.11,
|
| 762 |
+
"learning_rate": 0.00010531761033508039,
|
| 763 |
+
"loss": 3.5751,
|
| 764 |
+
"step": 25200
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.11,
|
| 768 |
+
"learning_rate": 0.00010633385280893134,
|
| 769 |
+
"loss": 3.5741,
|
| 770 |
+
"step": 25400
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.11,
|
| 774 |
+
"learning_rate": 0.00010735735354001593,
|
| 775 |
+
"loss": 3.5752,
|
| 776 |
+
"step": 25600
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.11,
|
| 780 |
+
"learning_rate": 0.00010838809456981471,
|
| 781 |
+
"loss": 3.5666,
|
| 782 |
+
"step": 25800
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.11,
|
| 786 |
+
"learning_rate": 0.00010942605781276871,
|
| 787 |
+
"loss": 3.5594,
|
| 788 |
+
"step": 26000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.11,
|
| 792 |
+
"learning_rate": 0.00011047122505659652,
|
| 793 |
+
"loss": 3.5652,
|
| 794 |
+
"step": 26200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.11,
|
| 798 |
+
"learning_rate": 0.00011152357796261427,
|
| 799 |
+
"loss": 3.5546,
|
| 800 |
+
"step": 26400
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.11,
|
| 804 |
+
"learning_rate": 0.00011258309806605742,
|
| 805 |
+
"loss": 3.5427,
|
| 806 |
+
"step": 26600
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.12,
|
| 810 |
+
"learning_rate": 0.00011364976677640404,
|
| 811 |
+
"loss": 3.5766,
|
| 812 |
+
"step": 26800
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.12,
|
| 816 |
+
"learning_rate": 0.00011472356537770196,
|
| 817 |
+
"loss": 3.5791,
|
| 818 |
+
"step": 27000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.12,
|
| 822 |
+
"learning_rate": 0.00011580447502889649,
|
| 823 |
+
"loss": 3.5722,
|
| 824 |
+
"step": 27200
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.12,
|
| 828 |
+
"learning_rate": 0.00011689247676416152,
|
| 829 |
+
"loss": 3.5775,
|
| 830 |
+
"step": 27400
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.12,
|
| 834 |
+
"learning_rate": 0.00011798755149323179,
|
| 835 |
+
"loss": 3.5579,
|
| 836 |
+
"step": 27600
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.12,
|
| 840 |
+
"learning_rate": 0.00011908968000173793,
|
| 841 |
+
"loss": 3.5618,
|
| 842 |
+
"step": 27800
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.12,
|
| 846 |
+
"learning_rate": 0.00012019884295154414,
|
| 847 |
+
"loss": 3.5614,
|
| 848 |
+
"step": 28000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.12,
|
| 852 |
+
"learning_rate": 0.00012131502088108667,
|
| 853 |
+
"loss": 3.5444,
|
| 854 |
+
"step": 28200
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.12,
|
| 858 |
+
"learning_rate": 0.00012243819420571607,
|
| 859 |
+
"loss": 3.5463,
|
| 860 |
+
"step": 28400
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.12,
|
| 864 |
+
"learning_rate": 0.00012356834321804048,
|
| 865 |
+
"loss": 3.5502,
|
| 866 |
+
"step": 28600
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.12,
|
| 870 |
+
"learning_rate": 0.00012470544808827115,
|
| 871 |
+
"loss": 3.5287,
|
| 872 |
+
"step": 28800
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.12,
|
| 876 |
+
"learning_rate": 0.00012584948886457082,
|
| 877 |
+
"loss": 3.5414,
|
| 878 |
+
"step": 29000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.13,
|
| 882 |
+
"learning_rate": 0.00012700044547340377,
|
| 883 |
+
"loss": 3.5504,
|
| 884 |
+
"step": 29200
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.13,
|
| 888 |
+
"learning_rate": 0.00012815829771988744,
|
| 889 |
+
"loss": 3.5381,
|
| 890 |
+
"step": 29400
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.13,
|
| 894 |
+
"learning_rate": 0.00012932302528814797,
|
| 895 |
+
"loss": 3.5551,
|
| 896 |
+
"step": 29600
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.13,
|
| 900 |
+
"learning_rate": 0.00013049460774167522,
|
| 901 |
+
"loss": 3.5331,
|
| 902 |
+
"step": 29800
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.13,
|
| 906 |
+
"learning_rate": 0.00013167302452368236,
|
| 907 |
+
"loss": 3.5359,
|
| 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:c10b0dd9b3e24c2c1ca2db9a9e924f901a4d183202a5c32479436a975f462f9d
|
| 3 |
size 146774203
|