Training in progress, step 600, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 234681136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1d34d69dffb2c4b13f69101d37856a75aa09dc083a674348259bfa0f2c28ab9
|
| 3 |
size 234681136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469516363
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39504b7c024bff9fa0fb04bf688ef360e9faf081aaec354fe731018ad0d7e11a
|
| 3 |
size 469516363
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25e3cd90b4b52da1b6dd5f1c3a7c71a1534283f13013c59ba10d201654481663
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf2ddddac28bab3ce3bced5d6f919d64d2cfe7cd07c4a0f8d5c9ad1b67097bee
|
| 3 |
size 1465
|
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": 0.
|
| 6 |
"eval_steps": 50,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -632,6 +632,318 @@
|
|
| 632 |
"eval_samples_per_second": 5.482,
|
| 633 |
"eval_steps_per_second": 2.815,
|
| 634 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 635 |
}
|
| 636 |
],
|
| 637 |
"logging_steps": 5,
|
|
@@ -651,7 +963,7 @@
|
|
| 651 |
"attributes": {}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
-
"total_flos": 1.
|
| 655 |
"train_batch_size": 2,
|
| 656 |
"trial_name": null,
|
| 657 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6,
|
| 6 |
"eval_steps": 50,
|
| 7 |
+
"global_step": 600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 632 |
"eval_samples_per_second": 5.482,
|
| 633 |
"eval_steps_per_second": 2.815,
|
| 634 |
"step": 400
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.405,
|
| 638 |
+
"grad_norm": 24.5,
|
| 639 |
+
"learning_rate": 5e-05,
|
| 640 |
+
"loss": 3.0751102447509764,
|
| 641 |
+
"step": 405
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.41,
|
| 645 |
+
"grad_norm": 2.65625,
|
| 646 |
+
"learning_rate": 5e-05,
|
| 647 |
+
"loss": 3.0429092407226563,
|
| 648 |
+
"step": 410
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.415,
|
| 652 |
+
"grad_norm": 16.0,
|
| 653 |
+
"learning_rate": 5e-05,
|
| 654 |
+
"loss": 3.0210216522216795,
|
| 655 |
+
"step": 415
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.42,
|
| 659 |
+
"grad_norm": 7.53125,
|
| 660 |
+
"learning_rate": 5e-05,
|
| 661 |
+
"loss": 3.065318489074707,
|
| 662 |
+
"step": 420
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.425,
|
| 666 |
+
"grad_norm": 24.375,
|
| 667 |
+
"learning_rate": 5e-05,
|
| 668 |
+
"loss": 3.0230634689331053,
|
| 669 |
+
"step": 425
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.43,
|
| 673 |
+
"grad_norm": 5.625,
|
| 674 |
+
"learning_rate": 5e-05,
|
| 675 |
+
"loss": 3.02874698638916,
|
| 676 |
+
"step": 430
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.435,
|
| 680 |
+
"grad_norm": 16.5,
|
| 681 |
+
"learning_rate": 5e-05,
|
| 682 |
+
"loss": 3.052432632446289,
|
| 683 |
+
"step": 435
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.44,
|
| 687 |
+
"grad_norm": 15.9375,
|
| 688 |
+
"learning_rate": 5e-05,
|
| 689 |
+
"loss": 3.0222875595092775,
|
| 690 |
+
"step": 440
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.445,
|
| 694 |
+
"grad_norm": 19.0,
|
| 695 |
+
"learning_rate": 5e-05,
|
| 696 |
+
"loss": 3.053955841064453,
|
| 697 |
+
"step": 445
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.45,
|
| 701 |
+
"grad_norm": 86.5,
|
| 702 |
+
"learning_rate": 5e-05,
|
| 703 |
+
"loss": 3.0460411071777345,
|
| 704 |
+
"step": 450
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.45,
|
| 708 |
+
"eval_loss": 3.317772626876831,
|
| 709 |
+
"eval_runtime": 6.7179,
|
| 710 |
+
"eval_samples_per_second": 5.508,
|
| 711 |
+
"eval_steps_per_second": 2.828,
|
| 712 |
+
"step": 450
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.455,
|
| 716 |
+
"grad_norm": 1.84375,
|
| 717 |
+
"learning_rate": 5e-05,
|
| 718 |
+
"loss": 3.115060806274414,
|
| 719 |
+
"step": 455
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.46,
|
| 723 |
+
"grad_norm": 19.375,
|
| 724 |
+
"learning_rate": 5e-05,
|
| 725 |
+
"loss": 3.071373176574707,
|
| 726 |
+
"step": 460
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.465,
|
| 730 |
+
"grad_norm": 6.6875,
|
| 731 |
+
"learning_rate": 5e-05,
|
| 732 |
+
"loss": 3.0433387756347656,
|
| 733 |
+
"step": 465
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.47,
|
| 737 |
+
"grad_norm": 2.09375,
|
| 738 |
+
"learning_rate": 5e-05,
|
| 739 |
+
"loss": 3.049169921875,
|
| 740 |
+
"step": 470
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.475,
|
| 744 |
+
"grad_norm": 3.9375,
|
| 745 |
+
"learning_rate": 5e-05,
|
| 746 |
+
"loss": 3.079736328125,
|
| 747 |
+
"step": 475
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.48,
|
| 751 |
+
"grad_norm": 3.796875,
|
| 752 |
+
"learning_rate": 5e-05,
|
| 753 |
+
"loss": 3.0374773025512694,
|
| 754 |
+
"step": 480
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.485,
|
| 758 |
+
"grad_norm": 37.25,
|
| 759 |
+
"learning_rate": 5e-05,
|
| 760 |
+
"loss": 3.022678756713867,
|
| 761 |
+
"step": 485
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.49,
|
| 765 |
+
"grad_norm": 65.0,
|
| 766 |
+
"learning_rate": 5e-05,
|
| 767 |
+
"loss": 3.032781410217285,
|
| 768 |
+
"step": 490
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.495,
|
| 772 |
+
"grad_norm": 10.375,
|
| 773 |
+
"learning_rate": 5e-05,
|
| 774 |
+
"loss": 3.0296302795410157,
|
| 775 |
+
"step": 495
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.5,
|
| 779 |
+
"grad_norm": 7.9375,
|
| 780 |
+
"learning_rate": 5e-05,
|
| 781 |
+
"loss": 3.0553735733032226,
|
| 782 |
+
"step": 500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.5,
|
| 786 |
+
"eval_loss": 3.3104944229125977,
|
| 787 |
+
"eval_runtime": 6.7677,
|
| 788 |
+
"eval_samples_per_second": 5.467,
|
| 789 |
+
"eval_steps_per_second": 2.807,
|
| 790 |
+
"step": 500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.505,
|
| 794 |
+
"grad_norm": 2.71875,
|
| 795 |
+
"learning_rate": 5e-05,
|
| 796 |
+
"loss": 3.063258743286133,
|
| 797 |
+
"step": 505
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.51,
|
| 801 |
+
"grad_norm": 10.4375,
|
| 802 |
+
"learning_rate": 5e-05,
|
| 803 |
+
"loss": 3.0316259384155275,
|
| 804 |
+
"step": 510
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.515,
|
| 808 |
+
"grad_norm": 9.5,
|
| 809 |
+
"learning_rate": 5e-05,
|
| 810 |
+
"loss": 3.0448724746704103,
|
| 811 |
+
"step": 515
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.52,
|
| 815 |
+
"grad_norm": 2.109375,
|
| 816 |
+
"learning_rate": 5e-05,
|
| 817 |
+
"loss": 3.0403762817382813,
|
| 818 |
+
"step": 520
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.525,
|
| 822 |
+
"grad_norm": 3.609375,
|
| 823 |
+
"learning_rate": 5e-05,
|
| 824 |
+
"loss": 2.9868940353393554,
|
| 825 |
+
"step": 525
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.53,
|
| 829 |
+
"grad_norm": 3.875,
|
| 830 |
+
"learning_rate": 5e-05,
|
| 831 |
+
"loss": 3.010245704650879,
|
| 832 |
+
"step": 530
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.535,
|
| 836 |
+
"grad_norm": 1.5859375,
|
| 837 |
+
"learning_rate": 5e-05,
|
| 838 |
+
"loss": 3.039686393737793,
|
| 839 |
+
"step": 535
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.54,
|
| 843 |
+
"grad_norm": 25.5,
|
| 844 |
+
"learning_rate": 5e-05,
|
| 845 |
+
"loss": 3.041441535949707,
|
| 846 |
+
"step": 540
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.545,
|
| 850 |
+
"grad_norm": 8.0,
|
| 851 |
+
"learning_rate": 5e-05,
|
| 852 |
+
"loss": 3.0453310012817383,
|
| 853 |
+
"step": 545
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.55,
|
| 857 |
+
"grad_norm": 9.6875,
|
| 858 |
+
"learning_rate": 5e-05,
|
| 859 |
+
"loss": 3.0214563369750977,
|
| 860 |
+
"step": 550
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.55,
|
| 864 |
+
"eval_loss": 3.3045036792755127,
|
| 865 |
+
"eval_runtime": 6.7272,
|
| 866 |
+
"eval_samples_per_second": 5.5,
|
| 867 |
+
"eval_steps_per_second": 2.824,
|
| 868 |
+
"step": 550
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.555,
|
| 872 |
+
"grad_norm": 64.0,
|
| 873 |
+
"learning_rate": 5e-05,
|
| 874 |
+
"loss": 3.0599187850952148,
|
| 875 |
+
"step": 555
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.56,
|
| 879 |
+
"grad_norm": 5.5,
|
| 880 |
+
"learning_rate": 5e-05,
|
| 881 |
+
"loss": 3.0171770095825194,
|
| 882 |
+
"step": 560
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.565,
|
| 886 |
+
"grad_norm": 2.0625,
|
| 887 |
+
"learning_rate": 5e-05,
|
| 888 |
+
"loss": 3.0361049652099608,
|
| 889 |
+
"step": 565
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.57,
|
| 893 |
+
"grad_norm": 1.296875,
|
| 894 |
+
"learning_rate": 5e-05,
|
| 895 |
+
"loss": 3.0191267013549803,
|
| 896 |
+
"step": 570
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.575,
|
| 900 |
+
"grad_norm": 2.28125,
|
| 901 |
+
"learning_rate": 5e-05,
|
| 902 |
+
"loss": 3.0235448837280274,
|
| 903 |
+
"step": 575
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.58,
|
| 907 |
+
"grad_norm": 4.0625,
|
| 908 |
+
"learning_rate": 5e-05,
|
| 909 |
+
"loss": 3.0432418823242187,
|
| 910 |
+
"step": 580
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.585,
|
| 914 |
+
"grad_norm": 28.25,
|
| 915 |
+
"learning_rate": 5e-05,
|
| 916 |
+
"loss": 3.0085990905761717,
|
| 917 |
+
"step": 585
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.59,
|
| 921 |
+
"grad_norm": 1.546875,
|
| 922 |
+
"learning_rate": 5e-05,
|
| 923 |
+
"loss": 2.9956476211547853,
|
| 924 |
+
"step": 590
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.595,
|
| 928 |
+
"grad_norm": 28.125,
|
| 929 |
+
"learning_rate": 5e-05,
|
| 930 |
+
"loss": 3.0316390991210938,
|
| 931 |
+
"step": 595
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.6,
|
| 935 |
+
"grad_norm": 13.6875,
|
| 936 |
+
"learning_rate": 5e-05,
|
| 937 |
+
"loss": 3.040385627746582,
|
| 938 |
+
"step": 600
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.6,
|
| 942 |
+
"eval_loss": 3.2979705333709717,
|
| 943 |
+
"eval_runtime": 6.7492,
|
| 944 |
+
"eval_samples_per_second": 5.482,
|
| 945 |
+
"eval_steps_per_second": 2.815,
|
| 946 |
+
"step": 600
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 5,
|
|
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
+
"total_flos": 1.739490745909248e+17,
|
| 967 |
"train_batch_size": 2,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|