Upload 11 files
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +279 -3
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 133466376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65e67105c48220d2074098ec1e37f0d61b97375cc55304f903567d3695295370
|
| 3 |
size 133466376
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267054330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0714840fa9604d2fc8f7ea5d59a366c8a93781aa1d7c495a9de1474c626848b4
|
| 3 |
size 267054330
|
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 sha256:38f537364220577dd4e5269dcefc13c34f9b3778f6daf6768a70fafb5a921478
|
| 3 |
size 14244
|
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 sha256:5da051eb48121dd050f992d01ba9f253f3d6fbc88a7c642a234fae20f61e7eb3
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 10000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -637,6 +637,282 @@
|
|
| 637 |
"learning_rate": 6.131178557351203e-06,
|
| 638 |
"loss": 0.0135,
|
| 639 |
"step": 88000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 640 |
}
|
| 641 |
],
|
| 642 |
"logging_steps": 1000,
|
|
@@ -644,7 +920,7 @@
|
|
| 644 |
"num_input_tokens_seen": 0,
|
| 645 |
"num_train_epochs": 50,
|
| 646 |
"save_steps": 500,
|
| 647 |
-
"total_flos":
|
| 648 |
"train_batch_size": 8,
|
| 649 |
"trial_name": null,
|
| 650 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
"eval_steps": 10000,
|
| 6 |
+
"global_step": 126850,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 637 |
"learning_rate": 6.131178557351203e-06,
|
| 638 |
"loss": 0.0135,
|
| 639 |
"step": 88000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 35.08,
|
| 643 |
+
"learning_rate": 5.973512022073315e-06,
|
| 644 |
+
"loss": 0.016,
|
| 645 |
+
"step": 89000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 35.47,
|
| 649 |
+
"learning_rate": 5.815845486795429e-06,
|
| 650 |
+
"loss": 0.0144,
|
| 651 |
+
"step": 90000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 35.47,
|
| 655 |
+
"eval_accuracy": 0.996594778660613,
|
| 656 |
+
"eval_f1": 0.9872340425531915,
|
| 657 |
+
"eval_loss": 0.009375466965138912,
|
| 658 |
+
"eval_precision": 0.9914529914529915,
|
| 659 |
+
"eval_recall": 0.9830508474576272,
|
| 660 |
+
"eval_runtime": 6.361,
|
| 661 |
+
"eval_samples_per_second": 276.999,
|
| 662 |
+
"eval_steps_per_second": 34.743,
|
| 663 |
+
"step": 90000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 35.87,
|
| 667 |
+
"learning_rate": 5.658336618052819e-06,
|
| 668 |
+
"loss": 0.0155,
|
| 669 |
+
"step": 91000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 36.26,
|
| 673 |
+
"learning_rate": 5.500670082774931e-06,
|
| 674 |
+
"loss": 0.0126,
|
| 675 |
+
"step": 92000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 36.66,
|
| 679 |
+
"learning_rate": 5.343161214032322e-06,
|
| 680 |
+
"loss": 0.0094,
|
| 681 |
+
"step": 93000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 37.05,
|
| 685 |
+
"learning_rate": 5.185494678754435e-06,
|
| 686 |
+
"loss": 0.0106,
|
| 687 |
+
"step": 94000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 37.45,
|
| 691 |
+
"learning_rate": 5.027828143476547e-06,
|
| 692 |
+
"loss": 0.0115,
|
| 693 |
+
"step": 95000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 37.84,
|
| 697 |
+
"learning_rate": 4.870161608198661e-06,
|
| 698 |
+
"loss": 0.0087,
|
| 699 |
+
"step": 96000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 38.23,
|
| 703 |
+
"learning_rate": 4.712495072920773e-06,
|
| 704 |
+
"loss": 0.0126,
|
| 705 |
+
"step": 97000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 38.63,
|
| 709 |
+
"learning_rate": 4.554986204178163e-06,
|
| 710 |
+
"loss": 0.009,
|
| 711 |
+
"step": 98000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 39.02,
|
| 715 |
+
"learning_rate": 4.397319668900277e-06,
|
| 716 |
+
"loss": 0.0129,
|
| 717 |
+
"step": 99000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 39.42,
|
| 721 |
+
"learning_rate": 4.239653133622389e-06,
|
| 722 |
+
"loss": 0.009,
|
| 723 |
+
"step": 100000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 39.42,
|
| 727 |
+
"eval_accuracy": 0.996594778660613,
|
| 728 |
+
"eval_f1": 0.9872881355932204,
|
| 729 |
+
"eval_loss": 0.008661070838570595,
|
| 730 |
+
"eval_precision": 0.9872881355932204,
|
| 731 |
+
"eval_recall": 0.9872881355932204,
|
| 732 |
+
"eval_runtime": 6.0434,
|
| 733 |
+
"eval_samples_per_second": 291.559,
|
| 734 |
+
"eval_steps_per_second": 36.569,
|
| 735 |
+
"step": 100000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 39.81,
|
| 739 |
+
"learning_rate": 4.081986598344502e-06,
|
| 740 |
+
"loss": 0.0066,
|
| 741 |
+
"step": 101000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 40.2,
|
| 745 |
+
"learning_rate": 3.924477729601892e-06,
|
| 746 |
+
"loss": 0.0116,
|
| 747 |
+
"step": 102000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 40.6,
|
| 751 |
+
"learning_rate": 3.7668111943240047e-06,
|
| 752 |
+
"loss": 0.0099,
|
| 753 |
+
"step": 103000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 40.99,
|
| 757 |
+
"learning_rate": 3.6091446590461178e-06,
|
| 758 |
+
"loss": 0.0087,
|
| 759 |
+
"step": 104000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 41.39,
|
| 763 |
+
"learning_rate": 3.4516357903035086e-06,
|
| 764 |
+
"loss": 0.0092,
|
| 765 |
+
"step": 105000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 41.78,
|
| 769 |
+
"learning_rate": 3.2939692550256207e-06,
|
| 770 |
+
"loss": 0.0098,
|
| 771 |
+
"step": 106000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 42.18,
|
| 775 |
+
"learning_rate": 3.1363027197477337e-06,
|
| 776 |
+
"loss": 0.0092,
|
| 777 |
+
"step": 107000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 42.57,
|
| 781 |
+
"learning_rate": 2.9787938510051245e-06,
|
| 782 |
+
"loss": 0.0111,
|
| 783 |
+
"step": 108000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 42.96,
|
| 787 |
+
"learning_rate": 2.821127315727237e-06,
|
| 788 |
+
"loss": 0.0077,
|
| 789 |
+
"step": 109000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 43.36,
|
| 793 |
+
"learning_rate": 2.66346078044935e-06,
|
| 794 |
+
"loss": 0.0084,
|
| 795 |
+
"step": 110000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 43.36,
|
| 799 |
+
"eval_accuracy": 0.9954597048808173,
|
| 800 |
+
"eval_f1": 0.9828326180257511,
|
| 801 |
+
"eval_loss": 0.018768297508358955,
|
| 802 |
+
"eval_precision": 0.9956521739130435,
|
| 803 |
+
"eval_recall": 0.9703389830508474,
|
| 804 |
+
"eval_runtime": 5.9996,
|
| 805 |
+
"eval_samples_per_second": 293.685,
|
| 806 |
+
"eval_steps_per_second": 36.836,
|
| 807 |
+
"step": 110000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 43.75,
|
| 811 |
+
"learning_rate": 2.5059519117067405e-06,
|
| 812 |
+
"loss": 0.0086,
|
| 813 |
+
"step": 111000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 44.15,
|
| 817 |
+
"learning_rate": 2.348285376428853e-06,
|
| 818 |
+
"loss": 0.0092,
|
| 819 |
+
"step": 112000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 44.54,
|
| 823 |
+
"learning_rate": 2.190618841150966e-06,
|
| 824 |
+
"loss": 0.0099,
|
| 825 |
+
"step": 113000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 44.93,
|
| 829 |
+
"learning_rate": 2.0331099724083565e-06,
|
| 830 |
+
"loss": 0.0101,
|
| 831 |
+
"step": 114000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 45.33,
|
| 835 |
+
"learning_rate": 1.8754434371304691e-06,
|
| 836 |
+
"loss": 0.0079,
|
| 837 |
+
"step": 115000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 45.72,
|
| 841 |
+
"learning_rate": 1.71793456838786e-06,
|
| 842 |
+
"loss": 0.0102,
|
| 843 |
+
"step": 116000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 46.12,
|
| 847 |
+
"learning_rate": 1.5602680331099725e-06,
|
| 848 |
+
"loss": 0.0086,
|
| 849 |
+
"step": 117000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 46.51,
|
| 853 |
+
"learning_rate": 1.4026014978320853e-06,
|
| 854 |
+
"loss": 0.0097,
|
| 855 |
+
"step": 118000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 46.91,
|
| 859 |
+
"learning_rate": 1.2449349625541981e-06,
|
| 860 |
+
"loss": 0.0048,
|
| 861 |
+
"step": 119000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 47.3,
|
| 865 |
+
"learning_rate": 1.0872684272763107e-06,
|
| 866 |
+
"loss": 0.0112,
|
| 867 |
+
"step": 120000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 47.3,
|
| 871 |
+
"eval_accuracy": 0.996594778660613,
|
| 872 |
+
"eval_f1": 0.9872881355932204,
|
| 873 |
+
"eval_loss": 0.008344221860170364,
|
| 874 |
+
"eval_precision": 0.9872881355932204,
|
| 875 |
+
"eval_recall": 0.9872881355932204,
|
| 876 |
+
"eval_runtime": 6.0461,
|
| 877 |
+
"eval_samples_per_second": 291.429,
|
| 878 |
+
"eval_steps_per_second": 36.553,
|
| 879 |
+
"step": 120000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 47.69,
|
| 883 |
+
"learning_rate": 9.297595585337013e-07,
|
| 884 |
+
"loss": 0.0069,
|
| 885 |
+
"step": 121000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 48.09,
|
| 889 |
+
"learning_rate": 7.72250689791092e-07,
|
| 890 |
+
"loss": 0.0103,
|
| 891 |
+
"step": 122000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 48.48,
|
| 895 |
+
"learning_rate": 6.145841545132046e-07,
|
| 896 |
+
"loss": 0.0079,
|
| 897 |
+
"step": 123000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 48.88,
|
| 901 |
+
"learning_rate": 4.5691761923531733e-07,
|
| 902 |
+
"loss": 0.0061,
|
| 903 |
+
"step": 124000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 49.27,
|
| 907 |
+
"learning_rate": 2.994087504927079e-07,
|
| 908 |
+
"loss": 0.0081,
|
| 909 |
+
"step": 125000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 49.66,
|
| 913 |
+
"learning_rate": 1.4174221521482067e-07,
|
| 914 |
+
"loss": 0.0101,
|
| 915 |
+
"step": 126000
|
| 916 |
}
|
| 917 |
],
|
| 918 |
"logging_steps": 1000,
|
|
|
|
| 920 |
"num_input_tokens_seen": 0,
|
| 921 |
"num_train_epochs": 50,
|
| 922 |
"save_steps": 500,
|
| 923 |
+
"total_flos": 1.0572380196462e+16,
|
| 924 |
"train_batch_size": 8,
|
| 925 |
"trial_name": null,
|
| 926 |
"trial_params": null
|