Training in progress, step 375, 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:814c0505ae9626a132eee74a5d49746ba88ce25071435a2e3bf44bf9a6955753
|
| 3 |
+
size 150487412
|
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 sha256:8d2e5ea8bbdbe6933b5b2f456e20e6bca2dc98048eecb503cf50ba6989aff775
|
| 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 sha256:128e0b0294b5389dce5b958620f0aba512ba88459c3fb7de261ee4ac77eb7fa5
|
| 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": 0.
|
| 5 |
"eval_steps": 125,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -612,6 +612,308 @@
|
|
| 612 |
"eval_samples_per_second": 45.252,
|
| 613 |
"eval_steps_per_second": 22.627,
|
| 614 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 615 |
}
|
| 616 |
],
|
| 617 |
"logging_steps": 3,
|
|
@@ -631,7 +933,7 @@
|
|
| 631 |
"attributes": {}
|
| 632 |
}
|
| 633 |
},
|
| 634 |
-
"total_flos":
|
| 635 |
"train_batch_size": 2,
|
| 636 |
"trial_name": null,
|
| 637 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.01212214270994541,
|
| 5 |
"eval_steps": 125,
|
| 6 |
+
"global_step": 375,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 612 |
"eval_samples_per_second": 45.252,
|
| 613 |
"eval_steps_per_second": 22.627,
|
| 614 |
"step": 250
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.008146079901083316,
|
| 618 |
+
"grad_norm": NaN,
|
| 619 |
+
"learning_rate": 5.0961652739384356e-05,
|
| 620 |
+
"loss": 0.0,
|
| 621 |
+
"step": 252
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.008243057042762878,
|
| 625 |
+
"grad_norm": NaN,
|
| 626 |
+
"learning_rate": 5e-05,
|
| 627 |
+
"loss": 0.0,
|
| 628 |
+
"step": 255
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.008340034184442442,
|
| 632 |
+
"grad_norm": NaN,
|
| 633 |
+
"learning_rate": 4.903834726061565e-05,
|
| 634 |
+
"loss": 0.0,
|
| 635 |
+
"step": 258
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.008437011326122006,
|
| 639 |
+
"grad_norm": NaN,
|
| 640 |
+
"learning_rate": 4.807705027948008e-05,
|
| 641 |
+
"loss": 0.0,
|
| 642 |
+
"step": 261
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.00853398846780157,
|
| 646 |
+
"grad_norm": NaN,
|
| 647 |
+
"learning_rate": 4.711646468323129e-05,
|
| 648 |
+
"loss": 0.0,
|
| 649 |
+
"step": 264
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.008630965609481131,
|
| 653 |
+
"grad_norm": NaN,
|
| 654 |
+
"learning_rate": 4.6156945835334184e-05,
|
| 655 |
+
"loss": 0.0,
|
| 656 |
+
"step": 267
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.008727942751160695,
|
| 660 |
+
"grad_norm": NaN,
|
| 661 |
+
"learning_rate": 4.5198848704615914e-05,
|
| 662 |
+
"loss": 0.0,
|
| 663 |
+
"step": 270
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.008824919892840259,
|
| 667 |
+
"grad_norm": NaN,
|
| 668 |
+
"learning_rate": 4.424252773394704e-05,
|
| 669 |
+
"loss": 0.0,
|
| 670 |
+
"step": 273
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.008921897034519823,
|
| 674 |
+
"grad_norm": NaN,
|
| 675 |
+
"learning_rate": 4.328833670911724e-05,
|
| 676 |
+
"loss": 0.0,
|
| 677 |
+
"step": 276
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.009018874176199385,
|
| 681 |
+
"grad_norm": NaN,
|
| 682 |
+
"learning_rate": 4.23366286279542e-05,
|
| 683 |
+
"loss": 0.0,
|
| 684 |
+
"step": 279
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.009115851317878948,
|
| 688 |
+
"grad_norm": NaN,
|
| 689 |
+
"learning_rate": 4.138775556973406e-05,
|
| 690 |
+
"loss": 0.0,
|
| 691 |
+
"step": 282
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.009212828459558512,
|
| 695 |
+
"grad_norm": NaN,
|
| 696 |
+
"learning_rate": 4.04420685649314e-05,
|
| 697 |
+
"loss": 0.0,
|
| 698 |
+
"step": 285
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.009309805601238074,
|
| 702 |
+
"grad_norm": NaN,
|
| 703 |
+
"learning_rate": 3.9499917465357534e-05,
|
| 704 |
+
"loss": 0.0,
|
| 705 |
+
"step": 288
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.009406782742917638,
|
| 709 |
+
"grad_norm": NaN,
|
| 710 |
+
"learning_rate": 3.856165081473474e-05,
|
| 711 |
+
"loss": 0.0,
|
| 712 |
+
"step": 291
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.009503759884597202,
|
| 716 |
+
"grad_norm": NaN,
|
| 717 |
+
"learning_rate": 3.762761571975429e-05,
|
| 718 |
+
"loss": 0.0,
|
| 719 |
+
"step": 294
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.009600737026276765,
|
| 723 |
+
"grad_norm": NaN,
|
| 724 |
+
"learning_rate": 3.6698157721666246e-05,
|
| 725 |
+
"loss": 0.0,
|
| 726 |
+
"step": 297
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.009697714167956327,
|
| 730 |
+
"grad_norm": NaN,
|
| 731 |
+
"learning_rate": 3.5773620668448384e-05,
|
| 732 |
+
"loss": 0.0,
|
| 733 |
+
"step": 300
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.009794691309635891,
|
| 737 |
+
"grad_norm": NaN,
|
| 738 |
+
"learning_rate": 3.48543465876014e-05,
|
| 739 |
+
"loss": 0.0,
|
| 740 |
+
"step": 303
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.009891668451315455,
|
| 744 |
+
"grad_norm": NaN,
|
| 745 |
+
"learning_rate": 3.3940675559617724e-05,
|
| 746 |
+
"loss": 0.0,
|
| 747 |
+
"step": 306
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.009988645592995019,
|
| 751 |
+
"grad_norm": NaN,
|
| 752 |
+
"learning_rate": 3.303294559217063e-05,
|
| 753 |
+
"loss": 0.0,
|
| 754 |
+
"step": 309
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.01008562273467458,
|
| 758 |
+
"grad_norm": NaN,
|
| 759 |
+
"learning_rate": 3.213149249506997e-05,
|
| 760 |
+
"loss": 0.0,
|
| 761 |
+
"step": 312
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.010182599876354144,
|
| 765 |
+
"grad_norm": NaN,
|
| 766 |
+
"learning_rate": 3.12366497560313e-05,
|
| 767 |
+
"loss": 0.0,
|
| 768 |
+
"step": 315
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.010279577018033708,
|
| 772 |
+
"grad_norm": NaN,
|
| 773 |
+
"learning_rate": 3.0348748417303823e-05,
|
| 774 |
+
"loss": 0.0,
|
| 775 |
+
"step": 318
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.010376554159713272,
|
| 779 |
+
"grad_norm": NaN,
|
| 780 |
+
"learning_rate": 2.9468116953203107e-05,
|
| 781 |
+
"loss": 0.0,
|
| 782 |
+
"step": 321
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.010473531301392834,
|
| 786 |
+
"grad_norm": NaN,
|
| 787 |
+
"learning_rate": 2.8595081148593738e-05,
|
| 788 |
+
"loss": 0.0,
|
| 789 |
+
"step": 324
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.010570508443072398,
|
| 793 |
+
"grad_norm": NaN,
|
| 794 |
+
"learning_rate": 2.772996397836704e-05,
|
| 795 |
+
"loss": 0.0,
|
| 796 |
+
"step": 327
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.010667485584751961,
|
| 800 |
+
"grad_norm": NaN,
|
| 801 |
+
"learning_rate": 2.687308548795825e-05,
|
| 802 |
+
"loss": 0.0,
|
| 803 |
+
"step": 330
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.010764462726431523,
|
| 807 |
+
"grad_norm": NaN,
|
| 808 |
+
"learning_rate": 2.6024762674947313e-05,
|
| 809 |
+
"loss": 0.0,
|
| 810 |
+
"step": 333
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.010861439868111087,
|
| 814 |
+
"grad_norm": NaN,
|
| 815 |
+
"learning_rate": 2.5185309371787513e-05,
|
| 816 |
+
"loss": 0.0,
|
| 817 |
+
"step": 336
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.01095841700979065,
|
| 821 |
+
"grad_norm": NaN,
|
| 822 |
+
"learning_rate": 2.43550361297047e-05,
|
| 823 |
+
"loss": 0.0,
|
| 824 |
+
"step": 339
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.011055394151470214,
|
| 828 |
+
"grad_norm": NaN,
|
| 829 |
+
"learning_rate": 2.353425010381063e-05,
|
| 830 |
+
"loss": 0.0,
|
| 831 |
+
"step": 342
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.011152371293149776,
|
| 835 |
+
"grad_norm": NaN,
|
| 836 |
+
"learning_rate": 2.272325493947257e-05,
|
| 837 |
+
"loss": 0.0,
|
| 838 |
+
"step": 345
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.01124934843482934,
|
| 842 |
+
"grad_norm": NaN,
|
| 843 |
+
"learning_rate": 2.192235065998126e-05,
|
| 844 |
+
"loss": 0.0,
|
| 845 |
+
"step": 348
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.011346325576508904,
|
| 849 |
+
"grad_norm": NaN,
|
| 850 |
+
"learning_rate": 2.1131833555559037e-05,
|
| 851 |
+
"loss": 0.0,
|
| 852 |
+
"step": 351
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.011443302718188468,
|
| 856 |
+
"grad_norm": NaN,
|
| 857 |
+
"learning_rate": 2.0351996073748713e-05,
|
| 858 |
+
"loss": 0.0,
|
| 859 |
+
"step": 354
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.01154027985986803,
|
| 863 |
+
"grad_norm": NaN,
|
| 864 |
+
"learning_rate": 1.9583126711224343e-05,
|
| 865 |
+
"loss": 0.0,
|
| 866 |
+
"step": 357
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.011637257001547593,
|
| 870 |
+
"grad_norm": NaN,
|
| 871 |
+
"learning_rate": 1.8825509907063327e-05,
|
| 872 |
+
"loss": 0.0,
|
| 873 |
+
"step": 360
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.011734234143227157,
|
| 877 |
+
"grad_norm": NaN,
|
| 878 |
+
"learning_rate": 1.807942593751973e-05,
|
| 879 |
+
"loss": 0.0,
|
| 880 |
+
"step": 363
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.011831211284906721,
|
| 884 |
+
"grad_norm": NaN,
|
| 885 |
+
"learning_rate": 1.7345150812337564e-05,
|
| 886 |
+
"loss": 0.0,
|
| 887 |
+
"step": 366
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.011928188426586283,
|
| 891 |
+
"grad_norm": NaN,
|
| 892 |
+
"learning_rate": 1.66229561726426e-05,
|
| 893 |
+
"loss": 0.0,
|
| 894 |
+
"step": 369
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.012025165568265847,
|
| 898 |
+
"grad_norm": NaN,
|
| 899 |
+
"learning_rate": 1.5913109190450032e-05,
|
| 900 |
+
"loss": 0.0,
|
| 901 |
+
"step": 372
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.01212214270994541,
|
| 905 |
+
"grad_norm": NaN,
|
| 906 |
+
"learning_rate": 1.5215872469825682e-05,
|
| 907 |
+
"loss": 0.0,
|
| 908 |
+
"step": 375
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.01212214270994541,
|
| 912 |
+
"eval_loss": NaN,
|
| 913 |
+
"eval_runtime": 573.9041,
|
| 914 |
+
"eval_samples_per_second": 45.393,
|
| 915 |
+
"eval_steps_per_second": 22.697,
|
| 916 |
+
"step": 375
|
| 917 |
}
|
| 918 |
],
|
| 919 |
"logging_steps": 3,
|
|
|
|
| 933 |
"attributes": {}
|
| 934 |
}
|
| 935 |
},
|
| 936 |
+
"total_flos": 2.551356850176e+16,
|
| 937 |
"train_batch_size": 2,
|
| 938 |
"trial_name": null,
|
| 939 |
"trial_params": null
|