Upload Step 150/9427
Browse files- adapter_model.safetensors +1 -1
- trainer_state.json +549 -3
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1907432232
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:badd47000be379b28f59dad18021a7b6074d3deaff0246e3db26f6e121fdd9c3
|
| 3 |
size 1907432232
|
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": 10,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -640,6 +640,552 @@
|
|
| 640 |
"eval_samples_per_second": 1.888,
|
| 641 |
"eval_steps_per_second": 0.472,
|
| 642 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 643 |
}
|
| 644 |
],
|
| 645 |
"logging_steps": 1,
|
|
@@ -659,7 +1205,7 @@
|
|
| 659 |
"attributes": {}
|
| 660 |
}
|
| 661 |
},
|
| 662 |
-
"total_flos":
|
| 663 |
"train_batch_size": 4,
|
| 664 |
"trial_name": null,
|
| 665 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.015910898965791568,
|
| 6 |
"eval_steps": 10,
|
| 7 |
+
"global_step": 150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 640 |
"eval_samples_per_second": 1.888,
|
| 641 |
"eval_steps_per_second": 0.472,
|
| 642 |
"step": 80
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.008591885441527447,
|
| 646 |
+
"grad_norm": 1.0189088582992554,
|
| 647 |
+
"learning_rate": 4.995886830373846e-07,
|
| 648 |
+
"loss": 1.5961,
|
| 649 |
+
"step": 81
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.00869795810129939,
|
| 653 |
+
"grad_norm": 0.7427169680595398,
|
| 654 |
+
"learning_rate": 4.995835649831073e-07,
|
| 655 |
+
"loss": 1.6456,
|
| 656 |
+
"step": 82
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.008804030761071334,
|
| 660 |
+
"grad_norm": 0.8337876796722412,
|
| 661 |
+
"learning_rate": 4.995784459437785e-07,
|
| 662 |
+
"loss": 1.2846,
|
| 663 |
+
"step": 83
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.008910103420843278,
|
| 667 |
+
"grad_norm": 0.6561726331710815,
|
| 668 |
+
"learning_rate": 4.995733259191137e-07,
|
| 669 |
+
"loss": 1.5769,
|
| 670 |
+
"step": 84
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.009016176080615222,
|
| 674 |
+
"grad_norm": 0.7599915862083435,
|
| 675 |
+
"learning_rate": 4.995682049088284e-07,
|
| 676 |
+
"loss": 1.7303,
|
| 677 |
+
"step": 85
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.009122248740387166,
|
| 681 |
+
"grad_norm": 0.7153452038764954,
|
| 682 |
+
"learning_rate": 4.995630829126379e-07,
|
| 683 |
+
"loss": 1.5249,
|
| 684 |
+
"step": 86
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.009228321400159108,
|
| 688 |
+
"grad_norm": 0.7663532495498657,
|
| 689 |
+
"learning_rate": 4.995579599302577e-07,
|
| 690 |
+
"loss": 1.4317,
|
| 691 |
+
"step": 87
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.009334394059931053,
|
| 695 |
+
"grad_norm": 0.8668680191040039,
|
| 696 |
+
"learning_rate": 4.995528359614027e-07,
|
| 697 |
+
"loss": 1.8046,
|
| 698 |
+
"step": 88
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.009440466719702997,
|
| 702 |
+
"grad_norm": 0.684675931930542,
|
| 703 |
+
"learning_rate": 4.99547711005788e-07,
|
| 704 |
+
"loss": 1.393,
|
| 705 |
+
"step": 89
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.00954653937947494,
|
| 709 |
+
"grad_norm": 0.8086925745010376,
|
| 710 |
+
"learning_rate": 4.995425850631287e-07,
|
| 711 |
+
"loss": 1.5898,
|
| 712 |
+
"step": 90
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.00954653937947494,
|
| 716 |
+
"eval_loss": 1.4867264032363892,
|
| 717 |
+
"eval_runtime": 68.2886,
|
| 718 |
+
"eval_samples_per_second": 1.874,
|
| 719 |
+
"eval_steps_per_second": 0.469,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.009652612039246885,
|
| 724 |
+
"grad_norm": 0.6806846261024475,
|
| 725 |
+
"learning_rate": 4.995374581331393e-07,
|
| 726 |
+
"loss": 1.5126,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.009758684699018827,
|
| 731 |
+
"grad_norm": 0.7875713109970093,
|
| 732 |
+
"learning_rate": 4.995323302155347e-07,
|
| 733 |
+
"loss": 1.5119,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.009864757358790771,
|
| 738 |
+
"grad_norm": 0.6719956398010254,
|
| 739 |
+
"learning_rate": 4.995272013100296e-07,
|
| 740 |
+
"loss": 1.611,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.009970830018562716,
|
| 745 |
+
"grad_norm": 0.7365944385528564,
|
| 746 |
+
"learning_rate": 4.995220714163384e-07,
|
| 747 |
+
"loss": 1.2394,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.01007690267833466,
|
| 752 |
+
"grad_norm": 0.6620836853981018,
|
| 753 |
+
"learning_rate": 4.995169405341754e-07,
|
| 754 |
+
"loss": 1.6405,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.010182975338106604,
|
| 759 |
+
"grad_norm": 0.7277278900146484,
|
| 760 |
+
"learning_rate": 4.995118086632551e-07,
|
| 761 |
+
"loss": 1.7809,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.010289047997878546,
|
| 766 |
+
"grad_norm": 0.7061654925346375,
|
| 767 |
+
"learning_rate": 4.995066758032913e-07,
|
| 768 |
+
"loss": 1.361,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.01039512065765049,
|
| 773 |
+
"grad_norm": 0.7945475578308105,
|
| 774 |
+
"learning_rate": 4.995015419539983e-07,
|
| 775 |
+
"loss": 1.608,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.010501193317422435,
|
| 780 |
+
"grad_norm": 0.7080848813056946,
|
| 781 |
+
"learning_rate": 4.994964071150901e-07,
|
| 782 |
+
"loss": 1.6869,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.010607265977194379,
|
| 787 |
+
"grad_norm": 0.6934227347373962,
|
| 788 |
+
"learning_rate": 4.994912712862803e-07,
|
| 789 |
+
"loss": 1.4698,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.010607265977194379,
|
| 794 |
+
"eval_loss": 1.4758180379867554,
|
| 795 |
+
"eval_runtime": 67.7252,
|
| 796 |
+
"eval_samples_per_second": 1.89,
|
| 797 |
+
"eval_steps_per_second": 0.472,
|
| 798 |
+
"step": 100
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.010713338636966323,
|
| 802 |
+
"grad_norm": 0.6977412700653076,
|
| 803 |
+
"learning_rate": 4.994861344672828e-07,
|
| 804 |
+
"loss": 1.6276,
|
| 805 |
+
"step": 101
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.010819411296738265,
|
| 809 |
+
"grad_norm": 0.8750130534172058,
|
| 810 |
+
"learning_rate": 4.994809966578113e-07,
|
| 811 |
+
"loss": 1.5425,
|
| 812 |
+
"step": 102
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.01092548395651021,
|
| 816 |
+
"grad_norm": 1.6952922344207764,
|
| 817 |
+
"learning_rate": 4.99475857857579e-07,
|
| 818 |
+
"loss": 1.6159,
|
| 819 |
+
"step": 103
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.011031556616282153,
|
| 823 |
+
"grad_norm": 0.7001510858535767,
|
| 824 |
+
"learning_rate": 4.994707180662995e-07,
|
| 825 |
+
"loss": 1.5937,
|
| 826 |
+
"step": 104
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.011137629276054098,
|
| 830 |
+
"grad_norm": 0.7474836707115173,
|
| 831 |
+
"learning_rate": 4.99465577283686e-07,
|
| 832 |
+
"loss": 1.4775,
|
| 833 |
+
"step": 105
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.011243701935826042,
|
| 837 |
+
"grad_norm": 1.114769458770752,
|
| 838 |
+
"learning_rate": 4.994604355094518e-07,
|
| 839 |
+
"loss": 1.4304,
|
| 840 |
+
"step": 106
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.011349774595597984,
|
| 844 |
+
"grad_norm": 0.7222145199775696,
|
| 845 |
+
"learning_rate": 4.994552927433097e-07,
|
| 846 |
+
"loss": 1.2972,
|
| 847 |
+
"step": 107
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.011455847255369928,
|
| 851 |
+
"grad_norm": 0.7787733674049377,
|
| 852 |
+
"learning_rate": 4.994501489849728e-07,
|
| 853 |
+
"loss": 1.8544,
|
| 854 |
+
"step": 108
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.011561919915141872,
|
| 858 |
+
"grad_norm": 0.6402618288993835,
|
| 859 |
+
"learning_rate": 4.994450042341541e-07,
|
| 860 |
+
"loss": 1.5189,
|
| 861 |
+
"step": 109
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.011667992574913817,
|
| 865 |
+
"grad_norm": 0.6818183064460754,
|
| 866 |
+
"learning_rate": 4.99439858490566e-07,
|
| 867 |
+
"loss": 1.3971,
|
| 868 |
+
"step": 110
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.011667992574913817,
|
| 872 |
+
"eval_loss": 1.4671616554260254,
|
| 873 |
+
"eval_runtime": 68.8225,
|
| 874 |
+
"eval_samples_per_second": 1.86,
|
| 875 |
+
"eval_steps_per_second": 0.465,
|
| 876 |
+
"step": 110
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.011774065234685759,
|
| 880 |
+
"grad_norm": 0.8468677997589111,
|
| 881 |
+
"learning_rate": 4.994347117539214e-07,
|
| 882 |
+
"loss": 1.6674,
|
| 883 |
+
"step": 111
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.011880137894457703,
|
| 887 |
+
"grad_norm": 0.9757254123687744,
|
| 888 |
+
"learning_rate": 4.994295640239325e-07,
|
| 889 |
+
"loss": 1.5847,
|
| 890 |
+
"step": 112
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.011986210554229647,
|
| 894 |
+
"grad_norm": 0.9481499195098877,
|
| 895 |
+
"learning_rate": 4.99424415300312e-07,
|
| 896 |
+
"loss": 1.3539,
|
| 897 |
+
"step": 113
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.012092283214001591,
|
| 901 |
+
"grad_norm": 0.6789958477020264,
|
| 902 |
+
"learning_rate": 4.99419265582772e-07,
|
| 903 |
+
"loss": 1.5099,
|
| 904 |
+
"step": 114
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.012198355873773535,
|
| 908 |
+
"grad_norm": 0.6501567959785461,
|
| 909 |
+
"learning_rate": 4.994141148710247e-07,
|
| 910 |
+
"loss": 1.5429,
|
| 911 |
+
"step": 115
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.012304428533545478,
|
| 915 |
+
"grad_norm": 1.262799859046936,
|
| 916 |
+
"learning_rate": 4.994089631647824e-07,
|
| 917 |
+
"loss": 1.1193,
|
| 918 |
+
"step": 116
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.012410501193317422,
|
| 922 |
+
"grad_norm": 0.685874342918396,
|
| 923 |
+
"learning_rate": 4.994038104637567e-07,
|
| 924 |
+
"loss": 1.728,
|
| 925 |
+
"step": 117
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.012516573853089366,
|
| 929 |
+
"grad_norm": 0.7375260591506958,
|
| 930 |
+
"learning_rate": 4.993986567676594e-07,
|
| 931 |
+
"loss": 1.6958,
|
| 932 |
+
"step": 118
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.01262264651286131,
|
| 936 |
+
"grad_norm": 0.7215054631233215,
|
| 937 |
+
"learning_rate": 4.993935020762025e-07,
|
| 938 |
+
"loss": 1.3697,
|
| 939 |
+
"step": 119
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.012728719172633254,
|
| 943 |
+
"grad_norm": 0.7148920297622681,
|
| 944 |
+
"learning_rate": 4.993883463890975e-07,
|
| 945 |
+
"loss": 1.6451,
|
| 946 |
+
"step": 120
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.012728719172633254,
|
| 950 |
+
"eval_loss": 1.459830403327942,
|
| 951 |
+
"eval_runtime": 68.6763,
|
| 952 |
+
"eval_samples_per_second": 1.864,
|
| 953 |
+
"eval_steps_per_second": 0.466,
|
| 954 |
+
"step": 120
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.012834791832405197,
|
| 958 |
+
"grad_norm": 0.6565997004508972,
|
| 959 |
+
"learning_rate": 4.993831897060559e-07,
|
| 960 |
+
"loss": 1.4405,
|
| 961 |
+
"step": 121
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.012940864492177141,
|
| 965 |
+
"grad_norm": 0.7842444181442261,
|
| 966 |
+
"learning_rate": 4.993780320267891e-07,
|
| 967 |
+
"loss": 1.659,
|
| 968 |
+
"step": 122
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.013046937151949085,
|
| 972 |
+
"grad_norm": 0.7806555032730103,
|
| 973 |
+
"learning_rate": 4.993728733510084e-07,
|
| 974 |
+
"loss": 1.6056,
|
| 975 |
+
"step": 123
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.01315300981172103,
|
| 979 |
+
"grad_norm": 0.8176814317703247,
|
| 980 |
+
"learning_rate": 4.993677136784249e-07,
|
| 981 |
+
"loss": 1.6902,
|
| 982 |
+
"step": 124
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.013259082471492973,
|
| 986 |
+
"grad_norm": 0.7916125059127808,
|
| 987 |
+
"learning_rate": 4.993625530087498e-07,
|
| 988 |
+
"loss": 1.4324,
|
| 989 |
+
"step": 125
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.013365155131264916,
|
| 993 |
+
"grad_norm": 0.6581283211708069,
|
| 994 |
+
"learning_rate": 4.993573913416939e-07,
|
| 995 |
+
"loss": 1.753,
|
| 996 |
+
"step": 126
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.01347122779103686,
|
| 1000 |
+
"grad_norm": 0.6454209685325623,
|
| 1001 |
+
"learning_rate": 4.99352228676968e-07,
|
| 1002 |
+
"loss": 1.5184,
|
| 1003 |
+
"step": 127
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.013577300450808804,
|
| 1007 |
+
"grad_norm": 0.746411919593811,
|
| 1008 |
+
"learning_rate": 4.99347065014283e-07,
|
| 1009 |
+
"loss": 1.5564,
|
| 1010 |
+
"step": 128
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.013683373110580748,
|
| 1014 |
+
"grad_norm": 0.710649847984314,
|
| 1015 |
+
"learning_rate": 4.993419003533493e-07,
|
| 1016 |
+
"loss": 1.46,
|
| 1017 |
+
"step": 129
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.013789445770352692,
|
| 1021 |
+
"grad_norm": 0.7483745217323303,
|
| 1022 |
+
"learning_rate": 4.993367346938775e-07,
|
| 1023 |
+
"loss": 1.4491,
|
| 1024 |
+
"step": 130
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.013789445770352692,
|
| 1028 |
+
"eval_loss": 1.4538627862930298,
|
| 1029 |
+
"eval_runtime": 68.3516,
|
| 1030 |
+
"eval_samples_per_second": 1.873,
|
| 1031 |
+
"eval_steps_per_second": 0.468,
|
| 1032 |
+
"step": 130
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.013895518430124635,
|
| 1036 |
+
"grad_norm": 0.7695822715759277,
|
| 1037 |
+
"learning_rate": 4.993315680355781e-07,
|
| 1038 |
+
"loss": 1.5002,
|
| 1039 |
+
"step": 131
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.014001591089896579,
|
| 1043 |
+
"grad_norm": 0.7457824945449829,
|
| 1044 |
+
"learning_rate": 4.993264003781611e-07,
|
| 1045 |
+
"loss": 1.4464,
|
| 1046 |
+
"step": 132
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.014107663749668523,
|
| 1050 |
+
"grad_norm": 0.6966177821159363,
|
| 1051 |
+
"learning_rate": 4.99321231721337e-07,
|
| 1052 |
+
"loss": 1.5493,
|
| 1053 |
+
"step": 133
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.014213736409440467,
|
| 1057 |
+
"grad_norm": 0.7250157594680786,
|
| 1058 |
+
"learning_rate": 4.993160620648156e-07,
|
| 1059 |
+
"loss": 1.6838,
|
| 1060 |
+
"step": 134
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.014319809069212411,
|
| 1064 |
+
"grad_norm": 0.6885997653007507,
|
| 1065 |
+
"learning_rate": 4.993108914083069e-07,
|
| 1066 |
+
"loss": 1.3327,
|
| 1067 |
+
"step": 135
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.014425881728984354,
|
| 1071 |
+
"grad_norm": 0.6850383877754211,
|
| 1072 |
+
"learning_rate": 4.993057197515208e-07,
|
| 1073 |
+
"loss": 1.373,
|
| 1074 |
+
"step": 136
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.014531954388756298,
|
| 1078 |
+
"grad_norm": 0.8969720005989075,
|
| 1079 |
+
"learning_rate": 4.993005470941668e-07,
|
| 1080 |
+
"loss": 1.6318,
|
| 1081 |
+
"step": 137
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.014638027048528242,
|
| 1085 |
+
"grad_norm": 0.6809049844741821,
|
| 1086 |
+
"learning_rate": 4.992953734359548e-07,
|
| 1087 |
+
"loss": 1.3728,
|
| 1088 |
+
"step": 138
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.014744099708300186,
|
| 1092 |
+
"grad_norm": 0.6609801054000854,
|
| 1093 |
+
"learning_rate": 4.992901987765941e-07,
|
| 1094 |
+
"loss": 1.4302,
|
| 1095 |
+
"step": 139
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.01485017236807213,
|
| 1099 |
+
"grad_norm": 0.6714500188827515,
|
| 1100 |
+
"learning_rate": 4.99285023115794e-07,
|
| 1101 |
+
"loss": 1.3048,
|
| 1102 |
+
"step": 140
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.01485017236807213,
|
| 1106 |
+
"eval_loss": 1.4487165212631226,
|
| 1107 |
+
"eval_runtime": 68.3673,
|
| 1108 |
+
"eval_samples_per_second": 1.872,
|
| 1109 |
+
"eval_steps_per_second": 0.468,
|
| 1110 |
+
"step": 140
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.014956245027844072,
|
| 1114 |
+
"grad_norm": 0.7616133689880371,
|
| 1115 |
+
"learning_rate": 4.992798464532639e-07,
|
| 1116 |
+
"loss": 1.6308,
|
| 1117 |
+
"step": 141
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.015062317687616017,
|
| 1121 |
+
"grad_norm": 0.7023948431015015,
|
| 1122 |
+
"learning_rate": 4.99274668788713e-07,
|
| 1123 |
+
"loss": 1.4595,
|
| 1124 |
+
"step": 142
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.01516839034738796,
|
| 1128 |
+
"grad_norm": 1.1847342252731323,
|
| 1129 |
+
"learning_rate": 4.992694901218502e-07,
|
| 1130 |
+
"loss": 1.892,
|
| 1131 |
+
"step": 143
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.015274463007159905,
|
| 1135 |
+
"grad_norm": 0.6449259519577026,
|
| 1136 |
+
"learning_rate": 4.992643104523846e-07,
|
| 1137 |
+
"loss": 1.4526,
|
| 1138 |
+
"step": 144
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.015380535666931849,
|
| 1142 |
+
"grad_norm": 0.8200846910476685,
|
| 1143 |
+
"learning_rate": 4.992591297800247e-07,
|
| 1144 |
+
"loss": 1.6277,
|
| 1145 |
+
"step": 145
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.015486608326703791,
|
| 1149 |
+
"grad_norm": 0.627193808555603,
|
| 1150 |
+
"learning_rate": 4.992539481044796e-07,
|
| 1151 |
+
"loss": 1.2767,
|
| 1152 |
+
"step": 146
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.015592680986475736,
|
| 1156 |
+
"grad_norm": 0.6754332780838013,
|
| 1157 |
+
"learning_rate": 4.992487654254575e-07,
|
| 1158 |
+
"loss": 1.7414,
|
| 1159 |
+
"step": 147
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 0.01569875364624768,
|
| 1163 |
+
"grad_norm": 0.8303399682044983,
|
| 1164 |
+
"learning_rate": 4.992435817426671e-07,
|
| 1165 |
+
"loss": 1.5313,
|
| 1166 |
+
"step": 148
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.015804826306019624,
|
| 1170 |
+
"grad_norm": 0.7653703093528748,
|
| 1171 |
+
"learning_rate": 4.992383970558168e-07,
|
| 1172 |
+
"loss": 1.6444,
|
| 1173 |
+
"step": 149
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.015910898965791568,
|
| 1177 |
+
"grad_norm": 0.756195068359375,
|
| 1178 |
+
"learning_rate": 4.992332113646148e-07,
|
| 1179 |
+
"loss": 1.5063,
|
| 1180 |
+
"step": 150
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.015910898965791568,
|
| 1184 |
+
"eval_loss": 1.4446443319320679,
|
| 1185 |
+
"eval_runtime": 67.8607,
|
| 1186 |
+
"eval_samples_per_second": 1.886,
|
| 1187 |
+
"eval_steps_per_second": 0.472,
|
| 1188 |
+
"step": 150
|
| 1189 |
}
|
| 1190 |
],
|
| 1191 |
"logging_steps": 1,
|
|
|
|
| 1205 |
"attributes": {}
|
| 1206 |
}
|
| 1207 |
},
|
| 1208 |
+
"total_flos": 2.418837751332864e+17,
|
| 1209 |
"train_batch_size": 4,
|
| 1210 |
"trial_name": null,
|
| 1211 |
"trial_params": null
|