Training in progress, step 126, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 80792096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d62bd1b1aeca5b48840634b417207c9c4c09169919bf06b8c8da0f375271cd0a
|
| 3 |
size 80792096
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41459700
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6b8f03f3f0e8db3b09a38da8377783582d0876593c57b201c0069dccd794d5c
|
| 3 |
size 41459700
|
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 sha256:89875cf1fe47640e70f9e2ecabacd744805cbcd848b3213e20bfb7af6840fd49
|
| 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:baef09c38255daf871f5fc10bb6a87c467914d1dfa26b8771954f9499745efe8
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -595,6 +595,300 @@
|
|
| 595 |
"learning_rate": 5.146326588692438e-05,
|
| 596 |
"loss": 1.1875,
|
| 597 |
"step": 84
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 598 |
}
|
| 599 |
],
|
| 600 |
"logging_steps": 1,
|
|
@@ -614,7 +908,7 @@
|
|
| 614 |
"attributes": {}
|
| 615 |
}
|
| 616 |
},
|
| 617 |
-
"total_flos":
|
| 618 |
"train_batch_size": 4,
|
| 619 |
"trial_name": null,
|
| 620 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.762481089258699,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 126,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 595 |
"learning_rate": 5.146326588692438e-05,
|
| 596 |
"loss": 1.1875,
|
| 597 |
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5143721633888049,
|
| 601 |
+
"grad_norm": 9.615294456481934,
|
| 602 |
+
"learning_rate": 5.048781720696291e-05,
|
| 603 |
+
"loss": 1.5413,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.5204236006051437,
|
| 608 |
+
"grad_norm": 8.135547637939453,
|
| 609 |
+
"learning_rate": 4.95121827930371e-05,
|
| 610 |
+
"loss": 1.5035,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5264750378214826,
|
| 615 |
+
"grad_norm": 5.731124401092529,
|
| 616 |
+
"learning_rate": 4.853673411307564e-05,
|
| 617 |
+
"loss": 1.2925,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5325264750378215,
|
| 622 |
+
"grad_norm": 5.864335060119629,
|
| 623 |
+
"learning_rate": 4.756184256428992e-05,
|
| 624 |
+
"loss": 0.8643,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5385779122541604,
|
| 629 |
+
"grad_norm": 6.120126247406006,
|
| 630 |
+
"learning_rate": 4.658787933176646e-05,
|
| 631 |
+
"loss": 0.8852,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5446293494704992,
|
| 636 |
+
"grad_norm": 3.3239099979400635,
|
| 637 |
+
"learning_rate": 4.561521524713997e-05,
|
| 638 |
+
"loss": 0.6142,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5506807866868382,
|
| 643 |
+
"grad_norm": 3.291146993637085,
|
| 644 |
+
"learning_rate": 4.4644220647401136e-05,
|
| 645 |
+
"loss": 0.6233,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.556732223903177,
|
| 650 |
+
"grad_norm": 2.9767818450927734,
|
| 651 |
+
"learning_rate": 4.367526523389253e-05,
|
| 652 |
+
"loss": 0.4502,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5627836611195158,
|
| 657 |
+
"grad_norm": 2.5687639713287354,
|
| 658 |
+
"learning_rate": 4.2708717931546825e-05,
|
| 659 |
+
"loss": 0.4639,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5688350983358548,
|
| 664 |
+
"grad_norm": 2.8956291675567627,
|
| 665 |
+
"learning_rate": 4.174494674842038e-05,
|
| 666 |
+
"loss": 0.3833,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5748865355521936,
|
| 671 |
+
"grad_norm": 3.41869854927063,
|
| 672 |
+
"learning_rate": 4.0784318635576055e-05,
|
| 673 |
+
"loss": 0.3458,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5809379727685325,
|
| 678 |
+
"grad_norm": 2.012956142425537,
|
| 679 |
+
"learning_rate": 3.982719934736832e-05,
|
| 680 |
+
"loss": 0.2622,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5869894099848714,
|
| 685 |
+
"grad_norm": 1.7718323469161987,
|
| 686 |
+
"learning_rate": 3.887395330218429e-05,
|
| 687 |
+
"loss": 0.1466,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5930408472012103,
|
| 692 |
+
"grad_norm": 1.5787506103515625,
|
| 693 |
+
"learning_rate": 3.792494344369311e-05,
|
| 694 |
+
"loss": 0.1388,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5990922844175491,
|
| 699 |
+
"grad_norm": 1.3233414888381958,
|
| 700 |
+
"learning_rate": 3.698053110265699e-05,
|
| 701 |
+
"loss": 0.117,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6051437216338881,
|
| 706 |
+
"grad_norm": 1.1028014421463013,
|
| 707 |
+
"learning_rate": 3.604107585935638e-05,
|
| 708 |
+
"loss": 0.12,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.6111951588502269,
|
| 713 |
+
"grad_norm": 1.057910442352295,
|
| 714 |
+
"learning_rate": 3.510693540668151e-05,
|
| 715 |
+
"loss": 0.0996,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6172465960665658,
|
| 720 |
+
"grad_norm": 0.8907783031463623,
|
| 721 |
+
"learning_rate": 3.4178465413942625e-05,
|
| 722 |
+
"loss": 0.0811,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6232980332829047,
|
| 727 |
+
"grad_norm": 0.7459267377853394,
|
| 728 |
+
"learning_rate": 3.325601939145069e-05,
|
| 729 |
+
"loss": 0.0353,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.6293494704992436,
|
| 734 |
+
"grad_norm": 0.9089831113815308,
|
| 735 |
+
"learning_rate": 3.23399485559201e-05,
|
| 736 |
+
"loss": 0.0709,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.6354009077155824,
|
| 741 |
+
"grad_norm": 0.7159168124198914,
|
| 742 |
+
"learning_rate": 3.143060169674468e-05,
|
| 743 |
+
"loss": 0.0451,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.6414523449319214,
|
| 748 |
+
"grad_norm": 0.5289613008499146,
|
| 749 |
+
"learning_rate": 3.0528325043197785e-05,
|
| 750 |
+
"loss": 0.0278,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.6475037821482602,
|
| 755 |
+
"grad_norm": 0.5118010640144348,
|
| 756 |
+
"learning_rate": 2.963346213260737e-05,
|
| 757 |
+
"loss": 0.0221,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.653555219364599,
|
| 762 |
+
"grad_norm": 0.354955792427063,
|
| 763 |
+
"learning_rate": 2.874635367955579e-05,
|
| 764 |
+
"loss": 0.0104,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.659606656580938,
|
| 769 |
+
"grad_norm": 1.1922907829284668,
|
| 770 |
+
"learning_rate": 2.7867337446154396e-05,
|
| 771 |
+
"loss": 0.0275,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.6656580937972768,
|
| 776 |
+
"grad_norm": 0.9284811615943909,
|
| 777 |
+
"learning_rate": 2.6996748113442394e-05,
|
| 778 |
+
"loss": 0.0236,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.6717095310136157,
|
| 783 |
+
"grad_norm": 0.6479511857032776,
|
| 784 |
+
"learning_rate": 2.613491715395861e-05,
|
| 785 |
+
"loss": 0.0328,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.6777609682299546,
|
| 790 |
+
"grad_norm": 0.3264722526073456,
|
| 791 |
+
"learning_rate": 2.5282172705535013e-05,
|
| 792 |
+
"loss": 0.0126,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6838124054462935,
|
| 797 |
+
"grad_norm": 0.5275784134864807,
|
| 798 |
+
"learning_rate": 2.4438839446359933e-05,
|
| 799 |
+
"loss": 0.0267,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6898638426626323,
|
| 804 |
+
"grad_norm": 1.2883987426757812,
|
| 805 |
+
"learning_rate": 2.360523847135838e-05,
|
| 806 |
+
"loss": 0.0482,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.6959152798789713,
|
| 811 |
+
"grad_norm": 0.6634830832481384,
|
| 812 |
+
"learning_rate": 2.2781687169936795e-05,
|
| 813 |
+
"loss": 0.0287,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.7019667170953101,
|
| 818 |
+
"grad_norm": 0.8741732239723206,
|
| 819 |
+
"learning_rate": 2.196849910513858e-05,
|
| 820 |
+
"loss": 0.037,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.708018154311649,
|
| 825 |
+
"grad_norm": 0.7417043447494507,
|
| 826 |
+
"learning_rate": 2.1165983894256647e-05,
|
| 827 |
+
"loss": 0.0244,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.7140695915279879,
|
| 832 |
+
"grad_norm": 1.1073297262191772,
|
| 833 |
+
"learning_rate": 2.037444709094804e-05,
|
| 834 |
+
"loss": 0.0391,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.7201210287443268,
|
| 839 |
+
"grad_norm": 0.9330146908760071,
|
| 840 |
+
"learning_rate": 1.9594190068895968e-05,
|
| 841 |
+
"loss": 0.0312,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.7261724659606656,
|
| 846 |
+
"grad_norm": 0.8450430631637573,
|
| 847 |
+
"learning_rate": 1.8825509907063327e-05,
|
| 848 |
+
"loss": 0.0212,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.7322239031770046,
|
| 853 |
+
"grad_norm": 0.6666033864021301,
|
| 854 |
+
"learning_rate": 1.8068699276581285e-05,
|
| 855 |
+
"loss": 0.0202,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.7382753403933434,
|
| 860 |
+
"grad_norm": 0.8927512168884277,
|
| 861 |
+
"learning_rate": 1.732404632931625e-05,
|
| 862 |
+
"loss": 0.0204,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.7443267776096822,
|
| 867 |
+
"grad_norm": 0.919458270072937,
|
| 868 |
+
"learning_rate": 1.6591834588157523e-05,
|
| 869 |
+
"loss": 0.0185,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.7503782148260212,
|
| 874 |
+
"grad_norm": 1.465542197227478,
|
| 875 |
+
"learning_rate": 1.5872342839067306e-05,
|
| 876 |
+
"loss": 0.5584,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.75642965204236,
|
| 881 |
+
"grad_norm": 1.944527506828308,
|
| 882 |
+
"learning_rate": 1.5165845024934366e-05,
|
| 883 |
+
"loss": 0.7492,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.762481089258699,
|
| 888 |
+
"grad_norm": 2.006526470184326,
|
| 889 |
+
"learning_rate": 1.447261014127167e-05,
|
| 890 |
+
"loss": 0.725,
|
| 891 |
+
"step": 126
|
| 892 |
}
|
| 893 |
],
|
| 894 |
"logging_steps": 1,
|
|
|
|
| 908 |
"attributes": {}
|
| 909 |
}
|
| 910 |
},
|
| 911 |
+
"total_flos": 8.835164753677517e+16,
|
| 912 |
"train_batch_size": 4,
|
| 913 |
"trial_name": null,
|
| 914 |
"trial_params": null
|