Commit
•
8702ce7
1
Parent(s):
32ce1d5
Training in progress, step 116, 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 100198584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b570962ede4265c9488fa98dcd00095b1ca3d903d14f064ee79d3cb2379651f4
|
| 3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50675156
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68afdadf9dcafbea18732f32b8ac5fa2ad488bf587daf988c9af28727179daa0
|
| 3 |
size 50675156
|
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 sha256:07e779822c485743db355cfc0cc7805b58345253d12afcfcd7953cd3834152cb
|
| 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 +595,230 @@
|
|
| 595 |
"learning_rate": 1.6800000000000002e-05,
|
| 596 |
"loss": 1.6169,
|
| 597 |
"step": 84
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 598 |
}
|
| 599 |
],
|
| 600 |
"logging_steps": 1,
|
|
@@ -614,7 +838,7 @@
|
|
| 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": 0.16948223906492557,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 116,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 595 |
"learning_rate": 1.6800000000000002e-05,
|
| 596 |
"loss": 1.6169,
|
| 597 |
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.12418957172860925,
|
| 601 |
+
"grad_norm": 0.3446858525276184,
|
| 602 |
+
"learning_rate": 1.7e-05,
|
| 603 |
+
"loss": 1.6721,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.12565062551365172,
|
| 608 |
+
"grad_norm": 0.33179470896720886,
|
| 609 |
+
"learning_rate": 1.72e-05,
|
| 610 |
+
"loss": 1.578,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.12711167929869419,
|
| 615 |
+
"grad_norm": 0.3791605830192566,
|
| 616 |
+
"learning_rate": 1.7400000000000003e-05,
|
| 617 |
+
"loss": 1.6055,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.12857273308373665,
|
| 622 |
+
"grad_norm": 0.5245212912559509,
|
| 623 |
+
"learning_rate": 1.76e-05,
|
| 624 |
+
"loss": 1.626,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.13003378686877912,
|
| 629 |
+
"grad_norm": 0.43215855956077576,
|
| 630 |
+
"learning_rate": 1.7800000000000002e-05,
|
| 631 |
+
"loss": 1.6177,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.13149484065382158,
|
| 636 |
+
"grad_norm": 0.4050828516483307,
|
| 637 |
+
"learning_rate": 1.8e-05,
|
| 638 |
+
"loss": 1.4903,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.13295589443886402,
|
| 643 |
+
"grad_norm": 0.399501234292984,
|
| 644 |
+
"learning_rate": 1.8200000000000002e-05,
|
| 645 |
+
"loss": 1.6079,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.13441694822390649,
|
| 650 |
+
"grad_norm": 0.439622700214386,
|
| 651 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 652 |
+
"loss": 1.5405,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.13587800200894895,
|
| 657 |
+
"grad_norm": 0.4368193447589874,
|
| 658 |
+
"learning_rate": 1.86e-05,
|
| 659 |
+
"loss": 1.415,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.13733905579399142,
|
| 664 |
+
"grad_norm": 0.3644118010997772,
|
| 665 |
+
"learning_rate": 1.88e-05,
|
| 666 |
+
"loss": 1.525,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.13880010957903388,
|
| 671 |
+
"grad_norm": 0.3868708312511444,
|
| 672 |
+
"learning_rate": 1.9e-05,
|
| 673 |
+
"loss": 1.4903,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.14026116336407635,
|
| 678 |
+
"grad_norm": 0.43034952878952026,
|
| 679 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 680 |
+
"loss": 1.4605,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.1417222171491188,
|
| 685 |
+
"grad_norm": 0.4087560772895813,
|
| 686 |
+
"learning_rate": 1.94e-05,
|
| 687 |
+
"loss": 1.3544,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.14318327093416128,
|
| 692 |
+
"grad_norm": 0.29801666736602783,
|
| 693 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 694 |
+
"loss": 1.4098,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.14464432471920372,
|
| 699 |
+
"grad_norm": 0.275905966758728,
|
| 700 |
+
"learning_rate": 1.98e-05,
|
| 701 |
+
"loss": 1.4732,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.14610537850424618,
|
| 706 |
+
"grad_norm": 0.32271912693977356,
|
| 707 |
+
"learning_rate": 2e-05,
|
| 708 |
+
"loss": 1.4156,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.14756643228928865,
|
| 713 |
+
"grad_norm": 0.3191397190093994,
|
| 714 |
+
"learning_rate": 1.9965753424657538e-05,
|
| 715 |
+
"loss": 1.3254,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.1490274860743311,
|
| 720 |
+
"grad_norm": 0.26260653138160706,
|
| 721 |
+
"learning_rate": 1.993150684931507e-05,
|
| 722 |
+
"loss": 1.3877,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.15048853985937358,
|
| 727 |
+
"grad_norm": 0.2782766819000244,
|
| 728 |
+
"learning_rate": 1.9897260273972604e-05,
|
| 729 |
+
"loss": 1.3683,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.15194959364441604,
|
| 734 |
+
"grad_norm": 0.2510565221309662,
|
| 735 |
+
"learning_rate": 1.9863013698630137e-05,
|
| 736 |
+
"loss": 1.3996,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.1534106474294585,
|
| 741 |
+
"grad_norm": 0.2523151934146881,
|
| 742 |
+
"learning_rate": 1.9828767123287674e-05,
|
| 743 |
+
"loss": 1.3192,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.15487170121450095,
|
| 748 |
+
"grad_norm": 0.20559488236904144,
|
| 749 |
+
"learning_rate": 1.9794520547945207e-05,
|
| 750 |
+
"loss": 1.2096,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.1563327549995434,
|
| 755 |
+
"grad_norm": 0.17568816244602203,
|
| 756 |
+
"learning_rate": 1.9760273972602743e-05,
|
| 757 |
+
"loss": 1.3795,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.15779380878458588,
|
| 762 |
+
"grad_norm": 0.1778278350830078,
|
| 763 |
+
"learning_rate": 1.9726027397260276e-05,
|
| 764 |
+
"loss": 1.3146,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.15925486256962834,
|
| 769 |
+
"grad_norm": 0.18488670885562897,
|
| 770 |
+
"learning_rate": 1.969178082191781e-05,
|
| 771 |
+
"loss": 1.4105,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.1607159163546708,
|
| 776 |
+
"grad_norm": 0.1593291312456131,
|
| 777 |
+
"learning_rate": 1.9657534246575346e-05,
|
| 778 |
+
"loss": 1.3054,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.16217697013971327,
|
| 783 |
+
"grad_norm": 0.14311783015727997,
|
| 784 |
+
"learning_rate": 1.962328767123288e-05,
|
| 785 |
+
"loss": 1.3985,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.16363802392475574,
|
| 790 |
+
"grad_norm": 0.14948627352714539,
|
| 791 |
+
"learning_rate": 1.9589041095890412e-05,
|
| 792 |
+
"loss": 1.3395,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.1650990777097982,
|
| 797 |
+
"grad_norm": 0.14075608551502228,
|
| 798 |
+
"learning_rate": 1.9554794520547945e-05,
|
| 799 |
+
"loss": 1.3868,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.16656013149484064,
|
| 804 |
+
"grad_norm": 0.14439420402050018,
|
| 805 |
+
"learning_rate": 1.952054794520548e-05,
|
| 806 |
+
"loss": 1.2985,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.1680211852798831,
|
| 811 |
+
"grad_norm": 0.13425147533416748,
|
| 812 |
+
"learning_rate": 1.9486301369863014e-05,
|
| 813 |
+
"loss": 1.3855,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.16948223906492557,
|
| 818 |
+
"grad_norm": 0.1291724145412445,
|
| 819 |
+
"learning_rate": 1.945205479452055e-05,
|
| 820 |
+
"loss": 1.2942,
|
| 821 |
+
"step": 116
|
| 822 |
}
|
| 823 |
],
|
| 824 |
"logging_steps": 1,
|
|
|
|
| 838 |
"attributes": {}
|
| 839 |
}
|
| 840 |
},
|
| 841 |
+
"total_flos": 1.304737835336663e+17,
|
| 842 |
"train_batch_size": 4,
|
| 843 |
"trial_name": null,
|
| 844 |
"trial_params": null
|