Training in progress, step 150, 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 119801528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bee9b8fba9e6033abe09846cc013ec8d7c039b75c51aff8664477dbc88103c70
|
3 |
size 119801528
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61392180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35265dbdfb4fdad67d493548f649e865209552437a1156ccc43f595d0b9c6cac
|
3 |
size 61392180
|
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:f8542cbce7ef9455b49f64fce1ae16984db581d2c2688d41c8a36593d40315c9
|
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,
|
@@ -532,6 +532,531 @@
|
|
532 |
"learning_rate": 3.551282051282052e-05,
|
533 |
"loss": 1.3052,
|
534 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
535 |
}
|
536 |
],
|
537 |
"logging_steps": 1,
|
@@ -551,7 +1076,7 @@
|
|
551 |
"attributes": {}
|
552 |
}
|
553 |
},
|
554 |
-
"total_flos":
|
555 |
"train_batch_size": 2,
|
556 |
"trial_name": null,
|
557 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.23823704586063132,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 150,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
532 |
"learning_rate": 3.551282051282052e-05,
|
533 |
"loss": 1.3052,
|
534 |
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.12070676990271988,
|
538 |
+
"grad_norm": 0.340273380279541,
|
539 |
+
"learning_rate": 3.544871794871795e-05,
|
540 |
+
"loss": 1.0866,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.12229501687512408,
|
545 |
+
"grad_norm": 0.42024505138397217,
|
546 |
+
"learning_rate": 3.538461538461539e-05,
|
547 |
+
"loss": 1.3908,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.12388326384752829,
|
552 |
+
"grad_norm": 0.3871309757232666,
|
553 |
+
"learning_rate": 3.532051282051282e-05,
|
554 |
+
"loss": 1.1443,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.1254715108199325,
|
559 |
+
"grad_norm": 0.4081447124481201,
|
560 |
+
"learning_rate": 3.525641025641026e-05,
|
561 |
+
"loss": 1.256,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.12705975779233672,
|
566 |
+
"grad_norm": 0.398825079202652,
|
567 |
+
"learning_rate": 3.519230769230769e-05,
|
568 |
+
"loss": 1.0935,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.12864800476474092,
|
573 |
+
"grad_norm": 0.41756635904312134,
|
574 |
+
"learning_rate": 3.512820512820513e-05,
|
575 |
+
"loss": 1.3101,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.13023625173714512,
|
580 |
+
"grad_norm": 0.3089386522769928,
|
581 |
+
"learning_rate": 3.5064102564102565e-05,
|
582 |
+
"loss": 1.0133,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.13182449870954935,
|
587 |
+
"grad_norm": 0.319243848323822,
|
588 |
+
"learning_rate": 3.5000000000000004e-05,
|
589 |
+
"loss": 0.8617,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.13341274568195355,
|
594 |
+
"grad_norm": 0.4051594138145447,
|
595 |
+
"learning_rate": 3.4935897435897436e-05,
|
596 |
+
"loss": 1.2443,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.13500099265435775,
|
601 |
+
"grad_norm": 0.43612000346183777,
|
602 |
+
"learning_rate": 3.4871794871794875e-05,
|
603 |
+
"loss": 1.269,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.13658923962676195,
|
608 |
+
"grad_norm": 0.43578770756721497,
|
609 |
+
"learning_rate": 3.4807692307692315e-05,
|
610 |
+
"loss": 1.2405,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.13817748659916618,
|
615 |
+
"grad_norm": 0.4056044816970825,
|
616 |
+
"learning_rate": 3.474358974358975e-05,
|
617 |
+
"loss": 1.0946,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.13976573357157038,
|
622 |
+
"grad_norm": 0.3657781779766083,
|
623 |
+
"learning_rate": 3.4679487179487186e-05,
|
624 |
+
"loss": 1.0036,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.14135398054397458,
|
629 |
+
"grad_norm": 0.38766562938690186,
|
630 |
+
"learning_rate": 3.461538461538462e-05,
|
631 |
+
"loss": 1.2921,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.1429422275163788,
|
636 |
+
"grad_norm": 0.3952920436859131,
|
637 |
+
"learning_rate": 3.455128205128206e-05,
|
638 |
+
"loss": 1.0871,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.144530474488783,
|
643 |
+
"grad_norm": 0.37682345509529114,
|
644 |
+
"learning_rate": 3.448717948717949e-05,
|
645 |
+
"loss": 1.3176,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.1461187214611872,
|
650 |
+
"grad_norm": 0.41130203008651733,
|
651 |
+
"learning_rate": 3.442307692307693e-05,
|
652 |
+
"loss": 1.4224,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.14770696843359143,
|
657 |
+
"grad_norm": 0.446526437997818,
|
658 |
+
"learning_rate": 3.435897435897436e-05,
|
659 |
+
"loss": 1.1269,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.14929521540599563,
|
664 |
+
"grad_norm": 0.3832029104232788,
|
665 |
+
"learning_rate": 3.4294871794871794e-05,
|
666 |
+
"loss": 1.2257,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.15088346237839984,
|
671 |
+
"grad_norm": 0.3874358534812927,
|
672 |
+
"learning_rate": 3.4230769230769234e-05,
|
673 |
+
"loss": 1.2198,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.15247170935080406,
|
678 |
+
"grad_norm": 0.44150203466415405,
|
679 |
+
"learning_rate": 3.4166666666666666e-05,
|
680 |
+
"loss": 1.4579,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.15405995632320826,
|
685 |
+
"grad_norm": 0.49795201420783997,
|
686 |
+
"learning_rate": 3.4102564102564105e-05,
|
687 |
+
"loss": 1.1809,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.15564820329561246,
|
692 |
+
"grad_norm": 0.38568922877311707,
|
693 |
+
"learning_rate": 3.403846153846154e-05,
|
694 |
+
"loss": 1.2511,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.15723645026801666,
|
699 |
+
"grad_norm": 0.3719356060028076,
|
700 |
+
"learning_rate": 3.397435897435898e-05,
|
701 |
+
"loss": 1.1881,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.1588246972404209,
|
706 |
+
"grad_norm": 0.4000978469848633,
|
707 |
+
"learning_rate": 3.391025641025641e-05,
|
708 |
+
"loss": 1.0767,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.1604129442128251,
|
713 |
+
"grad_norm": 0.46317172050476074,
|
714 |
+
"learning_rate": 3.384615384615385e-05,
|
715 |
+
"loss": 1.1606,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.1620011911852293,
|
720 |
+
"grad_norm": 0.42941561341285706,
|
721 |
+
"learning_rate": 3.378205128205129e-05,
|
722 |
+
"loss": 1.1359,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.16358943815763352,
|
727 |
+
"grad_norm": 0.3518621325492859,
|
728 |
+
"learning_rate": 3.371794871794872e-05,
|
729 |
+
"loss": 1.1586,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.16517768513003772,
|
734 |
+
"grad_norm": 0.45329567790031433,
|
735 |
+
"learning_rate": 3.365384615384616e-05,
|
736 |
+
"loss": 1.3658,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.16676593210244192,
|
741 |
+
"grad_norm": 0.39535844326019287,
|
742 |
+
"learning_rate": 3.358974358974359e-05,
|
743 |
+
"loss": 1.1398,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.16835417907484615,
|
748 |
+
"grad_norm": 0.3700944781303406,
|
749 |
+
"learning_rate": 3.352564102564103e-05,
|
750 |
+
"loss": 1.0872,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.16994242604725035,
|
755 |
+
"grad_norm": 0.3956209719181061,
|
756 |
+
"learning_rate": 3.346153846153846e-05,
|
757 |
+
"loss": 1.3071,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.17153067301965455,
|
762 |
+
"grad_norm": 0.3819758892059326,
|
763 |
+
"learning_rate": 3.33974358974359e-05,
|
764 |
+
"loss": 1.1822,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.17311891999205878,
|
769 |
+
"grad_norm": 0.44656893610954285,
|
770 |
+
"learning_rate": 3.3333333333333335e-05,
|
771 |
+
"loss": 1.3185,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.17470716696446298,
|
776 |
+
"grad_norm": 0.35640376806259155,
|
777 |
+
"learning_rate": 3.3269230769230774e-05,
|
778 |
+
"loss": 1.0616,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.17629541393686718,
|
783 |
+
"grad_norm": 0.3747159242630005,
|
784 |
+
"learning_rate": 3.3205128205128207e-05,
|
785 |
+
"loss": 1.1727,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.17788366090927138,
|
790 |
+
"grad_norm": 0.4224643409252167,
|
791 |
+
"learning_rate": 3.3141025641025646e-05,
|
792 |
+
"loss": 1.155,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.1794719078816756,
|
797 |
+
"grad_norm": 0.45572227239608765,
|
798 |
+
"learning_rate": 3.307692307692308e-05,
|
799 |
+
"loss": 1.1105,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.1810601548540798,
|
804 |
+
"grad_norm": 0.4539688527584076,
|
805 |
+
"learning_rate": 3.301282051282051e-05,
|
806 |
+
"loss": 1.1952,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.182648401826484,
|
811 |
+
"grad_norm": 0.45282796025276184,
|
812 |
+
"learning_rate": 3.294871794871795e-05,
|
813 |
+
"loss": 1.2254,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.18423664879888824,
|
818 |
+
"grad_norm": 0.37122872471809387,
|
819 |
+
"learning_rate": 3.288461538461539e-05,
|
820 |
+
"loss": 1.0683,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.18582489577129244,
|
825 |
+
"grad_norm": 0.5063671469688416,
|
826 |
+
"learning_rate": 3.282051282051282e-05,
|
827 |
+
"loss": 1.2554,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.18741314274369664,
|
832 |
+
"grad_norm": 0.4486718475818634,
|
833 |
+
"learning_rate": 3.275641025641026e-05,
|
834 |
+
"loss": 1.3148,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.18900138971610086,
|
839 |
+
"grad_norm": 0.43316200375556946,
|
840 |
+
"learning_rate": 3.269230769230769e-05,
|
841 |
+
"loss": 1.3,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.19058963668850507,
|
846 |
+
"grad_norm": 0.4560703635215759,
|
847 |
+
"learning_rate": 3.262820512820513e-05,
|
848 |
+
"loss": 1.0387,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.19217788366090927,
|
853 |
+
"grad_norm": 0.41410017013549805,
|
854 |
+
"learning_rate": 3.2564102564102565e-05,
|
855 |
+
"loss": 1.2125,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.1937661306333135,
|
860 |
+
"grad_norm": 0.43740931153297424,
|
861 |
+
"learning_rate": 3.2500000000000004e-05,
|
862 |
+
"loss": 1.1765,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.1953543776057177,
|
867 |
+
"grad_norm": 0.4682227671146393,
|
868 |
+
"learning_rate": 3.2435897435897436e-05,
|
869 |
+
"loss": 1.3742,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.1969426245781219,
|
874 |
+
"grad_norm": 0.47108888626098633,
|
875 |
+
"learning_rate": 3.2371794871794876e-05,
|
876 |
+
"loss": 1.3794,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.1985308715505261,
|
881 |
+
"grad_norm": 0.4044567048549652,
|
882 |
+
"learning_rate": 3.230769230769231e-05,
|
883 |
+
"loss": 1.2427,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.20011911852293032,
|
888 |
+
"grad_norm": 0.44156500697135925,
|
889 |
+
"learning_rate": 3.224358974358975e-05,
|
890 |
+
"loss": 1.1546,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.20170736549533452,
|
895 |
+
"grad_norm": 0.4503639340400696,
|
896 |
+
"learning_rate": 3.2179487179487186e-05,
|
897 |
+
"loss": 1.1677,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.20329561246773872,
|
902 |
+
"grad_norm": 0.40942591428756714,
|
903 |
+
"learning_rate": 3.211538461538462e-05,
|
904 |
+
"loss": 1.0108,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.20488385944014295,
|
909 |
+
"grad_norm": 0.5105980038642883,
|
910 |
+
"learning_rate": 3.205128205128206e-05,
|
911 |
+
"loss": 1.313,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.20647210641254715,
|
916 |
+
"grad_norm": 0.46841809153556824,
|
917 |
+
"learning_rate": 3.198717948717949e-05,
|
918 |
+
"loss": 1.3129,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.20806035338495135,
|
923 |
+
"grad_norm": 0.4008212387561798,
|
924 |
+
"learning_rate": 3.192307692307693e-05,
|
925 |
+
"loss": 1.2303,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.20964860035735558,
|
930 |
+
"grad_norm": 0.42567890882492065,
|
931 |
+
"learning_rate": 3.185897435897436e-05,
|
932 |
+
"loss": 1.2456,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.21123684732975978,
|
937 |
+
"grad_norm": 0.44130662083625793,
|
938 |
+
"learning_rate": 3.1794871794871795e-05,
|
939 |
+
"loss": 1.38,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.21282509430216398,
|
944 |
+
"grad_norm": 0.5576122999191284,
|
945 |
+
"learning_rate": 3.1730769230769234e-05,
|
946 |
+
"loss": 1.3357,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.2144133412745682,
|
951 |
+
"grad_norm": 0.4331263601779938,
|
952 |
+
"learning_rate": 3.1666666666666666e-05,
|
953 |
+
"loss": 1.0914,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.2160015882469724,
|
958 |
+
"grad_norm": 0.5117509961128235,
|
959 |
+
"learning_rate": 3.1602564102564105e-05,
|
960 |
+
"loss": 1.2846,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.2175898352193766,
|
965 |
+
"grad_norm": 0.5039793848991394,
|
966 |
+
"learning_rate": 3.153846153846154e-05,
|
967 |
+
"loss": 1.4331,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.2191780821917808,
|
972 |
+
"grad_norm": 0.4223591387271881,
|
973 |
+
"learning_rate": 3.147435897435898e-05,
|
974 |
+
"loss": 1.1687,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.22076632916418504,
|
979 |
+
"grad_norm": 0.40778806805610657,
|
980 |
+
"learning_rate": 3.141025641025641e-05,
|
981 |
+
"loss": 1.173,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.22235457613658924,
|
986 |
+
"grad_norm": 0.4686231017112732,
|
987 |
+
"learning_rate": 3.134615384615385e-05,
|
988 |
+
"loss": 1.3669,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.22394282310899344,
|
993 |
+
"grad_norm": 0.43122047185897827,
|
994 |
+
"learning_rate": 3.128205128205129e-05,
|
995 |
+
"loss": 1.2708,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.22553107008139767,
|
1000 |
+
"grad_norm": 0.3762079179286957,
|
1001 |
+
"learning_rate": 3.121794871794872e-05,
|
1002 |
+
"loss": 1.1584,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.22711931705380187,
|
1007 |
+
"grad_norm": 0.417106568813324,
|
1008 |
+
"learning_rate": 3.115384615384616e-05,
|
1009 |
+
"loss": 1.1314,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.22870756402620607,
|
1014 |
+
"grad_norm": 0.4525890052318573,
|
1015 |
+
"learning_rate": 3.108974358974359e-05,
|
1016 |
+
"loss": 1.124,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.2302958109986103,
|
1021 |
+
"grad_norm": 0.41886812448501587,
|
1022 |
+
"learning_rate": 3.102564102564103e-05,
|
1023 |
+
"loss": 1.1735,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.2318840579710145,
|
1028 |
+
"grad_norm": 0.39290478825569153,
|
1029 |
+
"learning_rate": 3.0961538461538464e-05,
|
1030 |
+
"loss": 1.2455,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.2334723049434187,
|
1035 |
+
"grad_norm": 0.42833879590034485,
|
1036 |
+
"learning_rate": 3.08974358974359e-05,
|
1037 |
+
"loss": 1.2274,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.23506055191582292,
|
1042 |
+
"grad_norm": 0.37532350420951843,
|
1043 |
+
"learning_rate": 3.0833333333333335e-05,
|
1044 |
+
"loss": 1.0969,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.23664879888822712,
|
1049 |
+
"grad_norm": 0.36185258626937866,
|
1050 |
+
"learning_rate": 3.0769230769230774e-05,
|
1051 |
+
"loss": 1.1227,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.23823704586063132,
|
1056 |
+
"grad_norm": 0.4009798765182495,
|
1057 |
+
"learning_rate": 3.070512820512821e-05,
|
1058 |
+
"loss": 1.0955,
|
1059 |
+
"step": 150
|
1060 |
}
|
1061 |
],
|
1062 |
"logging_steps": 1,
|
|
|
1076 |
"attributes": {}
|
1077 |
}
|
1078 |
},
|
1079 |
+
"total_flos": 1.0710275291755315e+17,
|
1080 |
"train_batch_size": 2,
|
1081 |
"trial_name": null,
|
1082 |
"trial_params": null
|