Training in progress, step 100, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9eebd580b914ef2cfb39cd442c0ac29721862bd9546a9e1469f6ba87e5904de3
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3b56714d7488507b9193156497f672b57afb02518fdb35aa925ffc7a2e40375
|
3 |
size 335922386
|
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:d6c4f649546a1ce505561ddfdb31c524a503f333d66811633631217add713d13
|
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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -564,6 +564,189 @@
|
|
564 |
"eval_samples_per_second": 3.508,
|
565 |
"eval_steps_per_second": 1.754,
|
566 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
567 |
}
|
568 |
],
|
569 |
"logging_steps": 1,
|
@@ -587,12 +770,12 @@
|
|
587 |
"should_evaluate": false,
|
588 |
"should_log": false,
|
589 |
"should_save": true,
|
590 |
-
"should_training_stop":
|
591 |
},
|
592 |
"attributes": {}
|
593 |
}
|
594 |
},
|
595 |
-
"total_flos": 1.
|
596 |
"train_batch_size": 2,
|
597 |
"trial_name": null,
|
598 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3503866195678711,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.0020115563914689895,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
564 |
"eval_samples_per_second": 3.508,
|
565 |
"eval_steps_per_second": 1.754,
|
566 |
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.001528782857516432,
|
570 |
+
"grad_norm": 0.6691503524780273,
|
571 |
+
"learning_rate": 2.9876321572751144e-05,
|
572 |
+
"loss": 0.1867,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.0015488984214311217,
|
577 |
+
"grad_norm": 1.2199984788894653,
|
578 |
+
"learning_rate": 2.7557479520891104e-05,
|
579 |
+
"loss": 0.2102,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.0015690139853458116,
|
584 |
+
"grad_norm": 0.6254073977470398,
|
585 |
+
"learning_rate": 2.5317852301584643e-05,
|
586 |
+
"loss": 0.1688,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.0015891295492605016,
|
591 |
+
"grad_norm": 0.7005298137664795,
|
592 |
+
"learning_rate": 2.315988891431412e-05,
|
593 |
+
"loss": 0.1579,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.0016092451131751915,
|
598 |
+
"grad_norm": 0.359977662563324,
|
599 |
+
"learning_rate": 2.1085949060360654e-05,
|
600 |
+
"loss": 0.0562,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.0016293606770898814,
|
605 |
+
"grad_norm": 1.038337230682373,
|
606 |
+
"learning_rate": 1.9098300562505266e-05,
|
607 |
+
"loss": 0.1723,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.0016494762410045713,
|
612 |
+
"grad_norm": 0.537745475769043,
|
613 |
+
"learning_rate": 1.7199116885197995e-05,
|
614 |
+
"loss": 0.0839,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.0016695918049192612,
|
619 |
+
"grad_norm": 0.7610992789268494,
|
620 |
+
"learning_rate": 1.5390474757906446e-05,
|
621 |
+
"loss": 0.1321,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.0016897073688339512,
|
626 |
+
"grad_norm": 0.8755677342414856,
|
627 |
+
"learning_rate": 1.3674351904242611e-05,
|
628 |
+
"loss": 0.158,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.0017098229327486409,
|
633 |
+
"grad_norm": 1.5665292739868164,
|
634 |
+
"learning_rate": 1.2052624879351104e-05,
|
635 |
+
"loss": 0.3811,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.0017299384966633308,
|
640 |
+
"grad_norm": 0.665432333946228,
|
641 |
+
"learning_rate": 1.0527067017923654e-05,
|
642 |
+
"loss": 0.1981,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.0017500540605780207,
|
647 |
+
"grad_norm": 0.6402338147163391,
|
648 |
+
"learning_rate": 9.09934649508375e-06,
|
649 |
+
"loss": 0.1776,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.0017701696244927106,
|
654 |
+
"grad_norm": 1.7284150123596191,
|
655 |
+
"learning_rate": 7.771024502261526e-06,
|
656 |
+
"loss": 0.4189,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.0017902851884074005,
|
661 |
+
"grad_norm": 0.9359285831451416,
|
662 |
+
"learning_rate": 6.543553540053926e-06,
|
663 |
+
"loss": 0.1095,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.0018104007523220905,
|
668 |
+
"grad_norm": 0.8026375770568848,
|
669 |
+
"learning_rate": 5.418275829936537e-06,
|
670 |
+
"loss": 0.1492,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.0018305163162367804,
|
675 |
+
"grad_norm": 2.1033782958984375,
|
676 |
+
"learning_rate": 4.3964218465642355e-06,
|
677 |
+
"loss": 0.4742,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.0018506318801514703,
|
682 |
+
"grad_norm": 3.3076441287994385,
|
683 |
+
"learning_rate": 3.4791089722651436e-06,
|
684 |
+
"loss": 0.4197,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.00187074744406616,
|
689 |
+
"grad_norm": 2.0006370544433594,
|
690 |
+
"learning_rate": 2.667340275199426e-06,
|
691 |
+
"loss": 0.5587,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.00189086300798085,
|
696 |
+
"grad_norm": 1.3604930639266968,
|
697 |
+
"learning_rate": 1.9620034125190644e-06,
|
698 |
+
"loss": 0.4432,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.0019109785718955398,
|
703 |
+
"grad_norm": 1.7596443891525269,
|
704 |
+
"learning_rate": 1.3638696597277679e-06,
|
705 |
+
"loss": 0.4846,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.0019310941358102298,
|
710 |
+
"grad_norm": 2.329746723175049,
|
711 |
+
"learning_rate": 8.735930673024806e-07,
|
712 |
+
"loss": 0.6485,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.0019512096997249197,
|
717 |
+
"grad_norm": 1.9191521406173706,
|
718 |
+
"learning_rate": 4.917097454988584e-07,
|
719 |
+
"loss": 0.2235,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.0019713252636396096,
|
724 |
+
"grad_norm": 2.7021889686584473,
|
725 |
+
"learning_rate": 2.1863727812254653e-07,
|
726 |
+
"loss": 0.7207,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.0019914408275542995,
|
731 |
+
"grad_norm": 2.9134979248046875,
|
732 |
+
"learning_rate": 5.467426590739511e-08,
|
733 |
+
"loss": 0.8107,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.0020115563914689895,
|
738 |
+
"grad_norm": 1.8843333721160889,
|
739 |
+
"learning_rate": 0.0,
|
740 |
+
"loss": 0.4125,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.0020115563914689895,
|
745 |
+
"eval_loss": 0.3503866195678711,
|
746 |
+
"eval_runtime": 5962.3258,
|
747 |
+
"eval_samples_per_second": 3.511,
|
748 |
+
"eval_steps_per_second": 1.755,
|
749 |
+
"step": 100
|
750 |
}
|
751 |
],
|
752 |
"logging_steps": 1,
|
|
|
770 |
"should_evaluate": false,
|
771 |
"should_log": false,
|
772 |
"should_save": true,
|
773 |
+
"should_training_stop": true
|
774 |
},
|
775 |
"attributes": {}
|
776 |
}
|
777 |
},
|
778 |
+
"total_flos": 1.4874840035386982e+17,
|
779 |
"train_batch_size": 2,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|