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 19552
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da4fc4bf8289a80e04830dd9442edc8eb91a99a5e683fa9a132eff0afd906a4f
|
3 |
size 19552
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 47860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbf048fe887df4897b8d0de8261f5eaf4cb6dc1d6e891caf100f9d88c0afd5f1
|
3 |
size 47860
|
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 sha256:719007b97d7d42a16c0d37198ce0dce3d5f047b897028fd22515dbec441991e3
|
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": 12.
|
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": 30.241,
|
565 |
"eval_steps_per_second": 15.12,
|
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":
|
596 |
"train_batch_size": 2,
|
597 |
"trial_name": null,
|
598 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 12.450624465942383,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.5181347150259067,
|
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": 30.241,
|
565 |
"eval_steps_per_second": 15.12,
|
566 |
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.39378238341968913,
|
570 |
+
"grad_norm": 0.09004762023687363,
|
571 |
+
"learning_rate": 2.9876321572751144e-05,
|
572 |
+
"loss": 12.4461,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.39896373056994816,
|
577 |
+
"grad_norm": 0.11161310225725174,
|
578 |
+
"learning_rate": 2.7557479520891104e-05,
|
579 |
+
"loss": 12.4585,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.40414507772020725,
|
584 |
+
"grad_norm": 0.09739028662443161,
|
585 |
+
"learning_rate": 2.5317852301584643e-05,
|
586 |
+
"loss": 12.4534,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.40932642487046633,
|
591 |
+
"grad_norm": 0.10811323672533035,
|
592 |
+
"learning_rate": 2.315988891431412e-05,
|
593 |
+
"loss": 12.4641,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.41450777202072536,
|
598 |
+
"grad_norm": 0.13142776489257812,
|
599 |
+
"learning_rate": 2.1085949060360654e-05,
|
600 |
+
"loss": 12.4527,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.41968911917098445,
|
605 |
+
"grad_norm": 0.11857596784830093,
|
606 |
+
"learning_rate": 1.9098300562505266e-05,
|
607 |
+
"loss": 12.4588,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.42487046632124353,
|
612 |
+
"grad_norm": 0.10847970843315125,
|
613 |
+
"learning_rate": 1.7199116885197995e-05,
|
614 |
+
"loss": 12.4547,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.43005181347150256,
|
619 |
+
"grad_norm": 0.0970698669552803,
|
620 |
+
"learning_rate": 1.5390474757906446e-05,
|
621 |
+
"loss": 12.4555,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.43523316062176165,
|
626 |
+
"grad_norm": 0.10735609382390976,
|
627 |
+
"learning_rate": 1.3674351904242611e-05,
|
628 |
+
"loss": 12.4597,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.44041450777202074,
|
633 |
+
"grad_norm": 0.12275223433971405,
|
634 |
+
"learning_rate": 1.2052624879351104e-05,
|
635 |
+
"loss": 12.4475,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.44559585492227977,
|
640 |
+
"grad_norm": 0.12521672248840332,
|
641 |
+
"learning_rate": 1.0527067017923654e-05,
|
642 |
+
"loss": 12.4532,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.45077720207253885,
|
647 |
+
"grad_norm": 0.10316548496484756,
|
648 |
+
"learning_rate": 9.09934649508375e-06,
|
649 |
+
"loss": 12.4575,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.45595854922279794,
|
654 |
+
"grad_norm": 0.12661558389663696,
|
655 |
+
"learning_rate": 7.771024502261526e-06,
|
656 |
+
"loss": 12.4529,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.46113989637305697,
|
661 |
+
"grad_norm": 0.13413290679454803,
|
662 |
+
"learning_rate": 6.543553540053926e-06,
|
663 |
+
"loss": 12.4472,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.46632124352331605,
|
668 |
+
"grad_norm": 0.1272674798965454,
|
669 |
+
"learning_rate": 5.418275829936537e-06,
|
670 |
+
"loss": 12.4598,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.47150259067357514,
|
675 |
+
"grad_norm": 0.11629094928503036,
|
676 |
+
"learning_rate": 4.3964218465642355e-06,
|
677 |
+
"loss": 12.4569,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.47668393782383417,
|
682 |
+
"grad_norm": 0.1196855679154396,
|
683 |
+
"learning_rate": 3.4791089722651436e-06,
|
684 |
+
"loss": 12.4585,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.48186528497409326,
|
689 |
+
"grad_norm": 0.11991642415523529,
|
690 |
+
"learning_rate": 2.667340275199426e-06,
|
691 |
+
"loss": 12.4523,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.48704663212435234,
|
696 |
+
"grad_norm": 0.12190738320350647,
|
697 |
+
"learning_rate": 1.9620034125190644e-06,
|
698 |
+
"loss": 12.4582,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.49222797927461137,
|
703 |
+
"grad_norm": 0.14460605382919312,
|
704 |
+
"learning_rate": 1.3638696597277679e-06,
|
705 |
+
"loss": 12.4452,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.49740932642487046,
|
710 |
+
"grad_norm": 0.12674753367900848,
|
711 |
+
"learning_rate": 8.735930673024806e-07,
|
712 |
+
"loss": 12.4645,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.5025906735751295,
|
717 |
+
"grad_norm": 0.08967099338769913,
|
718 |
+
"learning_rate": 4.917097454988584e-07,
|
719 |
+
"loss": 12.4606,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.5077720207253886,
|
724 |
+
"grad_norm": 0.09563156962394714,
|
725 |
+
"learning_rate": 2.1863727812254653e-07,
|
726 |
+
"loss": 12.4635,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.5129533678756477,
|
731 |
+
"grad_norm": 0.10204072296619415,
|
732 |
+
"learning_rate": 5.467426590739511e-08,
|
733 |
+
"loss": 12.4471,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.5181347150259067,
|
738 |
+
"grad_norm": 0.10895761102437973,
|
739 |
+
"learning_rate": 0.0,
|
740 |
+
"loss": 12.4487,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.5181347150259067,
|
745 |
+
"eval_loss": 12.450624465942383,
|
746 |
+
"eval_runtime": 2.712,
|
747 |
+
"eval_samples_per_second": 30.237,
|
748 |
+
"eval_steps_per_second": 15.118,
|
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": 123312537600.0,
|
779 |
"train_batch_size": 2,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|