Training in progress, step 95, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +144 -4
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100966336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:734b64962d96dde20b023dee1d4f48a32c2f43a89f28c32574feb174c92a94db
|
3 |
size 100966336
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 202110330
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8865d259e292f793426f33b44f11c87efee3fe3bc7670e3a87e04270a1cf39a7
|
3 |
size 202110330
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:041daf5e94442122ad595703364513594bdf36e7713b9c0db490c8994f88c956
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8166ac0a77c36bb471492a06a75508aaad02387972da4dcf704b58c21a637cf4
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f79238a0b6e15db3e74c57a6170e48b32d9f40bc01d1c6824672007b2d33032
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5aedaa79240e12d3c592e58fbcc92e6792f76f0ea0a5820fb0526c1014a97280
|
3 |
size 15024
|
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 sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 2.399653673171997,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-75",
|
4 |
-
"epoch": 2.
|
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 +564,146 @@
|
|
564 |
"eval_samples_per_second": 48.418,
|
565 |
"eval_steps_per_second": 12.589,
|
566 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
567 |
}
|
568 |
],
|
569 |
"logging_steps": 1,
|
@@ -587,12 +727,12 @@
|
|
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": 1,
|
597 |
"trial_name": null,
|
598 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 2.399653673171997,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-75",
|
4 |
+
"epoch": 2.931533269045323,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 95,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
564 |
"eval_samples_per_second": 48.418,
|
565 |
"eval_steps_per_second": 12.589,
|
566 |
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 2.3452266152362586,
|
570 |
+
"grad_norm": 0.5155852437019348,
|
571 |
+
"learning_rate": 1.91437699862843e-05,
|
572 |
+
"loss": 2.3823,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 2.376084860173578,
|
577 |
+
"grad_norm": 0.5314053297042847,
|
578 |
+
"learning_rate": 1.8236354814530112e-05,
|
579 |
+
"loss": 2.3937,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 2.406943105110897,
|
584 |
+
"grad_norm": 0.6399489045143127,
|
585 |
+
"learning_rate": 1.7371804408538024e-05,
|
586 |
+
"loss": 2.4228,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 2.437801350048216,
|
591 |
+
"grad_norm": 0.6850634217262268,
|
592 |
+
"learning_rate": 1.6551126795408016e-05,
|
593 |
+
"loss": 2.4441,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 2.468659594985535,
|
598 |
+
"grad_norm": 1.0091044902801514,
|
599 |
+
"learning_rate": 1.577527884852619e-05,
|
600 |
+
"loss": 2.3599,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 2.4995178399228544,
|
605 |
+
"grad_norm": 1.378424882888794,
|
606 |
+
"learning_rate": 1.5045165171893116e-05,
|
607 |
+
"loss": 2.1828,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 2.5303760848601735,
|
612 |
+
"grad_norm": 0.4469667673110962,
|
613 |
+
"learning_rate": 1.4361637045396029e-05,
|
614 |
+
"loss": 2.2746,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 2.5612343297974927,
|
619 |
+
"grad_norm": 0.48588716983795166,
|
620 |
+
"learning_rate": 1.3725491432254624e-05,
|
621 |
+
"loss": 2.3452,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 2.592092574734812,
|
626 |
+
"grad_norm": 0.5537601709365845,
|
627 |
+
"learning_rate": 1.313747004979751e-05,
|
628 |
+
"loss": 2.4595,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 2.6229508196721314,
|
633 |
+
"grad_norm": 0.5473658442497253,
|
634 |
+
"learning_rate": 1.2598258504653081e-05,
|
635 |
+
"loss": 2.3284,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 2.65380906460945,
|
640 |
+
"grad_norm": 0.6774117946624756,
|
641 |
+
"learning_rate": 1.2108485493362765e-05,
|
642 |
+
"loss": 2.3467,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 2.6846673095467697,
|
647 |
+
"grad_norm": 0.7467882633209229,
|
648 |
+
"learning_rate": 1.1668722069349041e-05,
|
649 |
+
"loss": 2.4901,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 2.715525554484089,
|
654 |
+
"grad_norm": 1.0815759897232056,
|
655 |
+
"learning_rate": 1.1279480977092635e-05,
|
656 |
+
"loss": 2.3596,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 2.746383799421408,
|
661 |
+
"grad_norm": 1.4572314023971558,
|
662 |
+
"learning_rate": 1.094121605429547e-05,
|
663 |
+
"loss": 2.1992,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 2.777242044358727,
|
668 |
+
"grad_norm": 0.4223305284976959,
|
669 |
+
"learning_rate": 1.0654321702726141e-05,
|
670 |
+
"loss": 2.2878,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 2.8081002892960463,
|
675 |
+
"grad_norm": 0.48473823070526123,
|
676 |
+
"learning_rate": 1.0419132428365116e-05,
|
677 |
+
"loss": 2.3765,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 2.8389585342333654,
|
682 |
+
"grad_norm": 0.5096808075904846,
|
683 |
+
"learning_rate": 1.0235922451385733e-05,
|
684 |
+
"loss": 2.4602,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 2.8698167791706846,
|
689 |
+
"grad_norm": 0.5460689663887024,
|
690 |
+
"learning_rate": 1.0104905386425733e-05,
|
691 |
+
"loss": 2.3527,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 2.9006750241080037,
|
696 |
+
"grad_norm": 0.6414793133735657,
|
697 |
+
"learning_rate": 1.002623399352217e-05,
|
698 |
+
"loss": 2.3315,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 2.931533269045323,
|
703 |
+
"grad_norm": 0.7416414022445679,
|
704 |
+
"learning_rate": 1e-05,
|
705 |
+
"loss": 2.4737,
|
706 |
+
"step": 95
|
707 |
}
|
708 |
],
|
709 |
"logging_steps": 1,
|
|
|
727 |
"should_evaluate": false,
|
728 |
"should_log": false,
|
729 |
"should_save": true,
|
730 |
+
"should_training_stop": true
|
731 |
},
|
732 |
"attributes": {}
|
733 |
}
|
734 |
},
|
735 |
+
"total_flos": 1.584532913431511e+17,
|
736 |
"train_batch_size": 1,
|
737 |
"trial_name": null,
|
738 |
"trial_params": null
|