Training in progress, step 100, 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 +189 -6
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:a209c94079127d839633d5e12ec7f4672fe06acdb9ad09830ceecf4f3b2594b6
|
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:f0fe18418e074b229083ce2c997215a90d9e81cb5300f50f810702d42235305f
|
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 sha256:50c0ae168e2ac6423fc22e5c53b5afe9cd2a546fa9508290240454dc5b510159
|
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:fa227bfc5d392392afa2a54851b7dcbf15cf8ba848c20449a4aec2d922256866
|
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:b5287b38cd630aab26ddfbc0b0a2e825c95832185fbe17db2cc7cd867181b6dc
|
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 sha256:4494aa87bcf898f5c06998891d4aee323c55900b54a38390c1b9b9b9777cc078
|
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 sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
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": 99.282,
|
565 |
"eval_steps_per_second": 25.813,
|
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": 1,
|
597 |
"trial_name": null,
|
598 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2960330247879028,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.24848578971890045,
|
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": 99.282,
|
565 |
"eval_steps_per_second": 25.813,
|
566 |
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.18884920018636434,
|
570 |
+
"grad_norm": 0.11335062235593796,
|
571 |
+
"learning_rate": 2.3444344707738015e-05,
|
572 |
+
"loss": 1.0473,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.19133405808355336,
|
577 |
+
"grad_norm": 0.12783244252204895,
|
578 |
+
"learning_rate": 2.2400865784401e-05,
|
579 |
+
"loss": 1.1195,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.19381891598074236,
|
584 |
+
"grad_norm": 0.13855738937854767,
|
585 |
+
"learning_rate": 2.1393033535713093e-05,
|
586 |
+
"loss": 1.1235,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.19630377387793135,
|
591 |
+
"grad_norm": 0.15133363008499146,
|
592 |
+
"learning_rate": 2.0421950011441354e-05,
|
593 |
+
"loss": 1.1776,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.19878863177512035,
|
598 |
+
"grad_norm": 0.18603986501693726,
|
599 |
+
"learning_rate": 1.9488677077162295e-05,
|
600 |
+
"loss": 1.1791,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.20127348967230937,
|
605 |
+
"grad_norm": 0.21596981585025787,
|
606 |
+
"learning_rate": 1.8594235253127375e-05,
|
607 |
+
"loss": 1.2859,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.20375834756949837,
|
612 |
+
"grad_norm": 0.2702946364879608,
|
613 |
+
"learning_rate": 1.77396025983391e-05,
|
614 |
+
"loss": 1.2849,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.20624320546668737,
|
619 |
+
"grad_norm": 0.3620724081993103,
|
620 |
+
"learning_rate": 1.6925713641057904e-05,
|
621 |
+
"loss": 1.4361,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.20872806336387636,
|
626 |
+
"grad_norm": 0.4550435543060303,
|
627 |
+
"learning_rate": 1.6153458356909176e-05,
|
628 |
+
"loss": 1.4325,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.2112129212610654,
|
633 |
+
"grad_norm": 0.5483496785163879,
|
634 |
+
"learning_rate": 1.5423681195707997e-05,
|
635 |
+
"loss": 1.3811,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.2136977791582544,
|
640 |
+
"grad_norm": 0.6991003155708313,
|
641 |
+
"learning_rate": 1.4737180158065644e-05,
|
642 |
+
"loss": 1.5162,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.21618263705544338,
|
647 |
+
"grad_norm": 1.0953775644302368,
|
648 |
+
"learning_rate": 1.4094705922787687e-05,
|
649 |
+
"loss": 1.8928,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.2186674949526324,
|
654 |
+
"grad_norm": 0.15279479324817657,
|
655 |
+
"learning_rate": 1.3496961026017687e-05,
|
656 |
+
"loss": 1.0786,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.2211523528498214,
|
661 |
+
"grad_norm": 0.12590041756629944,
|
662 |
+
"learning_rate": 1.2944599093024267e-05,
|
663 |
+
"loss": 1.0753,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.2236372107470104,
|
668 |
+
"grad_norm": 0.1294841170310974,
|
669 |
+
"learning_rate": 1.2438224123471442e-05,
|
670 |
+
"loss": 1.0813,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.2261220686441994,
|
675 |
+
"grad_norm": 0.14613628387451172,
|
676 |
+
"learning_rate": 1.1978389830953907e-05,
|
677 |
+
"loss": 1.1588,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.22860692654138842,
|
682 |
+
"grad_norm": 0.1669425517320633,
|
683 |
+
"learning_rate": 1.1565599037519316e-05,
|
684 |
+
"loss": 1.1472,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.23109178443857742,
|
689 |
+
"grad_norm": 0.19589902460575104,
|
690 |
+
"learning_rate": 1.1200303123839742e-05,
|
691 |
+
"loss": 1.2183,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.23357664233576642,
|
696 |
+
"grad_norm": 0.22734500467777252,
|
697 |
+
"learning_rate": 1.088290153563358e-05,
|
698 |
+
"loss": 1.3172,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.23606150023295544,
|
703 |
+
"grad_norm": 0.28079426288604736,
|
704 |
+
"learning_rate": 1.0613741346877497e-05,
|
705 |
+
"loss": 1.3149,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.23854635813014444,
|
710 |
+
"grad_norm": 0.3643316328525543,
|
711 |
+
"learning_rate": 1.0393116880286118e-05,
|
712 |
+
"loss": 1.4268,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.24103121602733343,
|
717 |
+
"grad_norm": 0.4831791818141937,
|
718 |
+
"learning_rate": 1.0221269385474488e-05,
|
719 |
+
"loss": 1.3909,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.24351607392452243,
|
724 |
+
"grad_norm": 0.6105121970176697,
|
725 |
+
"learning_rate": 1.0098386775155147e-05,
|
726 |
+
"loss": 1.5759,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.24600093182171145,
|
731 |
+
"grad_norm": 0.7750763297080994,
|
732 |
+
"learning_rate": 1.0024603419658329e-05,
|
733 |
+
"loss": 1.5506,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.24848578971890045,
|
738 |
+
"grad_norm": 1.7883683443069458,
|
739 |
+
"learning_rate": 1e-05,
|
740 |
+
"loss": 2.0048,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.24848578971890045,
|
745 |
+
"eval_loss": 1.2960330247879028,
|
746 |
+
"eval_runtime": 0.5034,
|
747 |
+
"eval_samples_per_second": 99.318,
|
748 |
+
"eval_steps_per_second": 25.823,
|
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": 1.666832784162816e+17,
|
779 |
"train_batch_size": 1,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|