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 sha256:0c80cda446853085128592ecba539d6c68d6b0ad92f60de753ab0f68a44330e7
|
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 sha256:80cd97638784869088cc698d7778dce85dc5cb4686fd5e8bf90cedfc7849a7bf
|
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:d21a9ba0e8e620bc7c4b0103ff676969c00bc4869f3f878cafe019f7db4fe00c
|
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 sha256:17aec51f080c21d526f91c05c94b07bf25af41368aa4c84d6f7ad6356f598c23
|
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:e0093bf299349b49047cdebfcba8383ad8db1ffad4fe76031c8db99f4d70dccc
|
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 sha256:6bd2a91fa18437ac891368dcdc208083c6650384c20992659d701885f986281f
|
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":
|
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": 99.195,
|
565 |
"eval_steps_per_second": 25.791,
|
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": 1.0146315097808838,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 1.262044653349001,
|
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": 99.195,
|
565 |
"eval_steps_per_second": 25.791,
|
566 |
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.9526047786917352,
|
570 |
+
"grad_norm": 0.4782760441303253,
|
571 |
+
"learning_rate": 2.3444344707738015e-05,
|
572 |
+
"loss": 1.4443,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.9651390520955738,
|
577 |
+
"grad_norm": 0.17578525841236115,
|
578 |
+
"learning_rate": 2.2400865784401e-05,
|
579 |
+
"loss": 1.0353,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.9776733254994124,
|
584 |
+
"grad_norm": 0.19925934076309204,
|
585 |
+
"learning_rate": 2.1393033535713093e-05,
|
586 |
+
"loss": 0.9825,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.990207598903251,
|
591 |
+
"grad_norm": 0.321463018655777,
|
592 |
+
"learning_rate": 2.0421950011441354e-05,
|
593 |
+
"loss": 1.1059,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 1.0113591852722288,
|
598 |
+
"grad_norm": 1.0701099634170532,
|
599 |
+
"learning_rate": 1.9488677077162295e-05,
|
600 |
+
"loss": 2.3199,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 1.0238934586760673,
|
605 |
+
"grad_norm": 0.20064501464366913,
|
606 |
+
"learning_rate": 1.8594235253127375e-05,
|
607 |
+
"loss": 1.193,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 1.036427732079906,
|
612 |
+
"grad_norm": 0.16497324407100677,
|
613 |
+
"learning_rate": 1.77396025983391e-05,
|
614 |
+
"loss": 1.0823,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 1.0489620054837445,
|
619 |
+
"grad_norm": 0.1805717796087265,
|
620 |
+
"learning_rate": 1.6925713641057904e-05,
|
621 |
+
"loss": 1.0458,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.0614962788875832,
|
626 |
+
"grad_norm": 0.17193178832530975,
|
627 |
+
"learning_rate": 1.6153458356909176e-05,
|
628 |
+
"loss": 0.9725,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 1.074030552291422,
|
633 |
+
"grad_norm": 0.18326754868030548,
|
634 |
+
"learning_rate": 1.5423681195707997e-05,
|
635 |
+
"loss": 0.9722,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 1.0865648256952605,
|
640 |
+
"grad_norm": 0.20325006544589996,
|
641 |
+
"learning_rate": 1.4737180158065644e-05,
|
642 |
+
"loss": 0.9446,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 1.0990990990990992,
|
647 |
+
"grad_norm": 0.23397134244441986,
|
648 |
+
"learning_rate": 1.4094705922787687e-05,
|
649 |
+
"loss": 0.9672,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 1.1116333725029377,
|
654 |
+
"grad_norm": 0.2701351046562195,
|
655 |
+
"learning_rate": 1.3496961026017687e-05,
|
656 |
+
"loss": 1.0053,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 1.1241676459067764,
|
661 |
+
"grad_norm": 0.3563973307609558,
|
662 |
+
"learning_rate": 1.2944599093024267e-05,
|
663 |
+
"loss": 1.1253,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 1.136701919310615,
|
668 |
+
"grad_norm": 0.3762572705745697,
|
669 |
+
"learning_rate": 1.2438224123471442e-05,
|
670 |
+
"loss": 1.1212,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 1.1492361927144537,
|
675 |
+
"grad_norm": 0.4805110991001129,
|
676 |
+
"learning_rate": 1.1978389830953907e-05,
|
677 |
+
"loss": 1.1656,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 1.1617704661182922,
|
682 |
+
"grad_norm": 0.9201070070266724,
|
683 |
+
"learning_rate": 1.1565599037519316e-05,
|
684 |
+
"loss": 1.5552,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 1.1743047395221309,
|
689 |
+
"grad_norm": 0.24048174917697906,
|
690 |
+
"learning_rate": 1.1200303123839742e-05,
|
691 |
+
"loss": 1.2953,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 1.1868390129259694,
|
696 |
+
"grad_norm": 0.159620463848114,
|
697 |
+
"learning_rate": 1.088290153563358e-05,
|
698 |
+
"loss": 1.1379,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 1.199373286329808,
|
703 |
+
"grad_norm": 0.17821361124515533,
|
704 |
+
"learning_rate": 1.0613741346877497e-05,
|
705 |
+
"loss": 1.0653,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 1.2119075597336466,
|
710 |
+
"grad_norm": 0.18576368689537048,
|
711 |
+
"learning_rate": 1.0393116880286118e-05,
|
712 |
+
"loss": 0.9979,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 1.2244418331374853,
|
717 |
+
"grad_norm": 0.17474296689033508,
|
718 |
+
"learning_rate": 1.0221269385474488e-05,
|
719 |
+
"loss": 0.95,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 1.2369761065413238,
|
724 |
+
"grad_norm": 0.18885326385498047,
|
725 |
+
"learning_rate": 1.0098386775155147e-05,
|
726 |
+
"loss": 0.9432,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 1.2495103799451626,
|
731 |
+
"grad_norm": 0.21814164519309998,
|
732 |
+
"learning_rate": 1.0024603419658329e-05,
|
733 |
+
"loss": 0.9849,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.262044653349001,
|
738 |
+
"grad_norm": 0.2603691816329956,
|
739 |
+
"learning_rate": 1e-05,
|
740 |
+
"loss": 1.0749,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 1.262044653349001,
|
745 |
+
"eval_loss": 1.0146315097808838,
|
746 |
+
"eval_runtime": 0.5028,
|
747 |
+
"eval_samples_per_second": 99.449,
|
748 |
+
"eval_steps_per_second": 25.857,
|
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": 1.6898819529847603e+17,
|
779 |
"train_batch_size": 1,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|