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 119801528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74fb4e2e79b702d18ecb0e3054321969c42e7ac05c86d1da5c3c99b7dedd72e7
|
3 |
size 119801528
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 239892858
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d9259ee1eb332efcb740768297dfad88170ed976ed41351684e1172f45fee50
|
3 |
size 239892858
|
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 sha256:86b7c41bffe49f31b8c2127a738b5a2e1ce2673c7fc76505c48f33a9224a1a4b
|
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": 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": 4.94,
|
565 |
"eval_steps_per_second": 2.47,
|
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": 1.62236487865448,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.0017317741593318816,
|
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": 4.94,
|
565 |
"eval_steps_per_second": 2.47,
|
566 |
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.00131614836109223,
|
570 |
+
"grad_norm": 2.4752883911132812,
|
571 |
+
"learning_rate": 2.9876321572751144e-05,
|
572 |
+
"loss": 2.0203,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.0013334661026855488,
|
577 |
+
"grad_norm": 2.1483538150787354,
|
578 |
+
"learning_rate": 2.7557479520891104e-05,
|
579 |
+
"loss": 1.5806,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.0013507838442788677,
|
584 |
+
"grad_norm": 1.9293116331100464,
|
585 |
+
"learning_rate": 2.5317852301584643e-05,
|
586 |
+
"loss": 2.0804,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.0013681015858721863,
|
591 |
+
"grad_norm": 1.519399881362915,
|
592 |
+
"learning_rate": 2.315988891431412e-05,
|
593 |
+
"loss": 1.4393,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.0013854193274655052,
|
598 |
+
"grad_norm": 1.9969561100006104,
|
599 |
+
"learning_rate": 2.1085949060360654e-05,
|
600 |
+
"loss": 1.5912,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.001402737069058824,
|
605 |
+
"grad_norm": 1.9334006309509277,
|
606 |
+
"learning_rate": 1.9098300562505266e-05,
|
607 |
+
"loss": 1.5095,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.0014200548106521429,
|
612 |
+
"grad_norm": 1.8917192220687866,
|
613 |
+
"learning_rate": 1.7199116885197995e-05,
|
614 |
+
"loss": 1.8712,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.0014373725522454617,
|
619 |
+
"grad_norm": 1.6807430982589722,
|
620 |
+
"learning_rate": 1.5390474757906446e-05,
|
621 |
+
"loss": 1.6938,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.0014546902938387806,
|
626 |
+
"grad_norm": 1.641627550125122,
|
627 |
+
"learning_rate": 1.3674351904242611e-05,
|
628 |
+
"loss": 1.5532,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.0014720080354320992,
|
633 |
+
"grad_norm": 2.6051013469696045,
|
634 |
+
"learning_rate": 1.2052624879351104e-05,
|
635 |
+
"loss": 1.8125,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.001489325777025418,
|
640 |
+
"grad_norm": 1.6829463243484497,
|
641 |
+
"learning_rate": 1.0527067017923654e-05,
|
642 |
+
"loss": 1.5045,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.001506643518618737,
|
647 |
+
"grad_norm": 1.6704628467559814,
|
648 |
+
"learning_rate": 9.09934649508375e-06,
|
649 |
+
"loss": 1.5594,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.0015239612602120558,
|
654 |
+
"grad_norm": 2.3541147708892822,
|
655 |
+
"learning_rate": 7.771024502261526e-06,
|
656 |
+
"loss": 2.2284,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.0015412790018053746,
|
661 |
+
"grad_norm": 2.744718074798584,
|
662 |
+
"learning_rate": 6.543553540053926e-06,
|
663 |
+
"loss": 1.2474,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.0015585967433986933,
|
668 |
+
"grad_norm": 2.3282785415649414,
|
669 |
+
"learning_rate": 5.418275829936537e-06,
|
670 |
+
"loss": 1.9081,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.0015759144849920121,
|
675 |
+
"grad_norm": 1.7221317291259766,
|
676 |
+
"learning_rate": 4.3964218465642355e-06,
|
677 |
+
"loss": 1.5467,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.001593232226585331,
|
682 |
+
"grad_norm": 2.2455320358276367,
|
683 |
+
"learning_rate": 3.4791089722651436e-06,
|
684 |
+
"loss": 1.8693,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.0016105499681786498,
|
689 |
+
"grad_norm": 1.896304726600647,
|
690 |
+
"learning_rate": 2.667340275199426e-06,
|
691 |
+
"loss": 1.3848,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.0016278677097719687,
|
696 |
+
"grad_norm": 2.8605098724365234,
|
697 |
+
"learning_rate": 1.9620034125190644e-06,
|
698 |
+
"loss": 1.6698,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.0016451854513652876,
|
703 |
+
"grad_norm": 1.6910480260849,
|
704 |
+
"learning_rate": 1.3638696597277679e-06,
|
705 |
+
"loss": 1.4249,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.0016625031929586062,
|
710 |
+
"grad_norm": 3.1670644283294678,
|
711 |
+
"learning_rate": 8.735930673024806e-07,
|
712 |
+
"loss": 1.7864,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.001679820934551925,
|
717 |
+
"grad_norm": 2.209742784500122,
|
718 |
+
"learning_rate": 4.917097454988584e-07,
|
719 |
+
"loss": 1.7708,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.001697138676145244,
|
724 |
+
"grad_norm": 2.015029191970825,
|
725 |
+
"learning_rate": 2.1863727812254653e-07,
|
726 |
+
"loss": 1.471,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.0017144564177385628,
|
731 |
+
"grad_norm": 2.405651569366455,
|
732 |
+
"learning_rate": 5.467426590739511e-08,
|
733 |
+
"loss": 1.6094,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.0017317741593318816,
|
738 |
+
"grad_norm": 4.6894025802612305,
|
739 |
+
"learning_rate": 0.0,
|
740 |
+
"loss": 2.0444,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.0017317741593318816,
|
745 |
+
"eval_loss": 1.62236487865448,
|
746 |
+
"eval_runtime": 4922.5195,
|
747 |
+
"eval_samples_per_second": 4.939,
|
748 |
+
"eval_steps_per_second": 2.47,
|
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": 5.51427898343424e+16,
|
779 |
"train_batch_size": 2,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|