Training in progress, step 12500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +153 -3
- pytorch_model.bin +1 -1
- runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1115513717
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57f3c69d772afc58e37ee903b2b7079a268d08467aafd7213c557e89eabc81a1
|
3 |
size 1115513717
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557969145
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87db461c28c81d8c1f329067e24f4856e8aa966760e3915178a00b7c12a98ad9
|
3 |
size 557969145
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15523
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c498e4129e3e140b55c067c9e46781a5ac9ad4114d9a53b3d323278fa7cab1b
|
3 |
size 15523
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9ff76b4edb8bccd8e7ba583674a071e8b77e61693d6d7c7089e776edb889d9d
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -606,11 +606,161 @@
|
|
606 |
"learning_rate": 1.883408071748879e-05,
|
607 |
"loss": 0.6866,
|
608 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
609 |
}
|
610 |
],
|
611 |
"max_steps": 32112,
|
612 |
"num_train_epochs": 2,
|
613 |
-
"total_flos":
|
614 |
"trial_name": null,
|
615 |
"trial_params": null
|
616 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7006726457399103,
|
5 |
+
"global_step": 12500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
606 |
"learning_rate": 1.883408071748879e-05,
|
607 |
"loss": 0.6866,
|
608 |
"step": 10000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.57,
|
612 |
+
"learning_rate": 1.8522670652715494e-05,
|
613 |
+
"loss": 0.7075,
|
614 |
+
"step": 10100
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.57,
|
618 |
+
"learning_rate": 1.82112605879422e-05,
|
619 |
+
"loss": 0.7549,
|
620 |
+
"step": 10200
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.58,
|
624 |
+
"learning_rate": 1.7899850523168908e-05,
|
625 |
+
"loss": 0.7435,
|
626 |
+
"step": 10300
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.58,
|
630 |
+
"learning_rate": 1.7588440458395615e-05,
|
631 |
+
"loss": 0.7484,
|
632 |
+
"step": 10400
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.59,
|
636 |
+
"learning_rate": 1.7277030393622322e-05,
|
637 |
+
"loss": 0.7309,
|
638 |
+
"step": 10500
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.59,
|
642 |
+
"learning_rate": 1.696562032884903e-05,
|
643 |
+
"loss": 0.8038,
|
644 |
+
"step": 10600
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.6,
|
648 |
+
"learning_rate": 1.6654210264075736e-05,
|
649 |
+
"loss": 0.7695,
|
650 |
+
"step": 10700
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.61,
|
654 |
+
"learning_rate": 1.634280019930244e-05,
|
655 |
+
"loss": 0.7406,
|
656 |
+
"step": 10800
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.61,
|
660 |
+
"learning_rate": 1.6031390134529147e-05,
|
661 |
+
"loss": 0.6867,
|
662 |
+
"step": 10900
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.62,
|
666 |
+
"learning_rate": 1.5719980069755854e-05,
|
667 |
+
"loss": 0.6952,
|
668 |
+
"step": 11000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.62,
|
672 |
+
"learning_rate": 1.540857000498256e-05,
|
673 |
+
"loss": 0.6863,
|
674 |
+
"step": 11100
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.63,
|
678 |
+
"learning_rate": 1.5097159940209268e-05,
|
679 |
+
"loss": 0.7765,
|
680 |
+
"step": 11200
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.63,
|
684 |
+
"learning_rate": 1.4785749875435975e-05,
|
685 |
+
"loss": 0.7468,
|
686 |
+
"step": 11300
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.64,
|
690 |
+
"learning_rate": 1.4474339810662682e-05,
|
691 |
+
"loss": 0.8029,
|
692 |
+
"step": 11400
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.64,
|
696 |
+
"learning_rate": 1.4162929745889389e-05,
|
697 |
+
"loss": 0.7224,
|
698 |
+
"step": 11500
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.65,
|
702 |
+
"learning_rate": 1.3851519681116093e-05,
|
703 |
+
"loss": 0.7289,
|
704 |
+
"step": 11600
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.66,
|
708 |
+
"learning_rate": 1.35401096163428e-05,
|
709 |
+
"loss": 0.758,
|
710 |
+
"step": 11700
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.66,
|
714 |
+
"learning_rate": 1.3228699551569507e-05,
|
715 |
+
"loss": 0.7118,
|
716 |
+
"step": 11800
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.67,
|
720 |
+
"learning_rate": 1.2917289486796214e-05,
|
721 |
+
"loss": 0.7478,
|
722 |
+
"step": 11900
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.67,
|
726 |
+
"learning_rate": 1.260587942202292e-05,
|
727 |
+
"loss": 0.7617,
|
728 |
+
"step": 12000
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.68,
|
732 |
+
"learning_rate": 1.2294469357249628e-05,
|
733 |
+
"loss": 0.7288,
|
734 |
+
"step": 12100
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.68,
|
738 |
+
"learning_rate": 1.1983059292476335e-05,
|
739 |
+
"loss": 0.7643,
|
740 |
+
"step": 12200
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.69,
|
744 |
+
"learning_rate": 1.167164922770304e-05,
|
745 |
+
"loss": 0.7059,
|
746 |
+
"step": 12300
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.7,
|
750 |
+
"learning_rate": 1.1360239162929747e-05,
|
751 |
+
"loss": 0.7185,
|
752 |
+
"step": 12400
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.7,
|
756 |
+
"learning_rate": 1.1048829098156454e-05,
|
757 |
+
"loss": 0.6894,
|
758 |
+
"step": 12500
|
759 |
}
|
760 |
],
|
761 |
"max_steps": 32112,
|
762 |
"num_train_epochs": 2,
|
763 |
+
"total_flos": 5.775039312666624e+16,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|
766 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557969145
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87db461c28c81d8c1f329067e24f4856e8aa966760e3915178a00b7c12a98ad9
|
3 |
size 557969145
|
runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eb77c9add49418cf9c6164ece1dbd00292b09e7083152c9df2cb409c236cba4
|
3 |
+
size 29264
|