Training in progress, step 90000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +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 +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893439185
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:134d6d1a136e6964ae2ed697436824732ef4204be572a5639879cde01c496fb4
|
3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f633f40ddd88931a1bcbba40dbb7908be8ffc1f11ca88c044ce2b036b207de26
|
3 |
size 449471589
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5672e7460ec4bb20926333b87c1de2eb753f75f0449ae9dd507ee1cf812c0bce
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cefa1feb46fb134136cae0514a9b4d7f5ee7c548f72ebedcd52cca0c9d5a1399
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:811c50c92fcf0d94c6c776ed6e8ceff3da691c7f85fb718fb2430787c3ac61c5
|
3 |
size 14503
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bbf02a4081ed4b267df817f2c1eebe3e21fb0c27efa334683d9878792c81135
|
3 |
+
size 14503
|
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:fbbaa3fc76ce5e36303621f0b3c2a3411cdf79310693a1e151a2d13a1eef02ee
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -598,11 +598,85 @@
|
|
598 |
"eval_samples_per_second": 922.521,
|
599 |
"eval_steps_per_second": 14.76,
|
600 |
"step": 80000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
601 |
}
|
602 |
],
|
603 |
"max_steps": 1000000,
|
604 |
"num_train_epochs": 16,
|
605 |
-
"total_flos":
|
606 |
"trial_name": null,
|
607 |
"trial_params": null
|
608 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.3743185670438407,
|
5 |
+
"global_step": 90000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
598 |
"eval_samples_per_second": 922.521,
|
599 |
"eval_steps_per_second": 14.76,
|
600 |
"step": 80000
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 1.24,
|
604 |
+
"learning_rate": 0.00014963249471630944,
|
605 |
+
"loss": 0.3906,
|
606 |
+
"step": 81000
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 1.25,
|
610 |
+
"learning_rate": 0.000149608424764662,
|
611 |
+
"loss": 0.391,
|
612 |
+
"step": 82000
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.27,
|
616 |
+
"learning_rate": 0.0001495835935864336,
|
617 |
+
"loss": 0.3875,
|
618 |
+
"step": 83000
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 1.28,
|
622 |
+
"learning_rate": 0.00014955800145317397,
|
623 |
+
"loss": 0.3861,
|
624 |
+
"step": 84000
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 1.3,
|
628 |
+
"learning_rate": 0.00014953164864475466,
|
629 |
+
"loss": 0.3844,
|
630 |
+
"step": 85000
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 1.3,
|
634 |
+
"eval_runtime": 1.0992,
|
635 |
+
"eval_samples_per_second": 909.734,
|
636 |
+
"eval_steps_per_second": 14.556,
|
637 |
+
"step": 85000
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 1.31,
|
641 |
+
"learning_rate": 0.0001495045354493657,
|
642 |
+
"loss": 0.3829,
|
643 |
+
"step": 86000
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 1.33,
|
647 |
+
"learning_rate": 0.00014947666216351272,
|
648 |
+
"loss": 0.3815,
|
649 |
+
"step": 87000
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 1.34,
|
653 |
+
"learning_rate": 0.00014944802909201344,
|
654 |
+
"loss": 0.38,
|
655 |
+
"step": 88000
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 1.36,
|
659 |
+
"learning_rate": 0.00014941863654799456,
|
660 |
+
"loss": 0.3789,
|
661 |
+
"step": 89000
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 1.37,
|
665 |
+
"learning_rate": 0.00014938848485288825,
|
666 |
+
"loss": 0.3785,
|
667 |
+
"step": 90000
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 1.37,
|
671 |
+
"eval_runtime": 0.9266,
|
672 |
+
"eval_samples_per_second": 1079.167,
|
673 |
+
"eval_steps_per_second": 17.267,
|
674 |
+
"step": 90000
|
675 |
}
|
676 |
],
|
677 |
"max_steps": 1000000,
|
678 |
"num_train_epochs": 16,
|
679 |
+
"total_flos": 6.309016922049755e+21,
|
680 |
"trial_name": null,
|
681 |
"trial_params": null
|
682 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f633f40ddd88931a1bcbba40dbb7908be8ffc1f11ca88c044ce2b036b207de26
|
3 |
size 449471589
|