mikhail-panzo
commited on
Commit
•
4c802d9
1
Parent(s):
21fbeb8
Training in progress, step 4500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6a0a45b5c73136651ea586a81a22e48be0c01723e388f5ecb20cadf32c2d146
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bfb144672a55867df598f92e30f306392e5627f25e7e988d31605510f3f6276
|
3 |
size 1155772233
|
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 sha256:23cfe734181a7e84ba3feae03eb5140aab76f01a3b8447c97bd8142d5e306dad
|
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 sha256:9becdbdb0c73597ccfbdbc6b4341353e796af8282a1a374bd120ee6357f11761
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.39598318934440613,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-3500",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -631,6 +631,84 @@
|
|
631 |
"eval_samples_per_second": 25.107,
|
632 |
"eval_steps_per_second": 3.208,
|
633 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
634 |
}
|
635 |
],
|
636 |
"logging_steps": 50,
|
@@ -650,7 +728,7 @@
|
|
650 |
"attributes": {}
|
651 |
}
|
652 |
},
|
653 |
-
"total_flos": 4.
|
654 |
"train_batch_size": 16,
|
655 |
"trial_name": null,
|
656 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.39598318934440613,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-3500",
|
4 |
+
"epoch": 178.21782178217822,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 4500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
631 |
"eval_samples_per_second": 25.107,
|
632 |
"eval_steps_per_second": 3.208,
|
633 |
"step": 4000
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 160.3960396039604,
|
637 |
+
"grad_norm": 0.9373750686645508,
|
638 |
+
"learning_rate": 6.585e-05,
|
639 |
+
"loss": 0.3537,
|
640 |
+
"step": 4050
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 162.37623762376236,
|
644 |
+
"grad_norm": 1.3369851112365723,
|
645 |
+
"learning_rate": 6.501666666666667e-05,
|
646 |
+
"loss": 0.3585,
|
647 |
+
"step": 4100
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 164.35643564356437,
|
651 |
+
"grad_norm": 0.6891220211982727,
|
652 |
+
"learning_rate": 6.418333333333334e-05,
|
653 |
+
"loss": 0.3519,
|
654 |
+
"step": 4150
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 166.33663366336634,
|
658 |
+
"grad_norm": 0.8272483944892883,
|
659 |
+
"learning_rate": 6.335e-05,
|
660 |
+
"loss": 0.3542,
|
661 |
+
"step": 4200
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 168.31683168316832,
|
665 |
+
"grad_norm": 0.9853746891021729,
|
666 |
+
"learning_rate": 6.251666666666666e-05,
|
667 |
+
"loss": 0.3553,
|
668 |
+
"step": 4250
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 170.2970297029703,
|
672 |
+
"grad_norm": 1.0020989179611206,
|
673 |
+
"learning_rate": 6.168333333333333e-05,
|
674 |
+
"loss": 0.3558,
|
675 |
+
"step": 4300
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 172.27722772277227,
|
679 |
+
"grad_norm": 1.4780181646347046,
|
680 |
+
"learning_rate": 6.085000000000001e-05,
|
681 |
+
"loss": 0.3505,
|
682 |
+
"step": 4350
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 174.25742574257427,
|
686 |
+
"grad_norm": 0.9966872334480286,
|
687 |
+
"learning_rate": 6.0016666666666664e-05,
|
688 |
+
"loss": 0.3513,
|
689 |
+
"step": 4400
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 176.23762376237624,
|
693 |
+
"grad_norm": 1.2055169343948364,
|
694 |
+
"learning_rate": 5.918333333333333e-05,
|
695 |
+
"loss": 0.3509,
|
696 |
+
"step": 4450
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 178.21782178217822,
|
700 |
+
"grad_norm": 1.075426697731018,
|
701 |
+
"learning_rate": 5.835e-05,
|
702 |
+
"loss": 0.3545,
|
703 |
+
"step": 4500
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 178.21782178217822,
|
707 |
+
"eval_loss": 0.3981594443321228,
|
708 |
+
"eval_runtime": 6.8387,
|
709 |
+
"eval_samples_per_second": 26.321,
|
710 |
+
"eval_steps_per_second": 3.363,
|
711 |
+
"step": 4500
|
712 |
}
|
713 |
],
|
714 |
"logging_steps": 50,
|
|
|
728 |
"attributes": {}
|
729 |
}
|
730 |
},
|
731 |
+
"total_flos": 4.862391888488112e+16,
|
732 |
"train_batch_size": 16,
|
733 |
"trial_name": null,
|
734 |
"trial_params": null
|