mikhail-panzo
commited on
Commit
•
571a540
1
Parent(s):
de53b7c
Training in progress, step 4000, 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:d18172f59d8cdf13648e208a2c9ed68e2c35f57395062ef667619c24cf24b102
|
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:af71716effd1caa22736d3a7d131f24e94f7344597d19702a29f27b880db0d3d
|
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 sha256:6b7465f2e8b9bae857f76ec186b635aab5838dc4b5b3ef7b6cfb473e08afcb86
|
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 sha256:0bd01f1a543bd9ecb58737837f10f865ac053c6c89fa1a7cdbd04da0c2caf558
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.41326722502708435,
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_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,
|
@@ -553,6 +553,84 @@
|
|
553 |
"eval_samples_per_second": 24.518,
|
554 |
"eval_steps_per_second": 3.084,
|
555 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 50,
|
@@ -572,7 +650,7 @@
|
|
572 |
"attributes": {}
|
573 |
}
|
574 |
},
|
575 |
-
"total_flos": 5.
|
576 |
"train_batch_size": 64,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.41326722502708435,
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-3500",
|
4 |
+
"epoch": 173.91304347826087,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 4000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
553 |
"eval_samples_per_second": 24.518,
|
554 |
"eval_steps_per_second": 3.084,
|
555 |
"step": 3500
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 154.34782608695653,
|
559 |
+
"grad_norm": 2.30401611328125,
|
560 |
+
"learning_rate": 7.421666666666667e-06,
|
561 |
+
"loss": 0.4248,
|
562 |
+
"step": 3550
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 156.52173913043478,
|
566 |
+
"grad_norm": 0.9738525152206421,
|
567 |
+
"learning_rate": 7.338333333333334e-06,
|
568 |
+
"loss": 0.4354,
|
569 |
+
"step": 3600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 158.69565217391303,
|
573 |
+
"grad_norm": 2.276857376098633,
|
574 |
+
"learning_rate": 7.255000000000001e-06,
|
575 |
+
"loss": 0.4345,
|
576 |
+
"step": 3650
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 160.8695652173913,
|
580 |
+
"grad_norm": 1.118604063987732,
|
581 |
+
"learning_rate": 7.171666666666667e-06,
|
582 |
+
"loss": 0.4243,
|
583 |
+
"step": 3700
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 163.04347826086956,
|
587 |
+
"grad_norm": 1.1995043754577637,
|
588 |
+
"learning_rate": 7.088333333333334e-06,
|
589 |
+
"loss": 0.4229,
|
590 |
+
"step": 3750
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 165.2173913043478,
|
594 |
+
"grad_norm": 1.1676712036132812,
|
595 |
+
"learning_rate": 7.005000000000001e-06,
|
596 |
+
"loss": 0.4225,
|
597 |
+
"step": 3800
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 167.3913043478261,
|
601 |
+
"grad_norm": 1.7886515855789185,
|
602 |
+
"learning_rate": 6.921666666666668e-06,
|
603 |
+
"loss": 0.4243,
|
604 |
+
"step": 3850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 169.56521739130434,
|
608 |
+
"grad_norm": 1.0336685180664062,
|
609 |
+
"learning_rate": 6.838333333333334e-06,
|
610 |
+
"loss": 0.4288,
|
611 |
+
"step": 3900
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 171.7391304347826,
|
615 |
+
"grad_norm": 3.572209596633911,
|
616 |
+
"learning_rate": 6.7550000000000005e-06,
|
617 |
+
"loss": 0.4262,
|
618 |
+
"step": 3950
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 173.91304347826087,
|
622 |
+
"grad_norm": 3.631232261657715,
|
623 |
+
"learning_rate": 6.6716666666666674e-06,
|
624 |
+
"loss": 0.4264,
|
625 |
+
"step": 4000
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 173.91304347826087,
|
629 |
+
"eval_loss": 0.4149872660636902,
|
630 |
+
"eval_runtime": 6.8222,
|
631 |
+
"eval_samples_per_second": 23.306,
|
632 |
+
"eval_steps_per_second": 2.932,
|
633 |
+
"step": 4000
|
634 |
}
|
635 |
],
|
636 |
"logging_steps": 50,
|
|
|
650 |
"attributes": {}
|
651 |
}
|
652 |
},
|
653 |
+
"total_flos": 5.937591783240058e+16,
|
654 |
"train_batch_size": 64,
|
655 |
"trial_name": null,
|
656 |
"trial_params": null
|