mikhail-panzo
commited on
Commit
•
b5fe9f9
1
Parent(s):
ecc0750
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:e35f938dafa0b75d8c4ca77c92d79b765fb12686375a263279c54f290b522762
|
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:c4183e38736eff413cb2a7512c613a0d10aa6b21b48c377cdbc1311e4972fd76
|
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 sha256:546eb67e9ac703715999e4a48906215e9d1d8502c3d871bfb0192cba37d95e1c
|
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 sha256:4bfcce18e5763d964c4f2e7d8e731979c9aad30909fed83aa5130e2b917f0579
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s4000/checkpoint-
|
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": 24.652,
|
554 |
"eval_steps_per_second": 3.15,
|
555 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 50,
|
@@ -567,12 +645,12 @@
|
|
567 |
"should_evaluate": false,
|
568 |
"should_log": false,
|
569 |
"should_save": true,
|
570 |
-
"should_training_stop":
|
571 |
},
|
572 |
"attributes": {}
|
573 |
}
|
574 |
},
|
575 |
-
"total_flos":
|
576 |
"train_batch_size": 16,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3941996693611145,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s4000/checkpoint-4000",
|
4 |
+
"epoch": 158.41584158415841,
|
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": 24.652,
|
554 |
"eval_steps_per_second": 3.15,
|
555 |
"step": 3500
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 140.59405940594058,
|
559 |
+
"grad_norm": 0.9707288146018982,
|
560 |
+
"learning_rate": 2.2550000000000003e-05,
|
561 |
+
"loss": 0.3643,
|
562 |
+
"step": 3550
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 142.5742574257426,
|
566 |
+
"grad_norm": 0.7684584856033325,
|
567 |
+
"learning_rate": 2.0050000000000003e-05,
|
568 |
+
"loss": 0.3597,
|
569 |
+
"step": 3600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 144.55445544554456,
|
573 |
+
"grad_norm": 0.759428083896637,
|
574 |
+
"learning_rate": 1.755e-05,
|
575 |
+
"loss": 0.3576,
|
576 |
+
"step": 3650
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 146.53465346534654,
|
580 |
+
"grad_norm": 0.6662328839302063,
|
581 |
+
"learning_rate": 1.505e-05,
|
582 |
+
"loss": 0.3559,
|
583 |
+
"step": 3700
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 148.5148514851485,
|
587 |
+
"grad_norm": 0.5537445545196533,
|
588 |
+
"learning_rate": 1.255e-05,
|
589 |
+
"loss": 0.3563,
|
590 |
+
"step": 3750
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 150.4950495049505,
|
594 |
+
"grad_norm": 0.5476033687591553,
|
595 |
+
"learning_rate": 1.005e-05,
|
596 |
+
"loss": 0.3562,
|
597 |
+
"step": 3800
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 152.47524752475246,
|
601 |
+
"grad_norm": 1.056248426437378,
|
602 |
+
"learning_rate": 7.55e-06,
|
603 |
+
"loss": 0.3516,
|
604 |
+
"step": 3850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 154.45544554455446,
|
608 |
+
"grad_norm": 0.556987464427948,
|
609 |
+
"learning_rate": 5.050000000000001e-06,
|
610 |
+
"loss": 0.3575,
|
611 |
+
"step": 3900
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 156.43564356435644,
|
615 |
+
"grad_norm": 0.5589704513549805,
|
616 |
+
"learning_rate": 2.55e-06,
|
617 |
+
"loss": 0.3613,
|
618 |
+
"step": 3950
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 158.41584158415841,
|
622 |
+
"grad_norm": 0.6661315560340881,
|
623 |
+
"learning_rate": 5.0000000000000004e-08,
|
624 |
+
"loss": 0.3533,
|
625 |
+
"step": 4000
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 158.41584158415841,
|
629 |
+
"eval_loss": 0.3941996693611145,
|
630 |
+
"eval_runtime": 7.5266,
|
631 |
+
"eval_samples_per_second": 23.915,
|
632 |
+
"eval_steps_per_second": 3.056,
|
633 |
+
"step": 4000
|
634 |
}
|
635 |
],
|
636 |
"logging_steps": 50,
|
|
|
645 |
"should_evaluate": false,
|
646 |
"should_log": false,
|
647 |
"should_save": true,
|
648 |
+
"should_training_stop": true
|
649 |
},
|
650 |
"attributes": {}
|
651 |
}
|
652 |
},
|
653 |
+
"total_flos": 4.322114324975938e+16,
|
654 |
"train_batch_size": 16,
|
655 |
"trial_name": null,
|
656 |
"trial_params": null
|