mikhail-panzo
commited on
Commit
•
0ca5d1f
1
Parent(s):
f85cfcf
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 sha256:1299d4f1af262ec6ea8954bf3eef8f3fc7544a0e714353dfeaebf4bf62fa1ace
|
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:f48ab820dba57bfcef1153ac7b583dafe37425f3a6758334d4f47dd0d2e1470b
|
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 sha256:830fc52a0124fdca52368150d3b42c759356c29ec8af3826289864102f89fc8d
|
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:b861104f137d1fe8ca8f0827472a7b8a3a6723f1ff99340210bc3ae74cc04899
|
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_b32_le5_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": 24.833,
|
554 |
"eval_steps_per_second": 3.173,
|
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": 0.3955015242099762,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/ceb_b32_le5_s4000/checkpoint-4000",
|
4 |
+
"epoch": 79.20792079207921,
|
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": 24.833,
|
554 |
"eval_steps_per_second": 3.173,
|
555 |
"step": 3500
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 70.29702970297029,
|
559 |
+
"grad_norm": 1.282522439956665,
|
560 |
+
"learning_rate": 2.2550000000000004e-06,
|
561 |
+
"loss": 0.4161,
|
562 |
+
"step": 3550
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 71.2871287128713,
|
566 |
+
"grad_norm": 1.1820783615112305,
|
567 |
+
"learning_rate": 2.0050000000000003e-06,
|
568 |
+
"loss": 0.4195,
|
569 |
+
"step": 3600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 72.27722772277228,
|
573 |
+
"grad_norm": 0.9852460622787476,
|
574 |
+
"learning_rate": 1.7550000000000001e-06,
|
575 |
+
"loss": 0.4242,
|
576 |
+
"step": 3650
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 73.26732673267327,
|
580 |
+
"grad_norm": 1.0779832601547241,
|
581 |
+
"learning_rate": 1.505e-06,
|
582 |
+
"loss": 0.4216,
|
583 |
+
"step": 3700
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 74.25742574257426,
|
587 |
+
"grad_norm": 0.9809712171554565,
|
588 |
+
"learning_rate": 1.255e-06,
|
589 |
+
"loss": 0.4187,
|
590 |
+
"step": 3750
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 75.24752475247524,
|
594 |
+
"grad_norm": 1.067606806755066,
|
595 |
+
"learning_rate": 1.0050000000000001e-06,
|
596 |
+
"loss": 0.4295,
|
597 |
+
"step": 3800
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 76.23762376237623,
|
601 |
+
"grad_norm": 1.027479887008667,
|
602 |
+
"learning_rate": 7.550000000000001e-07,
|
603 |
+
"loss": 0.4257,
|
604 |
+
"step": 3850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 77.22772277227723,
|
608 |
+
"grad_norm": 1.2920273542404175,
|
609 |
+
"learning_rate": 5.05e-07,
|
610 |
+
"loss": 0.4236,
|
611 |
+
"step": 3900
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 78.21782178217822,
|
615 |
+
"grad_norm": 1.445709466934204,
|
616 |
+
"learning_rate": 2.55e-07,
|
617 |
+
"loss": 0.4216,
|
618 |
+
"step": 3950
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 79.20792079207921,
|
622 |
+
"grad_norm": 1.045529842376709,
|
623 |
+
"learning_rate": 5e-09,
|
624 |
+
"loss": 0.4241,
|
625 |
+
"step": 4000
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 79.20792079207921,
|
629 |
+
"eval_loss": 0.3955015242099762,
|
630 |
+
"eval_runtime": 7.4685,
|
631 |
+
"eval_samples_per_second": 24.101,
|
632 |
+
"eval_steps_per_second": 3.08,
|
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": 2.161155031107257e+16,
|
654 |
"train_batch_size": 16,
|
655 |
"trial_name": null,
|
656 |
"trial_params": null
|