Training in progress, step 1800, 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 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b109faeebfa0c0ba61658697fa9237074126c445642641b79158eb7ba30739
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc9233433683d3c753053a718e86d2d4fe0a922bf031d40e5d28f0e2784fb198
|
3 |
size 1925064044
|
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:be7e79fe3343879b02c09de94643d5ac71cd5dcd0d985d78489ded30fcafb6d1
|
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 sha256:095de9bddf48720b0136a232ba94acee339b784d05fa46f4489ae091d1c97a55
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
-
"epoch": 3.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -535,6 +535,72 @@
|
|
535 |
"eval_steps_per_second": 0.11,
|
536 |
"eval_wer": 166.51414309484193,
|
537 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
538 |
}
|
539 |
],
|
540 |
"logging_steps": 25,
|
@@ -542,7 +608,7 @@
|
|
542 |
"num_input_tokens_seen": 0,
|
543 |
"num_train_epochs": 8,
|
544 |
"save_steps": 100,
|
545 |
-
"total_flos": 1.
|
546 |
"trial_name": null,
|
547 |
"trial_params": null
|
548 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 3.435114503816794,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
535 |
"eval_steps_per_second": 0.11,
|
536 |
"eval_wer": 166.51414309484193,
|
537 |
"step": 1600
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 3.1,
|
541 |
+
"learning_rate": 6.8028571428571434e-06,
|
542 |
+
"loss": 0.0353,
|
543 |
+
"step": 1625
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 3.15,
|
547 |
+
"learning_rate": 6.7314285714285724e-06,
|
548 |
+
"loss": 0.0366,
|
549 |
+
"step": 1650
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 3.2,
|
553 |
+
"learning_rate": 6.660000000000001e-06,
|
554 |
+
"loss": 0.034,
|
555 |
+
"step": 1675
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 3.24,
|
559 |
+
"learning_rate": 6.588571428571429e-06,
|
560 |
+
"loss": 0.0324,
|
561 |
+
"step": 1700
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 3.24,
|
565 |
+
"eval_loss": 0.3962928354740143,
|
566 |
+
"eval_runtime": 1676.3692,
|
567 |
+
"eval_samples_per_second": 0.895,
|
568 |
+
"eval_steps_per_second": 0.112,
|
569 |
+
"eval_wer": 170.93039378813089,
|
570 |
+
"step": 1700
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 3.29,
|
574 |
+
"learning_rate": 6.517142857142858e-06,
|
575 |
+
"loss": 0.0332,
|
576 |
+
"step": 1725
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 3.34,
|
580 |
+
"learning_rate": 6.445714285714286e-06,
|
581 |
+
"loss": 0.0342,
|
582 |
+
"step": 1750
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 3.39,
|
586 |
+
"learning_rate": 6.374285714285715e-06,
|
587 |
+
"loss": 0.0353,
|
588 |
+
"step": 1775
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 3.44,
|
592 |
+
"learning_rate": 6.302857142857144e-06,
|
593 |
+
"loss": 0.0348,
|
594 |
+
"step": 1800
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 3.44,
|
598 |
+
"eval_loss": 0.40044304728507996,
|
599 |
+
"eval_runtime": 1648.6224,
|
600 |
+
"eval_samples_per_second": 0.91,
|
601 |
+
"eval_steps_per_second": 0.114,
|
602 |
+
"eval_wer": 163.39434276206325,
|
603 |
+
"step": 1800
|
604 |
}
|
605 |
],
|
606 |
"logging_steps": 25,
|
|
|
608 |
"num_input_tokens_seen": 0,
|
609 |
"num_train_epochs": 8,
|
610 |
"save_steps": 100,
|
611 |
+
"total_flos": 1.661645876502528e+19,
|
612 |
"trial_name": null,
|
613 |
"trial_params": null
|
614 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56b1eae5bcb377ffc0d4c8ff2741201cd456f48425776cda068ae6f4f3917a46
|
3 |
size 4856
|