Training in progress, step 2100, 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:ce5374a700f6cb8856fec0d069890cb1c699a8142cbab7571daa3287a2b3058b
|
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 sha256:10dcd11e2cb1895f7c3e1c68032ca79221ba9837804ddc4c0ad628db4cb3bbbb
|
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:a9f1fe924fb046e82f32a9e9633992150d028a3f688d46144a5a5c7f5cbc6bad
|
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:d6c2e8507c15e11b5d34f126b0dbb02f39afdf32066bd4c386593945bed215e3
|
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":
|
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,
|
@@ -601,6 +601,105 @@
|
|
601 |
"eval_steps_per_second": 0.114,
|
602 |
"eval_wer": 163.39434276206325,
|
603 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
604 |
}
|
605 |
],
|
606 |
"logging_steps": 25,
|
@@ -608,7 +707,7 @@
|
|
608 |
"num_input_tokens_seen": 0,
|
609 |
"num_train_epochs": 8,
|
610 |
"save_steps": 100,
|
611 |
-
"total_flos": 1.
|
612 |
"trial_name": null,
|
613 |
"trial_params": null
|
614 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 4.00763358778626,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
601 |
"eval_steps_per_second": 0.114,
|
602 |
"eval_wer": 163.39434276206325,
|
603 |
"step": 1800
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 3.48,
|
607 |
+
"learning_rate": 6.231428571428571e-06,
|
608 |
+
"loss": 0.0348,
|
609 |
+
"step": 1825
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 3.53,
|
613 |
+
"learning_rate": 6.16e-06,
|
614 |
+
"loss": 0.0336,
|
615 |
+
"step": 1850
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 3.58,
|
619 |
+
"learning_rate": 6.088571428571429e-06,
|
620 |
+
"loss": 0.0347,
|
621 |
+
"step": 1875
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 3.63,
|
625 |
+
"learning_rate": 6.017142857142858e-06,
|
626 |
+
"loss": 0.0345,
|
627 |
+
"step": 1900
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 3.63,
|
631 |
+
"eval_loss": 0.40161246061325073,
|
632 |
+
"eval_runtime": 1812.1091,
|
633 |
+
"eval_samples_per_second": 0.828,
|
634 |
+
"eval_steps_per_second": 0.104,
|
635 |
+
"eval_wer": 158.56905158069884,
|
636 |
+
"step": 1900
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 3.67,
|
640 |
+
"learning_rate": 5.945714285714286e-06,
|
641 |
+
"loss": 0.0327,
|
642 |
+
"step": 1925
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 3.72,
|
646 |
+
"learning_rate": 5.874285714285715e-06,
|
647 |
+
"loss": 0.0363,
|
648 |
+
"step": 1950
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 3.77,
|
652 |
+
"learning_rate": 5.802857142857144e-06,
|
653 |
+
"loss": 0.0328,
|
654 |
+
"step": 1975
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 3.82,
|
658 |
+
"learning_rate": 5.731428571428572e-06,
|
659 |
+
"loss": 0.0346,
|
660 |
+
"step": 2000
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 3.82,
|
664 |
+
"eval_loss": 0.40199828147888184,
|
665 |
+
"eval_runtime": 1770.9946,
|
666 |
+
"eval_samples_per_second": 0.847,
|
667 |
+
"eval_steps_per_second": 0.106,
|
668 |
+
"eval_wer": 176.11619523017194,
|
669 |
+
"step": 2000
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 3.86,
|
673 |
+
"learning_rate": 5.66e-06,
|
674 |
+
"loss": 0.0363,
|
675 |
+
"step": 2025
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 3.91,
|
679 |
+
"learning_rate": 5.588571428571429e-06,
|
680 |
+
"loss": 0.0346,
|
681 |
+
"step": 2050
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 3.96,
|
685 |
+
"learning_rate": 5.517142857142857e-06,
|
686 |
+
"loss": 0.0342,
|
687 |
+
"step": 2075
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 4.01,
|
691 |
+
"learning_rate": 5.445714285714286e-06,
|
692 |
+
"loss": 0.0317,
|
693 |
+
"step": 2100
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 4.01,
|
697 |
+
"eval_loss": 0.400082528591156,
|
698 |
+
"eval_runtime": 1696.9765,
|
699 |
+
"eval_samples_per_second": 0.884,
|
700 |
+
"eval_steps_per_second": 0.111,
|
701 |
+
"eval_wer": 134.65058236272878,
|
702 |
+
"step": 2100
|
703 |
}
|
704 |
],
|
705 |
"logging_steps": 25,
|
|
|
707 |
"num_input_tokens_seen": 0,
|
708 |
"num_train_epochs": 8,
|
709 |
"save_steps": 100,
|
710 |
+
"total_flos": 1.938485851029504e+19,
|
711 |
"trial_name": null,
|
712 |
"trial_params": null
|
713 |
}
|
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 sha256:77aa736647908221a6b18a6489ddd200e9a64629e700dfb2729d6eac836a4004
|
3 |
size 4856
|