Training in progress, step 2000, 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 sha256:1b5ba145e3e92fb66ec788be874f8cbee7f0085ff368bcc6e82e40aaa73a0d5f
|
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 sha256:1740cd8b874efa4ad122d863e23ff5318215a8e3b731c7097e12bd5a7057bcab
|
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:f03aeefa39ca2fb11f1333722fa756c6e72bf123601f13c4e37abb0a0813d75e
|
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:db935c5df4ebb31f619d9a38b43de8eafe4ba340e61b0eff0830784e21464f5b
|
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,
|
@@ -601,6 +601,72 @@
|
|
601 |
"eval_steps_per_second": 0.114,
|
602 |
"eval_wer": 163.39434276206325,
|
603 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
604 |
}
|
605 |
],
|
606 |
"logging_steps": 25,
|
@@ -608,7 +674,7 @@
|
|
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": 3.816793893129771,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2000,
|
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 |
"logging_steps": 25,
|
|
|
674 |
"num_input_tokens_seen": 0,
|
675 |
"num_train_epochs": 8,
|
676 |
"save_steps": 100,
|
677 |
+
"total_flos": 1.846340532707328e+19,
|
678 |
"trial_name": null,
|
679 |
"trial_params": null
|
680 |
}
|
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
|