Training in progress, step 2400
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +3 -69
- last-checkpoint/training_args.bin +1 -1
- model.safetensors +1 -1
- runs/Dec05_16-06-51_968fe8348316/events.out.tfevents.1701792431.968fe8348316.6138.0 +2 -2
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": 4.
|
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,
|
@@ -700,72 +700,6 @@
|
|
700 |
"eval_steps_per_second": 0.111,
|
701 |
"eval_wer": 134.65058236272878,
|
702 |
"step": 2100
|
703 |
-
},
|
704 |
-
{
|
705 |
-
"epoch": 4.06,
|
706 |
-
"learning_rate": 5.374285714285715e-06,
|
707 |
-
"loss": 0.018,
|
708 |
-
"step": 2125
|
709 |
-
},
|
710 |
-
{
|
711 |
-
"epoch": 4.1,
|
712 |
-
"learning_rate": 5.3028571428571425e-06,
|
713 |
-
"loss": 0.0165,
|
714 |
-
"step": 2150
|
715 |
-
},
|
716 |
-
{
|
717 |
-
"epoch": 4.15,
|
718 |
-
"learning_rate": 5.2314285714285716e-06,
|
719 |
-
"loss": 0.0157,
|
720 |
-
"step": 2175
|
721 |
-
},
|
722 |
-
{
|
723 |
-
"epoch": 4.2,
|
724 |
-
"learning_rate": 5.1600000000000006e-06,
|
725 |
-
"loss": 0.0173,
|
726 |
-
"step": 2200
|
727 |
-
},
|
728 |
-
{
|
729 |
-
"epoch": 4.2,
|
730 |
-
"eval_loss": 0.4140649735927582,
|
731 |
-
"eval_runtime": 1834.1524,
|
732 |
-
"eval_samples_per_second": 0.818,
|
733 |
-
"eval_steps_per_second": 0.102,
|
734 |
-
"eval_wer": 189.33721575152524,
|
735 |
-
"step": 2200
|
736 |
-
},
|
737 |
-
{
|
738 |
-
"epoch": 4.25,
|
739 |
-
"learning_rate": 5.08857142857143e-06,
|
740 |
-
"loss": 0.0157,
|
741 |
-
"step": 2225
|
742 |
-
},
|
743 |
-
{
|
744 |
-
"epoch": 4.29,
|
745 |
-
"learning_rate": 5.017142857142857e-06,
|
746 |
-
"loss": 0.015,
|
747 |
-
"step": 2250
|
748 |
-
},
|
749 |
-
{
|
750 |
-
"epoch": 4.34,
|
751 |
-
"learning_rate": 4.945714285714286e-06,
|
752 |
-
"loss": 0.0146,
|
753 |
-
"step": 2275
|
754 |
-
},
|
755 |
-
{
|
756 |
-
"epoch": 4.39,
|
757 |
-
"learning_rate": 4.874285714285715e-06,
|
758 |
-
"loss": 0.0174,
|
759 |
-
"step": 2300
|
760 |
-
},
|
761 |
-
{
|
762 |
-
"epoch": 4.39,
|
763 |
-
"eval_loss": 0.41064801812171936,
|
764 |
-
"eval_runtime": 1771.4749,
|
765 |
-
"eval_samples_per_second": 0.847,
|
766 |
-
"eval_steps_per_second": 0.106,
|
767 |
-
"eval_wer": 175.0207986688852,
|
768 |
-
"step": 2300
|
769 |
}
|
770 |
],
|
771 |
"logging_steps": 25,
|
@@ -773,7 +707,7 @@
|
|
773 |
"num_input_tokens_seen": 0,
|
774 |
"num_train_epochs": 8,
|
775 |
"save_steps": 100,
|
776 |
-
"total_flos":
|
777 |
"trial_name": null,
|
778 |
"trial_params": null
|
779 |
}
|
|
|
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,
|
|
|
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
|
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 sha256:427ae072cbc49ae148942a74b9f051c838d316269f69b8f3611c391c8a391f3c
|
3 |
size 966995080
|
runs/Dec05_16-06-51_968fe8348316/events.out.tfevents.1701792431.968fe8348316.6138.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47be3583b3ea8f6b10ad8bcc7877ca061c8642616e3a44bc640324ff87ce607d
|
3 |
+
size 8011
|