Training in progress, step 3000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +84 -3
- pytorch_model.bin +1 -1
- runs/Apr12_05-50-01_129-159-47-80/events.out.tfevents.1681278622.129-159-47-80.68729.10 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 302223127
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32cef5ab050e632515a0a2aaf3445b5327ddb40735bec95e5a98a5c88722de3e
|
3 |
size 302223127
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151097331
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7e8cac498b492ce5e234a66e906c5bb4a45ff41a3563056385f45009b84142e
|
3 |
size 151097331
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfc172c91a14f3a61f00ce1202c6ffe9f6f9e454d5d0e8b9b96f1057561102fb
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5a79439619f4b20ecf7c8d20593147464500cb27c3d447ec4f9e2d9cb88ff40
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 42.17917675544795,
|
3 |
"best_model_checkpoint": "whisper-tiny-v2-ta_tf32_adamBetas_2/checkpoint-2100",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -735,11 +735,92 @@
|
|
735 |
"eval_steps_per_second": 0.835,
|
736 |
"eval_wer": 43.389830508474574,
|
737 |
"step": 2700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
738 |
}
|
739 |
],
|
740 |
"max_steps": 4000,
|
741 |
"num_train_epochs": 2,
|
742 |
-
"total_flos": 2.
|
743 |
"trial_name": null,
|
744 |
"trial_params": null
|
745 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 42.17917675544795,
|
3 |
"best_model_checkpoint": "whisper-tiny-v2-ta_tf32_adamBetas_2/checkpoint-2100",
|
4 |
+
"epoch": 1.052816283558519,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
735 |
"eval_steps_per_second": 0.835,
|
736 |
"eval_wer": 43.389830508474574,
|
737 |
"step": 2700
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.96,
|
741 |
+
"learning_rate": 5.464285714285714e-06,
|
742 |
+
"loss": 0.2813,
|
743 |
+
"step": 2725
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 0.97,
|
747 |
+
"learning_rate": 5.357142857142857e-06,
|
748 |
+
"loss": 0.2723,
|
749 |
+
"step": 2750
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 0.97,
|
753 |
+
"learning_rate": 5.25e-06,
|
754 |
+
"loss": 0.3075,
|
755 |
+
"step": 2775
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 0.98,
|
759 |
+
"learning_rate": 5.142857142857143e-06,
|
760 |
+
"loss": 0.29,
|
761 |
+
"step": 2800
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.99,
|
765 |
+
"learning_rate": 5.035714285714285e-06,
|
766 |
+
"loss": 0.2939,
|
767 |
+
"step": 2825
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 1.0,
|
771 |
+
"learning_rate": 4.9285714285714286e-06,
|
772 |
+
"loss": 0.2718,
|
773 |
+
"step": 2850
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 1.01,
|
777 |
+
"learning_rate": 4.821428571428572e-06,
|
778 |
+
"loss": 0.2876,
|
779 |
+
"step": 2875
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 1.02,
|
783 |
+
"learning_rate": 4.714285714285714e-06,
|
784 |
+
"loss": 0.2661,
|
785 |
+
"step": 2900
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 1.03,
|
789 |
+
"learning_rate": 4.6071428571428574e-06,
|
790 |
+
"loss": 0.2742,
|
791 |
+
"step": 2925
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 1.04,
|
795 |
+
"learning_rate": 4.5e-06,
|
796 |
+
"loss": 0.2796,
|
797 |
+
"step": 2950
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 1.04,
|
801 |
+
"learning_rate": 4.392857142857143e-06,
|
802 |
+
"loss": 0.2745,
|
803 |
+
"step": 2975
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 1.05,
|
807 |
+
"learning_rate": 4.2857142857142855e-06,
|
808 |
+
"loss": 0.2717,
|
809 |
+
"step": 3000
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 1.05,
|
813 |
+
"eval_loss": 0.3490868806838989,
|
814 |
+
"eval_runtime": 15.5303,
|
815 |
+
"eval_samples_per_second": 6.439,
|
816 |
+
"eval_steps_per_second": 0.837,
|
817 |
+
"eval_wer": 43.14769975786925,
|
818 |
+
"step": 3000
|
819 |
}
|
820 |
],
|
821 |
"max_steps": 4000,
|
822 |
"num_train_epochs": 2,
|
823 |
+
"total_flos": 2.36333911486464e+18,
|
824 |
"trial_name": null,
|
825 |
"trial_params": null
|
826 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151097331
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7e8cac498b492ce5e234a66e906c5bb4a45ff41a3563056385f45009b84142e
|
3 |
size 151097331
|
runs/Apr12_05-50-01_129-159-47-80/events.out.tfevents.1681278622.129-159-47-80.68729.10
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 sha256:3c393ea2a6dc948c7db1f9b9365c73d8079e84ebe79bb9986dbc909620cf258e
|
3 |
+
size 26815
|