cp 21600
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- scheduler.pt +1 -1
- trainer_state.json +45 -3
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490339591
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2097409e22b1fab03277ae466406bfb2f48efaa2987c211dc571d6aeb8354e54
|
3 |
size 2490339591
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262065048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11e8cefb76774bf50b86c1bc9486e5ec95567c8f849a411556992285820275c2
|
3 |
size 1262065048
|
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:e58b5205a60751338b8db83fc32e97ce49b5dbb4327655a27ca0de316c1b3f76
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -720,11 +720,53 @@
|
|
720 |
"eval_samples_per_second": 7.916,
|
721 |
"eval_wer": 0.3406633906633907,
|
722 |
"step": 20400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
723 |
}
|
724 |
],
|
725 |
"max_steps": 29490,
|
726 |
"num_train_epochs": 30,
|
727 |
-
"total_flos": 1.
|
728 |
"trial_name": null,
|
729 |
"trial_params": null
|
730 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 21.9735503560529,
|
5 |
+
"global_step": 21600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
720 |
"eval_samples_per_second": 7.916,
|
721 |
"eval_wer": 0.3406633906633907,
|
722 |
"step": 20400
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 21.16,
|
726 |
+
"learning_rate": 8.992756122800964e-05,
|
727 |
+
"loss": 0.049,
|
728 |
+
"step": 20800
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 21.16,
|
732 |
+
"eval_loss": 0.484068900346756,
|
733 |
+
"eval_runtime": 237.5327,
|
734 |
+
"eval_samples_per_second": 7.877,
|
735 |
+
"eval_wer": 0.3410933660933661,
|
736 |
+
"step": 20800
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 21.57,
|
740 |
+
"learning_rate": 8.578820282856158e-05,
|
741 |
+
"loss": 0.048,
|
742 |
+
"step": 21200
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 21.57,
|
746 |
+
"eval_loss": 0.4956786334514618,
|
747 |
+
"eval_runtime": 240.2049,
|
748 |
+
"eval_samples_per_second": 7.789,
|
749 |
+
"eval_wer": 0.3418304668304668,
|
750 |
+
"step": 21200
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 21.97,
|
754 |
+
"learning_rate": 8.164884442911348e-05,
|
755 |
+
"loss": 0.0453,
|
756 |
+
"step": 21600
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 21.97,
|
760 |
+
"eval_loss": 0.5122228860855103,
|
761 |
+
"eval_runtime": 237.8707,
|
762 |
+
"eval_samples_per_second": 7.866,
|
763 |
+
"eval_wer": 0.3369164619164619,
|
764 |
+
"step": 21600
|
765 |
}
|
766 |
],
|
767 |
"max_steps": 29490,
|
768 |
"num_train_epochs": 30,
|
769 |
+
"total_flos": 1.1986301431319814e+20,
|
770 |
"trial_name": null,
|
771 |
"trial_params": null
|
772 |
}
|