cp 29200
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 sha256:49d87731bb26150050af1cdbd0e26840a767ab743ddc158b8c1597d81ce8a17e
|
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 sha256:459f2dc6a6b6135d1129c3ad4f9bb3c65df5ba310cc45a192a13377852feef76
|
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 sha256:2de514341497aeb2d969571853d3ddb165789f77a56da57480f7ae711d12e6df
|
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,
|
@@ -986,11 +986,53 @@
|
|
986 |
"eval_samples_per_second": 6.23,
|
987 |
"eval_wer": 0.3269041769041769,
|
988 |
"step": 28000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
989 |
}
|
990 |
],
|
991 |
"max_steps": 29490,
|
992 |
"num_train_epochs": 30,
|
993 |
-
"total_flos": 1.
|
994 |
"trial_name": null,
|
995 |
"trial_params": null
|
996 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 29.70498474059003,
|
5 |
+
"global_step": 29200,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
986 |
"eval_samples_per_second": 6.23,
|
987 |
"eval_wer": 0.3269041769041769,
|
988 |
"step": 28000
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 28.89,
|
992 |
+
"learning_rate": 1.1279751638496032e-05,
|
993 |
+
"loss": 0.0337,
|
994 |
+
"step": 28400
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 28.89,
|
998 |
+
"eval_loss": 0.5360307693481445,
|
999 |
+
"eval_runtime": 238.3743,
|
1000 |
+
"eval_samples_per_second": 7.849,
|
1001 |
+
"eval_wer": 0.3269041769041769,
|
1002 |
+
"step": 28400
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 29.3,
|
1006 |
+
"learning_rate": 7.140393239047947e-06,
|
1007 |
+
"loss": 0.032,
|
1008 |
+
"step": 28800
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 29.3,
|
1012 |
+
"eval_loss": 0.5361535549163818,
|
1013 |
+
"eval_runtime": 851.2223,
|
1014 |
+
"eval_samples_per_second": 2.198,
|
1015 |
+
"eval_wer": 0.3257985257985258,
|
1016 |
+
"step": 28800
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 29.7,
|
1020 |
+
"learning_rate": 3.001034839599862e-06,
|
1021 |
+
"loss": 0.0314,
|
1022 |
+
"step": 29200
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 29.7,
|
1026 |
+
"eval_loss": 0.5325431823730469,
|
1027 |
+
"eval_runtime": 1467.4683,
|
1028 |
+
"eval_samples_per_second": 1.275,
|
1029 |
+
"eval_wer": 0.32524570024570026,
|
1030 |
+
"step": 29200
|
1031 |
}
|
1032 |
],
|
1033 |
"max_steps": 29490,
|
1034 |
"num_train_epochs": 30,
|
1035 |
+
"total_flos": 1.620248435122493e+20,
|
1036 |
"trial_name": null,
|
1037 |
"trial_params": null
|
1038 |
}
|