Commit
•
70787d0
1
Parent(s):
ab0ed87
Training in progress, step 307440
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 174303
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb5be4908db512efbc44d5adefa928609becb260203124b7a7d853d8e6d41cff
|
3 |
size 174303
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2db0a0e1cc18746fe4b5701d434a51f9e93e6ce0745f4beac3960712f8edb1c
|
3 |
size 377644503
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bca5b83f5e949001778d8b6b02b1bf0f265a262ded2662b80479c88d86cdd47
|
3 |
size 14567
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c9a22e1b525e08ba8a973cc8e85277c97ab6ef888ef3a92723108ac09e6970f
|
3 |
size 559
|
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 sha256:773aa6463599892e67f5dce110bd1d52fa3207c05957566f18dd040d314b1322
|
3 |
size 623
|
last-checkpoint/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,
|
@@ -134,11 +134,27 @@
|
|
134 |
"eval_steps_per_second": 26.211,
|
135 |
"eval_wer": 1.0,
|
136 |
"step": 273280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
137 |
}
|
138 |
],
|
139 |
"max_steps": 341600,
|
140 |
"num_train_epochs": 100,
|
141 |
-
"total_flos": 2.
|
142 |
"trial_name": null,
|
143 |
"trial_params": null
|
144 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 90.0,
|
5 |
+
"global_step": 307440,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
134 |
"eval_steps_per_second": 26.211,
|
135 |
"eval_wer": 1.0,
|
136 |
"step": 273280
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 90.0,
|
140 |
+
"learning_rate": 1.0566066806360162e-05,
|
141 |
+
"loss": 2.6524,
|
142 |
+
"step": 307440
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 90.0,
|
146 |
+
"eval_cer": 0.9324675324675324,
|
147 |
+
"eval_loss": 3.1949210166931152,
|
148 |
+
"eval_runtime": 1.0305,
|
149 |
+
"eval_samples_per_second": 203.786,
|
150 |
+
"eval_steps_per_second": 26.201,
|
151 |
+
"eval_wer": 1.0,
|
152 |
+
"step": 307440
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 341600,
|
156 |
"num_train_epochs": 100,
|
157 |
+
"total_flos": 2.9211097729200108e+20,
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2db0a0e1cc18746fe4b5701d434a51f9e93e6ce0745f4beac3960712f8edb1c
|
3 |
size 377644503
|