Commit
•
b3c1708
1
Parent(s):
d82c2e3
Training in progress, epoch 11
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 +20 -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 721655813
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d55952b33f7159e26bb47cecde3ddbf9ff8416a8d468f34fcdf4a1133e38237d
|
3 |
size 721655813
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8853012d08c5745ce49f40ca5aa305079bf52c75fd12264871faaf83ad42e7a1
|
3 |
size 377643361
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0dc460cea827e9b97fe3b951d3ba698c7ae580727aab053e6cc7a01b6f98752
|
3 |
size 14639
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:707b2982780dcbb9f68b4a6ad168ef240dbb5bb3fc43d18aca45666f7cdf38a5
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ed2216f57c0f86b33c65c6adcec7c99c6842e0735afb2a44d750fc77586cf5a
|
3 |
size 627
|
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,
|
@@ -176,11 +176,28 @@
|
|
176 |
"eval_samples_per_second": 26.848,
|
177 |
"eval_steps_per_second": 3.431,
|
178 |
"step": 2760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
179 |
}
|
180 |
],
|
181 |
"max_steps": 4140,
|
182 |
"num_train_epochs": 15,
|
183 |
-
"total_flos": 2.
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
186 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.0,
|
5 |
+
"global_step": 3036,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
176 |
"eval_samples_per_second": 26.848,
|
177 |
"eval_steps_per_second": 3.431,
|
178 |
"step": 2760
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 11.0,
|
182 |
+
"learning_rate": 2.8248156623442668e-05,
|
183 |
+
"loss": 0.9525,
|
184 |
+
"step": 3036
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 11.0,
|
188 |
+
"eval_cer": 0.704040404040404,
|
189 |
+
"eval_loss": 2.8678293228149414,
|
190 |
+
"eval_new_wer": 0.3611111111111111,
|
191 |
+
"eval_old_wer": 1.0,
|
192 |
+
"eval_runtime": 6.6184,
|
193 |
+
"eval_samples_per_second": 27.197,
|
194 |
+
"eval_steps_per_second": 3.475,
|
195 |
+
"step": 3036
|
196 |
}
|
197 |
],
|
198 |
"max_steps": 4140,
|
199 |
"num_train_epochs": 15,
|
200 |
+
"total_flos": 2.208649077237312e+18,
|
201 |
"trial_name": null,
|
202 |
"trial_params": null
|
203 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8853012d08c5745ce49f40ca5aa305079bf52c75fd12264871faaf83ad42e7a1
|
3 |
size 377643361
|