Commit
•
6586d5e
1
Parent(s):
1b6031a
Training in progress, step 1400
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 755294189
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3793e13a3fa8be22b923eb0f2a158cd68ba7615913165439571ce9e0a5f1367b
|
3 |
size 755294189
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377670039
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16a1a0929497bbcf0721bb49764a58adbd5c97f8829783633d57462c10551d15
|
3 |
size 377670039
|
last-checkpoint/rng_state.pth
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:bf23aebfa9c03c19d207fc344570a196569e50adf0c1ea576f5c73778924303c
|
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 sha256:1263f23283d72e5d2c9b5e29771a41d6d158f71fe361e754b7f031162906aca0
|
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,
|
@@ -214,11 +214,27 @@
|
|
214 |
"eval_steps_per_second": 1.256,
|
215 |
"eval_wer": 0.27742589308335447,
|
216 |
"step": 1300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
217 |
}
|
218 |
],
|
219 |
"max_steps": 4380,
|
220 |
"num_train_epochs": 60,
|
221 |
-
"total_flos": 3.
|
222 |
"trial_name": null,
|
223 |
"trial_params": null
|
224 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 19.17808219178082,
|
5 |
+
"global_step": 1400,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
214 |
"eval_steps_per_second": 1.256,
|
215 |
"eval_wer": 0.27742589308335447,
|
216 |
"step": 1300
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 19.18,
|
220 |
+
"learning_rate": 8.816568047337278e-05,
|
221 |
+
"loss": 0.2041,
|
222 |
+
"step": 1400
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 19.18,
|
226 |
+
"eval_cer": 0.04789959016393443,
|
227 |
+
"eval_loss": 0.2579464018344879,
|
228 |
+
"eval_runtime": 49.7945,
|
229 |
+
"eval_samples_per_second": 9.901,
|
230 |
+
"eval_steps_per_second": 1.245,
|
231 |
+
"eval_wer": 0.23764884722574106,
|
232 |
+
"step": 1400
|
233 |
}
|
234 |
],
|
235 |
"max_steps": 4380,
|
236 |
"num_train_epochs": 60,
|
237 |
+
"total_flos": 3.667522541032627e+17,
|
238 |
"trial_name": null,
|
239 |
"trial_params": null
|
240 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377670039
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16a1a0929497bbcf0721bb49764a58adbd5c97f8829783633d57462c10551d15
|
3 |
size 377670039
|