Commit
•
1d662e7
1
Parent(s):
984a0d3
Training in progress, epoch 14
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- 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:ef10961a783fd21b767b38e34d4402310e84d231dce4a4168c997d4244a8e46e
|
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 sha256:337e7ffe50fa9e3a5387db1b688aa14bb9c2798b69435940d259e0adb56b0c50
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1924972eff86195fe574f1ddfa5ece88769bf92998527896484a563a955fce8a
|
3 |
+
size 14575
|
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:bc7c52c01fdda3bac63f4dfda490bbcdf8d5df8a408abdccb89b76143d649f17
|
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:b3806613d1f4450820466558111da21d027b9b2bf74079bd93810d3c4f72176f
|
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,
|
@@ -227,11 +227,28 @@
|
|
227 |
"eval_samples_per_second": 25.999,
|
228 |
"eval_steps_per_second": 3.343,
|
229 |
"step": 4186
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
}
|
231 |
],
|
232 |
"max_steps": 4830,
|
233 |
"num_train_epochs": 15,
|
234 |
-
"total_flos": 3.
|
235 |
"trial_name": null,
|
236 |
"trial_params": null
|
237 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.0,
|
5 |
+
"global_step": 4508,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
227 |
"eval_samples_per_second": 25.999,
|
228 |
"eval_steps_per_second": 3.343,
|
229 |
"step": 4186
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 14.0,
|
233 |
+
"learning_rate": 7.1693179341904555e-06,
|
234 |
+
"loss": 0.1663,
|
235 |
+
"step": 4508
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 14.0,
|
239 |
+
"eval_cer": 0.6095238095238096,
|
240 |
+
"eval_loss": 4.294742107391357,
|
241 |
+
"eval_new_wer": 0.2904761904761905,
|
242 |
+
"eval_old_wer": 0.9809523809523809,
|
243 |
+
"eval_runtime": 8.1055,
|
244 |
+
"eval_samples_per_second": 25.908,
|
245 |
+
"eval_steps_per_second": 3.331,
|
246 |
+
"step": 4508
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 4830,
|
250 |
"num_train_epochs": 15,
|
251 |
+
"total_flos": 3.3465058101141115e+18,
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
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 sha256:337e7ffe50fa9e3a5387db1b688aa14bb9c2798b69435940d259e0adb56b0c50
|
3 |
size 377643361
|