mprzibilla
commited on
Commit
•
d5a3068
1
Parent(s):
1d662e7
Training in progress, epoch 15
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:b0ae381297ba7f4a6c10e763028de1578bf4c0436e416cdb13aa12decffd608e
|
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:b08ebe9cbb938da0cd57e31151c8655e45b91519a729886132d34ab6e2f09aca
|
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 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51adfc052c558fcf914acc5e9262b282d4c2718882b17e3fcea2c9c62303de62
|
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 sha256:717d4161b8645a0f617e0baff9da90c3334dc5c108874d8e52d1609d9bec3dbf
|
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 sha256:561f6fbca32fb997990be4388b58bc0a1f01ed57e625f6480f8c76c16b14e146
|
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,
|
@@ -244,11 +244,28 @@
|
|
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.
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 4830,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
244 |
"eval_samples_per_second": 25.908,
|
245 |
"eval_steps_per_second": 3.331,
|
246 |
"step": 4508
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 15.0,
|
250 |
+
"learning_rate": 1.5253867945086075e-07,
|
251 |
+
"loss": 0.1398,
|
252 |
+
"step": 4830
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 15.0,
|
256 |
+
"eval_cer": 0.6207792207792208,
|
257 |
+
"eval_loss": 4.198614120483398,
|
258 |
+
"eval_new_wer": 0.319047619047619,
|
259 |
+
"eval_old_wer": 0.9904761904761905,
|
260 |
+
"eval_runtime": 8.1622,
|
261 |
+
"eval_samples_per_second": 25.728,
|
262 |
+
"eval_steps_per_second": 3.308,
|
263 |
+
"step": 4830
|
264 |
}
|
265 |
],
|
266 |
"max_steps": 4830,
|
267 |
"num_train_epochs": 15,
|
268 |
+
"total_flos": 3.586056332009567e+18,
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
271 |
}
|
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:b08ebe9cbb938da0cd57e31151c8655e45b91519a729886132d34ab6e2f09aca
|
3 |
size 377643361
|