mprzibilla
commited on
Commit
•
91361da
1
Parent(s):
16d6619
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 +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 721668101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e80f53101704e60bca908cd905da0a0ac5b303e6cc1393dafcd7f332eff2495
|
3 |
size 721668101
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377649505
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60fd7eef09651ce94b3d5b0a604e2ffd8df5f55c0987ab7c0763dfcc18972c1a
|
3 |
size 377649505
|
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 sha256:173a4f63c5dc52f595db3984d079de7ae9a4994526e586f1e57bc8b90d46c1b9
|
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 sha256:6127f0710460879df48b559f6f61ada80c6e38341ca976067dd39afe2da63421
|
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:eaa5d770c6647d602a4bb66530afc224dc2142b8512997267e990a9f49228f49
|
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": 23.638,
|
245 |
"eval_steps_per_second": 2.994,
|
246 |
"step": 61124
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 65490,
|
250 |
"num_train_epochs": 15,
|
251 |
-
"total_flos": 4.
|
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": 65490,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
244 |
"eval_samples_per_second": 23.638,
|
245 |
"eval_steps_per_second": 2.994,
|
246 |
"step": 61124
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 15.0,
|
250 |
+
"learning_rate": 5.1433714800051435e-08,
|
251 |
+
"loss": 0.0407,
|
252 |
+
"step": 65490
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 15.0,
|
256 |
+
"eval_cer": 0.9381818181818182,
|
257 |
+
"eval_loss": 10.843835830688477,
|
258 |
+
"eval_new_wer": 0.8866666666666667,
|
259 |
+
"eval_old_wer": 1.0,
|
260 |
+
"eval_runtime": 6.0443,
|
261 |
+
"eval_samples_per_second": 24.817,
|
262 |
+
"eval_steps_per_second": 3.143,
|
263 |
+
"step": 65490
|
264 |
}
|
265 |
],
|
266 |
"max_steps": 65490,
|
267 |
"num_train_epochs": 15,
|
268 |
+
"total_flos": 4.9595844421947e+19,
|
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 377649505
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60fd7eef09651ce94b3d5b0a604e2ffd8df5f55c0987ab7c0763dfcc18972c1a
|
3 |
size 377649505
|