mprzibilla
commited on
Commit
•
d82c2e3
1
Parent(s):
850d02e
Training in progress, epoch 10
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 sha256:852ff3bf3392220b324e8d3ed9c2a150a79dc022353fafb46efa10b82461f478
|
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 sha256:035843258714c3d9de54fe73a94867103648ce92dff5c468b69e4b4e382c9262
|
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 sha256:455cf638736b0dfec19dee037522691e76bb1636e993dbc82d861871551a8115
|
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 sha256:8e930bf32c320afe82dbe731a3c075503b56957d5fce9ce6c6953c9338dd8e36
|
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 sha256:5a01e79a354f208e9980e9d0c0e22fcf1198f676da7d4a8a6fd231bbf3c8cda8
|
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,
|
@@ -159,11 +159,28 @@
|
|
159 |
"eval_samples_per_second": 26.836,
|
160 |
"eval_steps_per_second": 3.429,
|
161 |
"step": 2484
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
}
|
163 |
],
|
164 |
"max_steps": 4140,
|
165 |
"num_train_epochs": 15,
|
166 |
-
"total_flos":
|
167 |
"trial_name": null,
|
168 |
"trial_params": null
|
169 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 2760,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
159 |
"eval_samples_per_second": 26.836,
|
160 |
"eval_steps_per_second": 3.429,
|
161 |
"step": 2484
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 3.526570048309179e-05,
|
166 |
+
"loss": 1.0946,
|
167 |
+
"step": 2760
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_cer": 0.7212121212121212,
|
172 |
+
"eval_loss": 2.9549624919891357,
|
173 |
+
"eval_new_wer": 0.46111111111111114,
|
174 |
+
"eval_old_wer": 1.0,
|
175 |
+
"eval_runtime": 6.7043,
|
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": 2.007822728397696e+18,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
186 |
}
|
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 sha256:035843258714c3d9de54fe73a94867103648ce92dff5c468b69e4b4e382c9262
|
3 |
size 377643361
|