Commit
•
eb0dcff
1
Parent(s):
a120e79
Training in progress, epoch 11
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 721661957
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:597ee1cfec3df4ea086c635f8be5affb7a0513744f80ebcd5faa12d644075bd6
|
3 |
size 721661957
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52cf8ca18570399241e17f4e1c06e2bddd0be64e2f51f48f208a005a0ac99507
|
3 |
size 377646433
|
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 sha256:811e6c5c0aea2393723a2fe8d63f73839f007983d4731647bacb78b260a27b5f
|
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:f2aab3caac1bcd81c33b7cb5f28ebc037083d1b822ca510ee69c2e74de0694bb
|
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:a0d5fff130724d127477ebb43eacd79fe6a01e4a3241dd4098f37c94a8fcd5e2
|
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,
|
@@ -176,11 +176,28 @@
|
|
176 |
"eval_samples_per_second": 24.529,
|
177 |
"eval_steps_per_second": 3.154,
|
178 |
"step": 42700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
179 |
}
|
180 |
],
|
181 |
"max_steps": 64050,
|
182 |
"num_train_epochs": 15,
|
183 |
-
"total_flos": 3.
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
186 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.0,
|
5 |
+
"global_step": 46970,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
176 |
"eval_samples_per_second": 24.529,
|
177 |
"eval_steps_per_second": 3.154,
|
178 |
"step": 42700
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 11.0,
|
182 |
+
"learning_rate": 2.8106100447015514e-05,
|
183 |
+
"loss": 0.1088,
|
184 |
+
"step": 46970
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 11.0,
|
188 |
+
"eval_cer": 0.09610389610389611,
|
189 |
+
"eval_loss": 0.7578983902931213,
|
190 |
+
"eval_new_wer": 0.10476190476190476,
|
191 |
+
"eval_old_wer": 0.1761904761904762,
|
192 |
+
"eval_runtime": 8.5378,
|
193 |
+
"eval_samples_per_second": 24.597,
|
194 |
+
"eval_steps_per_second": 3.162,
|
195 |
+
"step": 46970
|
196 |
}
|
197 |
],
|
198 |
"max_steps": 64050,
|
199 |
"num_train_epochs": 15,
|
200 |
+
"total_flos": 3.5579446041976996e+19,
|
201 |
"trial_name": null,
|
202 |
"trial_params": null
|
203 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52cf8ca18570399241e17f4e1c06e2bddd0be64e2f51f48f208a005a0ac99507
|
3 |
size 377646433
|