Commit
·
70522f2
1
Parent(s):
f7155b5
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:e9ee4340810019408ac5d0f919d00ee383c14d970b8807261284456b0d6f3c88
|
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:bf1b0c2f3a6174da56223c257c0417b96f5234965399506ca0a151a4aac3feea
|
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 sha256:6b3f60134cbe46c77ac37b546f13f8fc16d3b713aaf0a7808f73f9c97d056277
|
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 sha256:34937d38369c2d00058fe1072238479be3d1cdc5e1a5164e4aa053632142bea6
|
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 sha256:6e7a293cd52a160bbfcf3b131665a43a8159b25cc3f6b188e76cc8796ef506e0
|
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": 24.518,
|
160 |
"eval_steps_per_second": 3.152,
|
161 |
"step": 2898
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
}
|
163 |
],
|
164 |
"max_steps": 4830,
|
165 |
"num_train_epochs": 15,
|
166 |
-
"total_flos": 2.
|
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": 3220,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
159 |
"eval_samples_per_second": 24.518,
|
160 |
"eval_steps_per_second": 3.152,
|
161 |
"step": 2898
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 3.5236434953148835e-05,
|
166 |
+
"loss": 0.4461,
|
167 |
+
"step": 3220
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_cer": 0.6562770562770562,
|
172 |
+
"eval_loss": 3.8030993938446045,
|
173 |
+
"eval_new_wer": 0.3523809523809524,
|
174 |
+
"eval_old_wer": 0.9952380952380953,
|
175 |
+
"eval_runtime": 8.652,
|
176 |
+
"eval_samples_per_second": 24.272,
|
177 |
+
"eval_steps_per_second": 3.121,
|
178 |
+
"step": 3220
|
179 |
}
|
180 |
],
|
181 |
"max_steps": 4830,
|
182 |
"num_train_epochs": 15,
|
183 |
+
"total_flos": 2.389652100159168e+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:bf1b0c2f3a6174da56223c257c0417b96f5234965399506ca0a151a4aac3feea
|
3 |
size 377643361
|