mprzibilla
commited on
Commit
·
984a0d3
1
Parent(s):
3519cd2
Training in progress, epoch 13
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 sha256:5aa780d23f261fbe14534c1f061b46d7bd76ae4cd50795414e4d4eea875e2d34
|
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:bd39a369045a1ca7bf01d41a399551551d09719307ae52530439e1660a82f955
|
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 sha256:6c5435668bbec6ec8b20c10cbb71c3db86bc816faed52598e03c0f03425c7ac6
|
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:f4ca55006e9db5181d043f177fa02ffbc328fabf8a734248e641f8b30be980ae
|
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 sha256:6ebd5da37c4db09cce4a3e449a64a14dd9fb9b14bec4d99cf79be83d911428dd
|
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,
|
@@ -210,11 +210,28 @@
|
|
210 |
"eval_samples_per_second": 24.556,
|
211 |
"eval_steps_per_second": 3.157,
|
212 |
"step": 3864
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
213 |
}
|
214 |
],
|
215 |
"max_steps": 4830,
|
216 |
"num_train_epochs": 15,
|
217 |
-
"total_flos":
|
218 |
"trial_name": null,
|
219 |
"trial_params": null
|
220 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.0,
|
5 |
+
"global_step": 4186,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
210 |
"eval_samples_per_second": 24.556,
|
211 |
"eval_steps_per_second": 3.157,
|
212 |
"step": 3864
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 13.0,
|
216 |
+
"learning_rate": 1.418609718893005e-05,
|
217 |
+
"loss": 0.1988,
|
218 |
+
"step": 4186
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 13.0,
|
222 |
+
"eval_cer": 0.5922077922077922,
|
223 |
+
"eval_loss": 3.9551496505737305,
|
224 |
+
"eval_new_wer": 0.2619047619047619,
|
225 |
+
"eval_old_wer": 0.9714285714285714,
|
226 |
+
"eval_runtime": 8.0772,
|
227 |
+
"eval_samples_per_second": 25.999,
|
228 |
+
"eval_steps_per_second": 3.343,
|
229 |
+
"step": 4186
|
230 |
}
|
231 |
],
|
232 |
"max_steps": 4830,
|
233 |
"num_train_epochs": 15,
|
234 |
+
"total_flos": 3.107559883348128e+18,
|
235 |
"trial_name": null,
|
236 |
"trial_params": null
|
237 |
}
|
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:bd39a369045a1ca7bf01d41a399551551d09719307ae52530439e1660a82f955
|
3 |
size 377643361
|