Commit
•
e2824aa
1
Parent(s):
610c3cc
Training in progress, step 5000
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 +24 -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 734250209
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5785e53ea79da9781bb12f642f90a42e9b93df7faf2f8438bb2c3663057822fc
|
3 |
size 734250209
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967102601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fbd7ff1c998dbb8be06959fe54b116c17f1042f3e4c11e85b3462aa5a4126e0
|
3 |
size 967102601
|
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:dcbd60b992bfc9022abff2bfe088028fc233682a34bb86fe0232c5b855c95e14
|
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 sha256:1a5c3ae4b97ead5b1298176cecc078fe3515bc92cd022f784176ab9698898a74
|
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:c1fb649e2d6b2f894130f500502c0c5c00a7aa41beefba757c94266b20b72796
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 27.7224217287947,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-4500",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -195,11 +195,32 @@
|
|
195 |
"eval_steps_per_second": 0.152,
|
196 |
"eval_wer": 27.7224217287947,
|
197 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
198 |
}
|
199 |
],
|
200 |
"max_steps": 10000,
|
201 |
"num_train_epochs": 26,
|
202 |
-
"total_flos":
|
203 |
"trial_name": null,
|
204 |
"trial_params": null
|
205 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 27.7224217287947,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-4500",
|
4 |
+
"epoch": 12.755102040816327,
|
5 |
+
"global_step": 5000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
195 |
"eval_steps_per_second": 0.152,
|
196 |
"eval_wer": 27.7224217287947,
|
197 |
"step": 4500
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 12.12,
|
201 |
+
"learning_rate": 5.531578947368421e-06,
|
202 |
+
"loss": 0.0376,
|
203 |
+
"step": 4750
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 12.76,
|
207 |
+
"learning_rate": 5.268421052631579e-06,
|
208 |
+
"loss": 0.0314,
|
209 |
+
"step": 5000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 12.76,
|
213 |
+
"eval_loss": 0.7565638422966003,
|
214 |
+
"eval_runtime": 294.0019,
|
215 |
+
"eval_samples_per_second": 4.69,
|
216 |
+
"eval_steps_per_second": 0.15,
|
217 |
+
"eval_wer": 27.950027818522077,
|
218 |
+
"step": 5000
|
219 |
}
|
220 |
],
|
221 |
"max_steps": 10000,
|
222 |
"num_train_epochs": 26,
|
223 |
+
"total_flos": 9.21914919862272e+19,
|
224 |
"trial_name": null,
|
225 |
"trial_params": null
|
226 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967102601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fbd7ff1c998dbb8be06959fe54b116c17f1042f3e4c11e85b3462aa5a4126e0
|
3 |
size 967102601
|