Commit
•
25f6635
1
Parent(s):
e2824aa
Training in progress, step 5500
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 +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 sha256:71e1a504149bb94555a32f4bb1e4adee93359785cd15512b561adf8293ceb068
|
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:f43f27ca71691dc2e96ebfdac9463f1a96323dd228f524f48d396c2fd087f46a
|
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 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92642751ef5ea9bb2672a394351f83e812c4229fb6148418d7c7f2e2fba3becc
|
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 sha256:7705a83e25cd0871fa2f58529ecd5390f06b01be20ebdefa7bc6e34106413105
|
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 sha256:47ffecce1f144e8645231e0201bdbe2cd97e769c76bcc89627358a09986467fb
|
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,
|
@@ -216,11 +216,32 @@
|
|
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":
|
224 |
"trial_name": null,
|
225 |
"trial_params": null
|
226 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 27.7224217287947,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-4500",
|
4 |
+
"epoch": 14.03061224489796,
|
5 |
+
"global_step": 5500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
216 |
"eval_steps_per_second": 0.15,
|
217 |
"eval_wer": 27.950027818522077,
|
218 |
"step": 5000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 13.39,
|
222 |
+
"learning_rate": 5.005263157894737e-06,
|
223 |
+
"loss": 0.0278,
|
224 |
+
"step": 5250
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 14.03,
|
228 |
+
"learning_rate": 4.7421052631578954e-06,
|
229 |
+
"loss": 0.026,
|
230 |
+
"step": 5500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 14.03,
|
234 |
+
"eval_loss": 0.7726335525512695,
|
235 |
+
"eval_runtime": 292.0072,
|
236 |
+
"eval_samples_per_second": 4.722,
|
237 |
+
"eval_steps_per_second": 0.151,
|
238 |
+
"eval_wer": 28.106823124778717,
|
239 |
+
"step": 5500
|
240 |
}
|
241 |
],
|
242 |
"max_steps": 10000,
|
243 |
"num_train_epochs": 26,
|
244 |
+
"total_flos": 1.014002521104384e+20,
|
245 |
"trial_name": null,
|
246 |
"trial_params": null
|
247 |
}
|
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:f43f27ca71691dc2e96ebfdac9463f1a96323dd228f524f48d396c2fd087f46a
|
3 |
size 967102601
|