codefactory4791
commited on
Commit
•
610c3cc
1
Parent(s):
e32f2b4
Training in progress, step 4500
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 +26 -5
- 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 sha256:11013d62aeea78f3966ae5806ff135ee22dc3484dc047f705acb03fb20df63f9
|
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:e076d92053ac14a3865486593a2a43174b9312b33355871c309cf72799dc2fd4
|
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 sha256:99ee6a141e7d1196dfbe311d5204e16edce0c3533f79aa7ef2b73ac440605fe5
|
3 |
+
size 14511
|
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 sha256:5e3e5ba78da00d506a06dad1a9dae6d6d09ad0ba3b092cc465bf95e080c40769
|
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 sha256:9401ffffd82bc444b011419eebbcc218ad4056d3c404d8bf965da8015e713f9b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -174,11 +174,32 @@
|
|
174 |
"eval_steps_per_second": 0.149,
|
175 |
"eval_wer": 28.354660866926306,
|
176 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
177 |
}
|
178 |
],
|
179 |
"max_steps": 10000,
|
180 |
"num_train_epochs": 26,
|
181 |
-
"total_flos":
|
182 |
"trial_name": null,
|
183 |
"trial_params": null
|
184 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 27.7224217287947,
|
3 |
+
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-4500",
|
4 |
+
"epoch": 11.479591836734693,
|
5 |
+
"global_step": 4500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
174 |
"eval_steps_per_second": 0.149,
|
175 |
"eval_wer": 28.354660866926306,
|
176 |
"step": 4000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 10.84,
|
180 |
+
"learning_rate": 6.057894736842106e-06,
|
181 |
+
"loss": 0.0486,
|
182 |
+
"step": 4250
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 11.48,
|
186 |
+
"learning_rate": 5.794736842105264e-06,
|
187 |
+
"loss": 0.0406,
|
188 |
+
"step": 4500
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 11.48,
|
192 |
+
"eval_loss": 0.72938472032547,
|
193 |
+
"eval_runtime": 288.8463,
|
194 |
+
"eval_samples_per_second": 4.774,
|
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": 8.29697455190016e+19,
|
203 |
"trial_name": null,
|
204 |
"trial_params": null
|
205 |
}
|
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:e076d92053ac14a3865486593a2a43174b9312b33355871c309cf72799dc2fd4
|
3 |
size 967102601
|