codefactory4791
commited on
Commit
•
e32f2b4
1
Parent(s):
c0d66f4
Training in progress, step 4000
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:e53b8393c19ea92d2a18531d9b75e06b620349e1d68f97c37cbc7a95cb870a42
|
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 sha256:4575da2b44d35a28ebec3c25ec89bc60887ac73764c041bf074fb451f70aeca0
|
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:a39174ab7630855516382cc02519abc01841eaa529bdd4e8da8d72fdcb59bb78
|
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:be254fb1fdb9dfdf6afcbdf45ee2365750670b32892ef49d2058dc7e7c8163d7
|
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 sha256:632d7a4d94f1b5766419fff45e9fe2ff8f578c10c1e94b1a442acbec86f76207
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 28.157402255829243,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-2000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -153,11 +153,32 @@
|
|
153 |
"eval_steps_per_second": 0.151,
|
154 |
"eval_wer": 29.841687319811843,
|
155 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
156 |
}
|
157 |
],
|
158 |
"max_steps": 10000,
|
159 |
"num_train_epochs": 26,
|
160 |
-
"total_flos":
|
161 |
"trial_name": null,
|
162 |
"trial_params": null
|
163 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 28.157402255829243,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-2000",
|
4 |
+
"epoch": 10.204081632653061,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
153 |
"eval_steps_per_second": 0.151,
|
154 |
"eval_wer": 29.841687319811843,
|
155 |
"step": 3500
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 9.57,
|
159 |
+
"learning_rate": 6.58421052631579e-06,
|
160 |
+
"loss": 0.0598,
|
161 |
+
"step": 3750
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.2,
|
165 |
+
"learning_rate": 6.321052631578948e-06,
|
166 |
+
"loss": 0.0537,
|
167 |
+
"step": 4000
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.2,
|
171 |
+
"eval_loss": 0.71231609582901,
|
172 |
+
"eval_runtime": 295.3003,
|
173 |
+
"eval_samples_per_second": 4.67,
|
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": 7.3747999051776e+19,
|
182 |
"trial_name": null,
|
183 |
"trial_params": null
|
184 |
}
|
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 sha256:4575da2b44d35a28ebec3c25ec89bc60887ac73764c041bf074fb451f70aeca0
|
3 |
size 967102601
|