codefactory4791
commited on
Commit
•
c0d66f4
1
Parent(s):
902ee1c
Training in progress, step 3500
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 sha256:738a0a5fd2f350b0697eb9233d95e291e82403ea7b6c4d2370f0f8f144817046
|
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 sha256:8e2ae203ed801800c54c0fab6d45f9aa50a30f1a0d287de7a24ea1a6ed71cdb9
|
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 sha256:5170d3d946ec218b995af55ab751cfb73b2fc6b832ea64ea893fb368eeb69953
|
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 sha256:05f9eac2d6750bafebae530b6d14aa76840edab22f64608237330bd39305bbe3
|
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 sha256:565f756026e62a90ad9bd944389e34a3d21c75abeddfd67a24d557af86e497f2
|
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,
|
@@ -132,11 +132,32 @@
|
|
132 |
"eval_steps_per_second": 0.152,
|
133 |
"eval_wer": 28.481108694552624,
|
134 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
135 |
}
|
136 |
],
|
137 |
"max_steps": 10000,
|
138 |
"num_train_epochs": 26,
|
139 |
-
"total_flos":
|
140 |
"trial_name": null,
|
141 |
"trial_params": null
|
142 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 28.157402255829243,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-2000",
|
4 |
+
"epoch": 8.928571428571429,
|
5 |
+
"global_step": 3500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
132 |
"eval_steps_per_second": 0.152,
|
133 |
"eval_wer": 28.481108694552624,
|
134 |
"step": 3000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 8.29,
|
138 |
+
"learning_rate": 7.110526315789474e-06,
|
139 |
+
"loss": 0.0869,
|
140 |
+
"step": 3250
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 8.93,
|
144 |
+
"learning_rate": 6.8473684210526325e-06,
|
145 |
+
"loss": 0.0767,
|
146 |
+
"step": 3500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 8.93,
|
150 |
+
"eval_loss": 0.671624481678009,
|
151 |
+
"eval_runtime": 290.9537,
|
152 |
+
"eval_samples_per_second": 4.74,
|
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": 6.45392389275648e+19,
|
161 |
"trial_name": null,
|
162 |
"trial_params": null
|
163 |
}
|
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 sha256:8e2ae203ed801800c54c0fab6d45f9aa50a30f1a0d287de7a24ea1a6ed71cdb9
|
3 |
size 967102601
|