mprzibilla
commited on
Commit
•
5c05f03
1
Parent(s):
04dd999
Training in progress, step 258000
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 +19 -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 168159
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac937a33dea6ea7a219a5d92302391d3b62c72a19f9ff5c54c2bed1c61cdffac
|
3 |
size 168159
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377641431
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:970781c36183b1552822b1fd90733e765d39fc56d7e083aa21858cc68f2befee
|
3 |
size 377641431
|
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 sha256:1bc4c868be43b8aee478444845fee509627b8673243a867ffa21afdae158b023
|
3 |
+
size 14567
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e7828115df4dda4d48eed4e47399971a9187269fd1c501ef2b68aaf29a23048
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3fd97d7f7086d7e8d98ca6ed02a950b267fc075dbd24b6b2d7d971d9f49782e
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -150,11 +150,27 @@
|
|
150 |
"eval_steps_per_second": 26.743,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 232200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 258000,
|
156 |
"num_train_epochs": 1000,
|
157 |
-
"total_flos": 2.
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1000.0,
|
5 |
+
"global_step": 258000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_steps_per_second": 26.743,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 232200
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1000.0,
|
156 |
+
"learning_rate": 4.569563443492452e-08,
|
157 |
+
"loss": 2.0195,
|
158 |
+
"step": 258000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1000.0,
|
162 |
+
"eval_cer": 0.8883116883116883,
|
163 |
+
"eval_loss": 2.979724645614624,
|
164 |
+
"eval_runtime": 0.9979,
|
165 |
+
"eval_samples_per_second": 210.433,
|
166 |
+
"eval_steps_per_second": 27.056,
|
167 |
+
"eval_wer": 1.0,
|
168 |
+
"step": 258000
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 258000,
|
172 |
"num_train_epochs": 1000,
|
173 |
+
"total_flos": 2.393792072555994e+20,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377641431
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:970781c36183b1552822b1fd90733e765d39fc56d7e083aa21858cc68f2befee
|
3 |
size 377641431
|