Dmitriy007
commited on
Commit
•
aa22b54
1
Parent(s):
989671e
Training in progress, step 10000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
- runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d43d75d9a69cab6bbdc5d807e2bb46ff6cdc4a8d041a08ec646f4a6e3cd2db85
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddbae1252128d10be81c8573c827bec76386fb0202a5c3196a13dad3d7c56f87
|
3 |
size 1524261149
|
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 sha256:4726f886967d0edea6aba4d768b4e7e6c5f2c77453e08bd258b36ebd6bbf0054
|
3 |
size 14575
|
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:d83ea694a86cc0c579d479f8a93d9e180abe564de49dd67c75124cdac727a14a
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -186,11 +186,31 @@
|
|
186 |
"eval_samples_per_second": 15.509,
|
187 |
"eval_steps_per_second": 5.172,
|
188 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
189 |
}
|
190 |
],
|
191 |
"max_steps": 19990,
|
192 |
"num_train_epochs": 5,
|
193 |
-
"total_flos": 1.
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
196 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.5012506253126565,
|
5 |
+
"global_step": 10000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
186 |
"eval_samples_per_second": 15.509,
|
187 |
"eval_steps_per_second": 5.172,
|
188 |
"step": 9000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.38,
|
192 |
+
"learning_rate": 1.0495247623811906e-05,
|
193 |
+
"loss": 2.6288,
|
194 |
+
"step": 9500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.5,
|
198 |
+
"learning_rate": 9.994997498749376e-06,
|
199 |
+
"loss": 2.6195,
|
200 |
+
"step": 10000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.5,
|
204 |
+
"eval_loss": 3.1362624168395996,
|
205 |
+
"eval_runtime": 136.2977,
|
206 |
+
"eval_samples_per_second": 15.532,
|
207 |
+
"eval_steps_per_second": 5.18,
|
208 |
+
"step": 10000
|
209 |
}
|
210 |
],
|
211 |
"max_steps": 19990,
|
212 |
"num_train_epochs": 5,
|
213 |
+
"total_flos": 1.41481746432e+16,
|
214 |
"trial_name": null,
|
215 |
"trial_params": null
|
216 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddbae1252128d10be81c8573c827bec76386fb0202a5c3196a13dad3d7c56f87
|
3 |
size 1524261149
|
runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2
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 sha256:51b3505aa1c3f58a43b4b0acb4829eae3e65a7712b622e74547c28cca297f34c
|
3 |
+
size 8878
|