Training in progress, epoch 12, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 30026872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c38ef6ff821f73509cf96cb6d570b574a556c60551e1a3fd64d3062032c66ef1
|
3 |
size 30026872
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 60252034
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27210ffee9c882ecee501679082f3633d3297bc1de0bb800dadc3eea8a8cafe8
|
3 |
size 60252034
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12603df9abfa498776dd4507dacec9d6818946d74ccd08dae235342b9b938e6f
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18a3d3963bcbd050078a2c68d817121cba1d8d2caa3515782b9d593a8cf72958
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -196,6 +196,20 @@
|
|
196 |
"learning_rate": 0.0002,
|
197 |
"loss": 0.2066,
|
198 |
"step": 2700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
199 |
}
|
200 |
],
|
201 |
"logging_steps": 100,
|
@@ -215,7 +229,7 @@
|
|
215 |
"attributes": {}
|
216 |
}
|
217 |
},
|
218 |
-
"total_flos": 4.
|
219 |
"train_batch_size": 4,
|
220 |
"trial_name": null,
|
221 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 12.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2977,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
196 |
"learning_rate": 0.0002,
|
197 |
"loss": 0.2066,
|
198 |
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 11.287726358148893,
|
202 |
+
"grad_norm": 0.4034820795059204,
|
203 |
+
"learning_rate": 0.0002,
|
204 |
+
"loss": 0.1857,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 11.690140845070422,
|
209 |
+
"grad_norm": 0.44169268012046814,
|
210 |
+
"learning_rate": 0.0002,
|
211 |
+
"loss": 0.1859,
|
212 |
+
"step": 2900
|
213 |
}
|
214 |
],
|
215 |
"logging_steps": 100,
|
|
|
229 |
"attributes": {}
|
230 |
}
|
231 |
},
|
232 |
+
"total_flos": 4.486806508582994e+17,
|
233 |
"train_batch_size": 4,
|
234 |
"trial_name": null,
|
235 |
"trial_params": null
|