Training in progress, step 21, 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 27024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:838106fb050e383c9bec891c171230c955ff7d45388c35d970a855d576327d0d
|
3 |
size 27024
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 70922
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb0d7d24ae3096c7701e4bef1a45e1d8b70c14bc79bb6ca1cf3106ac6fa1a7fe
|
3 |
size 70922
|
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 sha256:6b54d8e57ffc18ea0865542a8b90aa7d2794c67bc2df78595b0c6c1b3bc6975b
|
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:cfc868d168373f518aa3d81b0bcf5eaf44208e53fb25d46f5a39136146621a60
|
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": 0.
|
5 |
"eval_steps": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -189,6 +189,35 @@
|
|
189 |
"eval_samples_per_second": 135.412,
|
190 |
"eval_steps_per_second": 135.412,
|
191 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 1,
|
@@ -208,7 +237,7 @@
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
-
"total_flos":
|
212 |
"train_batch_size": 1,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0014885699096225413,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 21,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"eval_samples_per_second": 135.412,
|
190 |
"eval_steps_per_second": 135.412,
|
191 |
"step": 18
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.0013468013468013469,
|
195 |
+
"grad_norm": 0.0887003093957901,
|
196 |
+
"learning_rate": 6.909830056250527e-05,
|
197 |
+
"loss": 10.3812,
|
198 |
+
"step": 19
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.001417685628211944,
|
202 |
+
"grad_norm": 0.10247205197811127,
|
203 |
+
"learning_rate": 5.000000000000002e-05,
|
204 |
+
"loss": 10.3803,
|
205 |
+
"step": 20
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.0014885699096225413,
|
209 |
+
"grad_norm": 0.10386703908443451,
|
210 |
+
"learning_rate": 3.308693936411421e-05,
|
211 |
+
"loss": 10.3872,
|
212 |
+
"step": 21
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.0014885699096225413,
|
216 |
+
"eval_loss": 10.382221221923828,
|
217 |
+
"eval_runtime": 21.9648,
|
218 |
+
"eval_samples_per_second": 135.217,
|
219 |
+
"eval_steps_per_second": 135.217,
|
220 |
+
"step": 21
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 1,
|
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
+
"total_flos": 543098142720.0,
|
241 |
"train_batch_size": 1,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|