Training in progress, step 27, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b3aef5f7bbcd9920fd5b3336513c8e8c5a96285b44f517ca1fe6d7e1f3b3ea0
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aad703a1f2470ac39e533521f6cd1918de2b3bc35d18c817539d2acb00be10a3
|
3 |
size 37430836
|
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 sha256:16b8426212eb3c43a98136460d3e2b3d2934754032d2fec5901339eefa073550
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -189,6 +189,13 @@
|
|
189 |
"learning_rate": 5.2000000000000004e-05,
|
190 |
"loss": 1.6733,
|
191 |
"step": 26
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 1,
|
@@ -208,7 +215,7 @@
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
-
"total_flos": 3.
|
212 |
"train_batch_size": 4,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07407407407407407,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 27,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"learning_rate": 5.2000000000000004e-05,
|
190 |
"loss": 1.6733,
|
191 |
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.07407407407407407,
|
195 |
+
"grad_norm": 0.4196024239063263,
|
196 |
+
"learning_rate": 5.4000000000000005e-05,
|
197 |
+
"loss": 1.6999,
|
198 |
+
"step": 27
|
199 |
}
|
200 |
],
|
201 |
"logging_steps": 1,
|
|
|
215 |
"attributes": {}
|
216 |
}
|
217 |
},
|
218 |
+
"total_flos": 3.3600484746940416e+16,
|
219 |
"train_batch_size": 4,
|
220 |
"trial_name": null,
|
221 |
"trial_params": null
|