Training in progress, step 63, 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 313820248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc5f824685ed837eb4c965f6a8702ea5f45371abc624b99e3278815a519e7c7
|
3 |
size 313820248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 159641092
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df9f26f72c76711da9bb1ee0824ea825c98a604250ee48a90f67c88e3ad4f8c5
|
3 |
size 159641092
|
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 sha256:955b7d659c2b79cbf43f60eb03c95e2c40c058e3741f341669014bfcc7840a0e
|
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:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
|
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": 9,
|
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": 27.586,
|
190 |
"eval_steps_per_second": 6.897,
|
191 |
"step": 54
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
@@ -208,7 +237,7 @@
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
-
"total_flos": 1.
|
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": 0.0024735710709973793,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 63,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"eval_samples_per_second": 27.586,
|
190 |
"eval_steps_per_second": 6.897,
|
191 |
"step": 54
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.0022379928737595338,
|
195 |
+
"grad_norm": 3.3493728551547974e-05,
|
196 |
+
"learning_rate": 4.6512176312793736e-05,
|
197 |
+
"loss": 0.0,
|
198 |
+
"step": 57
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.0023557819723784563,
|
202 |
+
"grad_norm": 3.4933964343508705e-05,
|
203 |
+
"learning_rate": 4.131759111665349e-05,
|
204 |
+
"loss": 0.0,
|
205 |
+
"step": 60
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.0024735710709973793,
|
209 |
+
"grad_norm": 2.990081520692911e-05,
|
210 |
+
"learning_rate": 3.6218132209150045e-05,
|
211 |
+
"loss": 0.0,
|
212 |
+
"step": 63
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.0024735710709973793,
|
216 |
+
"eval_loss": 0.0005307694664224982,
|
217 |
+
"eval_runtime": 777.489,
|
218 |
+
"eval_samples_per_second": 27.586,
|
219 |
+
"eval_steps_per_second": 6.897,
|
220 |
+
"step": 63
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 3,
|
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
+
"total_flos": 1.2759943102857216e+16,
|
241 |
"train_batch_size": 4,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|