Training in progress, step 30, 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 50624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d194b2f665e442bb00b11490c0edf1a28ada39517ca0bccda6e160fbdf0b424
|
3 |
size 50624
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 111142
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4385a46b9189b97f4df02efacc679455dd021f37e162ebbe9c3e1d35b72d299
|
3 |
size 111142
|
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 sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
|
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:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
|
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": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -207,6 +207,48 @@
|
|
207 |
"eval_samples_per_second": 179.407,
|
208 |
"eval_steps_per_second": 90.628,
|
209 |
"step": 24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
210 |
}
|
211 |
],
|
212 |
"logging_steps": 1,
|
@@ -221,12 +263,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos":
|
230 |
"train_batch_size": 2,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5223068552774756,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
207 |
"eval_samples_per_second": 179.407,
|
208 |
"eval_steps_per_second": 90.628,
|
209 |
"step": 24
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.4352557127312296,
|
213 |
+
"grad_norm": 0.05406927689909935,
|
214 |
+
"learning_rate": 1.4644660940672627e-05,
|
215 |
+
"loss": 11.762,
|
216 |
+
"step": 25
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.45266594124047876,
|
220 |
+
"grad_norm": 0.0536014661192894,
|
221 |
+
"learning_rate": 9.549150281252633e-06,
|
222 |
+
"loss": 11.7623,
|
223 |
+
"step": 26
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 0.470076169749728,
|
227 |
+
"grad_norm": 0.05207870528101921,
|
228 |
+
"learning_rate": 5.449673790581611e-06,
|
229 |
+
"loss": 11.7614,
|
230 |
+
"step": 27
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.48748639825897716,
|
234 |
+
"grad_norm": 0.05782800912857056,
|
235 |
+
"learning_rate": 2.4471741852423237e-06,
|
236 |
+
"loss": 11.7621,
|
237 |
+
"step": 28
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.5048966267682263,
|
241 |
+
"grad_norm": 0.05422654375433922,
|
242 |
+
"learning_rate": 6.15582970243117e-07,
|
243 |
+
"loss": 11.7636,
|
244 |
+
"step": 29
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 0.5223068552774756,
|
248 |
+
"grad_norm": 0.06374860554933548,
|
249 |
+
"learning_rate": 0.0,
|
250 |
+
"loss": 11.7614,
|
251 |
+
"step": 30
|
252 |
}
|
253 |
],
|
254 |
"logging_steps": 1,
|
|
|
263 |
"should_evaluate": false,
|
264 |
"should_log": false,
|
265 |
"should_save": true,
|
266 |
+
"should_training_stop": true
|
267 |
},
|
268 |
"attributes": {}
|
269 |
}
|
270 |
},
|
271 |
+
"total_flos": 48888010506240.0,
|
272 |
"train_batch_size": 2,
|
273 |
"trial_name": null,
|
274 |
"trial_params": null
|