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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09c315f50b22f72dd14cba2058fe33721bf21668ba86eb591bd3ac36c9d62b32
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168149074
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5706597b330e90541512aede454908ec2b68248e9b4ce53e5319deaf4b4c3be1
|
3 |
size 168149074
|
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:d3e077675f66773a81cbf019fe747215a64463738c7179426c26ea0177d7f67d
|
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:baae720e33260fead254c87141d85e241b839ae924033bfd9652fb777f3f1bf0
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -187,6 +187,92 @@
|
|
187 |
"eval_samples_per_second": 9.697,
|
188 |
"eval_steps_per_second": 4.849,
|
189 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
190 |
}
|
191 |
],
|
192 |
"logging_steps": 1,
|
@@ -206,7 +292,7 @@
|
|
206 |
"attributes": {}
|
207 |
}
|
208 |
},
|
209 |
-
"total_flos":
|
210 |
"train_batch_size": 2,
|
211 |
"trial_name": null,
|
212 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0005081612819215272,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
187 |
"eval_samples_per_second": 9.697,
|
188 |
"eval_steps_per_second": 4.849,
|
189 |
"step": 20
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.000355712897345069,
|
193 |
+
"grad_norm": 17.683870315551758,
|
194 |
+
"learning_rate": 0.00016494480483301836,
|
195 |
+
"loss": 17.1021,
|
196 |
+
"step": 21
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.00037265160674245326,
|
200 |
+
"grad_norm": 18.684045791625977,
|
201 |
+
"learning_rate": 0.00015877852522924732,
|
202 |
+
"loss": 15.9178,
|
203 |
+
"step": 22
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.0003895903161398375,
|
207 |
+
"grad_norm": 20.173887252807617,
|
208 |
+
"learning_rate": 0.0001522498564715949,
|
209 |
+
"loss": 17.3176,
|
210 |
+
"step": 23
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 0.00040652902553722173,
|
214 |
+
"grad_norm": 19.331239700317383,
|
215 |
+
"learning_rate": 0.00014539904997395468,
|
216 |
+
"loss": 16.0941,
|
217 |
+
"step": 24
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.000423467734934606,
|
221 |
+
"grad_norm": 19.496095657348633,
|
222 |
+
"learning_rate": 0.000138268343236509,
|
223 |
+
"loss": 15.8816,
|
224 |
+
"step": 25
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.000423467734934606,
|
228 |
+
"eval_loss": 2.0629289150238037,
|
229 |
+
"eval_runtime": 5134.9215,
|
230 |
+
"eval_samples_per_second": 9.682,
|
231 |
+
"eval_steps_per_second": 4.841,
|
232 |
+
"step": 25
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.0004404064443319902,
|
236 |
+
"grad_norm": 33.5986213684082,
|
237 |
+
"learning_rate": 0.00013090169943749476,
|
238 |
+
"loss": 15.7073,
|
239 |
+
"step": 26
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.00045734515372937445,
|
243 |
+
"grad_norm": 16.573434829711914,
|
244 |
+
"learning_rate": 0.00012334453638559057,
|
245 |
+
"loss": 14.8196,
|
246 |
+
"step": 27
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 0.0004742838631267587,
|
250 |
+
"grad_norm": 20.38245391845703,
|
251 |
+
"learning_rate": 0.0001156434465040231,
|
252 |
+
"loss": 16.6963,
|
253 |
+
"step": 28
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 0.0004912225725241429,
|
257 |
+
"grad_norm": 16.84417724609375,
|
258 |
+
"learning_rate": 0.0001078459095727845,
|
259 |
+
"loss": 16.4005,
|
260 |
+
"step": 29
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.0005081612819215272,
|
264 |
+
"grad_norm": 20.52333641052246,
|
265 |
+
"learning_rate": 0.0001,
|
266 |
+
"loss": 15.0153,
|
267 |
+
"step": 30
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.0005081612819215272,
|
271 |
+
"eval_loss": 2.041257858276367,
|
272 |
+
"eval_runtime": 5138.2338,
|
273 |
+
"eval_samples_per_second": 9.676,
|
274 |
+
"eval_steps_per_second": 4.838,
|
275 |
+
"step": 30
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 1,
|
|
|
292 |
"attributes": {}
|
293 |
}
|
294 |
},
|
295 |
+
"total_flos": 4.206407486275584e+16,
|
296 |
"train_batch_size": 2,
|
297 |
"trial_name": null,
|
298 |
"trial_params": null
|