Training in progress, step 39, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18810036
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f9cda1f22207af92b948d52198d50ebccf16400377369fabbe3eaa0d48c3d26
|
3 |
size 18810036
|
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 sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
|
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 sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -213,6 +213,105 @@
|
|
213 |
"eval_samples_per_second": 23.284,
|
214 |
"eval_steps_per_second": 11.652,
|
215 |
"step": 26
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 1,
|
@@ -232,7 +331,7 @@
|
|
232 |
"attributes": {}
|
233 |
}
|
234 |
},
|
235 |
-
"total_flos":
|
236 |
"train_batch_size": 2,
|
237 |
"trial_name": null,
|
238 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05747973470891673,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
213 |
"eval_samples_per_second": 23.284,
|
214 |
"eval_steps_per_second": 11.652,
|
215 |
"step": 26
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.0397936624907885,
|
219 |
+
"grad_norm": NaN,
|
220 |
+
"learning_rate": 6.167226819279528e-05,
|
221 |
+
"loss": 0.0,
|
222 |
+
"step": 27
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 0.04126750184229919,
|
226 |
+
"grad_norm": NaN,
|
227 |
+
"learning_rate": 5.782172325201155e-05,
|
228 |
+
"loss": 0.0,
|
229 |
+
"step": 28
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.04274134119380987,
|
233 |
+
"grad_norm": NaN,
|
234 |
+
"learning_rate": 5.392295478639225e-05,
|
235 |
+
"loss": 0.0,
|
236 |
+
"step": 29
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.04421518054532056,
|
240 |
+
"grad_norm": NaN,
|
241 |
+
"learning_rate": 5e-05,
|
242 |
+
"loss": 0.0,
|
243 |
+
"step": 30
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.045689019896831246,
|
247 |
+
"grad_norm": NaN,
|
248 |
+
"learning_rate": 4.607704521360776e-05,
|
249 |
+
"loss": 0.0,
|
250 |
+
"step": 31
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.04716285924834193,
|
254 |
+
"grad_norm": NaN,
|
255 |
+
"learning_rate": 4.2178276747988446e-05,
|
256 |
+
"loss": 0.0,
|
257 |
+
"step": 32
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.04863669859985262,
|
261 |
+
"grad_norm": NaN,
|
262 |
+
"learning_rate": 3.832773180720475e-05,
|
263 |
+
"loss": 0.0,
|
264 |
+
"step": 33
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.050110537951363304,
|
268 |
+
"grad_norm": NaN,
|
269 |
+
"learning_rate": 3.4549150281252636e-05,
|
270 |
+
"loss": 0.0,
|
271 |
+
"step": 34
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.051584377302873984,
|
275 |
+
"grad_norm": NaN,
|
276 |
+
"learning_rate": 3.086582838174551e-05,
|
277 |
+
"loss": 0.0,
|
278 |
+
"step": 35
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.05305821665438467,
|
282 |
+
"grad_norm": NaN,
|
283 |
+
"learning_rate": 2.7300475013022663e-05,
|
284 |
+
"loss": 0.0,
|
285 |
+
"step": 36
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.054532056005895356,
|
289 |
+
"grad_norm": NaN,
|
290 |
+
"learning_rate": 2.3875071764202563e-05,
|
291 |
+
"loss": 0.0,
|
292 |
+
"step": 37
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.05600589535740604,
|
296 |
+
"grad_norm": NaN,
|
297 |
+
"learning_rate": 2.061073738537635e-05,
|
298 |
+
"loss": 0.0,
|
299 |
+
"step": 38
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.05747973470891673,
|
303 |
+
"grad_norm": NaN,
|
304 |
+
"learning_rate": 1.7527597583490822e-05,
|
305 |
+
"loss": 0.0,
|
306 |
+
"step": 39
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.05747973470891673,
|
310 |
+
"eval_loss": NaN,
|
311 |
+
"eval_runtime": 49.1161,
|
312 |
+
"eval_samples_per_second": 23.271,
|
313 |
+
"eval_steps_per_second": 11.646,
|
314 |
+
"step": 39
|
315 |
}
|
316 |
],
|
317 |
"logging_steps": 1,
|
|
|
331 |
"attributes": {}
|
332 |
}
|
333 |
},
|
334 |
+
"total_flos": 1.22562231140352e+16,
|
335 |
"train_batch_size": 2,
|
336 |
"trial_name": null,
|
337 |
"trial_params": null
|