Training in progress, step 50, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a4dc31756b1ec3279719e01e3fe8b32bd098aeca78651343cca78c1dc7c7b34
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623b8a4121cff716dbbe9b77901594b53c5fc70885a1ba76f17fac1f3c9d20e4
|
3 |
size 335922386
|
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 sha256:7d602f002ceb4f1394ef501a72438705f77760c4d95a2f2377ec6a53bc6d1ce7
|
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:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -198,6 +198,189 @@
|
|
198 |
"eval_samples_per_second": 7.057,
|
199 |
"eval_steps_per_second": 3.544,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +404,12 @@
|
|
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": 0.10715995728969574,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 0.08956560680698612,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 7.057,
|
199 |
"eval_steps_per_second": 3.544,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.04657411553963278,
|
204 |
+
"grad_norm": 2.4748008251190186,
|
205 |
+
"learning_rate": 5e-05,
|
206 |
+
"loss": 0.2563,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.0483654276757725,
|
211 |
+
"grad_norm": 4.218332290649414,
|
212 |
+
"learning_rate": 4.6729843538492847e-05,
|
213 |
+
"loss": 0.4993,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.050156739811912224,
|
218 |
+
"grad_norm": 2.3692610263824463,
|
219 |
+
"learning_rate": 4.347369038899744e-05,
|
220 |
+
"loss": 0.235,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.05194805194805195,
|
225 |
+
"grad_norm": 3.3568317890167236,
|
226 |
+
"learning_rate": 4.0245483899193595e-05,
|
227 |
+
"loss": 0.3957,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.05373936408419167,
|
232 |
+
"grad_norm": 4.579010009765625,
|
233 |
+
"learning_rate": 3.705904774487396e-05,
|
234 |
+
"loss": 0.4771,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.05553067622033139,
|
239 |
+
"grad_norm": 3.82382869720459,
|
240 |
+
"learning_rate": 3.392802673484193e-05,
|
241 |
+
"loss": 0.2925,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.057321988356471114,
|
246 |
+
"grad_norm": 2.7304625511169434,
|
247 |
+
"learning_rate": 3.086582838174551e-05,
|
248 |
+
"loss": 0.2957,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.059113300492610835,
|
253 |
+
"grad_norm": 4.2830352783203125,
|
254 |
+
"learning_rate": 2.7885565489049946e-05,
|
255 |
+
"loss": 0.4469,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.06090461262875056,
|
260 |
+
"grad_norm": 2.769845724105835,
|
261 |
+
"learning_rate": 2.500000000000001e-05,
|
262 |
+
"loss": 0.4208,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.06269592476489028,
|
267 |
+
"grad_norm": 2.1712167263031006,
|
268 |
+
"learning_rate": 2.2221488349019903e-05,
|
269 |
+
"loss": 0.1889,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.06448723690103,
|
274 |
+
"grad_norm": 3.581455707550049,
|
275 |
+
"learning_rate": 1.9561928549563968e-05,
|
276 |
+
"loss": 0.3311,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.06627854903716973,
|
281 |
+
"grad_norm": 4.364194393157959,
|
282 |
+
"learning_rate": 1.703270924499656e-05,
|
283 |
+
"loss": 0.5934,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.06806986117330945,
|
288 |
+
"grad_norm": 2.803682565689087,
|
289 |
+
"learning_rate": 1.4644660940672627e-05,
|
290 |
+
"loss": 0.3943,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.06986117330944917,
|
295 |
+
"grad_norm": 3.7528460025787354,
|
296 |
+
"learning_rate": 1.2408009626051137e-05,
|
297 |
+
"loss": 0.4517,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.07165248544558889,
|
302 |
+
"grad_norm": 3.5302984714508057,
|
303 |
+
"learning_rate": 1.0332332985438248e-05,
|
304 |
+
"loss": 0.5168,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.07344379758172861,
|
309 |
+
"grad_norm": 5.849757194519043,
|
310 |
+
"learning_rate": 8.426519384872733e-06,
|
311 |
+
"loss": 0.6599,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.07523510971786834,
|
316 |
+
"grad_norm": 4.0423760414123535,
|
317 |
+
"learning_rate": 6.698729810778065e-06,
|
318 |
+
"loss": 0.5821,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.07702642185400806,
|
323 |
+
"grad_norm": 4.6589484214782715,
|
324 |
+
"learning_rate": 5.156362923365588e-06,
|
325 |
+
"loss": 0.6031,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.07881773399014778,
|
330 |
+
"grad_norm": 3.569039821624756,
|
331 |
+
"learning_rate": 3.8060233744356633e-06,
|
332 |
+
"loss": 0.5059,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.08060904612628751,
|
337 |
+
"grad_norm": 5.747331619262695,
|
338 |
+
"learning_rate": 2.653493525244721e-06,
|
339 |
+
"loss": 0.8897,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.08240035826242723,
|
344 |
+
"grad_norm": 5.7729363441467285,
|
345 |
+
"learning_rate": 1.70370868554659e-06,
|
346 |
+
"loss": 0.8777,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.08419167039856695,
|
351 |
+
"grad_norm": 5.641356945037842,
|
352 |
+
"learning_rate": 9.607359798384785e-07,
|
353 |
+
"loss": 0.9093,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.08598298253470667,
|
358 |
+
"grad_norm": 4.868679523468018,
|
359 |
+
"learning_rate": 4.277569313094809e-07,
|
360 |
+
"loss": 0.7942,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.0877742946708464,
|
365 |
+
"grad_norm": 6.637969493865967,
|
366 |
+
"learning_rate": 1.0705383806982606e-07,
|
367 |
+
"loss": 0.746,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.08956560680698612,
|
372 |
+
"grad_norm": 4.852217197418213,
|
373 |
+
"learning_rate": 0.0,
|
374 |
+
"loss": 0.4853,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.08956560680698612,
|
379 |
+
"eval_loss": 0.10715995728969574,
|
380 |
+
"eval_runtime": 33.3425,
|
381 |
+
"eval_samples_per_second": 7.048,
|
382 |
+
"eval_steps_per_second": 3.539,
|
383 |
+
"step": 50
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
|
|
404 |
"should_evaluate": false,
|
405 |
"should_log": false,
|
406 |
"should_save": true,
|
407 |
+
"should_training_stop": true
|
408 |
},
|
409 |
"attributes": {}
|
410 |
}
|
411 |
},
|
412 |
+
"total_flos": 3.51564749340672e+16,
|
413 |
"train_batch_size": 2,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|