Training in progress, step 50, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +189 -6
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100966336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aad3581afae582e654416cdf003a9e32ee7738950198523070cfa5645ec79b2
|
3 |
size 100966336
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 202110330
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebf1a35bd3343e200844e0f13de3b6048f343550e0f89f80341e671aa8601470
|
3 |
size 202110330
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aad882531c3ac30efbd7e842ca19eeba897913705570fb32d76a9a4a8fec29c
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1662496cd6ffaec72b4b8cef804faa1e67929afbe7b15711562fc3f949cb2a00
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ca4d575edd0326db6b3f538ee0ad65fcc25278e2a5c18bb0db7090e8c053883
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac46fff64956cb6d71a047476e3cf9662861b1cc8c2a4691c4a06c70501eb8b6
|
3 |
size 15024
|
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": 107.262,
|
199 |
"eval_steps_per_second": 13.604,
|
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": 0.029691379517316818,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 0.8221993833504625,
|
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": 107.262,
|
199 |
"eval_steps_per_second": 13.604,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.42754367934224047,
|
204 |
+
"grad_norm": 0.4967133402824402,
|
205 |
+
"learning_rate": 5e-05,
|
206 |
+
"loss": 0.0747,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.44398766700924974,
|
211 |
+
"grad_norm": 0.6573581099510193,
|
212 |
+
"learning_rate": 4.6729843538492847e-05,
|
213 |
+
"loss": 0.051,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.460431654676259,
|
218 |
+
"grad_norm": 0.7091865539550781,
|
219 |
+
"learning_rate": 4.347369038899744e-05,
|
220 |
+
"loss": 0.0283,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.47687564234326824,
|
225 |
+
"grad_norm": 0.353059321641922,
|
226 |
+
"learning_rate": 4.0245483899193595e-05,
|
227 |
+
"loss": 0.0551,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.4933196300102775,
|
232 |
+
"grad_norm": 0.40428224205970764,
|
233 |
+
"learning_rate": 3.705904774487396e-05,
|
234 |
+
"loss": 0.0467,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.5097636176772867,
|
239 |
+
"grad_norm": 0.38357752561569214,
|
240 |
+
"learning_rate": 3.392802673484193e-05,
|
241 |
+
"loss": 0.0407,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.526207605344296,
|
246 |
+
"grad_norm": 0.4076400697231293,
|
247 |
+
"learning_rate": 3.086582838174551e-05,
|
248 |
+
"loss": 0.0214,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.5426515930113053,
|
253 |
+
"grad_norm": 0.5312539935112,
|
254 |
+
"learning_rate": 2.7885565489049946e-05,
|
255 |
+
"loss": 0.0276,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.5590955806783144,
|
260 |
+
"grad_norm": 0.24239972233772278,
|
261 |
+
"learning_rate": 2.500000000000001e-05,
|
262 |
+
"loss": 0.0114,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.5755395683453237,
|
267 |
+
"grad_norm": 0.21986766159534454,
|
268 |
+
"learning_rate": 2.2221488349019903e-05,
|
269 |
+
"loss": 0.0108,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.591983556012333,
|
274 |
+
"grad_norm": 0.43781280517578125,
|
275 |
+
"learning_rate": 1.9561928549563968e-05,
|
276 |
+
"loss": 0.0552,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.6084275436793423,
|
281 |
+
"grad_norm": 0.503707766532898,
|
282 |
+
"learning_rate": 1.703270924499656e-05,
|
283 |
+
"loss": 0.045,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.6248715313463515,
|
288 |
+
"grad_norm": 0.5236077308654785,
|
289 |
+
"learning_rate": 1.4644660940672627e-05,
|
290 |
+
"loss": 0.027,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.6413155190133607,
|
295 |
+
"grad_norm": 0.5696163773536682,
|
296 |
+
"learning_rate": 1.2408009626051137e-05,
|
297 |
+
"loss": 0.0188,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.65775950668037,
|
302 |
+
"grad_norm": 0.5354735851287842,
|
303 |
+
"learning_rate": 1.0332332985438248e-05,
|
304 |
+
"loss": 0.0348,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.6742034943473793,
|
309 |
+
"grad_norm": 0.5729418396949768,
|
310 |
+
"learning_rate": 8.426519384872733e-06,
|
311 |
+
"loss": 0.0507,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.6906474820143885,
|
316 |
+
"grad_norm": 0.29594871401786804,
|
317 |
+
"learning_rate": 6.698729810778065e-06,
|
318 |
+
"loss": 0.0176,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.7070914696813977,
|
323 |
+
"grad_norm": 0.2777194678783417,
|
324 |
+
"learning_rate": 5.156362923365588e-06,
|
325 |
+
"loss": 0.0149,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.723535457348407,
|
330 |
+
"grad_norm": 0.5910176634788513,
|
331 |
+
"learning_rate": 3.8060233744356633e-06,
|
332 |
+
"loss": 0.0334,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.7399794450154162,
|
337 |
+
"grad_norm": 0.47184309363365173,
|
338 |
+
"learning_rate": 2.653493525244721e-06,
|
339 |
+
"loss": 0.0284,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.7564234326824255,
|
344 |
+
"grad_norm": 0.36582136154174805,
|
345 |
+
"learning_rate": 1.70370868554659e-06,
|
346 |
+
"loss": 0.0392,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.7728674203494348,
|
351 |
+
"grad_norm": 0.3152853548526764,
|
352 |
+
"learning_rate": 9.607359798384785e-07,
|
353 |
+
"loss": 0.0294,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.789311408016444,
|
358 |
+
"grad_norm": 0.25798124074935913,
|
359 |
+
"learning_rate": 4.277569313094809e-07,
|
360 |
+
"loss": 0.017,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.8057553956834532,
|
365 |
+
"grad_norm": 0.1165856271982193,
|
366 |
+
"learning_rate": 1.0705383806982606e-07,
|
367 |
+
"loss": 0.0048,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.8221993833504625,
|
372 |
+
"grad_norm": 0.3071959614753723,
|
373 |
+
"learning_rate": 0.0,
|
374 |
+
"loss": 0.0306,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.8221993833504625,
|
379 |
+
"eval_loss": 0.029691379517316818,
|
380 |
+
"eval_runtime": 3.8208,
|
381 |
+
"eval_samples_per_second": 107.309,
|
382 |
+
"eval_steps_per_second": 13.61,
|
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": 8.336768348717056e+16,
|
413 |
"train_batch_size": 2,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|