Training in progress, step 50, 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 295765866
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b79d4ed598dc28a533adcfa8d039d4417f423af7f8b6826497f753633419dcf
|
3 |
size 295765866
|
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 sha256:4d8341a825bf0edd9f889e77623e76ae014e8d3e338d982f7ac89e24819ecf32
|
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 sha256:56cf34333972924bf577a960017f1290a0ecd7ae4a3003849fa5d5ca556c376f
|
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 sha256:17a87868050e48342af3d49219faf168c224cdf43cb20cfc6f36d74ee212a285
|
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:d466cdb98371ff73d7ee0213c2b73aa21b25dd671bfc67c95b1fd0800e14a387
|
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:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
-
"epoch":
|
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": 21.974,
|
199 |
"eval_steps_per_second": 5.713,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -212,7 +395,7 @@
|
|
212 |
"early_stopping_threshold": 0.0
|
213 |
},
|
214 |
"attributes": {
|
215 |
-
"early_stopping_patience_counter":
|
216 |
}
|
217 |
},
|
218 |
"TrainerControl": {
|
@@ -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": 1,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 1.8384879725085912,
|
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": 21.974,
|
199 |
"eval_steps_per_second": 5.713,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.9530355097365406,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 7.917848237560709e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.9896907216494846,
|
211 |
+
"grad_norm": NaN,
|
212 |
+
"learning_rate": 7.75e-05,
|
213 |
+
"loss": 0.0,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.0320733104238258,
|
218 |
+
"grad_norm": NaN,
|
219 |
+
"learning_rate": 7.577868759557654e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.0687285223367697,
|
225 |
+
"grad_norm": NaN,
|
226 |
+
"learning_rate": 7.401782177833148e-05,
|
227 |
+
"loss": 0.0,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 1.1053837342497137,
|
232 |
+
"grad_norm": NaN,
|
233 |
+
"learning_rate": 7.222075445642904e-05,
|
234 |
+
"loss": 0.0,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 1.1420389461626574,
|
239 |
+
"grad_norm": NaN,
|
240 |
+
"learning_rate": 7.03909064496551e-05,
|
241 |
+
"loss": 0.0,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.1786941580756014,
|
246 |
+
"grad_norm": NaN,
|
247 |
+
"learning_rate": 6.853176097769229e-05,
|
248 |
+
"loss": 0.0,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.2153493699885454,
|
253 |
+
"grad_norm": NaN,
|
254 |
+
"learning_rate": 6.664685702961344e-05,
|
255 |
+
"loss": 0.0,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.252004581901489,
|
260 |
+
"grad_norm": NaN,
|
261 |
+
"learning_rate": 6.473978262721463e-05,
|
262 |
+
"loss": 0.0,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.2886597938144329,
|
267 |
+
"grad_norm": NaN,
|
268 |
+
"learning_rate": 6.281416799501188e-05,
|
269 |
+
"loss": 0.0,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 1.3253150057273768,
|
274 |
+
"grad_norm": NaN,
|
275 |
+
"learning_rate": 6.087367864990233e-05,
|
276 |
+
"loss": 0.0,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 1.3619702176403208,
|
281 |
+
"grad_norm": NaN,
|
282 |
+
"learning_rate": 5.8922008423644624e-05,
|
283 |
+
"loss": 0.0,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.3986254295532645,
|
288 |
+
"grad_norm": NaN,
|
289 |
+
"learning_rate": 5.696287243144013e-05,
|
290 |
+
"loss": 0.0,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 1.4352806414662085,
|
295 |
+
"grad_norm": NaN,
|
296 |
+
"learning_rate": 5.500000000000001e-05,
|
297 |
+
"loss": 0.0,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 1.4719358533791524,
|
302 |
+
"grad_norm": NaN,
|
303 |
+
"learning_rate": 5.303712756855988e-05,
|
304 |
+
"loss": 0.0,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 1.5085910652920962,
|
309 |
+
"grad_norm": NaN,
|
310 |
+
"learning_rate": 5.107799157635538e-05,
|
311 |
+
"loss": 0.0,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 1.54524627720504,
|
316 |
+
"grad_norm": NaN,
|
317 |
+
"learning_rate": 4.912632135009769e-05,
|
318 |
+
"loss": 0.0,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 1.5819014891179841,
|
323 |
+
"grad_norm": NaN,
|
324 |
+
"learning_rate": 4.718583200498814e-05,
|
325 |
+
"loss": 0.0,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.6185567010309279,
|
330 |
+
"grad_norm": NaN,
|
331 |
+
"learning_rate": 4.526021737278538e-05,
|
332 |
+
"loss": 0.0,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 1.6552119129438716,
|
337 |
+
"grad_norm": NaN,
|
338 |
+
"learning_rate": 4.3353142970386564e-05,
|
339 |
+
"loss": 0.0,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 1.6918671248568156,
|
344 |
+
"grad_norm": NaN,
|
345 |
+
"learning_rate": 4.146823902230772e-05,
|
346 |
+
"loss": 0.0,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 1.7285223367697595,
|
351 |
+
"grad_norm": NaN,
|
352 |
+
"learning_rate": 3.960909355034491e-05,
|
353 |
+
"loss": 0.0,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 1.7651775486827033,
|
358 |
+
"grad_norm": NaN,
|
359 |
+
"learning_rate": 3.777924554357096e-05,
|
360 |
+
"loss": 0.0,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 1.8018327605956472,
|
365 |
+
"grad_norm": NaN,
|
366 |
+
"learning_rate": 3.598217822166854e-05,
|
367 |
+
"loss": 0.0,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.8384879725085912,
|
372 |
+
"grad_norm": NaN,
|
373 |
+
"learning_rate": 3.422131240442349e-05,
|
374 |
+
"loss": 0.0,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 1.8384879725085912,
|
379 |
+
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 2.2499,
|
381 |
+
"eval_samples_per_second": 22.223,
|
382 |
+
"eval_steps_per_second": 5.778,
|
383 |
+
"step": 50
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
|
|
395 |
"early_stopping_threshold": 0.0
|
396 |
},
|
397 |
"attributes": {
|
398 |
+
"early_stopping_patience_counter": 1
|
399 |
}
|
400 |
},
|
401 |
"TrainerControl": {
|
|
|
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": 1.067151776504873e+17,
|
413 |
"train_batch_size": 1,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|