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 646253418
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:400636f1de12a1f7168eb6762fd9904f32785f8150a2cc3041d6060ca1b2dc94
|
3 |
size 646253418
|
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:a2d6aabc024a9071194ecaba16e168843a901ead25baec1294e2f84669278e88
|
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:eb74a0040f8ba9822b2c68449d73ed216e2062a54dd68c08c25cbf03157232fd
|
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:c0d974e2950b9a96052853a1cbadd24f05269641f39a01c0fae36387781a1099
|
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 sha256:6cc52cbab8dfb53f8f8377d2b4352ad997ec146176d3479eaeea19408fcf7136
|
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 sha256:27a06debcc524d5e29377ca1c81e86a2cd28c93506013f68ac7d1bf85491fb4e
|
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": 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": 35.756,
|
199 |
"eval_steps_per_second": 9.297,
|
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": 2,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 0.21551724137931033,
|
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": 35.756,
|
199 |
"eval_steps_per_second": 9.297,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.11206896551724138,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 8.883279133655399e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.11637931034482758,
|
211 |
+
"grad_norm": NaN,
|
212 |
+
"learning_rate": 8.78438832714026e-05,
|
213 |
+
"loss": 0.0,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.1206896551724138,
|
218 |
+
"grad_norm": NaN,
|
219 |
+
"learning_rate": 8.681980515339464e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.125,
|
225 |
+
"grad_norm": NaN,
|
226 |
+
"learning_rate": 8.57616535910292e-05,
|
227 |
+
"loss": 0.0,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.12931034482758622,
|
232 |
+
"grad_norm": NaN,
|
233 |
+
"learning_rate": 8.467056167950311e-05,
|
234 |
+
"loss": 0.0,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.1336206896551724,
|
239 |
+
"grad_norm": NaN,
|
240 |
+
"learning_rate": 8.354769778736406e-05,
|
241 |
+
"loss": 0.0,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.13793103448275862,
|
246 |
+
"grad_norm": NaN,
|
247 |
+
"learning_rate": 8.239426430539243e-05,
|
248 |
+
"loss": 0.0,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.14224137931034483,
|
253 |
+
"grad_norm": NaN,
|
254 |
+
"learning_rate": 8.12114963590511e-05,
|
255 |
+
"loss": 0.0,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.14655172413793102,
|
260 |
+
"grad_norm": NaN,
|
261 |
+
"learning_rate": 8.000066048588211e-05,
|
262 |
+
"loss": 0.0,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.15086206896551724,
|
267 |
+
"grad_norm": NaN,
|
268 |
+
"learning_rate": 7.876305327926657e-05,
|
269 |
+
"loss": 0.0,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.15517241379310345,
|
274 |
+
"grad_norm": NaN,
|
275 |
+
"learning_rate": 7.75e-05,
|
276 |
+
"loss": 0.0,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.15948275862068967,
|
281 |
+
"grad_norm": NaN,
|
282 |
+
"learning_rate": 7.62128531571699e-05,
|
283 |
+
"loss": 0.0,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.16379310344827586,
|
288 |
+
"grad_norm": NaN,
|
289 |
+
"learning_rate": 7.490299105985507e-05,
|
290 |
+
"loss": 0.0,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.16810344827586207,
|
295 |
+
"grad_norm": NaN,
|
296 |
+
"learning_rate": 7.357181634119777e-05,
|
297 |
+
"loss": 0.0,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.1724137931034483,
|
302 |
+
"grad_norm": NaN,
|
303 |
+
"learning_rate": 7.222075445642904e-05,
|
304 |
+
"loss": 0.0,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.17672413793103448,
|
309 |
+
"grad_norm": NaN,
|
310 |
+
"learning_rate": 7.085125215645552e-05,
|
311 |
+
"loss": 0.0,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.1810344827586207,
|
316 |
+
"grad_norm": NaN,
|
317 |
+
"learning_rate": 6.946477593864228e-05,
|
318 |
+
"loss": 0.0,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.1853448275862069,
|
323 |
+
"grad_norm": NaN,
|
324 |
+
"learning_rate": 6.80628104764508e-05,
|
325 |
+
"loss": 0.0,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.1896551724137931,
|
330 |
+
"grad_norm": NaN,
|
331 |
+
"learning_rate": 6.664685702961344e-05,
|
332 |
+
"loss": 0.0,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.1939655172413793,
|
337 |
+
"grad_norm": NaN,
|
338 |
+
"learning_rate": 6.52184318365468e-05,
|
339 |
+
"loss": 0.0,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.19827586206896552,
|
344 |
+
"grad_norm": NaN,
|
345 |
+
"learning_rate": 6.377906449072578e-05,
|
346 |
+
"loss": 0.0,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.2025862068965517,
|
351 |
+
"grad_norm": NaN,
|
352 |
+
"learning_rate": 6.23302963027565e-05,
|
353 |
+
"loss": 0.0,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.20689655172413793,
|
358 |
+
"grad_norm": NaN,
|
359 |
+
"learning_rate": 6.087367864990233e-05,
|
360 |
+
"loss": 0.0,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.21120689655172414,
|
365 |
+
"grad_norm": NaN,
|
366 |
+
"learning_rate": 5.941077131483025e-05,
|
367 |
+
"loss": 0.0,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.21551724137931033,
|
372 |
+
"grad_norm": NaN,
|
373 |
+
"learning_rate": 5.794314081535644e-05,
|
374 |
+
"loss": 0.0,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.21551724137931033,
|
379 |
+
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 1.3982,
|
381 |
+
"eval_samples_per_second": 35.76,
|
382 |
+
"eval_steps_per_second": 9.297,
|
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": 5.6275728548338074e+17,
|
413 |
"train_batch_size": 2,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|