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 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:949dcbd30a0242483bafa481a73b675e0ffab3ce21b1088d2de31b5515edcf1a
|
3 |
size 640009682
|
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:ab524e2cd1b1a2d6449dcf038d3afe70a3349facb318e5b100f1cadb499c218c
|
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 sha256:225a4dbea8af85c08295c8025672889509a6661a67eb37b774d84e7d93737d97
|
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 sha256:55678e6b83acfcd4119c6e266d4afb16770a1c5a86005441c95f5ef62afde59a
|
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:f7953ae17275d0f82ad8343f3b36cae9dc118fff1d00d1aa7e7ac47c774d59ff
|
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 sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
|
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": 16.385,
|
199 |
"eval_steps_per_second": 4.26,
|
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": 0.08278145695364239,
|
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": 16.385,
|
199 |
"eval_steps_per_second": 4.26,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.04304635761589404,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 5.500000000000001e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.04470198675496689,
|
211 |
+
"grad_norm": NaN,
|
212 |
+
"learning_rate": 5.205685918464356e-05,
|
213 |
+
"loss": 0.0,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.046357615894039736,
|
218 |
+
"grad_norm": NaN,
|
219 |
+
"learning_rate": 4.912632135009769e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.048013245033112585,
|
225 |
+
"grad_norm": NaN,
|
226 |
+
"learning_rate": 4.6220935509274235e-05,
|
227 |
+
"loss": 0.0,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.04966887417218543,
|
232 |
+
"grad_norm": NaN,
|
233 |
+
"learning_rate": 4.3353142970386564e-05,
|
234 |
+
"loss": 0.0,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.05132450331125828,
|
239 |
+
"grad_norm": NaN,
|
240 |
+
"learning_rate": 4.053522406135775e-05,
|
241 |
+
"loss": 0.0,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.052980132450331126,
|
246 |
+
"grad_norm": NaN,
|
247 |
+
"learning_rate": 3.777924554357096e-05,
|
248 |
+
"loss": 0.0,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.054635761589403975,
|
253 |
+
"grad_norm": NaN,
|
254 |
+
"learning_rate": 3.509700894014496e-05,
|
255 |
+
"loss": 0.0,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.056291390728476824,
|
260 |
+
"grad_norm": NaN,
|
261 |
+
"learning_rate": 3.250000000000001e-05,
|
262 |
+
"loss": 0.0,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.057947019867549666,
|
267 |
+
"grad_norm": NaN,
|
268 |
+
"learning_rate": 2.9999339514117912e-05,
|
269 |
+
"loss": 0.0,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.059602649006622516,
|
274 |
+
"grad_norm": NaN,
|
275 |
+
"learning_rate": 2.760573569460757e-05,
|
276 |
+
"loss": 0.0,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.061258278145695365,
|
281 |
+
"grad_norm": NaN,
|
282 |
+
"learning_rate": 2.53294383204969e-05,
|
283 |
+
"loss": 0.0,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.06291390728476821,
|
288 |
+
"grad_norm": NaN,
|
289 |
+
"learning_rate": 2.3180194846605367e-05,
|
290 |
+
"loss": 0.0,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.06456953642384106,
|
295 |
+
"grad_norm": NaN,
|
296 |
+
"learning_rate": 2.1167208663446025e-05,
|
297 |
+
"loss": 0.0,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.06622516556291391,
|
302 |
+
"grad_norm": NaN,
|
303 |
+
"learning_rate": 1.9299099686894423e-05,
|
304 |
+
"loss": 0.0,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.06788079470198675,
|
309 |
+
"grad_norm": NaN,
|
310 |
+
"learning_rate": 1.758386744638546e-05,
|
311 |
+
"loss": 0.0,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.0695364238410596,
|
316 |
+
"grad_norm": NaN,
|
317 |
+
"learning_rate": 1.602885682970026e-05,
|
318 |
+
"loss": 0.0,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.07119205298013245,
|
323 |
+
"grad_norm": NaN,
|
324 |
+
"learning_rate": 1.464072663102903e-05,
|
325 |
+
"loss": 0.0,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.0728476821192053,
|
330 |
+
"grad_norm": NaN,
|
331 |
+
"learning_rate": 1.3425421036992098e-05,
|
332 |
+
"loss": 0.0,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.07450331125827815,
|
337 |
+
"grad_norm": NaN,
|
338 |
+
"learning_rate": 1.2388144172720251e-05,
|
339 |
+
"loss": 0.0,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.076158940397351,
|
344 |
+
"grad_norm": NaN,
|
345 |
+
"learning_rate": 1.1533337816991932e-05,
|
346 |
+
"loss": 0.0,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.07781456953642384,
|
351 |
+
"grad_norm": NaN,
|
352 |
+
"learning_rate": 1.0864662381854632e-05,
|
353 |
+
"loss": 0.0,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.07947019867549669,
|
358 |
+
"grad_norm": NaN,
|
359 |
+
"learning_rate": 1.0384981238178534e-05,
|
360 |
+
"loss": 0.0,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.08112582781456953,
|
365 |
+
"grad_norm": NaN,
|
366 |
+
"learning_rate": 1.0096348454262845e-05,
|
367 |
+
"loss": 0.0,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.08278145695364239,
|
372 |
+
"grad_norm": NaN,
|
373 |
+
"learning_rate": 1e-05,
|
374 |
+
"loss": 0.0,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.08278145695364239,
|
379 |
+
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 3.0462,
|
381 |
+
"eval_samples_per_second": 16.414,
|
382 |
+
"eval_steps_per_second": 4.268,
|
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": 5.2640867875710566e+17,
|
413 |
"train_batch_size": 2,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|