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 400084608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5350d8e72b425180d98b8f5dfef792598915263fd55ce4923d0b43e19162bcbc
|
3 |
size 400084608
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 800394282
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52bf05ac3d9c61b34ec8f12e90972d3287097f25e00a7da72e988ca8609fc557
|
3 |
size 800394282
|
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 sha256:83140b979ee3fa53fe0358e62bbb225258af47af4d713ba13686c284fe6c1b16
|
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 sha256:48b3546366cea1175ea566c2f847a02d7284569e9f752f76e9e34a04be918f9e
|
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 sha256:7868df55a74f69b87bb923c58371ff9ca8bb2c69db917ecfe75f1339959b2ff9
|
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:a0b07962a90c556d75f13278a577df56a3d0dd3d5c037438711c1128bd7ea836
|
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": 1.
|
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": 21.595,
|
199 |
"eval_steps_per_second": 5.615,
|
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": 1.0213967561721802,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 0.6855184233076264,
|
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": 21.595,
|
199 |
"eval_steps_per_second": 5.615,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.3564695801199657,
|
204 |
+
"grad_norm": 0.3724190294742584,
|
205 |
+
"learning_rate": 5.500000000000001e-05,
|
206 |
+
"loss": 0.8609,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.37017994858611825,
|
211 |
+
"grad_norm": 0.3975992500782013,
|
212 |
+
"learning_rate": 5.205685918464356e-05,
|
213 |
+
"loss": 0.8236,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.3838903170522708,
|
218 |
+
"grad_norm": 0.4572630226612091,
|
219 |
+
"learning_rate": 4.912632135009769e-05,
|
220 |
+
"loss": 0.8765,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.3976006855184233,
|
225 |
+
"grad_norm": 0.5107871890068054,
|
226 |
+
"learning_rate": 4.6220935509274235e-05,
|
227 |
+
"loss": 0.8768,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.41131105398457585,
|
232 |
+
"grad_norm": 0.6196900606155396,
|
233 |
+
"learning_rate": 4.3353142970386564e-05,
|
234 |
+
"loss": 0.9245,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.4250214224507284,
|
239 |
+
"grad_norm": 0.6747974753379822,
|
240 |
+
"learning_rate": 4.053522406135775e-05,
|
241 |
+
"loss": 0.978,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.4387317909168809,
|
246 |
+
"grad_norm": 0.6937869191169739,
|
247 |
+
"learning_rate": 3.777924554357096e-05,
|
248 |
+
"loss": 0.935,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.4524421593830334,
|
253 |
+
"grad_norm": 0.7304213643074036,
|
254 |
+
"learning_rate": 3.509700894014496e-05,
|
255 |
+
"loss": 0.9434,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.4661525278491859,
|
260 |
+
"grad_norm": 0.8814483880996704,
|
261 |
+
"learning_rate": 3.250000000000001e-05,
|
262 |
+
"loss": 0.9642,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.47986289631533846,
|
267 |
+
"grad_norm": 1.1520628929138184,
|
268 |
+
"learning_rate": 2.9999339514117912e-05,
|
269 |
+
"loss": 0.9072,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.493573264781491,
|
274 |
+
"grad_norm": 1.8298850059509277,
|
275 |
+
"learning_rate": 2.760573569460757e-05,
|
276 |
+
"loss": 1.0162,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.5072836332476436,
|
281 |
+
"grad_norm": 1.9809646606445312,
|
282 |
+
"learning_rate": 2.53294383204969e-05,
|
283 |
+
"loss": 0.9673,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.5209940017137961,
|
288 |
+
"grad_norm": 0.39740994572639465,
|
289 |
+
"learning_rate": 2.3180194846605367e-05,
|
290 |
+
"loss": 0.9083,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.5347043701799485,
|
295 |
+
"grad_norm": 0.3018646240234375,
|
296 |
+
"learning_rate": 2.1167208663446025e-05,
|
297 |
+
"loss": 0.8195,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.5484147386461011,
|
302 |
+
"grad_norm": 0.3188331127166748,
|
303 |
+
"learning_rate": 1.9299099686894423e-05,
|
304 |
+
"loss": 0.7938,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.5621251071122536,
|
309 |
+
"grad_norm": 0.35798129439353943,
|
310 |
+
"learning_rate": 1.758386744638546e-05,
|
311 |
+
"loss": 0.849,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.5758354755784062,
|
316 |
+
"grad_norm": 0.4261307716369629,
|
317 |
+
"learning_rate": 1.602885682970026e-05,
|
318 |
+
"loss": 0.8968,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.5895458440445587,
|
323 |
+
"grad_norm": 0.4484318792819977,
|
324 |
+
"learning_rate": 1.464072663102903e-05,
|
325 |
+
"loss": 0.8825,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.6032562125107113,
|
330 |
+
"grad_norm": 0.5180601477622986,
|
331 |
+
"learning_rate": 1.3425421036992098e-05,
|
332 |
+
"loss": 0.91,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.6169665809768637,
|
337 |
+
"grad_norm": 0.621738851070404,
|
338 |
+
"learning_rate": 1.2388144172720251e-05,
|
339 |
+
"loss": 0.9466,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.6306769494430163,
|
344 |
+
"grad_norm": 0.6436194777488708,
|
345 |
+
"learning_rate": 1.1533337816991932e-05,
|
346 |
+
"loss": 0.9237,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.6443873179091688,
|
351 |
+
"grad_norm": 0.837110161781311,
|
352 |
+
"learning_rate": 1.0864662381854632e-05,
|
353 |
+
"loss": 0.9483,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.6580976863753213,
|
358 |
+
"grad_norm": 1.1074998378753662,
|
359 |
+
"learning_rate": 1.0384981238178534e-05,
|
360 |
+
"loss": 1.0255,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.6718080548414739,
|
365 |
+
"grad_norm": 1.4551877975463867,
|
366 |
+
"learning_rate": 1.0096348454262845e-05,
|
367 |
+
"loss": 1.0155,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.6855184233076264,
|
372 |
+
"grad_norm": 1.933646559715271,
|
373 |
+
"learning_rate": 1e-05,
|
374 |
+
"loss": 0.8422,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.6855184233076264,
|
379 |
+
"eval_loss": 1.0213967561721802,
|
380 |
+
"eval_runtime": 2.3124,
|
381 |
+
"eval_samples_per_second": 21.623,
|
382 |
+
"eval_steps_per_second": 5.622,
|
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": 6.174479344467968e+17,
|
413 |
"train_batch_size": 2,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|