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 70430032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b743c8b02459433701996d3fea8395707450581713e984a337e0e8baefa6afb
|
3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 141053442
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bda138f438bbf17d2268b6eb56a016e98c5ebbf75ff631ba8aea287a46a974f
|
3 |
size 141053442
|
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 sha256:46342187f4dc75c9e6c39a7b1878f43e0ec716b87dd40a756912014fb7ab4fe0
|
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 sha256:465716345b10469c5253861a2558865d7131ff7c526453a498941870d32e3baa
|
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 sha256:8647dbf034b9ef56d9c9724cba9f0dc9efe2ec86060c11c290af874fcb737722
|
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 sha256:2528df0f1c0d578da727283d5c1a0808f95ecc1dbeefb25dcf5ab37d8b6f0256
|
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": 3.
|
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": 147.295,
|
199 |
"eval_steps_per_second": 18.466,
|
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": 3.218653678894043,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 0.1983635011157947,
|
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": 147.295,
|
199 |
"eval_steps_per_second": 18.466,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.10314902058021325,
|
204 |
+
"grad_norm": 1.0147478580474854,
|
205 |
+
"learning_rate": 5e-05,
|
206 |
+
"loss": 3.2645,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.10711629060252914,
|
211 |
+
"grad_norm": 1.2164422273635864,
|
212 |
+
"learning_rate": 4.6729843538492847e-05,
|
213 |
+
"loss": 3.1775,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.11108356062484503,
|
218 |
+
"grad_norm": 1.3750309944152832,
|
219 |
+
"learning_rate": 4.347369038899744e-05,
|
220 |
+
"loss": 3.2619,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.11505083064716093,
|
225 |
+
"grad_norm": 1.3229867219924927,
|
226 |
+
"learning_rate": 4.0245483899193595e-05,
|
227 |
+
"loss": 3.2809,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.11901810066947682,
|
232 |
+
"grad_norm": 1.0716197490692139,
|
233 |
+
"learning_rate": 3.705904774487396e-05,
|
234 |
+
"loss": 3.2646,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.12298537069179272,
|
239 |
+
"grad_norm": 0.9642243385314941,
|
240 |
+
"learning_rate": 3.392802673484193e-05,
|
241 |
+
"loss": 3.2412,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.1269526407141086,
|
246 |
+
"grad_norm": 0.8288385272026062,
|
247 |
+
"learning_rate": 3.086582838174551e-05,
|
248 |
+
"loss": 3.2419,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1309199107364245,
|
253 |
+
"grad_norm": 0.8620959520339966,
|
254 |
+
"learning_rate": 2.7885565489049946e-05,
|
255 |
+
"loss": 3.3797,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.1348871807587404,
|
260 |
+
"grad_norm": 0.8693250417709351,
|
261 |
+
"learning_rate": 2.500000000000001e-05,
|
262 |
+
"loss": 3.218,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.1388544507810563,
|
267 |
+
"grad_norm": 0.9725481271743774,
|
268 |
+
"learning_rate": 2.2221488349019903e-05,
|
269 |
+
"loss": 3.2733,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.1428217208033722,
|
274 |
+
"grad_norm": 0.9870604276657104,
|
275 |
+
"learning_rate": 1.9561928549563968e-05,
|
276 |
+
"loss": 3.2407,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.14678899082568808,
|
281 |
+
"grad_norm": 1.25055992603302,
|
282 |
+
"learning_rate": 1.703270924499656e-05,
|
283 |
+
"loss": 3.301,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.15075626084800398,
|
288 |
+
"grad_norm": 0.8020516633987427,
|
289 |
+
"learning_rate": 1.4644660940672627e-05,
|
290 |
+
"loss": 3.2486,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.15472353087031987,
|
295 |
+
"grad_norm": 0.6509931087493896,
|
296 |
+
"learning_rate": 1.2408009626051137e-05,
|
297 |
+
"loss": 3.2495,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.15869080089263576,
|
302 |
+
"grad_norm": 0.6136582493782043,
|
303 |
+
"learning_rate": 1.0332332985438248e-05,
|
304 |
+
"loss": 3.2264,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.16265807091495166,
|
309 |
+
"grad_norm": 0.575463056564331,
|
310 |
+
"learning_rate": 8.426519384872733e-06,
|
311 |
+
"loss": 3.1638,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.16662534093726755,
|
316 |
+
"grad_norm": 0.5796473026275635,
|
317 |
+
"learning_rate": 6.698729810778065e-06,
|
318 |
+
"loss": 3.2206,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.17059261095958345,
|
323 |
+
"grad_norm": 0.6185922622680664,
|
324 |
+
"learning_rate": 5.156362923365588e-06,
|
325 |
+
"loss": 3.2557,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.17455988098189934,
|
330 |
+
"grad_norm": 0.648368239402771,
|
331 |
+
"learning_rate": 3.8060233744356633e-06,
|
332 |
+
"loss": 3.2409,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.17852715100421523,
|
337 |
+
"grad_norm": 0.7235672473907471,
|
338 |
+
"learning_rate": 2.653493525244721e-06,
|
339 |
+
"loss": 3.2006,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.18249442102653113,
|
344 |
+
"grad_norm": 0.8252574801445007,
|
345 |
+
"learning_rate": 1.70370868554659e-06,
|
346 |
+
"loss": 3.2917,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.18646169104884702,
|
351 |
+
"grad_norm": 0.9163631796836853,
|
352 |
+
"learning_rate": 9.607359798384785e-07,
|
353 |
+
"loss": 3.2976,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.19042896107116292,
|
358 |
+
"grad_norm": 0.9612374901771545,
|
359 |
+
"learning_rate": 4.277569313094809e-07,
|
360 |
+
"loss": 3.1845,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.1943962310934788,
|
365 |
+
"grad_norm": 1.0789424180984497,
|
366 |
+
"learning_rate": 1.0705383806982606e-07,
|
367 |
+
"loss": 3.1664,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.1983635011157947,
|
372 |
+
"grad_norm": 1.5217560529708862,
|
373 |
+
"learning_rate": 0.0,
|
374 |
+
"loss": 3.2755,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.1983635011157947,
|
379 |
+
"eval_loss": 3.218653678894043,
|
380 |
+
"eval_runtime": 11.5312,
|
381 |
+
"eval_samples_per_second": 147.339,
|
382 |
+
"eval_steps_per_second": 18.472,
|
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": 2.95300912644096e+16,
|
413 |
"train_batch_size": 2,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|