Training in progress, step 47, 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 sha256:0de9a1bf7b799ae2f2c48c2c6fa00f515764c2565d92ff135da9f0b829791484
|
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 sha256:13add29bf25498748acd4521b7d4fd086e7450d6a0c7e9fbe36191d39591c223
|
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 sha256:0b05748380eecea64690226b69158578c5f8673354f998098b6b2a6427bb82b8
|
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 sha256:41d211acfce0004f0a5cb0b4193773e6cef221cfcd2a2aae1868494b3555637c
|
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 sha256:37a1f5ddc57acbb31c8c629a263d0d4f6cc0f287735cedd233c6ebba1288fbe7
|
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 sha256:35151b95c3cc502d9e4fc6d9dc99d112a424ad3624e33428ecbe517e837a6fc0
|
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 +198,160 @@
|
|
198 |
"eval_samples_per_second": 87.608,
|
199 |
"eval_steps_per_second": 11.681,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +375,12 @@
|
|
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": 3.1164658634538154,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 47,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 87.608,
|
199 |
"eval_steps_per_second": 11.681,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.7028112449799195,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 4.477357683661734e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.7670682730923695,
|
211 |
+
"grad_norm": NaN,
|
212 |
+
"learning_rate": 4.131759111665349e-05,
|
213 |
+
"loss": 0.0,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.8313253012048194,
|
218 |
+
"grad_norm": NaN,
|
219 |
+
"learning_rate": 3.790390522001662e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.895582329317269,
|
225 |
+
"grad_norm": NaN,
|
226 |
+
"learning_rate": 3.4549150281252636e-05,
|
227 |
+
"loss": 0.0,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 1.9598393574297188,
|
232 |
+
"grad_norm": NaN,
|
233 |
+
"learning_rate": 3.12696703292044e-05,
|
234 |
+
"loss": 0.0,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.0562248995983934,
|
239 |
+
"grad_norm": NaN,
|
240 |
+
"learning_rate": 2.8081442660546125e-05,
|
241 |
+
"loss": 0.0,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.1204819277108435,
|
246 |
+
"grad_norm": NaN,
|
247 |
+
"learning_rate": 2.500000000000001e-05,
|
248 |
+
"loss": 0.0,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.1847389558232932,
|
253 |
+
"grad_norm": NaN,
|
254 |
+
"learning_rate": 2.2040354826462668e-05,
|
255 |
+
"loss": 0.0,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 2.248995983935743,
|
260 |
+
"grad_norm": NaN,
|
261 |
+
"learning_rate": 1.9216926233717085e-05,
|
262 |
+
"loss": 0.0,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 2.3132530120481927,
|
267 |
+
"grad_norm": NaN,
|
268 |
+
"learning_rate": 1.6543469682057106e-05,
|
269 |
+
"loss": 0.0,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 2.3775100401606424,
|
274 |
+
"grad_norm": NaN,
|
275 |
+
"learning_rate": 1.4033009983067452e-05,
|
276 |
+
"loss": 0.0,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 2.4417670682730925,
|
281 |
+
"grad_norm": NaN,
|
282 |
+
"learning_rate": 1.1697777844051105e-05,
|
283 |
+
"loss": 0.0,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.5060240963855422,
|
288 |
+
"grad_norm": NaN,
|
289 |
+
"learning_rate": 9.549150281252633e-06,
|
290 |
+
"loss": 0.0,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 2.570281124497992,
|
295 |
+
"grad_norm": NaN,
|
296 |
+
"learning_rate": 7.597595192178702e-06,
|
297 |
+
"loss": 0.0,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 2.6345381526104417,
|
302 |
+
"grad_norm": NaN,
|
303 |
+
"learning_rate": 5.852620357053651e-06,
|
304 |
+
"loss": 0.0,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 2.6987951807228914,
|
309 |
+
"grad_norm": NaN,
|
310 |
+
"learning_rate": 4.322727117869951e-06,
|
311 |
+
"loss": 0.0,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 2.7630522088353415,
|
316 |
+
"grad_norm": NaN,
|
317 |
+
"learning_rate": 3.0153689607045845e-06,
|
318 |
+
"loss": 0.0,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 2.8273092369477912,
|
323 |
+
"grad_norm": NaN,
|
324 |
+
"learning_rate": 1.9369152030840556e-06,
|
325 |
+
"loss": 0.0,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.891566265060241,
|
330 |
+
"grad_norm": NaN,
|
331 |
+
"learning_rate": 1.0926199633097157e-06,
|
332 |
+
"loss": 0.0,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 2.9558232931726907,
|
337 |
+
"grad_norm": NaN,
|
338 |
+
"learning_rate": 4.865965629214819e-07,
|
339 |
+
"loss": 0.0,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 3.0522088353413657,
|
344 |
+
"grad_norm": NaN,
|
345 |
+
"learning_rate": 1.2179748700879012e-07,
|
346 |
+
"loss": 0.0,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 3.1164658634538154,
|
351 |
+
"grad_norm": NaN,
|
352 |
+
"learning_rate": 0.0,
|
353 |
+
"loss": 0.0,
|
354 |
+
"step": 47
|
355 |
}
|
356 |
],
|
357 |
"logging_steps": 1,
|
|
|
375 |
"should_evaluate": false,
|
376 |
"should_log": false,
|
377 |
"should_save": true,
|
378 |
+
"should_training_stop": true
|
379 |
},
|
380 |
"attributes": {}
|
381 |
}
|
382 |
},
|
383 |
+
"total_flos": 9.959641726530355e+16,
|
384 |
"train_batch_size": 2,
|
385 |
"trial_name": null,
|
386 |
"trial_params": null
|