dsakerkwq commited on
Commit
53e98c0
1 Parent(s): 1ed725b

Training in progress, step 42, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b358ad0253115bd5d5130d1f49d30e4bf07c5d68ef60223c32bcd803ddffe8c4
3
  size 479362682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ec93f5f3ae839a92cf6b9cf18ed064f7beca49b6d9b38904eda1c92f6219ca
3
  size 479362682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33eaa656ac85ff67b5162b97358fcfa02013418493422bd8344673215fa431ae
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15138386766749b7c60b05cc1e321eb4346f007a788c67461d5eda2b6ceb3e6
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 sha256:4e7fa24dd339f02eaf48c538fb4068b5df21da0e6ac754d8f37bcee599eae6d5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b3d7a0ea8c700a3e0eb05433c4b1d6f8c9b26bba96ce3f1295a324f3b933686
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:e35481f632a8fde4f21e2b928a87e59f63ee97da06c7ff9ddf4309a57a6ff938
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cbf8c170dc06a9e158d227ed11c961d89f4fa8b745d27479a7b995b7a7cdee
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 sha256:76a40cbf2d19b21a23676917dbe8144796f8784860cbdb93b0c2d0080098b0dc
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b731be823c28d4317d9bc7652ddac48c775f35e1274b2fe13448699a5f9815b8
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f5af44da266da277e7531f687942d737458dea336c0a84bf03af6d775c87ac
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde78f0152770b6d9ff9d100a4e49fd7ae2ec975980251062a46af49a9f251c7
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": 1.810810810810811,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -198,6 +198,125 @@
198
  "eval_samples_per_second": 45.948,
199
  "eval_steps_per_second": 11.947,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +340,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 1.114626154561536e+17,
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": 3.054054054054054,
5
  "eval_steps": 25,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 45.948,
199
  "eval_steps_per_second": 11.947,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.8828828828828827,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 4.109423525312738e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.954954954954955,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 3.777924554357096e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 2.036036036036036,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 3.45704275117204e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 2.108108108108108,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 3.1487564587782306e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 2.18018018018018,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 2.854966364683872e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 2.2522522522522523,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 2.577483782514174e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 2.3243243243243246,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 2.3180194846605367e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 2.3963963963963963,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 2.0781731547998614e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 2.4684684684684686,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 1.8594235253127375e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 2.5405405405405403,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 1.6631192604065855e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 2.6126126126126126,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 1.490470641152345e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 2.684684684684685,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 1.3425421036992098e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 2.756756756756757,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 1.2202456766718093e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 2.828828828828829,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 1.1243353582104556e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 2.900900900900901,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 1.0554024673218807e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 2.972972972972973,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 1.0138719982009242e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 3.054054054054054,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 1e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
  }
321
  ],
322
  "logging_steps": 1,
 
340
  "should_evaluate": false,
341
  "should_log": false,
342
  "should_save": true,
343
+ "should_training_stop": true
344
  },
345
  "attributes": {}
346
  }
347
  },
348
+ "total_flos": 1.8725719396633805e+17,
349
  "train_batch_size": 2,
350
  "trial_name": null,
351
  "trial_params": null