eeeebbb2 commited on
Commit
cfbf00a
1 Parent(s): 20d968f

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 sha256:30070220779185f5fa7ab8b56e462ffabaec5a28c3ff2742f420499d0f7d5760
3
  size 479362682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb3ee5862430c1fbe790685e1b7f118dc8a22d76b91d190c55c72eef2f72085
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 sha256:5010da21efd1a7859316c8c5a657ee993504a81d10d11ae10b4c2c17cbc380eb
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af90fe86de9ef02a0b18f762dab9d4fe2a9b49226db13518ae08f0c8c56e5ab2
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 sha256:9f25f3f5b21153c2df22f399b2d232b597704b0349239b0b3d340041bef25ae4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87bbee8cd603b00c5c7679be730bdaaa746b30ca8586d9bc3ecc6b80e5ccb3a
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:b888e371bed7b817c992b85ab0d683cd698ff41e5532d72016c93fbbb19f52a3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2d79e71ad7524e9dacfc4442d3904749529bb6669fd5534d9a6270292d9931
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 sha256:9d619a2f75b88e061fd058bd49379968d8cc61d27224ac9caa6dd7f33a95ece2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0320b357984bc60caa36a4b756ca17ff7a8f03c5bb9274d6f913e7387625dc6
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
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": 0.21231422505307856,
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 +198,189 @@
198
  "eval_samples_per_second": 27.173,
199
  "eval_steps_per_second": 7.065,
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": 0
216
  }
217
  },
218
  "TrainerControl": {
@@ -221,12 +404,12 @@
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": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.42462845010615713,
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": 27.173,
199
  "eval_steps_per_second": 7.065,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.2208067940552017,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.22929936305732485,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.23779193205944799,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.24628450106157113,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.25477707006369427,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.2632696390658174,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.27176220806794055,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.2802547770700637,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.28874734607218683,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.29723991507430997,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.3057324840764331,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.31422505307855625,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.3227176220806794,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.33121019108280253,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.33970276008492567,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.3481953290870488,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.35668789808917195,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.3651804670912951,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.37367303609341823,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.3821656050955414,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.39065817409766457,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.3991507430997877,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.40764331210191085,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.416135881104034,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.42462845010615713,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.42462845010615713,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 1.8435,
381
+ "eval_samples_per_second": 27.122,
382
+ "eval_steps_per_second": 7.052,
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": 2.229252309123072e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null