bbytxt commited on
Commit
10735ef
1 Parent(s): 2b75cd9

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 sha256:422d9785c7e5ae607d8558fe078388cd4f5de28b810906bebb036de4da400453
3
  size 75471860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a30d0b928b4bf551f0c47963042b439e40fde1544b7358ad36c00d8bc609f5
3
  size 75471860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ee3245932971d68d44c15040c5b344cd7a9591c04218bc54d69711582b88920
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8956016ef6f672709872466580d9271cba47505d3848e8a2007c5338b539de7e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
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": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.08960573476702509,
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": 17.009,
199
  "eval_steps_per_second": 8.504,
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": 1.340975697887232e+16,
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": 0.17921146953405018,
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": 17.009,
199
  "eval_steps_per_second": 8.504,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.0931899641577061,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 6.545084971874738e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.0967741935483871,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 6.167226819279528e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.1003584229390681,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 5.782172325201155e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.1039426523297491,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 5.392295478639225e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.10752688172043011,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 5e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.1111111111111111,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 4.607704521360776e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.11469534050179211,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 4.2178276747988446e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.11827956989247312,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 3.832773180720475e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.12186379928315412,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 3.4549150281252636e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.12544802867383512,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 3.086582838174551e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.12903225806451613,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 2.7300475013022663e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.13261648745519714,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 2.3875071764202563e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.13620071684587814,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 2.061073738537635e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.13978494623655913,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 1.7527597583490822e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.14336917562724014,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 1.4644660940672627e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.14695340501792115,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 1.1979701719998453e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.15053763440860216,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 9.549150281252633e-06,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.15412186379928317,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 7.367991782295391e-06,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.15770609318996415,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 5.449673790581611e-06,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.16129032258064516,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 3.8060233744356633e-06,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.16487455197132617,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 2.4471741852423237e-06,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.16845878136200718,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 1.3815039801161721e-06,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.17204301075268819,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 6.15582970243117e-07,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.17562724014336917,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 1.5413331334360182e-07,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.17921146953405018,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.17921146953405018,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 27.5615,
381
+ "eval_samples_per_second": 17.053,
382
+ "eval_steps_per_second": 8.526,
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": 2.691884549092147e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null