dzanbek commited on
Commit
0f00d41
1 Parent(s): 39beae4

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3594c26aec8a4eaa9af07515f5ac9926def01a59bf558ddae02d4415d94b3e7a
3
  size 26008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244187f99b22e1143b553f915dc6ef22bfbc61d466939de308acf4b65848ef92
3
  size 26008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b2260f120de42c8c1e77eeb428737536da81e79af2faaab10111bfadd53fc62
3
  size 68874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af33521a1ccfd4b6d54afa15282f02f6bd5abc0a1b4a55324f85fb108a46cdbd
3
  size 68874
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5270a8ad33fa8f4633e4b858b5f92c1fafc05119f07ca49330569eeec336ada6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.03537944454272068,
5
  "eval_steps": 5,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -230,6 +230,221 @@
230
  "eval_samples_per_second": 69.369,
231
  "eval_steps_per_second": 34.684,
232
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  }
234
  ],
235
  "logging_steps": 1,
@@ -244,12 +459,12 @@
244
  "should_evaluate": false,
245
  "should_log": false,
246
  "should_save": true,
247
- "should_training_stop": false
248
  },
249
  "attributes": {}
250
  }
251
  },
252
- "total_flos": 37473484800.0,
253
  "train_batch_size": 2,
254
  "trial_name": null,
255
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.07075888908544135,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
230
  "eval_samples_per_second": 69.369,
231
  "eval_steps_per_second": 34.684,
232
  "step": 25
233
+ },
234
+ {
235
+ "epoch": 0.0367946223244295,
236
+ "grad_norm": 0.326715886592865,
237
+ "learning_rate": 0.00013090169943749476,
238
+ "loss": 11.8983,
239
+ "step": 26
240
+ },
241
+ {
242
+ "epoch": 0.038209800106138336,
243
+ "grad_norm": 0.2866935133934021,
244
+ "learning_rate": 0.00012334453638559057,
245
+ "loss": 11.9096,
246
+ "step": 27
247
+ },
248
+ {
249
+ "epoch": 0.03962497788784716,
250
+ "grad_norm": 0.30991116166114807,
251
+ "learning_rate": 0.0001156434465040231,
252
+ "loss": 11.8994,
253
+ "step": 28
254
+ },
255
+ {
256
+ "epoch": 0.04104015566955599,
257
+ "grad_norm": 0.3176131248474121,
258
+ "learning_rate": 0.0001078459095727845,
259
+ "loss": 11.9071,
260
+ "step": 29
261
+ },
262
+ {
263
+ "epoch": 0.042455333451264815,
264
+ "grad_norm": 0.29141172766685486,
265
+ "learning_rate": 0.0001,
266
+ "loss": 11.9017,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.042455333451264815,
271
+ "eval_loss": 11.898274421691895,
272
+ "eval_runtime": 8.8396,
273
+ "eval_samples_per_second": 67.424,
274
+ "eval_steps_per_second": 33.712,
275
+ "step": 30
276
+ },
277
+ {
278
+ "epoch": 0.04387051123297364,
279
+ "grad_norm": 0.3455469608306885,
280
+ "learning_rate": 9.215409042721552e-05,
281
+ "loss": 11.9159,
282
+ "step": 31
283
+ },
284
+ {
285
+ "epoch": 0.04528568901468247,
286
+ "grad_norm": 0.3515758812427521,
287
+ "learning_rate": 8.435655349597689e-05,
288
+ "loss": 11.8921,
289
+ "step": 32
290
+ },
291
+ {
292
+ "epoch": 0.046700866796391294,
293
+ "grad_norm": 0.40223929286003113,
294
+ "learning_rate": 7.66554636144095e-05,
295
+ "loss": 11.9068,
296
+ "step": 33
297
+ },
298
+ {
299
+ "epoch": 0.04811604457810013,
300
+ "grad_norm": 0.3547143042087555,
301
+ "learning_rate": 6.909830056250527e-05,
302
+ "loss": 11.9044,
303
+ "step": 34
304
+ },
305
+ {
306
+ "epoch": 0.04953122235980895,
307
+ "grad_norm": 0.38809290528297424,
308
+ "learning_rate": 6.173165676349103e-05,
309
+ "loss": 11.8962,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.04953122235980895,
314
+ "eval_loss": 11.895332336425781,
315
+ "eval_runtime": 8.7389,
316
+ "eval_samples_per_second": 68.201,
317
+ "eval_steps_per_second": 34.1,
318
+ "step": 35
319
+ },
320
+ {
321
+ "epoch": 0.05094640014151778,
322
+ "grad_norm": 0.4227261543273926,
323
+ "learning_rate": 5.4600950026045326e-05,
324
+ "loss": 11.8829,
325
+ "step": 36
326
+ },
327
+ {
328
+ "epoch": 0.052361577923226606,
329
+ "grad_norm": 0.38113293051719666,
330
+ "learning_rate": 4.7750143528405126e-05,
331
+ "loss": 11.8836,
332
+ "step": 37
333
+ },
334
+ {
335
+ "epoch": 0.05377675570493543,
336
+ "grad_norm": 0.39981311559677124,
337
+ "learning_rate": 4.12214747707527e-05,
338
+ "loss": 11.8975,
339
+ "step": 38
340
+ },
341
+ {
342
+ "epoch": 0.05519193348664426,
343
+ "grad_norm": 0.41320478916168213,
344
+ "learning_rate": 3.5055195166981645e-05,
345
+ "loss": 11.8876,
346
+ "step": 39
347
+ },
348
+ {
349
+ "epoch": 0.056607111268353084,
350
+ "grad_norm": 0.40017077326774597,
351
+ "learning_rate": 2.9289321881345254e-05,
352
+ "loss": 11.892,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.056607111268353084,
357
+ "eval_loss": 11.89357852935791,
358
+ "eval_runtime": 8.5747,
359
+ "eval_samples_per_second": 69.506,
360
+ "eval_steps_per_second": 34.753,
361
+ "step": 40
362
+ },
363
+ {
364
+ "epoch": 0.05802228905006191,
365
+ "grad_norm": 0.3937678337097168,
366
+ "learning_rate": 2.3959403439996907e-05,
367
+ "loss": 11.9013,
368
+ "step": 41
369
+ },
370
+ {
371
+ "epoch": 0.059437466831770744,
372
+ "grad_norm": 0.4014483392238617,
373
+ "learning_rate": 1.9098300562505266e-05,
374
+ "loss": 11.886,
375
+ "step": 42
376
+ },
377
+ {
378
+ "epoch": 0.06085264461347957,
379
+ "grad_norm": 0.38292697072029114,
380
+ "learning_rate": 1.4735983564590783e-05,
381
+ "loss": 11.8971,
382
+ "step": 43
383
+ },
384
+ {
385
+ "epoch": 0.062267822395188396,
386
+ "grad_norm": 0.38425660133361816,
387
+ "learning_rate": 1.0899347581163221e-05,
388
+ "loss": 11.898,
389
+ "step": 44
390
+ },
391
+ {
392
+ "epoch": 0.06368300017689722,
393
+ "grad_norm": 0.41762810945510864,
394
+ "learning_rate": 7.612046748871327e-06,
395
+ "loss": 11.8841,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.06368300017689722,
400
+ "eval_loss": 11.892833709716797,
401
+ "eval_runtime": 8.6566,
402
+ "eval_samples_per_second": 68.849,
403
+ "eval_steps_per_second": 34.425,
404
+ "step": 45
405
+ },
406
+ {
407
+ "epoch": 0.06509817795860605,
408
+ "grad_norm": 0.3865891396999359,
409
+ "learning_rate": 4.8943483704846475e-06,
410
+ "loss": 11.8881,
411
+ "step": 46
412
+ },
413
+ {
414
+ "epoch": 0.06651335574031488,
415
+ "grad_norm": 0.37985795736312866,
416
+ "learning_rate": 2.7630079602323442e-06,
417
+ "loss": 11.8981,
418
+ "step": 47
419
+ },
420
+ {
421
+ "epoch": 0.0679285335220237,
422
+ "grad_norm": 0.4050770401954651,
423
+ "learning_rate": 1.231165940486234e-06,
424
+ "loss": 11.8896,
425
+ "step": 48
426
+ },
427
+ {
428
+ "epoch": 0.06934371130373253,
429
+ "grad_norm": 0.3997718095779419,
430
+ "learning_rate": 3.0826662668720364e-07,
431
+ "loss": 11.9002,
432
+ "step": 49
433
+ },
434
+ {
435
+ "epoch": 0.07075888908544135,
436
+ "grad_norm": 0.401860773563385,
437
+ "learning_rate": 0.0,
438
+ "loss": 11.8901,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.07075888908544135,
443
+ "eval_loss": 11.892694473266602,
444
+ "eval_runtime": 8.599,
445
+ "eval_samples_per_second": 69.31,
446
+ "eval_steps_per_second": 34.655,
447
+ "step": 50
448
  }
449
  ],
450
  "logging_steps": 1,
 
459
  "should_evaluate": false,
460
  "should_log": false,
461
  "should_save": true,
462
+ "should_training_stop": true
463
  },
464
  "attributes": {}
465
  }
466
  },
467
+ "total_flos": 74946969600.0,
468
  "train_batch_size": 2,
469
  "trial_name": null,
470
  "trial_params": null