dimasik2987 commited on
Commit
9036e99
·
verified ·
1 Parent(s): bc06475

Training in progress, step 48, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c4048ab4f9a52bda607705c3f5bb13958a649c75b8765f2ac41060997a2703d
3
  size 148047722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8785178ab67973d156e1bf32e0bd7e58b58ed5bbeb60e7d49dea8c6e1fb8bc6b
3
  size 148047722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56493e7ecd4aec71b70e1f846eade27edc70447ddf6a39a2642358dcc3382d73
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06befea34ff2bfd28b299135677677cb8125609004f72f75f1e909cf7c3d734a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
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": 0.20114285714285715,
5
  "eval_steps": 4,
6
- "global_step": 44,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -411,6 +411,42 @@
411
  "eval_samples_per_second": 22.991,
412
  "eval_steps_per_second": 11.619,
413
  "step": 44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
414
  }
415
  ],
416
  "logging_steps": 1,
@@ -430,7 +466,7 @@
430
  "attributes": {}
431
  }
432
  },
433
- "total_flos": 5747582882021376.0,
434
  "train_batch_size": 2,
435
  "trial_name": null,
436
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.21942857142857142,
5
  "eval_steps": 4,
6
+ "global_step": 48,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
411
  "eval_samples_per_second": 22.991,
412
  "eval_steps_per_second": 11.619,
413
  "step": 44
414
+ },
415
+ {
416
+ "epoch": 0.2057142857142857,
417
+ "grad_norm": NaN,
418
+ "learning_rate": 7.612046748871327e-06,
419
+ "loss": 0.0,
420
+ "step": 45
421
+ },
422
+ {
423
+ "epoch": 0.2102857142857143,
424
+ "grad_norm": NaN,
425
+ "learning_rate": 4.8943483704846475e-06,
426
+ "loss": 0.0,
427
+ "step": 46
428
+ },
429
+ {
430
+ "epoch": 0.21485714285714286,
431
+ "grad_norm": NaN,
432
+ "learning_rate": 2.7630079602323442e-06,
433
+ "loss": 0.0,
434
+ "step": 47
435
+ },
436
+ {
437
+ "epoch": 0.21942857142857142,
438
+ "grad_norm": NaN,
439
+ "learning_rate": 1.231165940486234e-06,
440
+ "loss": 0.0,
441
+ "step": 48
442
+ },
443
+ {
444
+ "epoch": 0.21942857142857142,
445
+ "eval_loss": NaN,
446
+ "eval_runtime": 4.0555,
447
+ "eval_samples_per_second": 22.932,
448
+ "eval_steps_per_second": 11.589,
449
+ "step": 48
450
  }
451
  ],
452
  "logging_steps": 1,
 
466
  "attributes": {}
467
  }
468
  },
469
+ "total_flos": 6270090416750592.0,
470
  "train_batch_size": 2,
471
  "trial_name": null,
472
  "trial_params": null