dimasik87 commited on
Commit
9a03748
·
verified ·
1 Parent(s): 5416759

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 sha256:427776be467d9f16b7f0cdef32eea028e04f09d77dec3df57cbcdeddcf642247
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93e59cfc3e5e4bd25a317833269fe8d56cd732816afdcab5747569426f5d14a
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e61ad4b53f154b31a93a0157080b7bfe2b2146a56957bcea44dc77c0516cf565
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4263065f0705b0cf8b0dc5607080d5bcce046aec28d5a88967b575cf7d8eb09
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
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": 0.040523427606585054,
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,
@@ -447,6 +447,20 @@
447
  "eval_samples_per_second": 12.487,
448
  "eval_steps_per_second": 6.256,
449
  "step": 48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
450
  }
451
  ],
452
  "logging_steps": 1,
@@ -461,12 +475,12 @@
461
  "should_evaluate": false,
462
  "should_log": false,
463
  "should_save": true,
464
- "should_training_stop": false
465
  },
466
  "attributes": {}
467
  }
468
  },
469
- "total_flos": 1.7805294805450752e+16,
470
  "train_batch_size": 2,
471
  "trial_name": null,
472
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04221190375685943,
5
  "eval_steps": 4,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
447
  "eval_samples_per_second": 12.487,
448
  "eval_steps_per_second": 6.256,
449
  "step": 48
450
+ },
451
+ {
452
+ "epoch": 0.041367665681722246,
453
+ "grad_norm": NaN,
454
+ "learning_rate": 3.0826662668720364e-07,
455
+ "loss": 0.0,
456
+ "step": 49
457
+ },
458
+ {
459
+ "epoch": 0.04221190375685943,
460
+ "grad_norm": NaN,
461
+ "learning_rate": 0.0,
462
+ "loss": 0.0,
463
+ "step": 50
464
  }
465
  ],
466
  "logging_steps": 1,
 
475
  "should_evaluate": false,
476
  "should_log": false,
477
  "should_save": true,
478
+ "should_training_stop": true
479
  },
480
  "attributes": {}
481
  }
482
  },
483
+ "total_flos": 1.85471820890112e+16,
484
  "train_batch_size": 2,
485
  "trial_name": null,
486
  "trial_params": null