dzanbek commited on
Commit
d8b2fda
·
verified ·
1 Parent(s): f2030c6

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:c9b12d9f65706b4fa55face47fe6bc68919e545beb17280e3c956239b8d40a05
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7750ac5aaef63acea01f729afc9148d5366eface2f3d2c5d52da7a7551b3649
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fb269b125680bfae7a8447ce31fd683c3c1742d8647b631af7e8bd384058579
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492c6d7113866946c9284f09a3b7cafc8d301bf13ccc0184880e71a8fe9d4d49
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e693ed8c359ae45c0158f874d55fa99240ad57354a7f85c3af64934c52feb8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abc4c9236fdc27316b72fe0e715c36127c40dedb514582d316c7415b64087ed5
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": 0.24181360201511334,
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": 128.135,
448
  "eval_steps_per_second": 64.068,
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": 9777602101248.0,
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": 0.2518891687657431,
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": 128.135,
448
  "eval_steps_per_second": 64.068,
449
  "step": 48
450
+ },
451
+ {
452
+ "epoch": 0.24685138539042822,
453
+ "grad_norm": 0.16592900454998016,
454
+ "learning_rate": 3.0826662668720364e-07,
455
+ "loss": 11.7754,
456
+ "step": 49
457
+ },
458
+ {
459
+ "epoch": 0.2518891687657431,
460
+ "grad_norm": 0.19010961055755615,
461
+ "learning_rate": 0.0,
462
+ "loss": 11.7793,
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": 10185002188800.0,
484
  "train_batch_size": 2,
485
  "trial_name": null,
486
  "trial_params": null