dimasik87 commited on
Commit
202452b
·
verified ·
1 Parent(s): 713e705

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:dadce3bfe987462a5cafc68fc08131a37caea2ef0560e67e36a44a07b1fa7943
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb02ead05f515f4ddb3f52965dd480211c897dd7da6ccf6a3d8714593fa8e4b1
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9613635f59f1a0e4273673e708f901ab92fcdf7bca8c76daa6c91152293ab567
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9613cd7221dc222738d1fcd11c434cfb4f053075503cf40724f987af90bff302
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:148ea586316f8f5aa1bd86e07b936f021b6002c24ba7c39e3d88ebc3b263f688
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d87e3a96252518b314cf9ce8200f8b1355eeff351e53a46c1c14851db212ecd
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": 0.004352063830269511,
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": 8.236,
448
  "eval_steps_per_second": 8.236,
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": 1.808381660626944e+16,
470
  "train_batch_size": 1,
471
  "trial_name": null,
472
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0045333998231974065,
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": 8.236,
448
  "eval_steps_per_second": 8.236,
449
  "step": 48
450
+ },
451
+ {
452
+ "epoch": 0.004442731826733459,
453
+ "grad_norm": 0.44641199707984924,
454
+ "learning_rate": 3.0826662668720364e-07,
455
+ "loss": 0.1428,
456
+ "step": 49
457
+ },
458
+ {
459
+ "epoch": 0.0045333998231974065,
460
+ "grad_norm": 0.2606041431427002,
461
+ "learning_rate": 0.0,
462
+ "loss": 0.1358,
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": 1.8825716774731776e+16,
484
  "train_batch_size": 1,
485
  "trial_name": null,
486
  "trial_params": null