dimasik2987 commited on
Commit
5d28cf5
·
verified ·
1 Parent(s): a189372

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 sha256:721849f9bdf743472f0a10f2087a30067665ff85385534c8af1c753ca4391b5e
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a8cfec121aed3b2eb456ef26187166d332389a02d695da96b910a03885f06a
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6173d1adfdb2ad6474b9e162945362478d2c0792a577497c5edb6ddbaaee7644
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624a7619a233fc638433dca7f1b8527530ac1003e2a9d435c71d50be7d2c8b8e
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:d3d170c8db509ef67a93e9ec03a7cb684f62e9573629664fc6b02b7f7348875f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e15c2455bd410737bfe4e1e98e79cb73c7d3698b1342e569308f3f2a97bc3c
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": 0.21029572836801752,
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": 9.345,
448
  "eval_steps_per_second": 4.72,
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": 3.5610589610901504e+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": 0.21905805038335158,
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": 9.345,
448
  "eval_steps_per_second": 4.72,
449
  "step": 48
450
+ },
451
+ {
452
+ "epoch": 0.21467688937568455,
453
+ "grad_norm": 0.10799823701381683,
454
+ "learning_rate": 3.0826662668720364e-07,
455
+ "loss": 0.0058,
456
+ "step": 49
457
+ },
458
+ {
459
+ "epoch": 0.21905805038335158,
460
+ "grad_norm": 0.07520440220832825,
461
+ "learning_rate": 0.0,
462
+ "loss": 0.0121,
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": 3.70943641780224e+16,
484
  "train_batch_size": 2,
485
  "trial_name": null,
486
  "trial_params": null