leixa commited on
Commit
682398d
1 Parent(s): 8a59c43

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1685ede40bf022895c16fdd979d8441ad50f25d8a257e5bdc89189c167dab1c3
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459c0610e02d4e5747374bb90aafdecf6aa5406ccddf16cf2ce94a7d8fd7ac93
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:275a46bdf722787b2aa4bf4d5b996d0a53af3e3e0a682f890bc4c8fb30eb8213
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f44bf417b843c3aa44e927f45adc6a66febb33e8e88abe36981cf5fcffe335f2
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5cfad76a3456e3da824d7fc27ce2b7f891ca9d74102cfe39e4e466ffaf61ef4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc22126403b59b65062d0b411cf697d0fd080479d34646424c69e8278caa6e01
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a71f60f9bd2ac4332e4682c06bcf0e8b6f23e0f17b0fa94d84f1fe3045e8b4a8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0edab479cf5df2fd0e0eb08833b9040a0342b7b3b1ce5f746c88e4c78156c68
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": 0.03960121849903074,
5
  "eval_steps": 13,
6
- "global_step": 143,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -432,6 +432,27 @@
432
  "eval_samples_per_second": 13.197,
433
  "eval_steps_per_second": 1.651,
434
  "step": 143
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
435
  }
436
  ],
437
  "logging_steps": 3,
@@ -446,12 +467,12 @@
446
  "should_evaluate": false,
447
  "should_log": false,
448
  "should_save": true,
449
- "should_training_stop": false
450
  },
451
  "attributes": {}
452
  }
453
  },
454
- "total_flos": 2.2917789711649997e+17,
455
  "train_batch_size": 8,
456
  "trial_name": null,
457
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04153973968429798,
5
  "eval_steps": 13,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
432
  "eval_samples_per_second": 13.197,
433
  "eval_steps_per_second": 1.651,
434
  "step": 143
435
+ },
436
+ {
437
+ "epoch": 0.03987815009692606,
438
+ "grad_norm": 2.2642595767974854,
439
+ "learning_rate": 4.52511911603265e-07,
440
+ "loss": 1.3243,
441
+ "step": 144
442
+ },
443
+ {
444
+ "epoch": 0.04070894489061202,
445
+ "grad_norm": 2.4517059326171875,
446
+ "learning_rate": 1.132562476771959e-07,
447
+ "loss": 1.3393,
448
+ "step": 147
449
+ },
450
+ {
451
+ "epoch": 0.04153973968429798,
452
+ "grad_norm": 2.226973533630371,
453
+ "learning_rate": 0.0,
454
+ "loss": 1.3837,
455
+ "step": 150
456
  }
457
  ],
458
  "logging_steps": 3,
 
467
  "should_evaluate": false,
468
  "should_log": false,
469
  "should_save": true,
470
+ "should_training_stop": true
471
  },
472
  "attributes": {}
473
  }
474
  },
475
+ "total_flos": 2.4048711119772058e+17,
476
  "train_batch_size": 8,
477
  "trial_name": null,
478
  "trial_params": null