leixa commited on
Commit
647a71e
·
verified ·
1 Parent(s): 7a602d7

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:ba8f92fff3d0704cfd2878c9aa27bb09f39f0ef1e36537ab31b00f6a2c8a455e
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b44e932ff59c9c7ec6ebc048c1c159639073e2ddba2538970918d77f28b010
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c32d27d70ffbf1baca00df2feb354808d5cf048c65ef6a942fa8d997b9f702a8
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1272f0b655fcf51b76f3d79732705a2f0e462f8f714fb478d0bb1f6304c83291
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9acb4bb3f272325115fb1e1ca543e5418b0ce7c8f1090e6957b7e3fd0ec598ee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138ecb300f51325feb9eb3bbb26fed10559fd0a6866768e8bfd392a595962066
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:431c6c53bdba57f808cd9c2e6f738bda5a26247416d68b6f96cb4f3eef6f54ca
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1320cc0c91c904e1b37627facbc7bdd09ad072c5e9a4fe376e5569a5cdf3a73
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": 0.044489383215369056,
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": 13.887,
433
  "eval_steps_per_second": 1.736,
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": 2.1217976309828813e+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": 0.046667185190946564,
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": 13.887,
433
  "eval_steps_per_second": 1.736,
434
  "step": 143
435
+ },
436
+ {
437
+ "epoch": 0.044800497783308704,
438
+ "grad_norm": 1.2946685552597046,
439
+ "learning_rate": 2.262559558016325e-07,
440
+ "loss": 1.5154,
441
+ "step": 144
442
+ },
443
+ {
444
+ "epoch": 0.045733841487127634,
445
+ "grad_norm": 1.1807682514190674,
446
+ "learning_rate": 5.662812383859795e-08,
447
+ "loss": 1.4998,
448
+ "step": 147
449
+ },
450
+ {
451
+ "epoch": 0.046667185190946564,
452
+ "grad_norm": 1.2081470489501953,
453
+ "learning_rate": 0.0,
454
+ "loss": 1.5239,
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": 2.225661850681344e+17,
476
  "train_batch_size": 8,
477
  "trial_name": null,
478
  "trial_params": null