leixa commited on
Commit
ed7a05f
·
verified ·
1 Parent(s): afb5405

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 sha256:634b6a927ae18e97c4c07991e07dd64b32bd8e7e003c9e5ed96dd58dbe353cf0
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f4d68c21c29f2d7cf3bb57260228b7f572b45f66e8e8a788f1f575d11b59123
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d98a3a8934a79aca0a61f3b5e3aed8b72e0bc57f02c44917431dd53653da7a16
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e255b55e80116103d2899354045e82c6c9bf21bf76cfbb0a8f7680cab72e1d8b
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4461f5df9ea7a1e757a22e95b1d101c9e4bb83dc17672e8e32a75cf1ab4c8f76
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73434c4ac7d5f411c52d87bbdab7ca4b29aa35baad3510e41657a3bc5dcb13a3
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": 1.395121951219512,
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": 35.638,
433
  "eval_steps_per_second": 4.532,
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": 4.875582621037363e+16,
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": 1.4634146341463414,
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": 35.638,
433
  "eval_steps_per_second": 4.532,
434
  "step": 143
435
+ },
436
+ {
437
+ "epoch": 1.4048780487804877,
438
+ "grad_norm": 0.25628089904785156,
439
+ "learning_rate": 2.262559558016325e-07,
440
+ "loss": 2.3778,
441
+ "step": 144
442
+ },
443
+ {
444
+ "epoch": 1.4341463414634146,
445
+ "grad_norm": 0.17649215459823608,
446
+ "learning_rate": 5.662812383859795e-08,
447
+ "loss": 2.3724,
448
+ "step": 147
449
+ },
450
+ {
451
+ "epoch": 1.4634146341463414,
452
+ "grad_norm": 0.3153819739818573,
453
+ "learning_rate": 0.0,
454
+ "loss": 2.8507,
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": 5.115759104832307e+16,
476
  "train_batch_size": 8,
477
  "trial_name": null,
478
  "trial_params": null