dimasik2987 commited on
Commit
697d323
·
verified ·
1 Parent(s): e0466b3

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:e04b47f7ca7ce78e14b25e42b5a01aaebcfea582152272fb9a5dcc171e1729af
3
  size 200068512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8f55b2c6ed5a309ebc7fb6789ff76da7e3a4caae3e9739349e352f18fe37ad
3
  size 200068512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:782a84899ed9a6e6c9fe7e8cbe3fa2c8cd40f913da461a3fa5f567111fe4b26d
3
  size 400361770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c5715a012a7d799267139e1c9f735a90f5a99b1a1a6cb6c34497a5404bc568
3
  size 400361770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea2e2d2952d0dc4b1d6777f3568c14a1bf5bc275182c95c6c0212b96c839ec9a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92eeec514d7ccd9181648af1e726b197b2f674b228ea30941c1c61a6c50e7a31
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": 0.012921461740359378,
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": 8.37,
448
  "eval_steps_per_second": 4.188,
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": 3.681092935404749e+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": 0.01345985597954102,
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": 8.37,
448
  "eval_steps_per_second": 4.188,
449
  "step": 48
450
+ },
451
+ {
452
+ "epoch": 0.013190658859950199,
453
+ "grad_norm": 2.3129959106445312,
454
+ "learning_rate": 3.0826662668720364e-07,
455
+ "loss": 3.8164,
456
+ "step": 49
457
+ },
458
+ {
459
+ "epoch": 0.01345985597954102,
460
+ "grad_norm": 2.5126748085021973,
461
+ "learning_rate": 0.0,
462
+ "loss": 3.8391,
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": 3.83447180771328e+16,
484
  "train_batch_size": 2,
485
  "trial_name": null,
486
  "trial_params": null