mgh6 commited on
Commit
4054aec
·
verified ·
1 Parent(s): 74eef4e

Training in progress, step 5200, 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:c4dc78a06614b74f2b7993cd2f4ad16e3daecd08d36efab1e342631d48b9793a
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c6acc70fa4f5e7bf510dd02770d8ffb6b6d807ee77cba32e2c8a8a88ac779a
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e033f05ae018b75c2c7b5b237f01e0f1e6386139b7bb3a6a878d149aebe6d4f8
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a050356e3fa35dc2f5e98f5bf002bd900d4af63dd215855e0bcaf4fe7d4ca174
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9362e68e86622bc0c486fa360901e87403d41efefa49dfa18c3cc0346850378d
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:596168ea31aa8520fa08663f46c9a78fe4d819bc8af7a71e5784222f49670142
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbfc4e557ce12b317d9b824c5de2de360b0c6c861af7a535f3a5a58e102dd318
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb37dd47c771a0397467c44c29c37f04bf1b459ccf3af99a642cb6cb448eb4b
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": 10.198406498984534,
5
  "eval_steps": 500,
6
- "global_step": 5100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -444,6 +444,13 @@
444
  "learning_rate": 6.6e-05,
445
  "loss": 1.2515,
446
  "step": 5100
 
 
 
 
 
 
 
447
  }
448
  ],
449
  "logging_steps": 100,
@@ -463,7 +470,7 @@
463
  "attributes": {}
464
  }
465
  },
466
- "total_flos": 7.959731961893749e+18,
467
  "train_batch_size": 8,
468
  "trial_name": null,
469
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.398375253866583,
5
  "eval_steps": 500,
6
+ "global_step": 5200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
444
  "learning_rate": 6.6e-05,
445
  "loss": 1.2515,
446
  "step": 5100
447
+ },
448
+ {
449
+ "epoch": 10.398375253866583,
450
+ "grad_norm": 0.19390232861042023,
451
+ "learning_rate": 6.533333333333334e-05,
452
+ "loss": 1.2466,
453
+ "step": 5200
454
  }
455
  ],
456
  "logging_steps": 100,
 
470
  "attributes": {}
471
  }
472
  },
473
+ "total_flos": 8.115806933081915e+18,
474
  "train_batch_size": 8,
475
  "trial_name": null,
476
  "trial_params": null