Aivesa commited on
Commit
c9dbc1a
·
verified ·
1 Parent(s): 013b42f

Training in progress, step 10, 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:c74bb3b4f9da4327c2f51245c8a8eef2de98c0f9c1837901361cb37bdde4baa7
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0804e9f84fcc96f46b5c48e5604b1c43fd65d485ff0848998dc765b993d631
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08673bafed238e6e8c5693d8c26a89ae8ae31ff4e8be70dfc90a2b253be2deef
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d6a235c9a894e42696d03e90422b85acaadf1bcdf0a5882d82be52ccb9dcfa
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.012028065486134313,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 62.041,
95
  "eval_steps_per_second": 31.119,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 1456024977408.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.013364517206815904,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 62.041,
95
  "eval_steps_per_second": 31.119,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.013364517206815904,
100
+ "grad_norm": 0.23867052793502808,
101
+ "learning_rate": 0.0002,
102
+ "loss": 10.8361,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 1620084129792.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null