Paladiso commited on
Commit
c232a91
·
verified ·
1 Parent(s): 7e17592

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 sha256:25f1f332ed296e6e7a749e61f61ac16592a2ba6fbb9f1b9f9b737da1547ef470
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa1ed4c30300aead85318fafc259d2ec8a8d1c4261d22725ed7342ae5ab995a
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95ec74b870ccf0ff0901d1cf4f0e1a02abd2eb601405d5cc9814a7fffc53412a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a89e3ef594867a8a105963e754534f3f946fd209459d87fc0db1477f4d8733
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a02d055fd1532df55c5a8db423d165f840db8dc41c6f626c052a7498079b221a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a921066ba995ceface607eb302fe5fbc656882a0c65440f7d36f790f14c392
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": 0.0031878154609049853,
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": 14.163,
95
  "eval_steps_per_second": 7.088,
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": 1757086035738624.0,
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": 0.0035420171787833173,
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": 14.163,
95
  "eval_steps_per_second": 7.088,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0035420171787833173,
100
+ "grad_norm": 0.544064998626709,
101
+ "learning_rate": 0.0002,
102
+ "loss": 1.2178,
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": 1988281566756864.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null