Hugging Face's logo

cwaud
/
d8a5519b-748a-4954-a590-e63634d3bbb9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
cwaud commited on
Commit
25ee609
·
verified ·
1 Parent(s): 01ceb70

Training in progress, step 10, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8802d01bdf21ebc1cd8876fdaedd328c72b557b0ab308e984b30099f97e0bdbe
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcc0208768e81fc91e53cc7a9530e8f00ab4fbe23d704ea6d18ad0b84fb7399
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3e8bee9b091f27dca0874eab22e89045985f973e3ef960f6f3b34453f13e0e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a8195ab0a1efa171c8d45b75e74c7eb4dca0f3ddae3395509575322a725ec9e
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7170a2d9b24ecc77552af509fa5ca848d0a66f21c29b073517cc02fd19368fe3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b308b5e594ea75d70a9db0c7e4c8ae8b3c774396b79358868a60b3a58dba9e
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": 0.007853403141361256,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 9.177,
103
  "eval_steps_per_second": 4.598,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1664636814360576.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008726003490401396,
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,
 
102
  "eval_samples_per_second": 9.177,
103
  "eval_steps_per_second": 4.598,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.008726003490401396,
108
+ "grad_norm": 4.1800923347473145,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.5439,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1849596460400640.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null