Hugging Face's logo

Paladiso
/
1005f286-e100-45d2-a7b1-478c52161b87

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
Paladiso commited on
Commit
2884ee3
·
verified ·
1 Parent(s): a93f761

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 sha256:9380fd64cd6464faf358de4404e935454fb676569f1d11586b1b9cec2e438093
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e175e59ac1505cf7c07004734f79beab7b3ee759045a20b76ad3d845044903e7
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9ef81451fc26c6380bdb037a2f709fb9d529b3f4f5768875903fd2bbaade096
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a168d22966104af4a030502d0601680b057d4bd1d73d57a37cfe3608f5c97d
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01d1d3562e662dfbd91e690130aa701ac09bf0d8729d2c72db9926fea6f11ea2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815251bad1c9b9f7659b76bd03de1138f924720d511b31972ddb413b47a4c932
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": 0.023968042609853527,
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": 20.092,
95
  "eval_steps_per_second": 10.109,
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": 447635961937920.0,
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": 0.02663115845539281,
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": 20.092,
95
  "eval_steps_per_second": 10.109,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.02663115845539281,
100
+ "grad_norm": 0.8706778883934021,
101
+ "learning_rate": 0.0002,
102
+ "loss": 1.5596,
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": 498794357587968.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null