Hugging Face's logo

yuansui
/
llama2_7b_instruct_sft_dpo

Text Generation
Transformers
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
yuansui commited on
Commit
e5879d7
•
1 Parent(s): f05c27d

Model save

Browse files
Files changed (4) hide show
  1. all_results.json +5 -5
  2. train_results.json +5 -5
  3. trainer_state.json +5 -5
  4. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 7.272,
3
  "total_flos": 0.0,
4
- "train_loss": 0.5793062054685184,
5
- "train_runtime": 6908.77,
6
- "train_samples": 1000,
7
- "train_samples_per_second": 1.158,
8
- "train_steps_per_second": 0.008
9
  }
 
1
  {
2
  "epoch": 7.272,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 5.7891,
6
+ "train_samples": 100,
7
+ "train_samples_per_second": 138.19,
8
+ "train_steps_per_second": 1.382
9
  }
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 7.272,
3
  "total_flos": 0.0,
4
- "train_loss": 0.5793062054685184,
5
- "train_runtime": 6908.77,
6
- "train_samples": 1000,
7
- "train_samples_per_second": 1.158,
8
- "train_steps_per_second": 0.008
9
  }
 
1
  {
2
  "epoch": 7.272,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 5.7891,
6
+ "train_samples": 100,
7
+ "train_samples_per_second": 138.19,
8
+ "train_steps_per_second": 1.382
9
  }
trainer_state.json CHANGED
@@ -852,14 +852,14 @@
852
  "epoch": 7.272,
853
  "step": 56,
854
  "total_flos": 0.0,
855
- "train_loss": 0.5793062054685184,
856
- "train_runtime": 6908.77,
857
- "train_samples_per_second": 1.158,
858
- "train_steps_per_second": 0.008
859
  }
860
  ],
861
  "logging_steps": 1,
862
- "max_steps": 56,
863
  "num_input_tokens_seen": 0,
864
  "num_train_epochs": 8,
865
  "save_steps": 400,
 
852
  "epoch": 7.272,
853
  "step": 56,
854
  "total_flos": 0.0,
855
+ "train_loss": 0.0,
856
+ "train_runtime": 5.7891,
857
+ "train_samples_per_second": 138.19,
858
+ "train_steps_per_second": 1.382
859
  }
860
  ],
861
  "logging_steps": 1,
862
+ "max_steps": 8,
863
  "num_input_tokens_seen": 0,
864
  "num_train_epochs": 8,
865
  "save_steps": 400,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7c0f8ad444d41f1febad513f205c387ea8b6103d9ca189dccf55d4e63547c25
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5168499f3fc64737f1ce9247e6726910111081c7dc6744367cb73a1b51353d2a
3
  size 7672