fenguhao commited on
Commit
ca44aef
1 Parent(s): b002b79

End of training

Browse files
Files changed (2) hide show
  1. README.md +5 -1
  2. config.json +1 -1
README.md CHANGED
@@ -1,9 +1,13 @@
1
  ---
2
  base_model: princeton-nlp/Llama-3-Base-8B-SFT
3
  tags:
 
 
4
  - trl
5
  - dpo
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: llama-8b-dpo-full
9
  results: []
@@ -14,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # llama-8b-dpo-full
16
 
17
- This model is a fine-tuned version of [princeton-nlp/Llama-3-Base-8B-SFT](https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
  - Loss: 0.6316
20
  - Rewards/chosen: 0.6899
 
1
  ---
2
  base_model: princeton-nlp/Llama-3-Base-8B-SFT
3
  tags:
4
+ - alignment-handbook
5
+ - generated_from_trainer
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
+ datasets:
10
+ - HuggingFaceH4/ultrafeedback_binarized
11
  model-index:
12
  - name: llama-8b-dpo-full
13
  results: []
 
18
 
19
  # llama-8b-dpo-full
20
 
21
+ This model is a fine-tuned version of [princeton-nlp/Llama-3-Base-8B-SFT](https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT) on the HuggingFaceH4/ultrafeedback_binarized dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.6316
24
  - Rewards/chosen: 0.6899
config.json CHANGED
@@ -23,6 +23,6 @@
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.36.2",
26
- "use_cache": false,
27
  "vocab_size": 128256
28
  }
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
  "vocab_size": 128256
28
  }