Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3 commited on
Commit
bc1045d
1 Parent(s): c6d2c53

End of training

Browse files
Files changed (2) hide show
  1. README.md +9 -1
  2. config.json +1 -1
README.md CHANGED
@@ -2,9 +2,17 @@
2
  license: other
3
  base_model: deepseek-ai/deepseek-llm-7b-chat
4
  tags:
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
 
 
 
 
 
 
 
8
  model-index:
9
  - name: ds_chat_sigmoid_iter0_2024-09-14-21.15
10
  results: []
@@ -16,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
16
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://ml.byteintl.net/experiment/tracking/detail?Id=project_20240915_20321b8f&selectedTrial=run_20240915_d060d7a7)
17
  # ds_chat_sigmoid_iter0_2024-09-14-21.15
18
 
19
- This model is a fine-tuned version of [deepseek-ai/deepseek-llm-7b-chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7009
22
  - Rewards/chosen: 0.3500
 
2
  license: other
3
  base_model: deepseek-ai/deepseek-llm-7b-chat
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
+ - trl
10
+ - dpo
11
+ - generated_from_trainer
12
+ datasets:
13
+ - self-generate/ds_chat_original_cn_mining_oj_iter0-binarized
14
+ - self-generate/ds_chat_original_cn_mining_sandbox_iter0-binarized
15
+ - self-generate/ds_chat_original_cn_rl_oj_iter0-binarized
16
  model-index:
17
  - name: ds_chat_sigmoid_iter0_2024-09-14-21.15
18
  results: []
 
24
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://ml.byteintl.net/experiment/tracking/detail?Id=project_20240915_20321b8f&selectedTrial=run_20240915_d060d7a7)
25
  # ds_chat_sigmoid_iter0_2024-09-14-21.15
26
 
27
+ This model is a fine-tuned version of [deepseek-ai/deepseek-llm-7b-chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat) on the self-generate/ds_chat_original_cn_mining_oj_iter0-binarized, the self-generate/ds_chat_original_cn_mining_sandbox_iter0-binarized and the self-generate/ds_chat_original_cn_rl_oj_iter0-binarized datasets.
28
  It achieves the following results on the evaluation set:
29
  - Loss: 0.7009
30
  - Rewards/chosen: 0.3500
config.json CHANGED
@@ -24,6 +24,6 @@
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.42.0",
27
- "use_cache": false,
28
  "vocab_size": 102400
29
  }
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.42.0",
27
+ "use_cache": true,
28
  "vocab_size": 102400
29
  }