README.md

---
license: other
tags:
- moe
- DPO
- RL-TUNED
model-index:
- name: 13B_MATH_DPO
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 74.66
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/13B_MATH_DPO
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 89.51
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/13B_MATH_DPO
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 64.53
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/13B_MATH_DPO
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 78.63
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/13B_MATH_DPO
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 88.08
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/13B_MATH_DPO
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 67.1
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/13B_MATH_DPO
      name: Open LLM Leaderboard
---

 * [DPO Trainer](https://huggingface.co./docs/trl/main/en/dpo_trainer) with dataset kyujinpy/orca_math_dpo to improve [yunconglong/MoE_13B_DPO]
   ```
DPO Trainer
TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023. 
   ```

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co./datasets/open-llm-leaderboard/details_yunconglong__13B_MATH_DPO)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |77.08|
|AI2 Reasoning Challenge (25-Shot)|74.66|
|HellaSwag (10-Shot)              |89.51|
|MMLU (5-Shot)                    |64.53|
|TruthfulQA (0-shot)              |78.63|
|Winogrande (5-shot)              |88.08|
|GSM8k (5-shot)                   |67.10|