---
license: apache-2.0
datasets:
- abacusai/MetaMathFewshot
model-index:
- name: MetaMath-Bagel-DPO-34B
  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: 68.17
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/MetaMath-Bagel-DPO-34B
      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: 84.23
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/MetaMath-Bagel-DPO-34B
      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: 76.54
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/MetaMath-Bagel-DPO-34B
      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: 65.44
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/MetaMath-Bagel-DPO-34B
      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: 82.24
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/MetaMath-Bagel-DPO-34B
      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: 72.18
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/MetaMath-Bagel-DPO-34B
      name: Open LLM Leaderboard
---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png)

DPO finetune of our [MetaMath SFT Model](https://huggingface.co/abacusai/MM-Orc-Vic-bagel-34b-c1000) on the [Truthy DPO dataset](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1)

### Evaluation Results

| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- |
|  75.54  | 69.20 | 84.34  |   76.46 | 67.58 | 82.87 | 72.78 |
# [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_abacusai__MetaMath-Bagel-DPO-34B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |74.80|
|AI2 Reasoning Challenge (25-Shot)|68.17|
|HellaSwag (10-Shot)              |84.23|
|MMLU (5-Shot)                    |76.54|
|TruthfulQA (0-shot)              |65.44|
|Winogrande (5-shot)              |82.24|
|GSM8k (5-shot)                   |72.18|