README.md

metadata

license: apache-2.0
model-index:
  - name: 7B_ppo_phiRM_2GPU_3e-7step_4000
    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: 57.25
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
          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: 80.24
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
          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: 60.06
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
          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: 41.48
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
          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: 76.32
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
          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: 29.42
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
          name: Open LLM Leaderboard

zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	57.46
AI2 Reasoning Challenge (25-Shot)	57.25
HellaSwag (10-Shot)	80.24
MMLU (5-Shot)	60.06
TruthfulQA (0-shot)	41.48
Winogrande (5-shot)	76.32
GSM8k (5-shot)	29.42