BlouseJury's picture
Adding Evaluation Results (#2)
c09c051 verified
metadata
language:
  - en
license: apache-2.0
tags:
  - finetune
pipeline_tag: text-generation
model-index:
  - name: Mistral-7B-Discord-0.1
    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: 60.24
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BlouseJury/Mistral-7B-Discord-0.1
          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: 83.13
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BlouseJury/Mistral-7B-Discord-0.1
          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: 62.82
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BlouseJury/Mistral-7B-Discord-0.1
          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: 44.1
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BlouseJury/Mistral-7B-Discord-0.1
          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: 78.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BlouseJury/Mistral-7B-Discord-0.1
          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: 32.45
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BlouseJury/Mistral-7B-Discord-0.1
          name: Open LLM Leaderboard

Mistral-7B-Discord-0.1

This model is a finetune of Mistral-7B-0.1 on ~20 Million tokens worth of mostly not formatted, anonymized discord messages for 4 Epochs.

This is a base model.

Model Details

  • Finetuned from model : mistralai/Mistral-7B-v0.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 60.28
AI2 Reasoning Challenge (25-Shot) 60.24
HellaSwag (10-Shot) 83.13
MMLU (5-Shot) 62.82
TruthfulQA (0-shot) 44.10
Winogrande (5-shot) 78.93
GSM8k (5-shot) 32.45