README.md

metadata

license: llama3.2
language:
  - en
datasets:
  - PJMixers-Dev/HailMary-v0.1-KTO
base_model:
  - PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.2-SFT-3B
model-index:
  - name: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 65.04
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/datasets/open-llm-leaderboard/PJMixers-Dev__LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B-details
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 22.29
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/datasets/open-llm-leaderboard/PJMixers-Dev__LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B-details
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 11.78
            name: exact match
        source:
          url: >-
            https://huggingface.co/datasets/open-llm-leaderboard/PJMixers-Dev__LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B-details
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 2.91
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/datasets/open-llm-leaderboard/PJMixers-Dev__LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B-details
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 4.69
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/datasets/open-llm-leaderboard/PJMixers-Dev__LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B-details
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 23.42
            name: accuracy
        source:
          url: >-
            https://huggingface.co/datasets/open-llm-leaderboard/PJMixers-Dev__LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B-details
          name: Open LLM Leaderboard

PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.2-SFT-3B was further trained using KTO (with apo_zero_unpaired loss type) using a mix of instruct, RP, and storygen datasets. I created rejected samples by using the SFT with bad settings (including logit bias) for every model turn.

The model was only trained at max_length=6144, and is nowhere near a full epoch as it eventually crashed. So think of this like a test of a test.

W&B Training Logs

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.69
IFEval (0-Shot)	65.04
BBH (3-Shot)	22.29
MATH Lvl 5 (4-Shot)	11.78
GPQA (0-shot)	2.91
MuSR (0-shot)	4.69
MMLU-PRO (5-shot)	23.42