README.md

metadata

license: apache-2.0
datasets:
  - euclaise/SuperMC
  - euclaise/prm800k_preferences
model-index:
  - name: crow-1b
    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: 25.51
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=euclaise/crow-1b
          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: 25.87
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=euclaise/crow-1b
          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: 24.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=euclaise/crow-1b
          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: 48.28
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=euclaise/crow-1b
          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: 49.41
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=euclaise/crow-1b
          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: 0.83
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=euclaise/crow-1b
          name: Open LLM Leaderboard

Expirements in large-scale small-scale preference learning.

This one was a failure, it benchmarks horribly, despite responding okay to trivia questions in testing

falcon-rw-1b trained with PRO (preference ranking optimization, see https://arxiv.org/abs/2306.17492) on SuperMC and PRM800K (only stage 1) for 3 epochs, using my supertrainer2000 framework.

This is an expiremental model.

Benchmarks coming soon.

Hyperparameters:

• AdamW, weight decay of 0.01, otherwise default hyperparams
• Maximum LR of 1e-5
• Cosine schedule with a warmup of 5400 steps
• Batch size of 4 (2 real x 2 accumulated)
• Maximum of 5 epochs, early stopping (visual observation), stopped after 3
• Gradient clipping norm value of 1.0
• PRO beta of 4

Training prompt format:

### Query
[insert instruction here]

### Answer
[insert response here]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.12
AI2 Reasoning Challenge (25-Shot)	25.51
HellaSwag (10-Shot)	25.87
MMLU (5-Shot)	24.80
TruthfulQA (0-shot)	48.28
Winogrande (5-shot)	49.41
GSM8k (5-shot)	0.83