README.md

metadata

library_name: transformers
license: llama3.1
base_model: meta-llama/Llama-3.1-8B
language: en
datasets:
  - Word2Li/MiddOptimized
tags:
  - llama-factory
  - full
pipeline_tag: text-generation
model-index:
  - name: Llama3.1-8B-Middo-Alpaca-4o-mini
    results:
      - task:
          type: text-generation
        dataset:
          name: MMLU
          type: MMLU
        metrics:
          - name: weighted accuarcy
            type: weighted accuarcy
            value: 44.69
            verified: true
      - task:
          type: text-generation
        dataset:
          name: IFEval
          type: IFEval
        metrics:
          - name: overall accuarcy
            type: overall accuarcy
            value: 47.96
            verified: true
      - task:
          type: text-generation
        dataset:
          name: GSM8K
          type: GSM8K
        metrics:
          - name: accuarcy
            type: accuarcy
            value: 57.62
            verified: true
      - task:
          type: text-generation
        dataset:
          name: MATH
          type: MATH
        metrics:
          - name: accuarcy
            type: accuarcy
            value: 18.5
            verified: true
      - task:
          type: text-generation
        dataset:
          name: HumanEval
          type: HumanEval
        metrics:
          - name: humaneval_pass@1
            type: humaneval_pass@1
            value: 52.44
            verified: true
      - task:
          type: text-generation
        dataset:
          name: MBPP
          type: MBPP
        metrics:
          - name: score
            type: score
            value: 45.4
            verified: true
      - task:
          type: text-generation
        dataset:
          name: Hellaswag
          type: Hellaswag
        metrics:
          - name: accuarcy
            type: accuarcy
            value: 57.37
            verified: true
      - task:
          type: text-generation
        dataset:
          name: GPQA
          type: GPQA
        metrics:
          - name: accuarcy
            type: accuarcy
            value: 19.7
            verified: true
metrics:
  - accuracy

Llama3.1-8B-Middo-Alpaca-4o-mini

Paper: Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning

Code: https://github.com/Word2VecT/Middo

Model description

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the MiddOptimzed/llama_alpaca_4o_mini dataset.

Training and evaluation data

Training data

Middo optimized Word2Li/Alpaca-4o-mini on meta-llama/Llama-3.1-8B.

Evaluation data

• General
  • MMLU
  • IFEval
• Math
  • GSM8K
  • MATH
• Code
  • HumanEval
  • MBPP
• Reasoning
  • Hellaswag
  • GPQA

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1.0

Training results

• epoch: 0.9964556962025316
• total_flos: 2.1359726465573192e + 18
• train_loss: 0.9420681825982846
• train_runtime: 3147.8466
• train_samples_per_second: 20.072
• train_steps_per_second: 0.078

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu121
• Datasets 2.21.0
• Tokenizers 0.20.1