Mistral-7B-v0.3-Middo-Alpaca

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 mistralai/Mistral-7B-v0.3 on the MiddOptimzed/llama_alpaca dataset.

Training and evaluation data

Training data

Middo optimized Alpaca on mistralai/Mistral-7B-v0.3.

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: 1e-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: 1.0
• total_flos: 1.387246770039292e + 18
• train_loss: 1.0000714727661066
• train_runtime: 2851.6353
• train_samples_per_second: 20.461
• train_steps_per_second: 0.08

Framework versions

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