# Machine Learning Fine-Tuning & Model Evaluation

> Practices for preparing JSONL datasets, fine-tuning open-source LLMs (Llama/Mistral) using LoRA, and benchmarking output quality.

Canonical: https://www.agentickit.co/skills/ml-training
Last updated: 2026-11-18

## Key practices
- Deduplicate and clean training datasets to eliminate biased or low-quality pairs
- Format training examples with consistent system prompts and conversation turns
- Evaluate fine-tuned models against an un-seen validation dataset to detect overfitting
- Compare model output embeddings against ground truth benchmark answers

## Related
- [ml-engineer](https://www.agentickit.co/agents/ml-engineer)
- [ai-engineer](https://www.agentickit.co/agents/ai-engineer)
- [/ml-finetune](https://www.agentickit.co/commands/ml-finetune)
- [/ai-feature](https://www.agentickit.co/commands/ai-feature)
