Introduction to LLM Fine-Tuning
Chapter 1: Foundations of Model Customization
What is Fine-Tuning?
Pre-training vs. Fine-Tuning
When to Fine-Tune: An Analytical Framework
Overview of Fine-Tuning Strategies
The Role of Transfer Learning in LLMs
Setting Up Your Development Environment
Chapter 2: Data Preparation for Fine-Tuning
Sourcing and Selecting High-Quality Datasets
Instruction-Based vs. Conversational Data Formats
Data Cleaning and Preprocessing Techniques
Creating and Structuring Custom Datasets
Tokenization for Fine-Tuning
Hands-on Practical: Building a Fine-Tuning Dataset
Chapter 3: Full Parameter Fine-Tuning
The Mechanics of Full Fine-Tuning
Architectural Considerations for Full Fine-Tuning
Managing Computational Resources
Configuring Training Arguments and Hyperparameters
Monitoring Training: Loss and Metrics
Saving and Loading Fine-Tuned Models
Practice: Full Fine-Tuning on a Small-Scale Model
Chapter 4: Parameter-Efficient Fine-Tuning (PEFT)
Introduction to Parameter-Efficient Fine-Tuning
Low-Rank Adaptation (LoRA): Theory and Operation
Implementing LoRA with the PEFT Library
Quantization and its effect on Fine-Tuning (QLoRA)
Other PEFT Methods: A Brief Survey
Comparing PEFT and Full Fine-Tuning Trade-offs
Hands-on Practical: Fine-Tuning with LoRA
Chapter 5: Evaluation and Deployment
Defining Performance Metrics for Generative Tasks
Quantitative Evaluation: ROUGE, BLEU, and Perplexity
Qualitative Evaluation: Human-in-the-Loop Assessment
Building an Evaluation Pipeline
Strategies for Merging Adapters with the Base Model
Preparing Models for Inference
Practice: Evaluating a Fine-Tuned Model
Defining Performance Metrics for Generative Tasks
Was this section helpful?
- BLEU: a Method for Automatic Evaluation of Machine Translation, Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu, 2002 Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (Association for Computational Linguistics) DOI: 10.3115/1073083.1073135 - This foundational paper introduces BLEU, a widely used automatic metric for evaluating the quality of machine-translated text by comparing it to human reference translations.
- ROUGE: A Package for Automatic Evaluation of Summaries, Chin-Yew Lin, 2004 Text Summarization Branches Out (Association for Computational Linguistics) DOI: 10.3115/1621300.1621316 - This paper introduces ROUGE, a set of metrics widely used for automatic evaluation of summaries and other text generation tasks, based on n-gram overlap with reference summaries.
- Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Daniel Jurafsky, James H. Martin, 2025 - A comprehensive textbook (4th edition draft) with chapters on language models (including perplexity) and evaluation metrics for text generation, providing a strong academic foundation.