Glossary › Fine-Tuning
Fine-Tuning
Adapting a pretrained model to a new task by continuing training on task-specific data. The pretrained weights serve as initialization. The key hyperparameter is the learning rate - too high and you destroy the pretrained representations; too low and learning is slow. Typically 10–100x smaller than the learning rate used for pretraining.
← Feature Importance · Gradient Vanishing / Exploding → · All terms
Where Fine-Tuning shows up
All matching postsFine-Tuning and Post-Training: LoRA, SFT, DPO, and Reasoning RL
What actually happens after pretraining, and when you should do any of it yourself. Parameter-efficient fine-tuning with LoRA, supervised fine-tuning data, preference optimization, and the reinforcement learning recipe behind reasoning models, with a decision framework and a project you can run on one GPU.
NLP Engineering: From Text to Production
NLP has transformed with the rise of transformers, but the engineering fundamentals remain: preprocessing, embeddings, fine-tuning, and serving. Here is the full practical stack.
Transformers and Modern NLP Fundamentals
Bridge into LLM systems with practical understanding of tokenization, attention, and fine-tuning.