Quick definition
Regularization constrains models to reduce overfitting.
- Category: Training
- Focus: model adaptation
- Used in: Adapting a base model to your domain or style.
What it means
Common methods include dropout and weight decay. In training workflows, regularization often shapes model adaptation.
How it works
Training adapts models through fine-tuning or preference optimization. It uses curated datasets and evaluation loops.
Why it matters
Training methods tailor models to your domain and use case.
Common use cases
- Adapting a base model to your domain or style.
- Improving instruction following for specific tasks.
- Reducing errors with better training data.
Example
Apply dropout during training.
Pitfalls and tips
Low-quality data can degrade performance. Keep datasets clean, representative, and well-labeled.
In BoltAI
In BoltAI, this is referenced when discussing model customization.
