Overfitting and Catastrophic Forgetting — Fine-Tuning & Model Customi…
Protecting quality outside the target task
Steps in Overfitting and Catastrophic Forgetting
- Recognizing Overfitting in Fine-Tuned Models — beginner · Signs that a model has memorized training data rather than generalized
- Catastrophic Forgetting — beginner · How fine-tuning can degrade a model's pre-existing capabilities
- Regularization Techniques — beginner · Methods to prevent overfitting during training
- Balancing Dataset Size and Diversity — beginner · Avoiding overfitting to a narrow or repetitive dataset
- Mitigating Forgetting with Replay and Mixed Data — beginner · Blending general and task-specific data during training
Part of
- Fine-Tuning & Model Customization roadmap — the full learning path