Training

How models learn from data, and how that goes wrong.

Fine-tuningTraining an already-trained model a little more on a smaller, focused dataset so it gets better at a specific task or style.
OverfittingWhen a model memorizes its training data instead of learning the general pattern, so it scores well in training but poorly on new data.
RegularizationTechniques that discourage a model from becoming too complex during training, which helps it avoid overfitting.
UnderfittingWhen a model is too simple or trained too little to capture the pattern in the data, so it does poorly even on its training data.

Basics Large language models Data Evaluation Safety and ethics