LLM Training Vocabulary

initial training on vast text data to learn language patterns before task-specific fine-tuning

“Pre-training on internet text gives the model broad world knowledge.”

additional training on specific data to adapt a pre-trained model for particular tasks

“Fine-tuning on medical texts improved the model's diagnostic suggestions.”

reinforcement learning from human feedback—training models using human preference judgments

“RLHF shaped the model's helpfulness by learning from human ratings of responses.”

training on labeled examples where correct outputs are provided

“Supervised learning on question-answer pairs teaches the model to respond helpfully.”

training where labels are derived from the data itself, like predicting masked words

“Self-supervised learning on next-token prediction requires no human labeling.”

a mathematical measure of how wrong the model's predictions are, minimized during training

“Cross-entropy loss measures how different the predicted token distribution is from the actual next token.”

an optimization algorithm that iteratively adjusts parameters to minimize loss

“Gradient descent slowly nudges billions of parameters toward better predictions.”

the algorithm for computing gradients by propagating errors backward through the network

“Backpropagation calculates how each weight contributed to the prediction error.”

when a model memorizes training data rather than learning generalizable patterns

“Overfitting caused the model to excel on training examples but fail on new ones.”

techniques to prevent overfitting by constraining model complexity

“Dropout regularization randomly disables neurons during training to improve generalization.”