Skip to content
All tags

#training

6 posts

How Models Improve Themselves: Gradient Descent and the Training Loop

A model uses loss to know how wrong it is and gradients to know which direction to adjust. Gradient descent repeats three things: compute loss, compute gradients, update parameters. The learning rate controls step size — too large and you overshoot, too small and training takes forever.

How a Model Knows It's Wrong: Loss Functions and Cross-Entropy

Every time a model predicts the next token, it assigns a probability to every candidate word. A loss function measures how far that probability distribution is from the correct answer — the further off, the higher the loss, the more the model knows it got it wrong. Cross-entropy is the standard formula; perplexity is its human-readable translation.

Scaling Laws: How Big Should a Model Be, and Why Bigger Isn't Always Better

Scaling laws show that loss decreases predictably with more parameters, data, and compute — following power-law relationships. The Chinchilla paper's key finding: most models were too large and undertrained. Given the same compute budget, training a smaller model on more data produces better results. This reshaped the entire industry's training strategy.

Pre-training, SFT, RLHF: Three Stages That Turn a Text Predictor into a Useful Assistant

Every LLM goes through three training stages: pre-training reads the internet to learn language, SFT uses example conversations to learn the format, and RLHF uses human preferences to learn what a good answer looks like. The gap between a base model and a chat model is what the last two stages do.

CS336 Lecture 9: Scaling Laws Are Extrapolation Tools, Not Crystal Balls

Lecture 9 begins with log-log linear relationships between data and error, then uses scaling laws to compare architectures, optimizers, batches, and model-data allocations. The Chinchilla dispute shows how fitting methods, observed ranges, and deployment objectives change the answer.

climbing deep-dive

A Knowledge Map of Climbing Books: 60+ Books from Training Science to Mental Philosophy

Climbing books don't exist in isolation — they represent competing schools of thought, philosophical differences, and knowledge gaps. This post maps the relationships between 60+ books to help you pick the right one to read next.