liveBook · Manning

Training

As explained in Build a Reasoning Model (From Scratch)

A method that improves model behavior by further updating the model through training.

Training improves a pretrained language model by updating its weights through additional training, turning a conventional base model into a dedicated reasoning model. It follows evaluation in the build workflow: measure the baseline, train, then evaluate again to determine whether reasoning behavior improved. section 1.7

The workflow positions training after the baseline model and evaluation tools:

  • Load an existing pretrained base LLM rather than training a model from scratch. section 1.7
  • Evaluate reasoning behavior before and after training so the change can be measured. section 1.7
  • Use training-time methods based on reinforcement learning and distillation. section 1.7
Figure 1.9 A high-level road map of what we’ll build in this book. We’ll start with a conventional LLM, add evaluation methods so we can measure its progress, and then explore two broad families of reasoning improvements: inference techniques and training techniques.

The roadmap shows training as one of two improvement families, alongside inference techniques, within a measure-and-improve loop. section 1.7

How Build a Reasoning Model (From Scratch) covers it

How deep it goes
Outlines the workflow and names reinforcement learning and distillation, but defers their implementation details.
Examples
Uses a conventional pretrained LLM, evaluation tools, and reinforcement-learning or distillation workflows as concrete anchors.
What it assumes
Assumes a pretrained conventional LLM and introduces evaluation before additional training.
What you can do after
Evaluate whether additional training improves reasoning behavior and understand its place in the model-building workflow.
How it connects
Connects pretrained language models, reasoning models, evaluation, inference techniques, reinforcement learning, and distillation.

Also explained in

Compare how 24 books explain training →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build a Reasoning Model (From Scratch). The section links point to the parts of the book it draws on.