Learn AI Create the Future — with Pranay
Main site

Doing the Work Section 020

Reading Training Curves

A loss curve is a message from your model about what is going wrong. This section teaches you to read it.

Every lesson in this section is written by .

7 of 7 lessons published Three reading levels on every lesson

Start with “How to read a loss curve”

Lessons in order

Work top to bottom. Each lesson assumes the one above it.

  1. How to read a loss curve
  2. When validation loss rises but accuracy improves
  3. When your validation curve is too noisy to trust
  4. What changing batch size actually changes
  5. How smoothing and log scales mislead you
  6. Plateaus, sudden drops and double descent
  7. Too small a model, or trained too little?