Lesson 10 · 12 min
Capstone — diagnose a training run
You're handed a broken run. What's wrong, and what do you check first?
The brief
A teammate says "I trained a classifier and the model is bad. Help me debug." You see:
- Train accuracy: 52% (chance is 50%)
- Val accuracy: 51%
- Training ran for 50 epochs
- Loss curve: roughly flat the whole way through