Diagnosing with Curves and Errors

2 min

Objective: turn a symptom into testable hypotheses.

Learning curves

Plot train and validation loss per epoch, then the business metric. Do not conclude on a single epoch: look at trend, variance and time of the best checkpoint.

ObservationHypothesesTargeted actions
train and val both poorunderfitting, bug, weak signalbaseline, capacity, data
train good, val badoverfitting or shiftregularize, audit the split
NaN lossesinstability, invalid datalower lr, inspect values
val better than traindropout/augmentation, possible leakcompare modes and pipeline

Small-batch overfitting test

Before a long training run, ask the model to memorize 16 to 64 examples. If it cannot, suspect an error in shapes, labels, loss, gradients or capacity. Passing this test does not prove generalization; it only proves the pipeline can learn.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Training the Network” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one