Syllabus Lesson 164 of 246 · Module 14: Run Clinic II
Module 14: Run Clinic II

Trust the helper? Sequence edition

Why it matters Same skill as Module 8, harder faults: several of these look alike from the loss curve alone, so a helper that only reads curves gets them wrong with full confidence.

An AI helper has named a fault for each of eight broken runs. Some claims are wrong. Watch for pairs that share a symptom: two faults can both make the training loss suspiciously low, and two can both make it stall.

ProbeWhat it tells youHealthy run
loss_curve(c)Training loss every 25 steps, and the loss on unseen text at the end. Always look first.4.55 down to about 2.9; unseen about 3.0
loss_at_init(c)Loss before training. A fresh model guessing evenly over 95 characters gives ln(95).4.55
leak_check(c)Can a later character change an earlier prediction?False
show_batch(c)One training input and its target, as text.target = input moved one character left
update_ratio(c)After the first Adam step, how far weights moved relative to their size. Not Module 8's rule: that 0.001 to 0.1 range is for plain SGD steps. Adam's first step moves every weight by about the learning rate whatever its gradient, and these weights start near 0.02, so 0.01 / 0.02 gives about 0.5. Compare a case with this healthy run, not with Module 8's range.about 0.5
block_change(c)How much the first block changes each vector at the start.about 0.3
Words and symbols in this lesson
ln(V)
the starting loss of a model that guesses evenly over V symbols: 4.55 for 95 characters
block change
how much one block changes a vector at the start; near 1 means it replaced it
Your turn

For each case A to H, set verdicts[case] to True (the helper is right) or False. You need at least 7 of 8 right.

Spotted a problem in this lesson? Report it · Ask about this lesson

This exercise opens soon

Finish the lesson before it and this one unlocks. The whole course is free, no account needed, and you can read this lesson right now.