Practice — Model Training & Experimentation at Scale (7 questions)

A team is building a "recommended for you" module for a mid-sized e-commerce site (2 M monthly users, 300 k products). Their first plan is to train a two-tower neural network with user- and item-history encoders and ship it if offline recall@50 exceeds 0.30.

1. Which baselines should they build first, and what does each one tell them?
2. The two-tower model reaches recall@50 = 0.31. Popularity ranking reaches 0.27. How would you use these numbers in a go/no-go discussion?
3. Name one operational reason, unrelated to accuracy, why the baseline should still be maintained after the neural model ships.

GPT-2 XL has 1.5 B parameters. Its weights in FP16 take ~3 GB on disk.

Roughly how much GPU memory is needed to train it (full fine-tuning, standard mixed-precision Adam) on a single GPU?

Show the per-parameter memory breakdown that gets you to your answer, and name two techniques that would bring the requirement down.