Lab 04 — Transfer Learning

2 min

What does freezing a backbone mean?
Why keep the preprocessing of the checkpoint?
What control quantifies the value of the transfer?
What symptom suggests catastrophic forgetting?
[E] What must be versioned to deliver a reliable adapter?

Answers. 1. Its parameters receive no update. 2. It defines the expected input distribution. 3. A from-scratch training at the same budget. 4. Validation drops sharply at unfreezing. 5. Base, tokenizer, adapter, preprocessing and configuration.

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.

This lesson is part of the “Hands-on Labs (5 Labs)” 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.

Subscribe — 19 $ US/month Back to the outline