Warmup and Cosine Annealing Schedules Quiz

Answers and explanations appear as you take the quiz.

1. What is the main purpose of the warmup phase at the start of training?
   • To stabilize early training when weights are random and gradients are noisy
   • To increase the batch size gradually
   • To freeze the model's bottom layers
   • To compress the model for faster inference
2. Cosine annealing decays the learning rate following which shape?
   • A straight diagonal line
   • A cosine curve that starts high, eases, and flattens near zero
   • A step function that drops at fixed epochs
   • An exponential spike upward
3. Which optimizer especially benefits from warmup because its variance estimates are unreliable early on?
   • Plain SGD with no momentum
   • Grid search
   • Adam and its variants
   • K-means
4. In the cosine formula, what does T represent?
   • The model's temperature for sampling
   • The number of GPUs used
   • The tokenizer vocabulary size
   • The total number of training steps in the schedule
5. In the guide’s warmup-plus-cosine schedule, what begins after warmup reaches its target rate?
   • Cosine decay begins from the peak learning rate
   • All model weights are reset
   • The schedule switches to a constant zero rate
   • Momentum is removed from every optimizer
6. A linear warmup rises from zero to its target rate over 200 steps. About what rate is used halfway through?
   • The full target rate
   • About half of the target rate
   • The learning rate is exactly zero
   • Twice the target rate
7. At the cosine horizon t = T, what multiplier does the guide’s cosine formula produce?
   • One
   • One-half
   • Zero
   • It becomes negative one
8. Why use a gradual cosine decay after warmup rather than abruptly setting the rate to zero?
   • It guarantees a global minimum
   • It increases the model’s parameter count
   • It removes the need to check training loss
   • It lets the rate ease down so optimization can settle gradually