promptdojo_promptdojo_promptdojo_promptdojo_promptdojo_promptdojo_promptdojo_promptdojo_promptdojo_promptdojo_promptdojo_

Optimizers and learning-rate schedulers — step 7 of 7

ch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulersch 43 · training loops, backprop, optimizers, and schedulers7/7
Checkpoint

One last thing before we move on. pass this to mark the lesson done, or skip and keep moving. hop to the next when you're ready.

Implement lr_at(t) — linear warmup from 0 to PEAK over the first WARMUP steps, then cosine decay PEAK * 0.5 * (1 + cos(pi * progress)) over the rest. Print f"step {t:>4}: lr={lr_at(t):.4f}" for t in (0, 50, 100, 550, 1000), then two property checks: "peak at warmup end:" (lr_at(100) == PEAK) and "near zero at the end:" (lr_at(1000) < 1e-9). The lr as a plan, not a constant.

full-screen editor opens — close anytime to keep reading.

open the editor to run it.