Foundation Lab

Learning Rate Schedules: Warmup, Decay & Cycling

LR schedule is one of the highest-leverage hyperparameters—same model can fail or succeed based on schedule

Concept 47 of 100OptimizationPhase 3

#47LR SchedulesOptimization

key equation\eta_t = \eta_{\min} + \frac{1}{2}(\eta_{\max} - \eta_{\min})\left(1 + \cos\left(\frac{\pi t}{T}\right)\right)

Selected Foundation Object

Keep the equation fixed; move through the evidence.

Concept 47 of 100LR SchedulesOptimization / Phase 3: Optimization & generalization

Current question

Why warmup helps: gradients are noisy/wrong at random init; small steps let moments stabilize

\eta_t = \eta_{\min} + \frac{1}{2}(\eta_{\max} - \eta_{\min})\left(1 + \cos\left(\frac{\pi t}{T}\right)\right)

PredictionCommit before the demo.

Ask what should change when the equation is manipulated, then let the visualization test that expectation.

EvidenceCompare local witness and source.

Use the runnable panel, the key equation, and canonical papers as separate forms of evidence for the same object.

InvariantName what survives notation changes.

The useful learning product is the reusable mechanism you can carry into another model, paper, or engineering tradeoff.

Next moveContinue in the newer notebook.

This atlas page keeps the working demo; the domain notebook carries the fuller Intuition -> Math -> Code -> Demo sequence.

LR schedule is one of the highest-leverage hyperparameters—same model can fail or succeed based on schedule
Warmup prevents early instability: Adam moments are biased at start, large LR can diverge
Cosine decay + warmup is the default for LLM pretraining (GPT, LLaMA, etc.)

What is still poorly explained in textbooks and papers:

Why warmup helps: gradients are noisy/wrong at random init; small steps let moments stabilize
Cosine vs linear decay: cosine spends more time at high LR (exploration) before annealing (exploitation)
The "LR range test" finds optimal peak LR by training briefly at increasing LR until loss spikes

If you want intuition first, start with the key equation and the visualization. Come back here for the full walkthrough.

Key Equation

\eta_t = \eta_{\min} + \frac{1}{2}(\eta_{\max} - \eta_{\min})\left(1 + \cos\left(\frac{\pi t}{T}\right)\right)

Warmup ramps LR from 0 to peak over $T_w$ steps:

\eta_t = \eta_{\max} \cdot \frac{t}{T_w}, \quad t \leq T_w

Cosine decay smoothly anneals:

\eta_t = \eta_{\min} + \frac{1}{2}(\eta_{\max} - \eta_{\min})\left(1 + \cos\left(\frac{t - T_w}{T - T_w}\pi\right)\right)

1/√t decay (classical):

\eta_t = \frac{\eta_0}{\sqrt{t}}

Modern LLM training typically uses: warmup → constant → cosine decay.

Loshchilov & Hutter2017ICLR

Choose the next question to carry this object forward.