Model techniques map
Techniquesoptimizationlearning-rate schedule

specific method · filed under optimization

Cosine decay

A learning-rate schedule that decays the rate according to a cosine curve.

Also called Cosine decay learning rate schedule, cosine learning rate schedule.

sources
4
models
4
labs adopt it
4
strongest
default

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 3default 2

Documented in

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

Evidence

5 spans quoted from the sources, strongest treatment first.

Our scaling-law study consistently favors cosine decay over Warmup Stable Decay (WSD) [46], leading us to adopt cosine decay as the default learning rate schedule.

defaultoptimizationin Kimi K3Moonshot AI

Our scaling-law study consistently favors cosine decay over Warmup Stable Decay (WSD), leading us to adopt cosine decay as the default learning rate schedule.

defaultunclearin Kimi K3Moonshot AI

using a cosine learning-rate schedule with peak learning rate 1.5×10−5

usedoptimizationin Nemotron 3 UltraNVIDIA

including the Muon optimizer, cosine decay, and batch size warmup

usedoptimizationin GLM-5Z.ai

cosine decay to

usedoptimizationin MiMo-V2-FlashXiaomi

Filed alongside

Other methods under optimization :: learning-rate schedule.