lr_scheduler_cosine: Cosine-annealing learning rate scheduler
In ggmlR: 'GGML' Tensor Operations for Machine Learning

lr_scheduler_cosine

R Documentation

Cosine-annealing learning rate scheduler

Description

Varies the learning rate following a cosine curve from lr_max down to lr_min over T_max steps. Restarts (SGDR-style) if restart = TRUE.

Usage

lr_scheduler_cosine(optimizer, T_max, lr_min = 0, restart = FALSE)

Arguments

`optimizer`	Optimizer environment.
`T_max`	Number of steps for one cosine cycle.
`lr_min`	Minimum learning rate (default 0).
`restart`	Logical; if `TRUE` restart after `T_max` steps.

Value

An lr_scheduler_cosine environment

Examples


w   <- ag_param(matrix(runif(4), 2, 2))
opt <- optimizer_adam(list(w = w), lr = 0.1)
sch <- lr_scheduler_cosine(opt, T_max = 50L)
for (epoch in 1:50) sch$step()

ggmlR documentation built on July 14, 2026, 1:08 a.m.