Struct OptimizerState 

pub struct OptimizerState {
    pub m: Vec<f64>,
    pub v: Vec<f64>,
    pub step: u64,
}

Per-parameter-group optimizer state (first moment, second moment, step counter).

This is the internal accumulator state maintained by AdaptiveOptimizer. It corresponds to the PyTorch state_dict entries for a parameter group.

Fields

m: Vec<f64>

First-moment (mean) vector; length equals the number of parameters.

v: Vec<f64>

Second-moment (uncentered variance) vector; same length as m.

step: u64

Number of optimizer steps taken for this group (1-indexed when used).

Implementations

impl OptimizerState

pub fn zeros(n: usize) -> Self

Construct a zeroed state for n parameters.

pub fn reset(&mut self)

Reset state back to zeros without reallocating.

Trait Implementations

impl Clone for OptimizerState

fn clone(&self) -> OptimizerState

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for OptimizerState

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.