Struct BERTOptimizer 

pub struct BERTOptimizer { /* private fields */ }

BERT-specific optimizer with tailored hyperparameters and scheduling

Implementations

impl BERTOptimizer

pub fn new( learning_rate: f32, warmup_steps: usize, total_steps: usize, layer_wise_decay: f32, ) -> Result<Self>

Trait Implementations

impl Optimizer for BERTOptimizer

fn update(&mut self, parameter: &mut Tensor, grad: &Tensor) -> Result<()>

Updates a parameter based on its gradient.

fn zero_grad(&mut self)

Clears all accumulated gradients.

fn step(&mut self)

Performs a single optimization step.

fn get_lr(&self) -> f32

Gets the current learning rate.

fn set_lr(&mut self, lr: f32)

Sets a new learning rate.

fn accumulate_grad( &mut self, parameter: &mut Tensor, grad: &Tensor, ) -> Result<(), TrustformersError>

Accumulates gradients for gradient accumulation.

fn apply_accumulated_grads( &mut self, accumulation_steps: usize, ) -> Result<(), TrustformersError>

Applies accumulated gradients after gradient accumulation.