oa::ml::training::PpoTrainerMetrics

Scalar results from the last completed PPO update epoch.

StRust public API

Declaration

pub struct PpoTrainerMetrics { pub rollout: u64, pub update_epoch: u64, pub total_loss: f32, pub policy_loss: f32, pub value_loss: f32, pub entropy: f32, }
Public Rust declaration.

Public Methods

fn clone(&self) -> PpoTrainerMetrics
fn fmt(&self, f: &mut Formatter<'_>) -> Result
fn eq(&self, other: &PpoTrainerMetrics) -> bool

Associated Functions

fn default() -> PpoTrainerMetrics

Public Data Members

rolloutu64field
update_epochu64field
total_lossf32field
policy_lossf32field
value_lossf32field
entropyf32field

Public Method Documentation

fn clone( &self ) -> PpoTrainerMetrics
No public source comment is attached to this declaration.
fn fmt( &self, f: &mut Formatter<'_> ) -> Result
No public source comment is attached to this declaration.
fn eq( &self, other: &PpoTrainerMetrics ) -> bool
No public source comment is attached to this declaration.
fn default() -> PpoTrainerMetrics
No public source comment is attached to this declaration.