Struct TrainingConfig 

pub struct TrainingConfig {
    pub learning_rate: f32,
    pub negative_weight: f32,
    pub margin: f32,
    pub regularization: f32,
    pub epochs: usize,
    pub batch_size: usize,
    pub warmup_epochs: usize,
    pub use_self_adversarial: bool,
    pub adversarial_temperature: f32,
    pub early_stopping_patience: Option<usize>,
    pub early_stopping_min_delta: f32,
    pub positive_focus_epochs: Option<usize>,
}

Training configuration for box embeddings.

Fields

learning_rate: f32

Learning rate

negative_weight: f32

Weight for negative pairs

margin: f32

Margin for negative pairs

regularization: f32

L2 regularization weight

epochs: usize

Number of training epochs

batch_size: usize

Batch size (for mini-batch training)

warmup_epochs: usize

Warmup epochs (linear increase from 0.1*lr to lr)

use_self_adversarial: bool

Use self-adversarial negative sampling

adversarial_temperature: f32

Temperature for self-adversarial sampling

early_stopping_patience: Option<usize>

Early stopping patience (stop if no improvement for N epochs)

early_stopping_min_delta: f32

Minimum improvement for early stopping (relative)

positive_focus_epochs: Option<usize>

Multi-stage training: focus on positives first (epochs), then negatives

Trait Implementations

impl Clone for TrainingConfig

fn clone(&self) -> TrainingConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TrainingConfig

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

Formats the value using the given formatter.

impl Default for TrainingConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TrainingConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TrainingConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.