Struct TrainingConfig 

pub struct TrainingConfig {
    pub learning_rate: f64,
    pub batch_size: usize,
    pub gradient_accumulation_steps: usize,
    pub num_epochs: usize,
    pub warmup_ratio: f32,
    pub weight_decay: f32,
    pub max_grad_norm: f32,
    pub lr_scheduler_type: String,
    pub save_steps: usize,
    pub eval_steps: usize,
    pub logging_steps: usize,
}

Training hyperparameters

Fields

learning_rate: f64

Learning rate (benchmark optimal: 0.002)

batch_size: usize

Batch size (benchmark optimal: 32)

gradient_accumulation_steps: usize

Gradient accumulation steps

num_epochs: usize

Number of epochs

warmup_ratio: f32

Warmup ratio

weight_decay: f32

Weight decay

max_grad_norm: f32

Max gradient norm

lr_scheduler_type: String

LR scheduler type

save_steps: usize

Save steps

eval_steps: usize

Evaluation steps

logging_steps: usize

Logging steps

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.