Struct RftHyperParametersBuilder 

#[non_exhaustive]
pub struct RftHyperParametersBuilder { /* private fields */ }

A builder for RftHyperParameters.

Implementations

impl RftHyperParametersBuilder

pub fn epoch_count(self, input: i32) -> Self

Number of training epochs to run during reinforcement fine-tuning. Higher values may improve performance but increase training time.

pub fn set_epoch_count(self, input: Option<i32>) -> Self

Number of training epochs to run during reinforcement fine-tuning. Higher values may improve performance but increase training time.

pub fn get_epoch_count(&self) -> &Option<i32>

Number of training epochs to run during reinforcement fine-tuning. Higher values may improve performance but increase training time.

pub fn batch_size(self, input: i32) -> Self

Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training. Larger batches may improve training stability.

pub fn set_batch_size(self, input: Option<i32>) -> Self

Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training. Larger batches may improve training stability.

pub fn get_batch_size(&self) -> &Option<i32>

Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training. Larger batches may improve training stability.

pub fn learning_rate(self, input: f32) -> Self

Learning rate for the reinforcement fine-tuning. Controls how quickly the model adapts to reward signals.

pub fn set_learning_rate(self, input: Option<f32>) -> Self

Learning rate for the reinforcement fine-tuning. Controls how quickly the model adapts to reward signals.

pub fn get_learning_rate(&self) -> &Option<f32>

Learning rate for the reinforcement fine-tuning. Controls how quickly the model adapts to reward signals.

pub fn max_prompt_length(self, input: i32) -> Self

Maximum length of input prompts during RFT training, measured in tokens. Longer prompts allow more context but increase memory usage and training-time.

pub fn set_max_prompt_length(self, input: Option<i32>) -> Self

Maximum length of input prompts during RFT training, measured in tokens. Longer prompts allow more context but increase memory usage and training-time.

pub fn get_max_prompt_length(&self) -> &Option<i32>

Maximum length of input prompts during RFT training, measured in tokens. Longer prompts allow more context but increase memory usage and training-time.

pub fn training_sample_per_prompt(self, input: i32) -> Self

Number of response samples generated per prompt during RFT training. More samples provide better reward signal estimation.

pub fn set_training_sample_per_prompt(self, input: Option<i32>) -> Self

Number of response samples generated per prompt during RFT training. More samples provide better reward signal estimation.

pub fn get_training_sample_per_prompt(&self) -> &Option<i32>

Number of response samples generated per prompt during RFT training. More samples provide better reward signal estimation.

pub fn inference_max_tokens(self, input: i32) -> Self

Maximum number of tokens the model can generate in response to each prompt during RFT training.

pub fn set_inference_max_tokens(self, input: Option<i32>) -> Self

Maximum number of tokens the model can generate in response to each prompt during RFT training.

pub fn get_inference_max_tokens(&self) -> &Option<i32>

Maximum number of tokens the model can generate in response to each prompt during RFT training.

pub fn reasoning_effort(self, input: ReasoningEffort) -> Self

Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time.

pub fn set_reasoning_effort(self, input: Option<ReasoningEffort>) -> Self

Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time.

pub fn get_reasoning_effort(&self) -> &Option<ReasoningEffort>

Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time.

pub fn eval_interval(self, input: i32) -> Self

Interval between evaluation runs during RFT training, measured in training steps. More frequent evaluation provides better monitoring.

pub fn set_eval_interval(self, input: Option<i32>) -> Self

Interval between evaluation runs during RFT training, measured in training steps. More frequent evaluation provides better monitoring.

pub fn get_eval_interval(&self) -> &Option<i32>

Interval between evaluation runs during RFT training, measured in training steps. More frequent evaluation provides better monitoring.

pub fn build(self) -> RftHyperParameters

Consumes the builder and constructs a RftHyperParameters.

Trait Implementations

impl Clone for RftHyperParametersBuilder

fn clone(&self) -> RftHyperParametersBuilder

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RftHyperParametersBuilder

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

Formats the value using the given formatter.

impl Default for RftHyperParametersBuilder

fn default() -> RftHyperParametersBuilder

Returns the “default value” for a type.

impl PartialEq for RftHyperParametersBuilder

fn eq(&self, other: &RftHyperParametersBuilder) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for RftHyperParametersBuilder