Struct FineTuneReinforcementHyperparameters

pub struct FineTuneReinforcementHyperparameters {
    pub batch_size: Option<FineTuneReinforcementHyperparametersBatchSize>,
    pub learning_rate_multiplier: Option<FineTuneReinforcementHyperparametersLearningRateMultiplier>,
    pub n_epochs: Option<FineTuneReinforcementHyperparametersNEpochs>,
    pub reasoning_effort: Option<FineTuneReinforcementHyperparametersReasoningEffort>,
    pub compute_multiplier: Option<FineTuneReinforcementHyperparametersComputeMultiplier>,
    pub eval_interval: Option<FineTuneReinforcementHyperparametersEvalInterval>,
    pub eval_samples: Option<FineTuneReinforcementHyperparametersEvalSamples>,
}

The hyperparameters used for the reinforcement fine-tuning job.

Fields

batch_size: Option<FineTuneReinforcementHyperparametersBatchSize>

Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

learning_rate_multiplier: Option<FineTuneReinforcementHyperparametersLearningRateMultiplier>

Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

n_epochs: Option<FineTuneReinforcementHyperparametersNEpochs>

The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

reasoning_effort: Option<FineTuneReinforcementHyperparametersReasoningEffort>

Level of reasoning effort.

compute_multiplier: Option<FineTuneReinforcementHyperparametersComputeMultiplier>

Multiplier on amount of compute used for exploring search space during training.

eval_interval: Option<FineTuneReinforcementHyperparametersEvalInterval>

The number of training steps between evaluation runs.

eval_samples: Option<FineTuneReinforcementHyperparametersEvalSamples>

Number of evaluation samples to generate per training step.

Implementations

impl FineTuneReinforcementHyperparameters

pub fn builder() -> FineTuneReinforcementHyperparametersBuilder<((), (), (), (), (), (), ())>

Create a builder for building FineTuneReinforcementHyperparameters. On the builder, call .batch_size(...)(optional), .learning_rate_multiplier(...)(optional), .n_epochs(...)(optional), .reasoning_effort(...)(optional), .compute_multiplier(...)(optional), .eval_interval(...)(optional), .eval_samples(...)(optional) to set the values of the fields. Finally, call .build() to create the instance of FineTuneReinforcementHyperparameters.

Trait Implementations

impl Clone for FineTuneReinforcementHyperparameters

fn clone(&self) -> FineTuneReinforcementHyperparameters

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FineTuneReinforcementHyperparameters

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

Formats the value using the given formatter.

impl Default for FineTuneReinforcementHyperparameters

fn default() -> FineTuneReinforcementHyperparameters

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FineTuneReinforcementHyperparameters

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for FineTuneReinforcementHyperparameters

fn eq(&self, other: &FineTuneReinforcementHyperparameters) -> 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 Serialize for FineTuneReinforcementHyperparameters

fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for FineTuneReinforcementHyperparameters

impl StructuralPartialEq for FineTuneReinforcementHyperparameters