Struct FineTuneDpoMethodHyperparameters

pub struct FineTuneDpoMethodHyperparameters {
    pub beta: Option<FineTuneDpoMethodHyperparametersBeta>,
    pub batch_size: Option<FineTuneDpoMethodHyperparametersBatchSize>,
    pub learning_rate_multiplier: Option<FineTuneDpoMethodHyperparametersLearningRateMultiplier>,
    pub n_epochs: Option<FineTuneDpoMethodHyperparametersNEpochs>,
}

The hyperparameters used for the fine-tuning job.

Fields

beta: Option<FineTuneDpoMethodHyperparametersBeta>

The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.

batch_size: Option<FineTuneDpoMethodHyperparametersBatchSize>

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<FineTuneDpoMethodHyperparametersLearningRateMultiplier>

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

n_epochs: Option<FineTuneDpoMethodHyperparametersNEpochs>

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

Implementations

impl FineTuneDpoMethodHyperparameters

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

Create a builder for building FineTuneDpoMethodHyperparameters. On the builder, call .beta(...)(optional), .batch_size(...)(optional), .learning_rate_multiplier(...)(optional), .n_epochs(...)(optional) to set the values of the fields. Finally, call .build() to create the instance of FineTuneDpoMethodHyperparameters.

Trait Implementations

impl Clone for FineTuneDpoMethodHyperparameters

fn clone(&self) -> FineTuneDpoMethodHyperparameters

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FineTuneDpoMethodHyperparameters

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

Formats the value using the given formatter.

impl Default for FineTuneDpoMethodHyperparameters

fn default() -> FineTuneDpoMethodHyperparameters

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FineTuneDpoMethodHyperparameters

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

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for FineTuneDpoMethodHyperparameters

fn eq(&self, other: &FineTuneDpoMethodHyperparameters) -> 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 FineTuneDpoMethodHyperparameters

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 FineTuneDpoMethodHyperparameters

impl StructuralPartialEq for FineTuneDpoMethodHyperparameters