Struct FineTuneSupervisedMethodHyperparameters

pub struct FineTuneSupervisedMethodHyperparameters {
    pub batch_size: Option<FineTuneSupervisedMethodHyperparametersBatchSize>,
    pub learning_rate_multiplier: Option<FineTuneSupervisedMethodHyperparametersLearningRateMultiplier>,
    pub n_epochs: Option<FineTuneSupervisedMethodHyperparametersNEpochs>,
}

The hyperparameters used for the fine-tuning job.

Fields

batch_size: Option<FineTuneSupervisedMethodHyperparametersBatchSize>

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<FineTuneSupervisedMethodHyperparametersLearningRateMultiplier>

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

n_epochs: Option<FineTuneSupervisedMethodHyperparametersNEpochs>

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

Implementations

impl FineTuneSupervisedMethodHyperparameters

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

Create a builder for building FineTuneSupervisedMethodHyperparameters. On the builder, call .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 FineTuneSupervisedMethodHyperparameters.

Trait Implementations

impl Clone for FineTuneSupervisedMethodHyperparameters

fn clone(&self) -> FineTuneSupervisedMethodHyperparameters

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FineTuneSupervisedMethodHyperparameters

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

Formats the value using the given formatter.

impl Default for FineTuneSupervisedMethodHyperparameters

fn default() -> FineTuneSupervisedMethodHyperparameters

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FineTuneSupervisedMethodHyperparameters

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

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for FineTuneSupervisedMethodHyperparameters

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

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 FineTuneSupervisedMethodHyperparameters

impl StructuralPartialEq for FineTuneSupervisedMethodHyperparameters