pub struct FineTuneDpoHyperparameters {
pub beta: Option<FineTuneDpoHyperparametersBeta>,
pub batch_size: Option<FineTuneDpoHyperparametersBatchSize>,
pub learning_rate_multiplier: Option<FineTuneDpoHyperparametersLearningRateMultiplier>,
pub n_epochs: Option<FineTuneDpoHyperparametersNEpochs>,
}
Expand description
The hyperparameters used for the DPO fine-tuning job.
Fields§
§beta: Option<FineTuneDpoHyperparametersBeta>
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<FineTuneDpoHyperparametersBatchSize>
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<FineTuneDpoHyperparametersLearningRateMultiplier>
Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
n_epochs: Option<FineTuneDpoHyperparametersNEpochs>
The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
Implementations§
Source§impl FineTuneDpoHyperparameters
impl FineTuneDpoHyperparameters
Sourcepub fn builder() -> FineTuneDpoHyperparametersBuilder<((), (), (), ())>
pub fn builder() -> FineTuneDpoHyperparametersBuilder<((), (), (), ())>
Create a builder for building FineTuneDpoHyperparameters
.
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 FineTuneDpoHyperparameters
.
Trait Implementations§
Source§impl Clone for FineTuneDpoHyperparameters
impl Clone for FineTuneDpoHyperparameters
Source§fn clone(&self) -> FineTuneDpoHyperparameters
fn clone(&self) -> FineTuneDpoHyperparameters
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source
. Read more