class

OpenAI::FineTuneSupervisedHyperparameters

Inherits JSON::Serializable < Reference < Object

The hyperparameters used for the fine-tuning job.

Constructors

new(pull : JSON::PullParser)
Source
new(batch_size : FineTuneSupervisedHyperparametersBatchSize | Nil = nil, learning_rate_multiplier : FineTuneSupervisedHyperparametersLearningRateMultiplier | Nil = nil, n_epochs : FineTuneSupervisedHyperparametersNEpochs | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

batch_size

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

Source
batch_size=(batch_size : FineTuneSupervisedHyperparametersBatchSize | Nil)

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

Source
learning_rate_multiplier

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

Source
learning_rate_multiplier=(learning_rate_multiplier : FineTuneSupervisedHyperparametersLearningRateMultiplier | Nil)

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

Source
n_epochs

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

Source
n_epochs=(n_epochs : FineTuneSupervisedHyperparametersNEpochs | Nil)

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

Source