Interface TrainProcessorVersionRequest.FoundationModelTuningOptionsOrBuilder (2.92.0) 

public static interface TrainProcessorVersionRequest.FoundationModelTuningOptionsOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getLearningRateMultiplier()

public abstract float getLearningRateMultiplier()

Optional. The multiplier to apply to the recommended learning rate. Valid values are between 0.1 and 10. If not provided, recommended learning rate will be used.

float learning_rate_multiplier = 3 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
float

The learningRateMultiplier.

getPreviousFineTunedProcessorVersionName()

public abstract String getPreviousFineTunedProcessorVersionName()

Optional. Resource name of a previously fine tuned version id to copy the overwritten configs from. The base_processor_version should be newer than the base processor version used to fine tune this provided processor version. Format: projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}.

string previous_fine_tuned_processor_version_name = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
String

The previousFineTunedProcessorVersionName.

getPreviousFineTunedProcessorVersionNameBytes()

public abstract ByteString getPreviousFineTunedProcessorVersionNameBytes()

Optional. Resource name of a previously fine tuned version id to copy the overwritten configs from. The base_processor_version should be newer than the base processor version used to fine tune this provided processor version. Format: projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}.

string previous_fine_tuned_processor_version_name = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
ByteString

The bytes for previousFineTunedProcessorVersionName.

getTrainSteps()

public abstract int getTrainSteps()

Optional. The number of steps to run for model tuning. Valid values are between 1 and 400. If not provided, recommended steps will be used.

int32 train_steps = 2 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The trainSteps.