Package com.google.genai.types

Class SupervisedTuningSpec

java.lang.Object

com.google.genai.JsonSerializable

com.google.genai.types.SupervisedTuningSpec

public abstract class SupervisedTuningSpec
extends JsonSerializable

Tuning Spec for Supervised Tuning for first party models.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	SupervisedTuningSpec.Builder	Builder for SupervisedTuningSpec.

Constructor Summary

Constructors

Constructor	Description
SupervisedTuningSpec()

Method Summary

Modifier and Type	Method	Description
static SupervisedTuningSpec.Builder	builder()	Instantiates a builder for SupervisedTuningSpec.
abstract Optional<Boolean>	exportLastCheckpointOnly()	Optional.
static SupervisedTuningSpec	fromJson(String jsonString)	Deserializes a JSON string to a SupervisedTuningSpec object.
abstract Optional<SupervisedHyperParameters>	hyperParameters()	Optional.
abstract SupervisedTuningSpec.Builder	toBuilder()	Creates a builder with the same values as this instance.
abstract Optional<String>	trainingDatasetUri()	Required.
abstract Optional<TuningMode>	tuningMode()	Tuning mode.
abstract Optional<String>	validationDatasetUri()	Optional.

Methods inherited from class com.google.genai.JsonSerializable

stringToJsonNode, toJson

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

SupervisedTuningSpec

public SupervisedTuningSpec()

Method Details

exportLastCheckpointOnly

public abstract Optional<Boolean> exportLastCheckpointOnly()

Optional. If set to true, disable intermediate checkpoints for SFT and only the last checkpoint will be exported. Otherwise, enable intermediate checkpoints for SFT. Default is false.

hyperParameters

public abstract Optional<SupervisedHyperParameters> hyperParameters()

Optional. Hyperparameters for SFT.

trainingDatasetUri

public abstract Optional<String> trainingDatasetUri()

Required. Training dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset.

tuningMode

public abstract Optional<TuningMode> tuningMode()

Tuning mode.

validationDatasetUri

public abstract Optional<String> validationDatasetUri()

Optional. Validation dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset.

builder

public static SupervisedTuningSpec.Builder builder()

Instantiates a builder for SupervisedTuningSpec.

toBuilder

public abstract SupervisedTuningSpec.Builder toBuilder()

Creates a builder with the same values as this instance.

fromJson

public static SupervisedTuningSpec fromJson(String jsonString)

Deserializes a JSON string to a SupervisedTuningSpec object.