google-genai-kotlin/com.google.genai.kotlin.types/SupervisedTuningSpec

SupervisedTuningSpec

@Serializable
data class SupervisedTuningSpec(val exportLastCheckpointOnly: Boolean? = null, val hyperParameters: SupervisedHyperParameters? = null, val trainingDatasetUri: String? = null, val tuningMode: TuningMode? = null, val validationDatasetUri: String? = null)

Supervised tuning spec for tuning.

Constructors

Link copied to clipboard
constructor(exportLastCheckpointOnly: Boolean? = null, hyperParameters: SupervisedHyperParameters? = null, trainingDatasetUri: String? = null, tuningMode: TuningMode? = null, validationDatasetUri: String? = null)

Properties

Link copied to clipboard
val exportLastCheckpointOnly: Boolean? = null

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.

Link copied to clipboard
val hyperParameters: SupervisedHyperParameters? = null

Optional. Hyperparameters for SFT.

Link copied to clipboard
val trainingDatasetUri: String? = null

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.

Link copied to clipboard
val tuningMode: TuningMode? = null

Tuning mode.

Link copied to clipboard
val validationDatasetUri: String? = null

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.