All Implemented Interfaces:


public abstract class CreateTuningJobConfig
extends JsonSerializable

Fine-tuning job creation request - optional fields.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public abstract class`	`CreateTuningJobConfig.Builder`	Builder for CreateTuningJobConfig.

Field Summary

Fields
Modifier and Type	Field	Description
`public final static String`	`MAX_READ_LENGTH_PROPERTY`

Constructor Summary

Constructors
Constructor	Description
`CreateTuningJobConfig()`

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`abstract Optional<HttpOptions>`	`httpOptions()`	Used to override HTTP request options.
`abstract Optional<TuningMethod>`	`method()`	The method to use for tuning (SUPERVISED_FINE_TUNING or PREFERENCE_TUNING or DISTILLATION).
`abstract Optional<TuningValidationDataset>`	`validationDataset()`	Validation dataset for tuning.
`abstract Optional<String>`	`tunedModelDisplayName()`	The display name of the tuned Model.
`abstract Optional<String>`	`description()`	The description of the TuningJob
`abstract Optional<Integer>`	`epochCount()`	Number of complete passes the model makes over the entire training dataset during training.
`abstract Optional<Float>`	`learningRateMultiplier()`	Multiplier for adjusting the default learning rate.
`abstract Optional<Boolean>`	`exportLastCheckpointOnly()`	If set to true, disable intermediate checkpoints and only the last checkpoint will be exported.
`abstract Optional<String>`	`preTunedModelCheckpointId()`	The optional checkpoint id of the pre-tuned model to use for tuning, if applicable.
`abstract Optional<AdapterSize>`	`adapterSize()`	Adapter size for tuning.
`abstract Optional<TuningMode>`	`tuningMode()`	Tuning mode for tuning.
`abstract Optional<String>`	`customBaseModel()`	Custom base model for tuning.
`abstract Optional<Integer>`	`batchSize()`	The batch size hyperparameter for tuning.
`abstract Optional<Float>`	`learningRate()`	The learning rate for tuning.
`abstract Optional<EvaluationConfig>`	`evaluationConfig()`	Evaluation config for the tuning job.
`abstract Optional<Map<String, String>>`	`labels()`	Optional.
`abstract Optional<Float>`	`beta()`	Weight for KL Divergence regularization, Preference Optimization tuning only.
`abstract Optional<String>`	`baseTeacherModel()`	The base teacher model that is being distilled.
`abstract Optional<String>`	`tunedTeacherModelSource()`	The resource name of the Tuned teacher model.
`abstract Optional<Float>`	`sftLossWeightMultiplier()`	Multiplier for adjusting the weight of the SFT loss.
`abstract Optional<String>`	`outputUri()`	The Google Cloud Storage location where the tuning job outputs are written.
`abstract Optional<EncryptionSpec>`	`encryptionSpec()`	The encryption spec of the tuning job.
`static CreateTuningJobConfig.Builder`	`builder()`	Instantiates a builder for CreateTuningJobConfig.
`abstract CreateTuningJobConfig.Builder`	`toBuilder()`	Creates a builder with the same values as this instance.
`static CreateTuningJobConfig`	`fromJson(String jsonString)`	Deserializes a JSON string to a CreateTuningJobConfig object.

Methods inherited from class com.google.genai.JsonSerializable
fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - CreateTuningJobConfig
```
CreateTuningJobConfig()
```
- Method Detail
  - httpOptions
```
 abstract Optional<HttpOptions> httpOptions()
```
    Used to override HTTP request options.
  - method
```
 abstract Optional<TuningMethod> method()
```
    The method to use for tuning (SUPERVISED_FINE_TUNING or PREFERENCE_TUNING or DISTILLATION). If not set, the default method (SFT) will be used.
  - validationDataset
```
 abstract Optional<TuningValidationDataset> validationDataset()
```
    Validation dataset for tuning. The dataset must be formatted as a JSONL file.
  - tunedModelDisplayName
```
 abstract Optional<String> tunedModelDisplayName()
```
    The display name of the tuned Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  - description
```
 abstract Optional<String> description()
```
    The description of the TuningJob
  - epochCount
```
 abstract Optional<Integer> epochCount()
```
    Number of complete passes the model makes over the entire training dataset during training.
  - learningRateMultiplier
```
 abstract Optional<Float> learningRateMultiplier()
```
    Multiplier for adjusting the default learning rate. 1P models only. Mutually exclusive with learning_rate.
  - exportLastCheckpointOnly
```
 abstract Optional<Boolean> exportLastCheckpointOnly()
```
    If set to true, disable intermediate checkpoints and only the last checkpoint will be exported. Otherwise, enable intermediate checkpoints.
  - preTunedModelCheckpointId
```
 abstract Optional<String> preTunedModelCheckpointId()
```
    The optional checkpoint id of the pre-tuned model to use for tuning, if applicable.
  - adapterSize
```
 abstract Optional<AdapterSize> adapterSize()
```
    Adapter size for tuning.
  - tuningMode
```
 abstract Optional<TuningMode> tuningMode()
```
    Tuning mode for tuning.
  - customBaseModel
```
 abstract Optional<String> customBaseModel()
```
    Custom base model for tuning. This is only supported for OSS models in Gemini Enterprise Agent Platform.
  - batchSize
```
 abstract Optional<Integer> batchSize()
```
    The batch size hyperparameter for tuning. This is only supported for OSS models in Gemini Enterprise Agent Platform.
  - learningRate
```
 abstract Optional<Float> learningRate()
```
    The learning rate for tuning. OSS models only. Mutually exclusive with learning_rate_multiplier.
  - evaluationConfig
```
 abstract Optional<EvaluationConfig> evaluationConfig()
```
    Evaluation config for the tuning job.
  - labels
```
 abstract Optional<Map<String, String>> labels()
```
    Optional. The labels with user-defined metadata to organize TuningJob and generated resources such as Model and Endpoint. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
  - beta
```
 abstract Optional<Float> beta()
```
    Weight for KL Divergence regularization, Preference Optimization tuning only.
  - baseTeacherModel
```
 abstract Optional<String> baseTeacherModel()
```
    The base teacher model that is being distilled. Distillation only.
  - tunedTeacherModelSource
```
 abstract Optional<String> tunedTeacherModelSource()
```
    The resource name of the Tuned teacher model. Distillation only.
  - sftLossWeightMultiplier
```
 abstract Optional<Float> sftLossWeightMultiplier()
```
    Multiplier for adjusting the weight of the SFT loss. Distillation only.
  - outputUri
```
 abstract Optional<String> outputUri()
```
    The Google Cloud Storage location where the tuning job outputs are written.
  - encryptionSpec
```
 abstract Optional<EncryptionSpec> encryptionSpec()
```
    The encryption spec of the tuning job. Customer-managed encryption key options for a TuningJob. If this is set, then all resources created by the TuningJob will be encrypted with provided encryption key.
  - builder
```
 static CreateTuningJobConfig.Builder builder()
```
    Instantiates a builder for CreateTuningJobConfig.
  - toBuilder
```
 abstract CreateTuningJobConfig.Builder toBuilder()
```
    Creates a builder with the same values as this instance.
  - fromJson
```
 static CreateTuningJobConfig fromJson(String jsonString)
```
    Deserializes a JSON string to a CreateTuningJobConfig object.

Class CreateTuningJobConfig

Nested Class Summary

Field Summary

Constructor Summary

Enum Constant Summary

Method Summary

Methods inherited from class com.google.genai.JsonSerializable

Methods inherited from class java.lang.Object

Constructor Detail

CreateTuningJobConfig

Method Detail

httpOptions

method

validationDataset

tunedModelDisplayName

description

epochCount

learningRateMultiplier

exportLastCheckpointOnly

preTunedModelCheckpointId

adapterSize

tuningMode

customBaseModel

batchSize

learningRate

evaluationConfig

labels

beta

baseTeacherModel

tunedTeacherModelSource

sftLossWeightMultiplier

outputUri

encryptionSpec

builder

toBuilder

fromJson