SupervisedTuningSpec class final
Tuning Spec for Supervised Tuning for first party models.
Constructors
- SupervisedTuningSpec({required String trainingDatasetUri, String validationDatasetUri = '', SupervisedHyperParameters? hyperParameters, bool exportLastCheckpointOnly = false, EvaluationConfig? evaluationConfig, SupervisedTuningSpec_TuningMode tuningMode = SupervisedTuningSpec_TuningMode.$default})
- SupervisedTuningSpec.fromJson(Object? j)
-
factory
Properties
- evaluationConfig → EvaluationConfig?
-
Optional. Evaluation Config for Tuning Job.
final
- exportLastCheckpointOnly → bool
-
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.
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- hyperParameters → SupervisedHyperParameters?
-
Optional. Hyperparameters for SFT.
final
- qualifiedName → String
-
The fully qualified name of this message, i.e.,
google.protobuf.Durationorgoogle.rpc.ErrorInfo.finalinherited - runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- trainingDatasetUri → String
-
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.
final
- tuningMode → SupervisedTuningSpec_TuningMode
-
Tuning mode.
final
- validationDatasetUri → String
-
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.
final
Methods
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
toJson(
) → Object -
toString(
) → String -
A string representation of this object.
override
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited
Constants
- fullyQualifiedName → const String