Package com.google.genai.types

Class SupervisedTuningDataStats

java.lang.Object
com.google.genai.JsonSerializable
com.google.genai.types.SupervisedTuningDataStats
public abstract class SupervisedTuningDataStats extends JsonSerializable
Tuning data statistics for Supervised Tuning.

  • Constructor Details

    • SupervisedTuningDataStats

      public SupervisedTuningDataStats()

  • Method Details

    • droppedExampleReasons

      public abstract Optional<List<String>> droppedExampleReasons()
      Output only. For each index in `truncated_example_indices`, the user-facing reason why the example was dropped.

    • totalBillableCharacterCount

      public abstract Optional<Long> totalBillableCharacterCount()
      Output only. Number of billable characters in the tuning dataset.

    • totalBillableTokenCount

      public abstract Optional<Long> totalBillableTokenCount()
      Output only. Number of billable tokens in the tuning dataset.

    • totalTruncatedExampleCount

      public abstract Optional<Long> totalTruncatedExampleCount()
      Output only. The number of examples in the dataset that have been dropped. An example can be dropped for reasons including: too many tokens, contains an invalid image, contains too many images, etc.

    • totalTuningCharacterCount

      public abstract Optional<Long> totalTuningCharacterCount()
      Output only. Number of tuning characters in the tuning dataset.

    • truncatedExampleIndices

      public abstract Optional<List<Long>> truncatedExampleIndices()
      Output only. A partial sample of the indices (starting from 1) of the dropped examples.

    • tuningDatasetExampleCount

      public abstract Optional<Long> tuningDatasetExampleCount()
      Output only. Number of examples in the tuning dataset.

    • tuningStepCount

      public abstract Optional<Long> tuningStepCount()
      Output only. Number of tuning steps for this Tuning Job.

    • userDatasetExamples

      public abstract Optional<List<Content>> userDatasetExamples()
      Output only. Sample user messages in the training dataset uri.

    • userInputTokenDistribution

      public abstract Optional<SupervisedTuningDatasetDistribution> userInputTokenDistribution()
      Output only. Dataset distributions for the user input tokens.

    • userMessagePerExampleDistribution

      public abstract Optional<SupervisedTuningDatasetDistribution> userMessagePerExampleDistribution()
      Output only. Dataset distributions for the messages per example.

    • userOutputTokenDistribution

      public abstract Optional<SupervisedTuningDatasetDistribution> userOutputTokenDistribution()
      Output only. Dataset distributions for the user output tokens.

    • builder

      public static SupervisedTuningDataStats.Builder builder()
      Instantiates a builder for SupervisedTuningDataStats.

    • toBuilder

      public abstract SupervisedTuningDataStats.Builder toBuilder()
      Creates a builder with the same values as this instance.

    • fromJson

      public static SupervisedTuningDataStats fromJson(String jsonString)
      Deserializes a JSON string to a SupervisedTuningDataStats object.