SupervisedTuningDataStats

@Serializable
data class SupervisedTuningDataStats(val droppedExampleReasons: List<String>? = null, val totalBillableCharacterCount: Long? = null, val totalBillableTokenCount: Long? = null, val totalTruncatedExampleCount: Long? = null, val totalTuningCharacterCount: Long? = null, val truncatedExampleIndices: List<Long>? = null, val tuningDatasetExampleCount: Long? = null, val tuningStepCount: Long? = null, val userDatasetExamples: List<Content>? = null, val userInputTokenDistribution: SupervisedTuningDatasetDistribution? = null, val userMessagePerExampleDistribution: SupervisedTuningDatasetDistribution? = null, val userOutputTokenDistribution: SupervisedTuningDatasetDistribution? = null)

Tuning data statistics for Supervised Tuning. This data type is not supported in Gemini API.

Constructors

Link copied to clipboard
constructor(droppedExampleReasons: List<String>? = null, totalBillableCharacterCount: Long? = null, totalBillableTokenCount: Long? = null, totalTruncatedExampleCount: Long? = null, totalTuningCharacterCount: Long? = null, truncatedExampleIndices: List<Long>? = null, tuningDatasetExampleCount: Long? = null, tuningStepCount: Long? = null, userDatasetExamples: List<Content>? = null, userInputTokenDistribution: SupervisedTuningDatasetDistribution? = null, userMessagePerExampleDistribution: SupervisedTuningDatasetDistribution? = null, userOutputTokenDistribution: SupervisedTuningDatasetDistribution? = null)

Properties

Link copied to clipboard

Output only. For each index in truncated_example_indices, the user-facing reason why the example was dropped.

Link copied to clipboard

Output only. Number of billable characters in the tuning dataset.

Link copied to clipboard

Output only. Number of billable tokens in the tuning dataset.

Link copied to clipboard

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.

Link copied to clipboard

Output only. Number of tuning characters in the tuning dataset.

Link copied to clipboard

Output only. A partial sample of the indices (starting from 1) of the dropped examples.

Link copied to clipboard

Output only. Number of examples in the tuning dataset.

Link copied to clipboard
val tuningStepCount: Long? = null

Output only. Number of tuning steps for this Tuning Job.

Link copied to clipboard

Output only. Sample user messages in the training dataset uri.

Link copied to clipboard

Output only. Dataset distributions for the user input tokens.

Link copied to clipboard

Output only. Dataset distributions for the messages per example.

Link copied to clipboard

Output only. Dataset distributions for the user output tokens.