SupervisedTuningDataStats(mapping=None, *, ignore_unknown_fields=False, **kwargs)Tuning data statistics for Supervised Tuning.
Attributes |
|
|---|---|
| Name | Description |
tuning_dataset_example_count |
int
Output only. Number of examples in the tuning dataset. |
total_tuning_character_count |
int
Output only. Number of tuning characters in the tuning dataset. |
total_billable_character_count |
int
Output only. Number of billable characters in the tuning dataset. |
total_billable_token_count |
int
Output only. Number of billable tokens in the tuning dataset. |
tuning_step_count |
int
Output only. Number of tuning steps for this Tuning Job. |
user_input_token_distribution |
google.cloud.aiplatform_v1beta1.types.SupervisedTuningDatasetDistribution
Output only. Dataset distributions for the user input tokens. |
user_output_token_distribution |
google.cloud.aiplatform_v1beta1.types.SupervisedTuningDatasetDistribution
Output only. Dataset distributions for the user output tokens. |
user_message_per_example_distribution |
google.cloud.aiplatform_v1beta1.types.SupervisedTuningDatasetDistribution
Output only. Dataset distributions for the messages per example. |
user_dataset_examples |
MutableSequence[google.cloud.aiplatform_v1beta1.types.Content]
Output only. Sample user messages in the training dataset uri. |
total_truncated_example_count |
int
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. |
truncated_example_indices |
MutableSequence[int]
Output only. A partial sample of the indices (starting from 1) of the dropped examples. |
dropped_example_reasons |
MutableSequence[str]
Output only. For each index in truncated_example_indices, the user-facing reason why
the example was dropped.
|
Methods
SupervisedTuningDataStats
SupervisedTuningDataStats(mapping=None, *, ignore_unknown_fields=False, **kwargs)Tuning data statistics for Supervised Tuning.