Optional
droppedOutput only. For each index in truncated_example_indices
, the user-facing reason why the example was dropped.
Optional
totalOutput only. Number of billable characters in the tuning dataset.
Optional
totalOutput only. Number of billable tokens in the tuning dataset.
Optional
totalOutput 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.
Optional
totalOutput only. Number of tuning characters in the tuning dataset.
Optional
truncatedOutput only. A partial sample of the indices (starting from 1) of the dropped examples.
Optional
tuningOutput only. Number of examples in the tuning dataset.
Optional
tuningOutput only. Number of tuning steps for this Tuning Job.
Optional
userOutput only. Sample user messages in the training dataset uri.
Optional
userOutput only. Dataset distributions for the user input tokens.
Optional
userOutput only. Dataset distributions for the messages per example.
Optional
userOutput only. Dataset distributions for the user output tokens.
Tuning data statistics for Supervised Tuning.