str
Required. The parent resource for new fine
tuning job instance.
filter
str
Required. Filter for selecting the feedback
labels that needs to be used for training.
This filter can be used to limit the feedback
labels used for tuning to a feedback labels
created or updated for a specific time-window
etc.
validate_only
bool
Optional. Run in validate only mode, no fine
tuning will actually run. Data quality
validations like training data distributions
will run. Even when set to false, the data
quality validations will still run but once the
validations complete we will proceed with the
fine tune, if applicable.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-06-03 UTC."],[],[]]