Optional
abortAbort signal which can be used to cancel the request.
NOTE: AbortSignal is a client-only operation. Using it to cancel an operation will not cancel the request in the service. You will still be charged usage for any applicable operations.
Optional
adapterAdapter size for tuning.
Optional
batchThe batch size hyperparameter for tuning. If not set, a default of 4 or 16 will be used based on the number of training examples.
Optional
descriptionThe description of the TuningJob
Optional
epochNumber of complete passes the model makes over the entire training dataset during training.
Optional
exportIf set to true, disable intermediate checkpoints for SFT and only the last checkpoint will be exported. Otherwise, enable intermediate checkpoints for SFT.
Optional
httpUsed to override HTTP request options.
Optional
learningThe learning rate hyperparameter for tuning. If not set, a default of 0.001 or 0.0002 will be calculated based on the number of training examples.
Optional
learningMultiplier for adjusting the default learning rate.
Optional
preThe optional checkpoint id of the pre-tuned model to use for tuning, if applicable.
Optional
tunedThe display name of the tuned Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
Optional
validationCloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.
Supervised fine-tuning job creation request - optional fields.