OpenAI API

FineTuneDPOMethod

object

Configuration for the DPO fine-tuning method.

hyperparametersobject

The hyperparameters used for the fine-tuning job.

Show Child Parameters
Example

FineTuneMethod

object

The method used for fine-tuning.

typestring

The type of method. Is either supervised or dpo.

Allowed values:superviseddpo

supervisedobject

Configuration for the supervised fine-tuning method.

Show Child Parameters
dpoobject

Configuration for the DPO fine-tuning method.

Show Child Parameters
Example

FineTunePreferenceRequestInput

object

The per-line training example of a fine-tuning input file for chat models using the dpo method.

inputobject
Show Child Parameters
preferred_completionOne Of
array

The preferred completion message for the output.

<= 1 items

Assistant messageobject

Messages sent by the model in response to user messages.

Show Child Parameters
non_preferred_completionOne Of
array

The non-preferred completion message for the output.

<= 1 items

Assistant messageobject

Messages sent by the model in response to user messages.

Show Child Parameters
Example

FineTuneSupervisedMethod

object

Configuration for the supervised fine-tuning method.

hyperparametersobject

The hyperparameters used for the fine-tuning job.

Show Child Parameters
Example

Fine-Tuning Job Integration

object
typestringrequired

The type of the integration being enabled for the fine-tuning job

Allowed values:wandb

wandbobjectrequired

The settings for your integration with Weights and Biases. This payload specifies the project that
metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags
to your run, and set a default entity (team, username, etc) to be associated with your run.

Show Child Parameters
Example