OpenAI API

FineTuningJobCheckpoint

object

The fine_tuning.job.checkpoint object represents a model checkpoint for a fine-tuning job that is ready to use.

idstringrequired

The checkpoint identifier, which can be referenced in the API endpoints.

created_atintegerrequired

The Unix timestamp (in seconds) for when the checkpoint was created.

fine_tuned_model_checkpointstringrequired

The name of the fine-tuned checkpoint model that is created.

step_numberintegerrequired

The step number that the checkpoint was created at.

metricsobjectrequired

Metrics at the step number during the fine-tuning job.

Show Child Parameters
fine_tuning_job_idstringrequired

The name of the fine-tuning job that this checkpoint was created from.

objectstringrequired

The object type, which is always “fine_tuning.job.checkpoint”.

Allowed values:fine_tuning.job.checkpoint

Example

FineTuningJobEvent

object

Fine-tuning job event object

objectstringrequired

The object type, which is always “fine_tuning.job.event”.

Allowed values:fine_tuning.job.event

idstringrequired

The object identifier.

created_atintegerrequired

The Unix timestamp (in seconds) for when the fine-tuning job was created.

levelstringrequired

The log level of the event.

Allowed values:infowarnerror

messagestringrequired

The message of the event.

typestring

The type of event.

Allowed values:messagemetrics

dataobject

The data associated with the event.

Example

FunctionObject

object
descriptionstring

A description of what the function does, used by the model to choose when and how to call the function.

namestringrequired

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

parametersobject

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

* Additional properties are allowed.
strictboolean

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

Default:false

Example

FunctionParameters

object

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

* Additional properties are allowed.

Image

object

Represents the url or the content of an image generated by the OpenAI API.

b64_jsonstring

The base64-encoded JSON of the generated image, if response_format is b64_json.

urlstring

The URL of the generated image, if response_format is url (default).

revised_promptstring

The prompt that was used to generate the image, if there was any revision to the prompt.

Example