Implementation:Openai Openai python Fine Tuning Jobs Create

Knowledge Sources	openai-python OpenAI Fine-tuning API
Domains	Fine_Tuning, Model_Training
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete tool for creating fine-tuning jobs with configurable hyperparameters provided by the OpenAI Python SDK.

Description

The Jobs resource provides a create() method that submits fine-tuning jobs. It accepts a base model, training file ID, optional hyperparameters, validation data, and a custom suffix. The returned FineTuningJob object tracks the job's status and will contain the fine-tuned model name upon completion.

Usage

Call client.fine_tuning.jobs.create() with a model and training file ID.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/resources/fine_tuning/jobs/jobs.py

Signature

class Jobs(SyncAPIResource):
    def create(
        self,
        *,
        model: Union[str, ChatModel],
        training_file: str,
        hyperparameters: Hyperparameters | NotGiven = NOT_GIVEN,
        validation_file: Optional[str] | NotGiven = NOT_GIVEN,
        suffix: Optional[str] | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        integrations: Optional[List[Integration]] | NotGiven = NOT_GIVEN,
        method: Method | NotGiven = NOT_GIVEN,
    ) -> FineTuningJob:
        """
        Creates a fine-tuning job.

        Args:
            model: Base model to fine-tune (e.g., "gpt-4o-mini-2024-07-18").
            training_file: File ID of uploaded training data.
            hyperparameters: Training hyperparameters (n_epochs, batch_size, learning_rate_multiplier).
            validation_file: File ID of validation data.
            suffix: Custom model name suffix (max 64 chars).
            seed: Random seed for reproducibility.
        """

Import

from openai import OpenAI
# Access via client.fine_tuning.jobs.create()

I/O Contract

Inputs

Name	Type	Required	Description
model	Union[str, ChatModel]	Yes	Base model to fine-tune
training_file	str	Yes	File ID from upload step
hyperparameters	Hyperparameters	No	n_epochs, batch_size, learning_rate_multiplier
validation_file	str	No	Validation data file ID
suffix	str	No	Custom model name suffix (max 64 chars)
seed	int	No	Random seed for reproducibility

Outputs

Name	Type	Description
job	FineTuningJob	Job object with .id, .status, .fine_tuned_model

Usage Examples

Basic Fine-tuning Job

from openai import OpenAI

client = OpenAI()
job = client.fine_tuning.jobs.create(
    training_file="file-abc123",
    model="gpt-4o-mini-2024-07-18",
)
print(f"Job ID: {job.id}")
print(f"Status: {job.status}")

With Hyperparameters

job = client.fine_tuning.jobs.create(
    training_file="file-abc123",
    model="gpt-4o-mini-2024-07-18",
    validation_file="file-val456",
    hyperparameters={
        "n_epochs": 3,
        "batch_size": 4,
        "learning_rate_multiplier": 0.1,
    },
    suffix="my-classifier",
    seed=42,
)

Related Pages

Implements Principle

• Principle:Openai_Openai_python_Fine_Tuning_Job_Creation

Requires Environment

• Environment:Openai_Openai_python_Python_3_9_Plus