Customizing GPT-3 for your application

OpenAI

Fine-tune with a single command.

Developers can now fine-tune GPT‑3 on their own data, creating a custom version tailored to their application. Customizing makes GPT‑3 reliable for a wider variety of use cases and makes running the model cheaper and faster.

You can use an existing dataset of virtually any shape and size, or incrementally add data based on user feedback. With fine-tuning, one API customer was able to increase correct outputs from 83% to 95%. By adding new data from their product each week, another reduced error rates by 50%.

To get started, just run a single command in the OpenAI command line tool with a file you provide. Your custom version will start training and then be available immediately in our API.

It takes less than 100 examples to start seeing the benefits of fine-tuning GPT‑3 and performance continues to improve as you add more data. In research published last June⁠, we showed how fine-tuning with less than 100 examples can improve GPT‑3’s performance on certain tasks. We’ve also found that each doubling of the number of examples tends to improve quality linearly.

With one of our most challenging research datasets, grade school math problems⁠, fine-tuning GPT‑3 improves accuracy by 2 to 4x over what’s possible with prompt design.

Customizing GPT‑3 improves the reliability of output, offering more consistent results that you can count on for production use-cases. One customer found that customizing GPT‑3 reduced the frequency of unreliable outputs from 17% to 5%. Since custom versions of GPT‑3 are tailored to your application, the prompt can be much shorter, reducing costs and improving latency.

Whether text generation, summarization, classification, or any other natural language task GPT‑3 is capable of performing, customizing GPT‑3 will improve performance.

Apps powered by customized versions of GPT-3

All API customers can customize GPT‑3 today. Sign-up and get started with the fine-tuning documentation⁠(opens in a new window).