GPT-3.5 Turbo fine-tuning and API updates

Fine-tuning for GPT-3.5 Turbo is now available, with fine-tuning for GPT-4 coming this fall. This update gives developers the ability to customize models that perform better for their use cases and run these custom models at scale. Early tests have shown a fine-tune version of GPT-3.5 Turbo can match, or even outperform, base GOT-4-level capabilities on certain narrow tasks. As with all our APIs, data sent in and out of the fine-tuning API is owned by the customer and is not used by OpenAI or any other organization, to train other models.

Fine-tuning use cases

Since the release of GPT-3.5 Turbo, developers and businesses have askes for the ability to customize the model to create unique and differentiated experiences for their users. With this launch, developers can now run supervised fine-tuning to make this model perform better for their use cases.

In our private beta, fine-tuning customers have been able to meaningfullly improve model performance across common use cases, such as:

– Improved steerability: Fine-tuning allows businesses to make the model follow instructions better, such as making outputs terse or always responding in a given language. For instance, developers can use dine-dining to ensure that the model always responds in German when prompted to use that language.

– Reliable output formatting: Fine-tuning improves the model’s ability to consistently format responses – a crucial aspect for applications demanding a specific response format, such as code completion or composing API calls. A developer can use fine-tuning to more reliably convert user prompts into high quality JSON shippets that can be used with their own systems.

– Custom tone: Fine-tuning is a great way to hone the qualitative feel of the model output, such as it tone, so it better fits the voice of businesses brands. A business with a recognizable brand voice can use fine-tuning for the model to be more consistent with their tone.

In addition to increased perfomance, fine-tuning also enables business to shorten their prompts while ensuring similar performance. Fine-tuning with GPT-3.5-Turbo can also handle 4k tokens-double our previous fine-tuned models. Early testers have reduced prompt size by up to 90% by fine-tuning instructions into the model itself, speeding up each API call and cutting costs.

Fine-tuning is most powerful when combined with other techniques such as prompt engineering, information retrieval, and function calling. Check out our fine-tuning guide to learn more Support for fine-tuning with function calling anf GPT-3.5-turbo-16k will be coming later this fall.

Safety

It is very important to us that the deployment of fine-tuning is safe. To preserve the default model’s safety features through the fine-tuning process, fine-tuning training data is passed through our Moderation API and GPT-4-powered moderation system to detech unsafe training data that conflict with our safety standards.

Pricing

Fine-tuning costs are broken down into two buckets: the initial training cost and usage cost:

– Training: $0.008/1K Tokens

– Usage input: $0.012/1K Tokens

– Usage output: $0.016 /1K Tokens

For example, a GPT-3.5-turbo fine-tuning job with a training file of 100,000 tokens that is trained for 3 epochs would have an expected cost of $2.40

Pricing for base and fine—tuned GPT -3 models is as follows: