GPT-3.5 Turbo fine-tuning and API updates

GPT-3.5 Turbo fine-tuning and API updates

OpenAI (United States) - Press Release: Developers can now bring their own data to customize GPT-3.5 Turbo for their use cases.

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-tuned version of GPT-3.5 Turbo can match, or even outperform, base GPT-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 asked 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 meaningfully 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 fine-tuning 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 snippets 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 its 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 performance, fine-tuning also enables businesses 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 and gpt-3.5-turbo-16k will be coming later this fall.

Fine-tuning steps:

Step 1 Prepare your data

Step 2 Upload files

Step 3 Create a fine-tuning job

Once a model finishes the fine-tuning process, it is available to be used in production right away and has the same shared rate limits as the underlying model.

Step 4 Use a fine-tuned model

We will also be debuting a fine-tuning UI in the near future, which will give developers easier access to information about ongoing fine-tuning jobs, completed model snapshots, and more.


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 a GPT-4 powered moderation system to detect unsafe training data that conflict with our safety standards.


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.

Updated GPT-3 models:

In July, we announced that the original GPT-3 base models (ada, babbage, curie, and davinci) would be turned off on January 4th, 2024. Today, we are making babbage-002 and davinci-002 available as replacements for these models, either as base or fine-tuned models. Customers can access those models by querying the Completions API.

These models can be fine-tuned with our new API endpoint /v1/fine_tuning/jobs. This new endpoint offers pagination and more extensibility to support the future evolution of the fine-tuning API. Transitioning from /v1/fine-tunes to the updated endpoint is straightforward and more details can be found in our new fine-tuning guide. This deprecates the old /v1/fine-tunes endpoint, which will be turned off on January 4th, 2024.

For more information about this article from OpenAI click here.

Source link

Other articles from OpenAI.

Interesting Links: - Your Gaming Marketplace with Video Games, Consoles, PC Gaming, Retro Gaming, Accessories, etc. !

Are you interested on the Weighing Industry? Visit Weighing Review the First and Leading Global Resource for the Weighing Industry where you can find news, case studies, suppliers, marketplace, etc!

Are you interested to include your Link here, visible on all articles and marketplace product pages? Contact us

© OpenAI / Automation Inside

Share this Article!

Interested? Submit your enquiry using the form below:

Only available for registered users. Sign In to your account or register here.

Introducing 8BitDo Micro: A pocket-sized Bluetooth controller compatible with Switch & Android

An Icon Returns: AtariⓇ and PLAION Announce Faithful Recreation of the Atari 2600 (™)