Customize a model with fine-tuning

Prerequisites

• Read the When to use Azure OpenAI fine-tuning guide.
• An Azure subscription. Create one for free.
• An Azure OpenAI resource that's located in a region that supports fine-tuning of the Azure OpenAI model. Check the Model summary table and region availability for the list of available models by region and supported functionality. For more information, see Create a resource and deploy a model with Azure OpenAI.
• Fine-tuning access requires Cognitive Services OpenAI Contributor.
• If you do not already have access to view quota, and deploy models in Azure AI Foundry portal you will require additional permissions.

Models

The following models support fine-tuning:

• babbage-002
• davinci-002
• gpt-35-turbo (0613)
• gpt-35-turbo (1106)
• gpt-35-turbo (0125)
• gpt-4 (0613)^*
• gpt-4o (2024-08-06)
• gpt-4o-mini (2024-07-18)

^* Fine-tuning for this model is currently in public preview.

Or you can fine tune a previously fine-tuned model, formatted as base-model.ft-{jobid}.

Consult the models page to check which regions currently support fine-tuning.

Review the workflow for Azure AI Foundry

Take a moment to review the fine-tuning workflow for using Azure AI Foundry:

1. Prepare your training and validation data.
2. Use the Create custom model wizard in Azure AI Foundry portal to train your custom model.
   1. Select a base model.
   2. Choose your training data.
   3. Optionally, choose your validation data.
   4. Optionally, configure task parameters for your fine-tuning job.
   5. Review your choices and train your new custom model.
3. Check the status of your custom fine-tuned model.
4. Deploy your custom model for use.
5. Use your custom model.
6. Optionally, analyze your custom model for performance and fit.

Prepare your training and validation data

Your training data and validation data sets consist of input and output examples for how you would like the model to perform.

Different model types require a different format of training data.

{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Is Xbox better than PlayStation?"}, {"role": "assistant", "content": "I apologize, but I cannot provide personal opinions. My primary job is to assist you with any issues related to your Xbox device. Do you have any Xbox-related issues that need addressing?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Can I play PC games on my Xbox?"}, {"role": "assistant", "content": "While Xbox consoles don't natively support PC games, they can play an array of Xbox games, many of which are also available on PC. Can I assist you with finding games compatible with your Xbox device?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "I'm having trouble connecting my Xbox to the Wi-Fi."}, {"role": "assistant", "content": "No worries, let's go through the network settings on your Xbox. Can you please tell me what happens when you try to connect it to the Wi-Fi?"}]}

{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the capital of France?"}, {"role": "assistant", "content": "Paris", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Paris, as if everyone doesn't know that already.", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'Romeo and Juliet'?"}, {"role": "assistant", "content": "William Shakespeare", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Oh, just some guy named William Shakespeare. Ever heard of him?", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "How far is the Moon from Earth?"}, {"role": "assistant", "content": "384,400 kilometers", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Around 384,400 kilometers. Give or take a few, like that really matters.", "weight": 1}]}

{"messages": [{"role": "user", "content": [{"type": "text", "text": "What's in this image?"}, {"type": "image_url", "image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}, {"role": "assistant", "content": "The image appears to be a watercolor painting of a city skyline, featuring tall buildings and a recognizable structure often associated with Seattle, like the Space Needle. The artwork uses soft colors and brushstrokes to create a somewhat abstract and artistic representation of the cityscape."}]}

{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}

pip install openai==0.28.1

openai tools fine_tunes.prepare_data -f <LOCAL_FILE>

Use the Create custom model wizard

Azure AI Foundry provides the Create custom model wizard, so you can interactively create and train a fine-tuned model for your Azure resource.

1. Open Azure AI Foundry at https://oai.azure.com/ and sign in with credentials that have access to your Azure OpenAI resource. During the sign-in workflow, select the appropriate directory, Azure subscription, and Azure OpenAI resource.

2. In Azure AI Foundry portal, browse to the Tools > Fine-tuning pane, and select Fine-tune model.

   

The Create custom model wizard opens.

Select the base model

The first step in creating a custom model is to choose a base model. The Base model pane lets you choose a base model to use for your custom model. Your choice influences both the performance and the cost of your model.

Select the base model from the Base model type dropdown, and then select Next to continue.

You can create a custom model from one of the following available base models:

• babbage-002

• davinci-002

• gpt-35-turbo (0613)

• gpt-35-turbo (1106)

• gpt-35-turbo (0125)

• gpt-4 (0613)

• Or you can fine tune a previously fine-tuned model, formatted as base-model.ft-{jobid}.

For more information about our base models that can be fine-tuned, see Models.

Choose your training data

The next step is to either choose existing prepared training data or upload new prepared training data to use when customizing your model. The Training data pane displays any existing, previously uploaded datasets and also provides options to upload new training data.

• If your training data is already uploaded to the service, select Files from Azure OpenAI Connection.

  • Select the file from the dropdown list shown.

• To upload new training data, use one of the following options:

  • Select Local file to upload training data from a local file.

  • Select Azure blob or other shared web locations to import training data from Azure Blob or another shared web location.

For large data files, we recommend that you import from an Azure Blob store. Large files can become unstable when uploaded through multipart forms because the requests are atomic and can't be retried or resumed. For more information about Azure Blob Storage, see What is Azure Blob Storage?

Upload training data from local file

You can upload a new training dataset to the service from a local file by using one of the following methods:

• Drag and drop the file into the client area of the Training data pane, and then select Upload file.

• Select Browse for a file from the client area of the Training data pane, choose the file to upload from the Open dialog, and then select Upload file.

After you select and upload the training dataset, select Next to continue.

Import training data from Azure Blob store

You can import a training dataset from Azure Blob or another shared web location by providing the name and location of the file.

1. Enter the File name for the file.

2. For the File location, provide the Azure Blob URL, the Azure Storage shared access signature (SAS), or other link to an accessible shared web location.

3. Select Import to import the training dataset to the service.

After you select and upload the training dataset, select Next to continue.

Choose your validation data

The next step provides options to configure the model to use validation data in the training process. If you don't want to use validation data, you can choose Next to continue to the advanced options for the model. Otherwise, if you have a validation dataset, you can either choose existing prepared validation data or upload new prepared validation data to use when customizing your model.

The Validation data pane displays any existing, previously uploaded training and validation datasets and provides options by which you can upload new validation data.

• If your validation data is already uploaded to the service, select Choose dataset.

  • Select the file from the list shown in the Validation data pane.

• To upload new validation data, use one of the following options:

  • Select Local file to upload validation data from a local file.

  • Select Azure blob or other shared web locations to import validation data from Azure Blob or another shared web location.

For large data files, we recommend that you import from an Azure Blob store. Large files can become unstable when uploaded through multipart forms because the requests are atomic and can't be retried or resumed.

Upload validation data from local file

You can upload a new validation dataset to the service from a local file by using one of the following methods:

• Drag and drop the file into the client area of the Validation data pane, and then select Upload file.

• Select Browse for a file from the client area of the Validation data pane, choose the file to upload from the Open dialog, and then select Upload file.

After you select and upload the validation dataset, select Next to continue.

Import validation data from Azure Blob store

You can import a validation dataset from Azure Blob or another shared web location by providing the name and location of the file.

1. Enter the File name for the file.

2. For the File location, provide the Azure Blob URL, the Azure Storage shared access signature (SAS), or other link to an accessible shared web location.

3. Select Import to import the training dataset to the service.

After you select and upload the validation dataset, select Next to continue.

Configure task parameters

The Create custom model wizard shows the parameters for training your fine-tuned model on the Task parameters pane. The following parameters are available:

Select Default to use the default values for the fine-tuning job, or select Custom to display and edit the hyperparameter values. When defaults are selected, we determine the correct value algorithmically based on your training data.

After you configure the advanced options, select Next to review your choices and train your fine-tuned model.

Review your choices and train your model

The Review pane of the wizard displays information about your configuration choices.

If you're ready to train your model, select Start Training job to start the fine-tuning job and return to the Models pane.

Check the status of your custom model

The Models pane displays information about your custom model in the Customized models tab. The tab includes information about the status and job ID of the fine-tune job for your custom model. When the job completes, the tab displays the file ID of the result file. You might need to select Refresh in order to see an updated status for the model training job.

After you start a fine-tuning job, it can take some time to complete. Your job might be queued behind other jobs on the system. Training your model can take minutes or hours depending on the model and dataset size.

Here are some of the tasks you can do on the Models pane:

• Check the status of the fine-tuning job for your custom model in the Status column of the Customized models tab.

• In the Model name column, select the model name to view more information about the custom model. You can see the status of the fine-tuning job, training results, training events, and hyperparameters used in the job.

• Select Download training file to download the training data you used for the model.

• Select Download results to download the result file attached to the fine-tuning job for your model and analyze your custom model for training and validation performance.

• Select Refresh to update the information on the page.

Checkpoints

When each training epoch completes a checkpoint is generated. A checkpoint is a fully functional version of a model which can both be deployed and used as the target model for subsequent fine-tuning jobs. Checkpoints can be particularly useful, as they can provide a snapshot of your model prior to overfitting having occurred. When a fine-tuning job completes you will have the three most recent versions of the model available to deploy.

Safety evaluation GPT-4, GPT-4o, and GPT-4o-mini fine-tuning - public preview

GPT-4o, GPT-4o-mini, and GPT-4 are our most advanced models that can be fine-tuned to your needs. As with Azure OpenAI models generally, the advanced capabilities of fine-tuned models come with increased responsible AI challenges related to harmful content, manipulation, human-like behavior, privacy issues, and more. Learn more about risks, capabilities, and limitations in the Overview of Responsible AI practices and Transparency Note. To help mitigate the risks associated with advanced fine-tuned models, we have implemented additional evaluation steps to help detect and prevent harmful content in the training and outputs of fine-tuned models. These steps are grounded in the Microsoft Responsible AI Standard and Azure OpenAI Service content filtering.

• Evaluations are conducted in dedicated, customer specific, private workspaces;
• Evaluation endpoints are in the same geography as the Azure OpenAI resource;
• Training data is not stored in connection with performing evaluations; only the final model assessment (deployable or not deployable) is persisted; and

GPT-4o, GPT-4o-mini, and GPT-4 fine-tuned model evaluation filters are set to predefined thresholds and cannot be modified by customers; they aren't tied to any custom content filtering configuration you may have created.

Data evaluation

Before training starts, your data is evaluated for potentially harmful content (violence, sexual, hate, and fairness, self-harm – see category definitions here). If harmful content is detected above the specified severity level, your training job will fail, and you'll receive a message informing you of the categories of failure.

Sample message:

The provided training data failed RAI checks for harm types: [hate_fairness, self_harm, violence]. Please fix the data and try again.

Your training data is evaluated automatically within your data import job as part of providing the fine-tuning capability.

If the fine-tuning job fails due to the detection of harmful content in training data, you won't be charged.

Model evaluation

After training completes but before the fine-tuned model is available for deployment, the resulting model is evaluated for potentially harmful responses using Azure’s built-in risk and safety metrics. Using the same approach to testing that we use for the base large language models, our evaluation capability simulates a conversation with your fine-tuned model to assess the potential to output harmful content, again using specified harmful content categories (violence, sexual, hate, and fairness, self-harm).

If a model is found to generate output containing content detected as harmful at above an acceptable rate, you'll be informed that your model isn't available for deployment, with information about the specific categories of harm detected:

Sample Message:

This model is unable to be deployed. Model evaluation identified that this fine tuned model scores above acceptable thresholds for [Violence, Self Harm]. Please review your training data set and resubmit the job.

As with data evaluation, the model is evaluated automatically within your fine-tuning job as part of providing the fine-tuning capability. Only the resulting assessment (deployable or not deployable) is logged by the service. If deployment of the fine-tuned model fails due to the detection of harmful content in model outputs, you won't be charged for the training run.

Deploy a fine-tuned model

When the fine-tuning job succeeds, you can deploy the custom model from the Models pane. You must deploy your custom model to make it available for use with completion calls.

To deploy your custom model, select the custom model to deploy, and then select Deploy model.

The Deploy model dialog box opens. In the dialog box, enter your Deployment name and then select Create to start the deployment of your custom model.

You can monitor the progress of your deployment on the Deployments pane in Azure AI Foundry portal.

Cross region deployment

Fine-tuning supports deploying a fine-tuned model to a different region than where the model was originally fine-tuned. You can also deploy to a different subscription/region.

The only limitations are that the new region must also support fine-tuning and when deploying cross subscription the account generating the authorization token for the deployment must have access to both the source and destination subscriptions.

Cross subscription/region deployment can be accomplished via Python or REST.

Use a deployed custom model

After your custom model deploys, you can use it like any other deployed model. You can use the Playgrounds in Azure AI Foundry to experiment with your new deployment. You can continue to use the same parameters with your custom model, such as temperature and max_tokens, as you can with other deployed models. For fine-tuned babbage-002 and davinci-002 models you will use the Completions playground and the Completions API. For fine-tuned gpt-35-turbo-0613 models you will use the Chat playground and the Chat completion API.

Analyze your custom model

Azure OpenAI attaches a result file named results.csv to each fine-tuning job after it completes. You can use the result file to analyze the training and validation performance of your custom model. The file ID for the result file is listed for each custom model in the Result file Id column on the Models pane for Azure AI Foundry. You can use the file ID to identify and download the result file from the Data files pane of Azure AI Foundry.

The result file is a CSV file that contains a header row and a row for each training step performed by the fine-tuning job. The result file contains the following columns:

You can also view the data in your results.csv file as plots in Azure AI Foundry portal. Select the link for your trained model, and you will see three charts: loss, mean token accuracy, and token accuracy. If you provided validation data, both datasets will appear on the same plot.

Look for your loss to decrease over time, and your accuracy to increase. If you see a divergence between your training and validation data, that may indicate that you are overfitting. Try training with fewer epochs, or a smaller learning rate multiplier.

Clean up your deployments, custom models, and training files

When you're done with your custom model, you can delete the deployment and model. You can also delete the training and validation files you uploaded to the service, if needed.

Delete your model deployment

You can delete the deployment for your custom model on the Deployments pane in Azure AI Foundry portal. Select the deployment to delete, and then select Delete to delete the deployment.

Delete your custom model

You can delete a custom model on the Models pane in Azure AI Foundry portal. Select the custom model to delete from the Customized models tab, and then select Delete to delete the custom model.

Delete your training files

You can optionally delete training and validation files that you uploaded for training, and result files generated during training, on the Management > Data files pane in Azure AI Foundry portal. Select the file to delete, and then select Delete to delete the file.

Continuous fine-tuning

Once you have created a fine-tuned model you may wish to continue to refine the model over time through further fine-tuning. Continuous fine-tuning is the iterative process of selecting an already fine-tuned model as a base model and fine-tuning it further on new sets of training examples.

To perform fine-tuning on a model that you have previously fine-tuned you would use the same process as described in create a customized model but instead of specifying the name of a generic base model you would specify your already fine-tuned model. A custom fine-tuned model would look like gpt-35-turbo-0613.ft-5fd1918ee65d4cd38a5dcf6835066ed7

We also recommend including the suffix parameter to make it easier to distinguish between different iterations of your fine-tuned model. suffix takes a string, and is set to identify the fine-tuned model. With the OpenAI Python API a string of up to 18 characters is supported that will be added to your fine-tuned model name.

Prerequisites

• Read the When to use Azure OpenAI fine-tuning guide.

• An Azure subscription - Create one for free.

• An Azure AI hub resource.

• An Azure AI project in Azure AI Foundry portal.

• An Azure OpenAI connection to a resource in a region where fine-tuning is supported.

  Note

  The supported regions might vary if you use Azure OpenAI models in an AI Foundry project versus outside a project.

• Fine-tuning access requires Cognitive Services OpenAI Contributor role on the Azure OpenAI resource.

• If you don't already have access to view quota and deploy models in Azure AI Foundry portal you need more permissions.

Models

The following models support fine-tuning:

• babbage-002
• davinci-002
• gpt-35-turbo (0613)
• gpt-35-turbo (1106)
• gpt-35-turbo (0125)
• gpt-4 (0613)^*
• gpt-4o (2024-08-06)
• gpt-4o-mini (2024-07-18)

^* Fine-tuning for this model is currently in public preview.

Or you can fine tune a previously fine-tuned model, formatted as base-model.ft-{jobid}.

Consult the models page to check which regions currently support fine-tuning.

Review the workflow for Azure AI Foundry

Take a moment to review the fine-tuning workflow for using Azure AI Foundry:

1. Prepare your training and validation data.
2. Use the Fine-tune model wizard in Azure AI Foundry portal to train your custom model.
   1. Select a model.
   2. Choose your training data.
   3. Optionally, choose your validation data.
   4. Optionally, configure your parameters for your fine-tuning job.
   5. Review your choices and train your new custom model.
3. Check the status of your fine-tuned model.
4. Optionally, analyze your fine-tuned model for performance and fit.
5. Deploy your fine-tuned model for use.
6. Use your fine-tuned model.

Prepare your training and validation data

Your training data and validation data sets consist of input and output examples for how you would like the model to perform.

Different model types require a different format of training data.

{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Is Xbox better than PlayStation?"}, {"role": "assistant", "content": "I apologize, but I cannot provide personal opinions. My primary job is to assist you with any issues related to your Xbox device. Do you have any Xbox-related issues that need addressing?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Can I play PC games on my Xbox?"}, {"role": "assistant", "content": "While Xbox consoles don't natively support PC games, they can play an array of Xbox games, many of which are also available on PC. Can I assist you with finding games compatible with your Xbox device?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "I'm having trouble connecting my Xbox to the Wi-Fi."}, {"role": "assistant", "content": "No worries, let's go through the network settings on your Xbox. Can you please tell me what happens when you try to connect it to the Wi-Fi?"}]}

{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the capital of France?"}, {"role": "assistant", "content": "Paris", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Paris, as if everyone doesn't know that already.", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'Romeo and Juliet'?"}, {"role": "assistant", "content": "William Shakespeare", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Oh, just some guy named William Shakespeare. Ever heard of him?", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "How far is the Moon from Earth?"}, {"role": "assistant", "content": "384,400 kilometers", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Around 384,400 kilometers. Give or take a few, like that really matters.", "weight": 1}]}

{"messages": [{"role": "user", "content": [{"type": "text", "text": "What's in this image?"}, {"type": "image_url", "image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}, {"role": "assistant", "content": "The image appears to be a watercolor painting of a city skyline, featuring tall buildings and a recognizable structure often associated with Seattle, like the Space Needle. The artwork uses soft colors and brushstrokes to create a somewhat abstract and artistic representation of the cityscape."}]}

{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}

pip install openai==0.28.1

openai tools fine_tunes.prepare_data -f <LOCAL_FILE>

Create your fine-tuned model

To fine-tune an Azure OpenAI model in an existing Azure AI Foundry project, follow these steps:

1. Sign in to Azure AI Foundry and select your project. If you don't have a project already, first create a project.

2. From the collapsible left menu, select Fine-tuning > + Fine-tune model.

   

Select the base model

1. Select a base model to fine-tune. Your choice influences both the performance and the cost of your model. In this example, we are choosing the gpt-35-turbo model. Then select Confirm.

   

2. For gpt-35-turbo we have different versions available for fine-tuning, so please choose which version you'd like to fine-tune. We will choose (0301).

3. We also recommend including the suffix parameter to make it easier to distinguish between different iterations of your fine-tuned model. suffix takes a string, and is set to identify the fine-tuned model. With the OpenAI Python API a string of up to 18 characters is supported that will be added to your fine-tuned model name.

If you have more than one Azure OpenAI connection enabled for fine-tuning, then choose which resource you'd like to use. Please note that all users with access to your Azure OpenAI resource will have access to this fine-tuned model.

1. Then select Next.

   

Choose your training data

The next step is to either choose existing prepared training data or upload new prepared training data to use when customizing your model. The Training data pane displays any existing, previously uploaded datasets and also provides options to upload new training data.

• If your training data is already in your project, select Data in Azure AI Foundry portal.

  • Select the file from the list shown in the Training data pane.

• If your training data is already uploaded to the Azure OpenAI service, select your Azure OpenAI connection under Azure OpenAI Connection.

• To upload training data to fine-tune your model, select Upload data and then select Upload file.

  • Make sure all your training examples follow the expected format for inference. To fine-tune models effectively, ensure a balanced and diverse dataset. This involves maintaining data balance, including various scenarios, and periodically refining training data to align with real-world expectations, ultimately leading to more accurate and balanced model responses. See data preparation for more information.
  • For large data files, we recommend that you import from an Azure Blob store. Large files can become unstable when uploaded through multipart forms because the requests are atomic and can't be retried or resumed. For more information about Azure Blob Storage, see What is Azure Blob Storage?

After uploading files, you will see a preview of your training data. Select Next to continue.

Choose your validation data

Optionally, you can choose to provide validation data to fine-tune your model. If you don't want to use validation data, you can select None and select Next to continue to the advanced options for the model.

Otherwise, if you have a validation dataset, you can either choose from previously uploaded data or upload newly prepared validation data to use for fine-tuning your model.

Configure your parameters

Optionally, configure parameters for your fine-tuning job. The following are available:

You can choose to leave the default configuration or customize the values to your preference. After you finish making your configurations, select Next.

Review your choices and train your model

Review your choices and select Submit to start training your new fine-tuned model.

Check the status of your fine-tuned model

After you submit your fine-tuning job, you see a page with details about your fine-tuned model. You can find the status and more information about your fine-tuned model on the Fine-tuning > Models page in Azure AI Foundry portal.

Your job might be queued behind other jobs on the system. Training your model can take minutes or hours depending on the model and dataset size.

Analyze your fine-tuned model

After fine-tuning is successfully completed, you can download a result file named results.csv from the fine-tuned model page under the Details tab. You can use the result file to analyze the training and validation performance of your custom model.

The result file is a CSV file that contains a header row and a row for each training step performed by the fine-tuning job. The result file contains the following columns:

You can also view the data in your results.csv file as plots in Azure AI Foundry portal under the Metrics tab of your fine-tuned model. Select the link for your trained model, and you will see two charts: loss, and token accuracy. If you provided validation data, both datasets will appear on the same plot.

Look for your loss to decrease over time, and your accuracy to increase. If you see a divergence between your training and validation data that may indicate that you are overfitting. Try training with fewer epochs, or a smaller learning rate multiplier.

Checkpoints

When each training epoch completes a checkpoint is generated. A checkpoint is a fully functional version of a model which can both be deployed and used as the target model for subsequent fine-tuning jobs. Checkpoints can be particularly useful, as they can provide a snapshot of your model prior to overfitting having occurred. When a fine-tuning job completes you will have the three most recent versions of the model available to deploy.

Safety evaluation GPT-4, GPT-4o, GPT-4o-mini fine-tuning - public preview

GPT-4o, GPT-4o-mini, and GPT-4 are our most advanced models that can be fine-tuned to your needs. As with Azure OpenAI models generally, the advanced capabilities of fine-tuned models come with increased responsible AI challenges related to harmful content, manipulation, human-like behavior, privacy issues, and more. Learn more about risks, capabilities, and limitations in the Overview of Responsible AI practices and Transparency Note. To help mitigate the risks associated with advanced fine-tuned models, we have implemented additional evaluation steps to help detect and prevent harmful content in the training and outputs of fine-tuned models. These steps are grounded in the Microsoft Responsible AI Standard and Azure OpenAI Service content filtering.

• Evaluations are conducted in dedicated, customer specific, private workspaces;
• Evaluation endpoints are in the same geography as the Azure OpenAI resource;
• Training data is not stored in connection with performing evaluations; only the final model assessment (deployable or not deployable) is persisted; and

GPT-4o, GPT-4o-mini, and GPT-4 fine-tuned model evaluation filters are set to predefined thresholds and cannot be modified by customers; they aren't tied to any custom content filtering configuration you may have created.

Data evaluation

Before training starts, your data is evaluated for potentially harmful content (violence, sexual, hate, and fairness, self-harm – see category definitions here). If harmful content is detected above the specified severity level, your training job will fail, and you'll receive a message informing you of the categories of failure.

Sample message:

The provided training data failed RAI checks for harm types: [hate_fairness, self_harm, violence]. Please fix the data and try again.

Your training data is evaluated automatically within your data import job as part of providing the fine-tuning capability.

If the fine-tuning job fails due to the detection of harmful content in training data, you won't be charged.

Model evaluation

After training completes but before the fine-tuned model is available for deployment, the resulting model is evaluated for potentially harmful responses using Azure’s built-in risk and safety metrics. Using the same approach to testing that we use for the base large language models, our evaluation capability simulates a conversation with your fine-tuned model to assess the potential to output harmful content, again using specified harmful content categories (violence, sexual, hate, and fairness, self-harm).

If a model is found to generate output containing content detected as harmful at above an acceptable rate, you'll be informed that your model isn't available for deployment, with information about the specific categories of harm detected:

Sample Message:

This model is unable to be deployed. Model evaluation identified that this fine tuned model scores above acceptable thresholds for [Violence, Self Harm]. Please review your training data set and resubmit the job.

As with data evaluation, the model is evaluated automatically within your fine-tuning job as part of providing the fine-tuning capability. Only the resulting assessment (deployable or not deployable) is logged by the service. If deployment of the fine-tuned model fails due to the detection of harmful content in model outputs, you won't be charged for the training run.

Deploy a fine-tuned model

Once your model is fine-tuned, you can deploy the model and can use it in your own application. You can't deploy a fine-tuned model from the deployments page or the playground page in Azure AI Foundry portal. The only way, currently, to deploy a fine-tuned model is from the model details page for that model.

When you deploy the model, you make the model available for inferencing, and that incurs an hourly hosting charge. Fine-tuned models, however, can be stored in Azure AI Foundry portal at no cost until you're ready to use them.

You can monitor the progress of your deployment on the Deployments page in Azure AI Foundry portal.

Use a deployed fine-tuned model

After your fine-tuned model deploys, you can use it like any other deployed model. You can use the Playground in Azure AI Foundry to experiment with your new deployment. You can also use the REST API to call your fine-tuned model from your own application. You can even begin to use this new fine-tuned model in your prompt flow to build your generative AI application.

Clean up your deployments, fine-tuned models, and training files

When you're done with your fine-tuned model, you can delete the deployment and model. You can also delete the training and validation files you uploaded to the service, if needed.

Delete your fine-tuned model deployment

You can delete the deployment for your fine-tuned model on the Deployments page in Azure AI Foundry portal. Select the deployment to delete, and then select Delete to delete the deployment.

Delete your fine-tuned model

You can delete a fine-tuned model on the Fine-tuning page in Azure AI Foundry portal. Select the fine-tuned model to delete and then select Delete to delete the fine-tuned model.

Delete your training files

You can optionally delete training and validation files that you uploaded for training, and result files generated during training. For this you need to go to Azure OpenAI Studio and navigate to the Management > Data files pane. Select the file to delete, and then select Delete to delete the file.

The training and validation data you use must be formatted as a JSON Lines (JSONL) document. For gpt-35-turbo-0613 the fine-tuning dataset must be formatted in the conversational format that is used by the Chat completions API.

If you would like a step-by-step walk-through of fine-tuning a gpt-35-turbo-0613 please refer to the Azure OpenAI fine-tuning tutorial

Example file format

{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Is Xbox better than PlayStation?"}, {"role": "assistant", "content": "I apologize, but I cannot provide personal opinions. My primary job is to assist you with any issues related to your Xbox device. Do you have any Xbox-related issues that need addressing?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Can I play PC games on my Xbox?"}, {"role": "assistant", "content": "While Xbox consoles don't natively support PC games, they can play an array of Xbox games, many of which are also available on PC. Can I assist you with finding games compatible with your Xbox device?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "I'm having trouble connecting my Xbox to the Wi-Fi."}, {"role": "assistant", "content": "No worries, let's go through the network settings on your Xbox. Can you please tell me what happens when you try to connect it to the Wi-Fi?"}]}

Multi-turn chat file format

Multiple turns of a conversation in a single line of your jsonl training file is also supported. To skip fine-tuning on specific assistant messages add the optional weight key value pair. Currently weight can be set to 0 or 1.

{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the capital of France?"}, {"role": "assistant", "content": "Paris", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Paris, as if everyone doesn't know that already.", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'Romeo and Juliet'?"}, {"role": "assistant", "content": "William Shakespeare", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Oh, just some guy named William Shakespeare. Ever heard of him?", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "How far is the Moon from Earth?"}, {"role": "assistant", "content": "384,400 kilometers", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Around 384,400 kilometers. Give or take a few, like that really matters.", "weight": 1}]}

Chat completions with vision

{"messages": [{"role": "user", "content": [{"type": "text", "text": "What's in this image?"}, {"type": "image_url", "image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}, {"role": "assistant", "content": "The image appears to be a watercolor painting of a city skyline, featuring tall buildings and a recognizable structure often associated with Seattle, like the Space Needle. The artwork uses soft colors and brushstrokes to create a somewhat abstract and artistic representation of the cityscape."}]}

In addition to the JSONL format, training and validation data files must be encoded in UTF-8 and include a byte-order mark (BOM). The file must be less than 512 MB in size.

Create your training and validation datasets

The more training examples you have, the better. Fine tuning jobs will not proceed without at least 10 training examples, but such a small number is not enough to noticeably influence model responses. It is best practice to provide hundreds, if not thousands, of training examples to be successful.

In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data, without first pruning the dataset for only the highest quality examples you could end up with a model that performs much worse than expected.

The training and validation data you use must be formatted as a JSON Lines (JSONL) document in which each line represents a single prompt-completion pair. The OpenAI command-line interface (CLI) includes a data preparation tool that validates, gives suggestions, and reformats your training data into a JSONL file ready for fine-tuning.

{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}

In addition to the JSONL format, training and validation data files must be encoded in UTF-8 and include a byte-order mark (BOM). The file must be less than 512 MB in size.

Create your training and validation datasets

Designing your prompts and completions for fine-tuning is different from designing your prompts for use with any of our GPT-3 base models. Prompts for completion calls often use either detailed instructions or few-shot learning techniques, and consist of multiple examples. For fine-tuning, each training example should consist of a single input prompt and its desired completion output. You don't need to give detailed instructions or multiple completion examples for the same prompt.

The more training examples you have, the better. Fine tuning jobs will not proceed without at least 10 training examples, but such a small number is not enough to noticeably influence model responses. It is best practice to provide hundreds, if not thousands, of training examples to be successful.

In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data, without first pruning the dataset for only the highest quality examples you could end up with a model that performs much worse than expected.

OpenAI CLI data preparation tool

OpenAI's CLI data preparation tool was developed for the previous generation of fine-tuning models to assist with many of the data preparation steps. This tool will only work for data preparation for models that work with the completion API like babbage-002 and davinci-002. The tool validates, gives suggestions, and reformats your data into a JSONL file ready for fine-tuning.

To install the OpenAI CLI, run the following Python command:

pip install openai==0.28.1

To analyze your training data with the data preparation tool, run the following Python command. Replace the <LOCAL_FILE> argument with the full path and file name of the training data file to analyze:

openai tools fine_tunes.prepare_data -f <LOCAL_FILE>

This tool accepts files in the following data formats, if they contain a prompt and a completion column/key:

• Comma-separated values (CSV)
• Tab-separated values (TSV)
• Microsoft Excel workbook (XLSX)
• JavaScript Object Notation (JSON)
• JSON Lines (JSONL)

After it guides you through the process of implementing suggested changes, the tool reformats your training data and saves output into a JSONL file ready for fine-tuning.

# Upload fine-tuning files

import os
from openai import AzureOpenAI

client = AzureOpenAI(
  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
  api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
  api_version="2024-05-01-preview"  # This API version or later is required to access seed/events/checkpoint capabilities
)

training_file_name = 'training_set.jsonl'
validation_file_name = 'validation_set.jsonl'

# Upload the training and validation dataset files to Azure OpenAI with the SDK.

training_response = client.files.create(
    file=open(training_file_name, "rb"), purpose="fine-tune"
)
training_file_id = training_response.id

validation_response = client.files.create(
    file=open(validation_file_name, "rb"), purpose="fine-tune"
)
validation_file_id = validation_response.id

print("Training file ID:", training_file_id)
print("Validation file ID:", validation_file_id)

# Upload fine-tuning files

import openai
import os

openai.api_key = os.getenv("AZURE_OPENAI_API_KEY") 
openai.api_base =  os.getenv("AZURE_OPENAI_ENDPOINT")
openai.api_type = 'azure'
openai.api_version = '2024-02-01' # This API version or later is required to access fine-tuning for turbo/babbage-002/davinci-002

training_file_name = 'training_set.jsonl'
validation_file_name = 'validation_set.jsonl'

# Upload the training and validation dataset files to Azure OpenAI with the SDK.

training_response = openai.File.create(
    file=open(training_file_name, "rb"), purpose="fine-tune", user_provided_filename="training_set.jsonl"
)
training_file_id = training_response["id"]

validation_response = openai.File.create(
    file=open(validation_file_name, "rb"), purpose="fine-tune", user_provided_filename="validation_set.jsonl"
)
validation_file_id = validation_response["id"]

print("Training file ID:", training_file_id)
print("Validation file ID:", validation_file_id)

In this example we are also passing the seed parameter. The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed isn't specified, one will be generated for you.

response = client.fine_tuning.jobs.create(
    training_file=training_file_id,
    validation_file=validation_file_id,
    model="gpt-35-turbo-0613", # Enter base model name. Note that in Azure OpenAI the model name contains dashes and cannot contain dot/period characters. 
    seed = 105  # seed parameter controls reproducibility of the fine-tuning job. If no seed is specified one will be generated automatically.
)

job_id = response.id

# You can use the job ID to monitor the status of the fine-tuning job.
# The fine-tuning job will take some time to start and complete.

print("Job ID:", response.id)
print("Status:", response.id)
print(response.model_dump_json(indent=2))

response = openai.FineTuningJob.create(
    training_file=training_file_id,
    validation_file=validation_file_id,
    model="gpt-35-turbo-0613",
)

job_id = response["id"]

# You can use the job ID to monitor the status of the fine-tuning job.
# The fine-tuning job will take some time to start and complete.

print("Job ID:", response["id"])
print("Status:", response["status"])
print(response)

response = client.fine_tuning.jobs.retrieve(job_id)

print("Job ID:", response.id)
print("Status:", response.status)
print(response.model_dump_json(indent=2))

#Retrieve training job ID

response = openai.FineTuningJob.retrieve(job_id)

print("Job ID:", response["id"])
print("Status:", response["status"])
print(response)

You may need to upgrade your OpenAI client library to the latest version with pip install openai --upgrade to run this command.

response = client.fine_tuning.jobs.list_events(fine_tuning_job_id=job_id, limit=10)
print(response.model_dump_json(indent=2))

This command isn't available in the 0.28.1 OpenAI Python library. Upgrade to the latest release.

You may need to upgrade your OpenAI client library to the latest version with pip install openai --upgrade to run this command.

response = client.fine_tuning.jobs.list_events(fine_tuning_job_id=job_id, limit=10)
print(response.model_dump_json(indent=2))

This command isn't available in the 0.28.1 OpenAI Python library. Upgrade to the latest release.

import os
from openai import AzureOpenAI

client = AzureOpenAI(
  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
  api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
  api_version="2024-02-01"
)

response = client.chat.completions.create(
    model="gpt-35-turbo-ft", # model = "Custom deployment name you chose for your fine-tuning model"
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},
        {"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},
        {"role": "user", "content": "Do other Azure AI services support this too?"}
    ]
)

print(response.choices[0].message.content)

import os
import openai
openai.api_type = "azure"
openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT") 
openai.api_version = "2024-02-01"
openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")

response = openai.ChatCompletion.create(
    engine="gpt-35-turbo-ft", # engine = "Custom deployment name you chose for your fine-tuning model"
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},
        {"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},
        {"role": "user", "content": "Do other Azure AI services support this too?"}
    ]
)

print(response)
print(response['choices'][0]['message']['content'])

# Retrieve the file ID of the first result file from the fine-tuning job
# for the customized model.
response = client.fine_tuning.jobs.retrieve(job_id)
if response.status == 'succeeded':
    result_file_id = response.result_files[0]

retrieve = client.files.retrieve(result_file_id)

# Download the result file.
print(f'Downloading result file: {result_file_id}')

with open(retrieve.filename, "wb") as file:
    result = client.files.content(result_file_id).read()
    file.write(result)

# Retrieve the file ID of the first result file from the fine-tune job
# for the customized model.
response = openai.FineTuningJob.retrieve(job_id)
if response["status"] == 'succeeded':
    result_file_id = response.result_files[0].id
    result_file_name = response.result_files[0].filename

# Download the result file.
print(f'Downloading result file: {result_file_id}')
# Write the byte array returned by the File.download() method to 
# a local file in the working directory.
with open(result_file_name, "wb") as file:
    result = openai.File.download(id=result_file_id)
    file.write(result)

The training and validation data you use must be formatted as a JSON Lines (JSONL) document. For gpt-35-turbo-0613 and other related models, the fine-tuning dataset must be formatted in the conversational format that is used by the Chat completions API.

If you would like a step-by-step walk-through of fine-tuning a gpt-35-turbo-0613 please refer to the Azure OpenAI fine-tuning tutorial.

Example file format

{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Is Xbox better than PlayStation?"}, {"role": "assistant", "content": "I apologize, but I cannot provide personal opinions. My primary job is to assist you with any issues related to your Xbox device. Do you have any Xbox-related issues that need addressing?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Can I play PC games on my Xbox?"}, {"role": "assistant", "content": "While Xbox consoles don't natively support PC games, they can play an array of Xbox games, many of which are also available on PC. Can I assist you with finding games compatible with your Xbox device?"}]}
{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "I'm having trouble connecting my Xbox to the Wi-Fi."}, {"role": "assistant", "content": "No worries, let's go through the network settings on your Xbox. Can you please tell me what happens when you try to connect it to the Wi-Fi?"}]}

Multi-turn chat file format

Multiple turns of a conversation in a single line of your jsonl training file is also supported. To skip fine-tuning on specific assistant messages add the optional weight key value pair. Currently weight can be set to 0 or 1.

{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the capital of France?"}, {"role": "assistant", "content": "Paris", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Paris, as if everyone doesn't know that already.", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'Romeo and Juliet'?"}, {"role": "assistant", "content": "William Shakespeare", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Oh, just some guy named William Shakespeare. Ever heard of him?", "weight": 1}]}
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "How far is the Moon from Earth?"}, {"role": "assistant", "content": "384,400 kilometers", "weight": 0}, {"role": "user", "content": "Can you be more sarcastic?"}, {"role": "assistant", "content": "Around 384,400 kilometers. Give or take a few, like that really matters.", "weight": 1}]}

Chat completions with vision

{"messages": [{"role": "user", "content": [{"type": "text", "text": "What's in this image?"}, {"type": "image_url", "image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}, {"role": "assistant", "content": "The image appears to be a watercolor painting of a city skyline, featuring tall buildings and a recognizable structure often associated with Seattle, like the Space Needle. The artwork uses soft colors and brushstrokes to create a somewhat abstract and artistic representation of the cityscape."}]}

In addition to the JSONL format, training and validation data files must be encoded in UTF-8 and include a byte-order mark (BOM). The file must be less than 512 MB in size.

Create your training and validation datasets

The more training examples you have, the better. Fine tuning jobs will not proceed without at least 10 training examples, but such a small number is not enough to noticeably influence model responses. It is best practice to provide hundreds, if not thousands, of training examples to be successful.

In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data without first pruning the dataset for only the highest quality examples, you could end up with a model that performs much worse than expected.

The training and validation data you use must be formatted as a JSON Lines (JSONL) document in which each line represents a single prompt-completion pair. The OpenAI command-line interface (CLI) includes a data preparation tool that validates, gives suggestions, and reformats your training data into a JSONL file ready for fine-tuning.

{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}

In addition to the JSONL format, training and validation data files must be encoded in UTF-8 and include a byte-order mark (BOM). The file must be less than 512 MB in size.

Create your training and validation datasets

Designing your prompts and completions for fine-tuning is different from designing your prompts for use with any of our GPT-3 base models. Prompts for completion calls often use either detailed instructions or few-shot learning techniques, and consist of multiple examples. For fine-tuning, each training example should consist of a single input prompt and its desired completion output. You don't need to give detailed instructions or multiple completion examples for the same prompt.

The more training examples you have, the better. Fine tuning jobs will not proceed without at least 10 training examples, but such a small number is not enough to noticeably influence model responses. It is best practice to provide hundreds, if not thousands, of training examples to be successful.

In general, doubling the dataset size can lead to a linear increase in model quality. But keep in mind, low quality examples can negatively impact performance. If you train the model on a large amount of internal data without first pruning the dataset for only the highest quality examples, you could end up with a model that performs much worse than expected.

OpenAI CLI data preparation tool

OpenAI's CLI data preparation tool was developed for the previous generation of fine-tuning models to assist with many of the data preparation steps. This tool will only work for data preparation for models that work with the completion API like babbage-002 and davinci-002. The tool validates, gives suggestions, and reformats your data into a JSONL file ready for fine-tuning.

To install the OpenAI CLI, run the following Python command:

pip install openai==0.28.1

To analyze your training data with the data preparation tool, run the following Python command. Replace the <LOCAL_FILE> argument with the full path and file name of the training data file to analyze:

openai tools fine_tunes.prepare_data -f <LOCAL_FILE>

This tool accepts files in the following data formats, if they contain a prompt and a completion column/key:

• Comma-separated values (CSV)
• Tab-separated values (TSV)
• Microsoft Excel workbook (XLSX)
• JavaScript Object Notation (JSON)
• JSON Lines (JSONL)

After it guides you through the process of implementing suggested changes, the tool reformats your training data and saves output into a JSONL file ready for fine-tuning.