---
title: Fine-tuning
slug: fine-tuning
docTags: 
createdAt: 2024-07-03T04:39:36.244Z
---

Agenthost now supports fine-tuning in beta. Please reach out to info\@agenthost.ai should you experience any issues.&#x20;

# Introduction

Fine-tuning allows you to train a custom model based on your own specific needs and data. Generally fine-tuning is a way to create a better experience for your users. You can reach more about fine tuning by reading OpenAI's [documentation](https://platform.openai.com/docs/guides/fine-tuning). Fine-tuning is only available to users on Pro and Growth paid plans.&#x20;

# Useage and limits

Fine-tunes use 2x the message limits as gpt-3.5-turbo. This includes running the training as well as users chatting with the fine tuned model after training is complete. Fine-tuning is only supported with **v1 agents.**

# Create a fine-tuned model

To create a new fine-tuned model, follow these steps.

1. Go to the [workspace](https://agenthost.ai/workspace) and then select an agent.
2. Select ***Fine-tuning*** from the left side menu in the agent project page.
3. Select ***Create*** on the top right side of the page. This will bring up a modal view.
4. Enter a value for the name of the fine-tune. This can be anything you wish and is just for your referencing. Only gpt-3.5-turbo is available for fine tuning currently.&#x20;
5. Click ***Create*** to create the model.
6. Creating the model is the first part. Now we'll need to select the messages we want to use for fine-tuning our model.&#x20;

![](https://api.archbee.com/api/optimize/J9fYKyOC9LDUkZLauraw-/dzja0EGC7PKewU82S3XLm_screenshot-2024-07-02-at-95050-pm.png)

# Select messages to train the model on

Now we need to select the messages we want to train our new fine-tuned model on. You must select atleast 10 messages to fine tune your agent.&#x20;

![](https://api.archbee.com/api/optimize/J9fYKyOC9LDUkZLauraw-/f-ZH5JCq6g0qpyKT-qeHk_screenshot-2024-07-02-at-95303-pm.png)


1. Select `Manage` on the newly created fine-tune job
2. After selecting manage, click the `Add messages` button near the center of the modal that appears.
3. This will take you to the  `Conversations`  view. From there, open a thread with messages you want your model trained on.&#x20;
4. On all messages from your agent, you'll now see a `Train` option. Click that button to add the message to your fine-tuned model training list.
5. You must select atleast 10 messages to start fine-tuning.&#x20;


# Run the fine-tune job

Once happy with all the messages you've added to your training, go back to the `Fine-tuning` section.&#x20;

Then click `Run` to begin the fine-tune process. The `status` wil then change to `running`

How long the fine-tune process runs depends but it can be anywhere from a couple of minutes to hours. Once fine-tuning completes, you'll be notified and the status will change to completed.

![](https://api.archbee.com/api/optimize/J9fYKyOC9LDUkZLauraw-/ZtByD7ZBZ4E-cCw0y61Pl_screenshot-2024-07-02-at-95931-pm.png)


# Use the new fine-tuned model

Congratulations on creating your fine-tuned model. Now the final piece is to update your agent to use your newly created fine-tuned model.&#x20;

1. Go to the `Agent` tab from the left menu.&#x20;
2. Scroll down to `Advanced Settings` and find `GPT model`
3. Click the dropdown and select `use fine tuned model`
4. A modal should popup asking you to select your fine tuned model. Select the fine-tuned model you just created.
5. After selecting th model, be sure to scroll up and click `Save` to save your changes.&#x20;


Now you can go to the chat page and ask your agent questions. Fine-tuned models do sometimes take slightly longer to responded compared to the base models.&#x20;