# Train

{% hint style="info" %}
**Assumption :** It is assumed that training and train data have already been uploaded to the dashboard
{% endhint %}

If there is no data uploaded to the dashboard yet, please refer to the two sections below.

{% content-ref url="/pages/1indMA7sIOq2lTHmRdTn" %}
[Upload Data](/nlu-api-dashboard/data-management/upload-data.md)
{% endcontent-ref %}

{% content-ref url="/pages/1rrz1jI8HnFf3FFh5u36" %}
[Data Integration](/nlu-api-dashboard/getting-started/data-integration.md)
{% endcontent-ref %}

## 1. Set data for training 

Among the data uploaded to the dashboard, confirm or **toggle on the data to be used for training**. 

{% hint style="info" %}
Data for which Toggle is On in the Training column on the right is data for training..
{% endhint %}

See the section on how to[ set up your training/test data](/nlu-api-dashboard/data-management/set-data.md).

<figure><img src="/files/UfbuFRfdmQacH7heTHdS" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
To check the performance of the model trained with data, test data must also be set. The setting method is the same as for learning. Just **toggle on the data to be used for testing.**
{% endhint %}

##

## 2. Start Training

If you have confirmed that the training data is set (toggle on), press the Train Model button at the top right of the dashboard.

Isn't it very simple? The model starts learning right away.

{% hint style="info" %}
When the model starts training, the 'Train Model' button is diactivated and cannot be pressed again until training is complete.
{% endhint %}

{% hint style="warning" %}
Currently, there is no way to stop a model from learning as a function within the NLU Dashboard. So please proceed with caution.
{% endhint %}

When model learning is finished, a new version of the model is created at the top of the model list on the History menu page.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.allganize.ai/nlu-api-dashboard/model-training/train.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.