# Training and Predicting

Training and predicting jobs can be accessed through the UI to trigger a single predicting or training instance, or scheduled to match the refresh rate of the query.

## <mark style="color:blue;">Manual Triggers</mark>

The training and predicting manual triggers can be accessed directly from the model options on the UI.

### Start Training

After creating the model, you need to manually start the training process:

* Go to the model options by clicking on  **⋮**
* Click <mark style="color:yellow;">"Start Training"</mark> to begin the training process.

### Stop Training

Some ML training processes can be rather long and it can be that for we want to stop it for X reason (system resources, new data etc.)&#x20;

You can also  manually stop the training process:

* Go to the model options by clicking on  **⋮**
* Click <mark style="color:yellow;">"Stop Training"</mark> to begin the training process.

### Predict

## <mark style="color:blue;">Automatic Triggers</mark>

### Training Triggers

If you've set <mark style="color:orange;">"Retrain when"</mark> to <mark style="color:yellow;">"When query is refreshed"</mark>, the model will train automatically the next time the query refreshes.

For the time being, resources being limited it's better to avoid this option.

### Predict Triggers

If you've set <mark style="color:orange;">"Predict when"</mark> to <mark style="color:yellow;">"When query is refreshed",</mark> the model will train automatically the next time the query refreshes.


---

# 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.inverse.watch/user-guide/machine-learning/training-and-predicting.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.