> For the complete documentation index, see [llms.txt](https://docs.docbits.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training.md).

# Model Training

<figure><img src="https://578966019-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FT2n2w4uDCJvv7CJ5zrdk%2Fuploads%2Fgit-blob-88a65e60b2664a39944d53db115644ceb5a3191f%2Fmodel-training-page-en-20261010.png?alt=media" alt="Train Model page of the Invoice document type with sample metrics, Import, Train model, Test classification, and the training document list"><figcaption><p>The Train Model page shows the sample metrics, the Import, Train model and Test classification actions, and the list of training documents.</p></figcaption></figure>

#### Overview

Model Training allows administrators to oversee and manage the training of machine learning models specific to each document type. By providing a structured interface for importing sample data, training models, and testing their performance, Docbits ensures that its data extraction capabilities continuously improve over time.

#### Key Features and Options

1. **Metrics Overview**:
   * **Sample**: Number of sample documents used for training.
   * **Exported**: Number of documents that have been successfully exported after processing.
   * **Company Σ**: Total number of company-specific documents processed.
   * **Overall Σ**: Total number of documents processed across all categories.
2. **Training and Testing Options**:
   * **Import**: Allows administrators to import new training data sets which are typically structured samples of documents that should be recognized by the system. For the step-by-step workflow, see [Import sample documents for model training](https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training/import-data-model-training.md).
   * **Train model**: Starts the training process using the imported data to enhance the recognition and extraction capabilities of the system.
   * **Test classification**: Enables testing of the model to evaluate its performance on classifying and extracting data from new or unseen documents.
3. **Training Document List**:
   * **Name**: Shows the file name of each imported training document.
   * **Actions** (the three-dot menu in each row): Offers **Delete** to remove that training document from the list. For how to manage the imported samples, see [Manage training data](https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training/manage-training-data.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
