> For the complete documentation index, see [llms.txt](https://docs.tabiya.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tabiya.org/tabiya-documentation/es/nuestra-pila-tecnologica/livelihoods-classifier/training.md).

# Entrenamiento

Entrena tu modelo de extracción de entidades usando PyTorch.

Primero, activa el entorno virtual como se explica [aquí](/tabiya-documentation/es/nuestra-pila-tecnologica/livelihoods-classifier/getting-started.md#dep).

### Entrenar un modelo de extracción de entidades

Configura los hiperparámetros necesarios en el archivo config.json. Los valores predeterminados son:

```json
{
    "model_name": "bert-base-cased",
    "crf": false,
    "dataset_path": "tabiya/job_ner_dataset",   
    "label_list": ["O", "B-Skill", "B-Qualification", "I-Domain", "I-Experience", "I-Qualification", "B-Occupation", "B-Domain", "I-Occupation", "I-Skill", "B-Experience"],
    "model_max_length": 128,
    "batch_size": 32,
    "learning_rate": 1e-4,
    "epochs": 4,
    "weight_decay": 0.01,
    "save": false,
    "output_path": "bert_job_ner"
}
```

Para entrenar el modelo, ejecuta el siguiente script en el `train` directorio:

```sh
python train.py
```

El script de entrenamiento se basa en el [tutorial oficial de clasificación de tokens de HuggingFace](https://huggingface.co/docs/transformers/en/tasks/token_classification).

### Entrenar un modelo de similitud de entidades

Configura los hiperparámetros necesarios en la `sbert_train` función del archivo sbert\_train.py:

```python
sbert_train(model_id='all-MiniLM-L6-v2', dataset_path='your/dataset/path', output_path='your/output/path')
```

Para entrenar el modelo de similitud, ejecuta el siguiente script en el `train` directorio:

```sh
python sbert_train.py
```

El conjunto de datos debe estar formateado como un archivo CSV con dos columnas, como 'title' y 'esco\_label', donde cada fila contiene un par de datos textuales relacionados que se usarán durante el proceso de entrenamiento. Asegúrate de que no haya valores faltantes en tu conjunto de datos para garantizar un entrenamiento correcto del modelo. Aquí tienes un ejemplo de cómo podría verse tu archivo CSV:

| título                       | esco\_label                     |
| ---------------------------- | ------------------------------- |
| Gerente sénior de conflictos | director de institución pública |
| etc.                         | etc.                            |

Se puede encontrar más información [aquí](/tabiya-documentation/es/nuestra-pila-tecnologica/livelihoods-classifier/datasets.md#entity-similarity).


---

# 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.tabiya.org/tabiya-documentation/es/nuestra-pila-tecnologica/livelihoods-classifier/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.