Mt5 Small Spanish Summarization

🚀 mt5-small-spanish-summarization

This is a fine - tuned mt5 - small model designed to generate headlines from Spanish news bodies, offering an effective solution for news summarization tasks.

🚀 Quick Start

No specific quick - start content is provided in the original README. If you want to use this model, you may need to refer to the official documentation of the mt5 - small model and adapt it according to the fine - tuning details in this README.

✨ Features

• Language - Specific: Finetuned for Spanish news, enabling accurate headline generation for Spanish - language news content.
• Data - Driven: Trained on a large dataset of 58425 news articles from La Razón and Público newspapers, covering multiple news categories.

📦 Installation

No installation steps are provided in the original README.

💻 Usage Examples

No code examples are provided in the original README.

📚 Documentation

Model description

This is a mt5 - small model finetuned for generating headlines from the body of the news in Spanish.

Training data

The model was trained with 58425 news extracted from the La Razón (31477) and Público (26948) newspapers. These news belong to the following categories: "España", "Cultura", "Economía", "Igualdad" and "Política".

Training procedure

It was trained with Google Colab's GPU Tesla P100 - PCIE - 16GB for 2 epochs.

Hyperparameters

{
    "evaluation_strategy": "epoch",
    "learning_rate": 2e-4,
    "per_device_train_batch_size": 6,
    "per_device_eval_batch_size": 6,
    "weight_decay": 0.01,
    "save_total_limit": 3,
    "num_train_epochs": 2,
    "predict_with_generate": True,
    "fp16": False
}

Eval results

BibTeX entry and citation info

@inproceedings{ mt5lrpjosmunpen,
  year={2020},
}

📄 License

The model is licensed under the apache - 2.0 license.