Bert Multilingual Pt Archive

🚀 portuguese-archival-finding-aids

This model is a fine - tuned version of [bert - base - multilingual - cased](https://huggingface.co/bert - base - multilingual - cased) on an unknown dataset, achieving high accuracy in token classification.

🚀 Quick Start

This model is a fine - tuned version of [bert - base - multilingual - cased](https://huggingface.co/bert - base - multilingual - cased) on an unkown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1812
• Precision: 0.8624
• Recall: 0.9557
• F1: 0.9067
• Accuracy: 0.9618

✨ Features

• Tags: generated_from_trainer
• Metrics: precision, recall, f1, accuracy

The model achieves the following result in the Token Classification task:

• Task: Token Classification
• Metric: Accuracy
• Value: 0.9617770479839446

📦 Installation

No installation steps provided in the original document.

💻 Usage Examples

No code examples provided in the original document.

📚 Documentation

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Framework versions

• Transformers 4.10.0.dev0
• Pytorch 1.9.0+cu111
• Datasets 1.10.2
• Tokenizers 0.10.3

📄 License

This model is under the Apache - 2.0 license.