Albert Base V2 Fakenews Discriminator

🚀 albert-base-v2-fakenews-discriminator

This is a fine - tuned model based on albert - base - v2 for fake news discrimination, achieving high accuracy on the evaluation set.

🚀 Quick Start

The dataset used for this model is the "Fake and real news dataset" available at https://www.kaggle.com/clmentbisaillon/fake-and-real-news-dataset. The classifier is trained using the title and label information.

• label_0: Fake news
• label_1: Real news

This model is a fine - tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0910
• Accuracy: 0.9758

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

🔧 Technical Details

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e - 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Framework versions

• Transformers 4.12.3
• Pytorch 1.10.0+cu111
• Datasets 1.15.1
• Tokenizers 0.10.3

📄 License

This project is licensed under the Apache 2.0 License.