Edit model card

fakeBert

This model is a fine-tuned version of bert-base-uncased on a news dataset from Kaggle.

Model description

Fine-tuning Bert for text classification.

Training and evaluation data

Training & Validation: Fake and real news dataset Testing: Fake News Detection Challenge KDD 2020

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-5
  • train_batch_size: 16
  • eval_batch_size: 16
  • optimizer: AdamW
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Unable to determine this model's library. Check the docs .