|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilbert-base-casedfinetuned-fake-news-detection |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# distilbert-base-casedfinetuned-fake-news-detection |
|
|
|
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the [Fake and Reals News](https://www.kaggle.com/datasets/clmentbisaillon/fake-and-real-news-dataset) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0019 |
|
- F1: 0.9998 |
|
- Accuracy: 0.9998 |
|
|
|
The [Fake and Reals News](https://www.kaggle.com/datasets/clmentbisaillon/fake-and-real-news-dataset) dataset was used. It was stratified split into a train-val-test set (60/20/20). |
|
|
|
## 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: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
|
| No log | 1.0 | 1684 | 0.0021 | 0.9998 | 0.9998 | |
|
| No log | 2.0 | 3368 | 0.0019 | 0.9998 | 0.9998 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.0.0 |
|
- Tokenizers 0.11.6 |
|
|
