distilbert_finetuned_fake_news
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0295
- Accuracy: 0.9872
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 64
- 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
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.07 | 100 | 0.0971 | 0.9809 |
| No log | 0.13 | 200 | 0.0419 | 0.9808 |
| No log | 0.2 | 300 | 0.0531 | 0.9772 |
| No log | 0.26 | 400 | 0.0459 | 0.9807 |
| 0.1424 | 0.33 | 500 | 0.0400 | 0.9799 |
| 0.1424 | 0.39 | 600 | 0.0395 | 0.9804 |
| 0.1424 | 0.46 | 700 | 0.0444 | 0.9770 |
| 0.1424 | 0.53 | 800 | 0.0455 | 0.9824 |
| 0.1424 | 0.59 | 900 | 0.0326 | 0.9837 |
| 0.0419 | 0.66 | 1000 | 0.0456 | 0.9852 |
| 0.0419 | 0.72 | 1100 | 0.0357 | 0.9850 |
| 0.0419 | 0.79 | 1200 | 0.0327 | 0.9871 |
| 0.0419 | 0.85 | 1300 | 0.0309 | 0.9874 |
| 0.0419 | 0.92 | 1400 | 0.0309 | 0.9869 |
| 0.0334 | 0.98 | 1500 | 0.0295 | 0.9872 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2