results
This model is a fine-tuned version of distilbert-base-multilingual-cased on the Fake News Filipino dataset. It achieves the following results on the evaluation set:
- Loss: 0.1618
- F1: 0.9667
- Accuracy: 0.9667
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| No log | 1.0 | 71 | 0.1838 | 0.9314 | 0.9314 |
| 0.2872 | 2.0 | 142 | 0.1724 | 0.9521 | 0.9522 |
| 0.1337 | 3.0 | 213 | 0.1293 | 0.9584 | 0.9584 |
| 0.1337 | 4.0 | 284 | 0.1663 | 0.9646 | 0.9647 |
| 0.0496 | 5.0 | 355 | 0.1337 | 0.9709 | 0.9709 |
| 0.0247 | 6.0 | 426 | 0.2246 | 0.9500 | 0.9501 |
| 0.0247 | 7.0 | 497 | 0.1618 | 0.9667 | 0.9667 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4