empire-content-distilbert
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0786
- Accuracy: 0.9814
- F1 Macro: 0.9817
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: 16
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 0.4091 | 1.0 | 133 | 0.1518 | 0.9654 | 0.9630 |
| 0.0850 | 2.0 | 266 | 0.0976 | 0.9761 | 0.9757 |
| 0.0382 | 3.0 | 399 | 0.0757 | 0.9787 | 0.9780 |
| 0.0209 | 4.0 | 532 | 0.0786 | 0.9814 | 0.9817 |
| 0.0124 | 5.0 | 665 | 0.0842 | 0.9787 | 0.9790 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.12.0+cu130
- Datasets 4.8.5
- Tokenizers 0.22.2