Payment-NonPayment-distilbert-base-uncased_V2
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0102
- Accuracy: 0.9987
- F1: 0.9987
- Precision: 0.9987
- Recall: 0.9987
- Roc Auc: 0.9987
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 0.0186 | 1.0 | 3167 | 0.0101 | 0.9986 | 0.9986 | 0.9986 | 0.9986 | 0.9987 |
| 0.0186 | 2.0 | 6334 | 0.0096 | 0.9988 | 0.9988 | 0.9988 | 0.9988 | 0.9988 |
| 0.0194 | 3.0 | 9501 | 0.0071 | 0.9991 | 0.9991 | 0.9991 | 0.9991 | 0.9990 |
| 0.018 | 4.0 | 12668 | 0.0101 | 0.9987 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
| 0.0198 | 5.0 | 15835 | 0.0102 | 0.9987 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.21.0