Payment-NonPayment-distilbert-base-uncased
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: 0.0168
- Accuracy: 0.9976
- F1: 0.9976
- Precision: 0.9976
- Recall: 0.9976
- Roc Auc: 0.9977
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 |
|---|---|---|---|---|---|---|---|---|
| 0.6981 | 1.0 | 3166 | 0.6913 | 0.5348 | 0.3727 | 0.2860 | 0.5348 | 0.5 |
| 0.2889 | 2.0 | 6332 | 0.2500 | 0.9149 | 0.9138 | 0.9265 | 0.9149 | 0.9086 |
| 0.1408 | 3.0 | 9498 | 0.5305 | 0.8745 | 0.8737 | 0.9006 | 0.8745 | 0.8826 |
| 0.0114 | 4.0 | 12664 | 0.0184 | 0.9976 | 0.9976 | 0.9976 | 0.9976 | 0.9977 |
| 0.0417 | 5.0 | 15830 | 0.0168 | 0.9976 | 0.9976 | 0.9976 | 0.9976 | 0.9977 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.21.0