pii-layout-synth-v14
This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0047
- Precision: 0.9910
- Recall: 0.9941
- F1: 0.9925
- Accuracy: 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: cosine_with_restarts
- lr_scheduler_warmup_steps: 200
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0159 | 0.9685 | 2000 | 0.0080 | 0.9836 | 0.9899 | 0.9867 | 0.9976 |
| 0.0065 | 1.9370 | 4000 | 0.0043 | 0.9895 | 0.9935 | 0.9915 | 0.9985 |
| 0.0032 | 2.9056 | 6000 | 0.0044 | 0.9905 | 0.9929 | 0.9917 | 0.9986 |
| 0.0008 | 3.8741 | 8000 | 0.0047 | 0.9910 | 0.9942 | 0.9926 | 0.9987 |
| 0.0009 | 4.0 | 8260 | 0.0047 | 0.9910 | 0.9941 | 0.9925 | 0.9987 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.12.1+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2