pii-layout-synth-v13
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: 0.0050
- Precision: 0.9902
- Recall: 0.9943
- F1: 0.9923
- Accuracy: 0.9986
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 |
|---|---|---|---|---|---|---|---|
| 0.0141 | 0.9818 | 2000 | 0.0074 | 0.9806 | 0.9857 | 0.9832 | 0.9975 |
| 0.0078 | 1.9637 | 4000 | 0.0050 | 0.9889 | 0.9945 | 0.9917 | 0.9984 |
| 0.0029 | 2.9455 | 6000 | 0.0045 | 0.9903 | 0.9950 | 0.9926 | 0.9986 |
| 0.0009 | 3.9273 | 8000 | 0.0050 | 0.9902 | 0.9943 | 0.9922 | 0.9986 |
| 0.0009 | 4.0 | 8148 | 0.0050 | 0.9902 | 0.9943 | 0.9923 | 0.9986 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.12.1+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2