Pii Layout Synth v8

--- library_name: transformers license: apache-2.0 base_model: answerdotai/ModernBERT-base tags: - trackio - trackio:https://huggingface.co/spaces/jefftherover/huggingface-static-bb31b0 - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: pii-layout-synth-v8 results: [] --- # pii-layout-synth-v8 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0052 - Precision: 0.9911 - Recall: 0.9952 - F1: 0.9932 - 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: 0.1 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0867 | 0.2455 | 500 | 0.0315 | 0.9269 | 0.9599 | 0.9431 | 0.9912 | | 0.0366 | 0.4909 | 1000 | 0.0164 | 0.9655 | 0.9758 | 0.9706 | 0.9950 | | 0.0242 | 0.7364 | 1500 | 0.0132 | 0.9742 | 0.9835 | 0.9789 | 0.9961 | | 0.0179 | 0.9818 | 2000 | 0.0074 | 0.9833 | 0.9890 | 0.9861 | 0.9976 | | 0.0116 | 1.2273 | 2500 | 0.0064 | 0.9873 | 0.9930 | 0.9901 | 0.9981 | | 0.0108 | 1.4728 | 3000 | 0.0073 | 0.9849 | 0.9916 | 0.9883 | 0.9977 | | 0.0126 | 1.7182 | 3500 | 0.0070 | 0.9832 | 0.9912 | 0.9872 | 0.9978 | | 0.0119 | 1.9637 | 4000 | 0.0058 | 0.9873 | 0.9940 | 0.9907 | 0.9982 | | 0.0049 | 2.2091 | 4500 | 0.0054 | 0.9894 | 0.9924 | 0.9909 | 0.9983 | | 0.0054 | 2.4546 | 5000 | 0.0085 | 0.9832 | 0.9928 | 0.9880 | 0.9975 | | 0.0041 | 2.7000 | 5500 | 0.0048 | 0.9900 | 0.9943 | 0.9921 | 0.9985 | | 0.0041 | 2.9455 | 6000 | 0.0050 | 0.9911 | 0.9957 | 0.9934 | 0.9986 | | 0.0014 | 3.1910 | 6500 | 0.0058 | 0.9904 | 0.9948 | 0.9926 | 0.9985 | | 0.0017 | 3.4364 | 7000 | 0.0055 | 0.9912 | 0.9951 | 0.9932 | 0.9986 | | 0.0020 | 3.6819 | 7500 | 0.0052 | 0.9911 | 0.9952 | 0.9932 | 0.9987 | ### Framework versions - Transformers 5.12.1 - Pytorch 2.12.0+cu130 - Datasets 5.0.0 - Tokenizers 0.22.2