Pii Layout Synth v7

--- library_name: transformers license: apache-2.0 base_model: answerdotai/ModernBERT-base tags: - trackio - trackio:https://huggingface.co/spaces/jefftherover/huggingface-static-9c06f2 - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: pii-layout-synth-v7 results: [] --- # pii-layout-synth-v7 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: 0.0060 - Precision: 0.9910 - Recall: 0.9949 - F1: 0.9929 - 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: 0.1 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0987 | 0.2455 | 500 | 0.0422 | 0.9013 | 0.9460 | 0.9231 | 0.9875 | | 0.0373 | 0.4909 | 1000 | 0.0174 | 0.9622 | 0.9783 | 0.9702 | 0.9949 | | 0.0241 | 0.7364 | 1500 | 0.0133 | 0.9732 | 0.9856 | 0.9793 | 0.9962 | | 0.0185 | 0.9818 | 2000 | 0.0136 | 0.9731 | 0.9812 | 0.9771 | 0.9960 | | 0.0116 | 1.2273 | 2500 | 0.0070 | 0.9852 | 0.9919 | 0.9885 | 0.9978 | | 0.0115 | 1.4728 | 3000 | 0.0075 | 0.9841 | 0.9917 | 0.9879 | 0.9977 | | 0.0088 | 1.7182 | 3500 | 0.0057 | 0.9881 | 0.9936 | 0.9908 | 0.9982 | | 0.0106 | 1.9637 | 4000 | 0.0051 | 0.9894 | 0.9952 | 0.9923 | 0.9984 | | 0.0051 | 2.2091 | 4500 | 0.0050 | 0.9896 | 0.9925 | 0.9910 | 0.9984 | | 0.0043 | 2.4546 | 5000 | 0.0051 | 0.9898 | 0.9949 | 0.9923 | 0.9985 | | 0.0048 | 2.7000 | 5500 | 0.0055 | 0.9900 | 0.9934 | 0.9917 | 0.9984 | | 0.0044 | 2.9455 | 6000 | 0.0050 | 0.9897 | 0.9946 | 0.9921 | 0.9984 | | 0.0018 | 3.1910 | 6500 | 0.0054 | 0.9908 | 0.9949 | 0.9928 | 0.9986 | | 0.0014 | 3.4364 | 7000 | 0.0053 | 0.9910 | 0.9946 | 0.9928 | 0.9986 | | 0.0016 | 3.6819 | 7500 | 0.0053 | 0.9905 | 0.9944 | 0.9924 | 0.9986 | | 0.0016 | 3.9273 | 8000 | 0.0051 | 0.9915 | 0.9948 | 0.9931 | 0.9987 | | 0.0004 | 4.1728 | 8500 | 0.0056 | 0.9912 | 0.9939 | 0.9925 | 0.9986 | | 0.0003 | 4.4183 | 9000 | 0.0060 | 0.9913 | 0.9949 | 0.9931 | 0.9986 | | 0.0006 | 4.6637 | 9500 | 0.0060 | 0.9910 | 0.9949 | 0.9929 | 0.9986 | ### Framework versions - Transformers 5.12.1 - Pytorch 2.12.0+cu130 - Datasets 5.0.0 - Tokenizers 0.22.2