Mdeberta Crf Yarn Ner

--- library_name: transformers license: mit base_model: microsoft/mdeberta-v3-base tags: - generated_from_trainer metrics: - precision - recall - f1 model-index: - name: mdeberta-crf-yarn-ner results: [] --- # mdeberta-crf-yarn-ner This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1735 - Precision: 0.9871 - Recall: 0.9922 - F1: 0.9896 ## 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: 2e-05 - train_batch_size: 16 - eval_batch_size: 32 - seed: 42 - 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: linear - lr_scheduler_warmup_steps: 0.1 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:| | 1.0562 | 1.0 | 735 | 1.3849 | 0.9798 | 0.9849 | 0.9824 | | 0.9622 | 2.0 | 1470 | 0.8320 | 0.9791 | 0.9887 | 0.9839 | | 0.9311 | 3.0 | 2205 | 1.0320 | 0.9805 | 0.9870 | 0.9838 | | 0.7683 | 4.0 | 2940 | 0.9384 | 0.9801 | 0.9906 | 0.9853 | | 0.3901 | 5.0 | 3675 | 0.9550 | 0.9826 | 0.9889 | 0.9857 | | 0.3419 | 6.0 | 4410 | 0.9833 | 0.9871 | 0.9902 | 0.9886 | | 0.2612 | 7.0 | 5145 | 0.9339 | 0.9852 | 0.9902 | 0.9877 | | 0.2264 | 8.0 | 5880 | 1.0695 | 0.9867 | 0.9902 | 0.9884 | | 0.0923 | 9.0 | 6615 | 1.0227 | 0.9850 | 0.9900 | 0.9875 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2