--- base_model: haryoaw/scenario-TCR-NER_data-univner_half library_name: transformers license: mit metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer model-index: - name: scenario-non-kd-po-ner-full-mdeberta_data-univner_half44 results: [] --- # scenario-non-kd-po-ner-full-mdeberta_data-univner_half44 This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_half](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_half) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1899 - Precision: 0.7789 - Recall: 0.7960 - F1: 0.7874 - Accuracy: 0.9782 ## 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: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 44 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 30 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.2534 | 0.5828 | 500 | 0.1393 | 0.4829 | 0.5549 | 0.5164 | 0.9528 | | 0.1074 | 1.1655 | 1000 | 0.1049 | 0.6398 | 0.6839 | 0.6611 | 0.9677 | | 0.0707 | 1.7483 | 1500 | 0.0936 | 0.6774 | 0.7715 | 0.7214 | 0.9724 | | 0.0495 | 2.3310 | 2000 | 0.0966 | 0.6839 | 0.7790 | 0.7284 | 0.9722 | | 0.0393 | 2.9138 | 2500 | 0.0951 | 0.7067 | 0.7681 | 0.7361 | 0.9731 | | 0.0289 | 3.4965 | 3000 | 0.0962 | 0.7249 | 0.7863 | 0.7544 | 0.9751 | | 0.023 | 4.0793 | 3500 | 0.1101 | 0.7418 | 0.7791 | 0.7600 | 0.9764 | | 0.0176 | 4.6620 | 4000 | 0.1141 | 0.7400 | 0.7748 | 0.7570 | 0.9755 | | 0.0157 | 5.2448 | 4500 | 0.1200 | 0.7452 | 0.7973 | 0.7704 | 0.9761 | | 0.0123 | 5.8275 | 5000 | 0.1205 | 0.7619 | 0.7752 | 0.7685 | 0.9770 | | 0.0102 | 6.4103 | 5500 | 0.1261 | 0.7576 | 0.7769 | 0.7671 | 0.9762 | | 0.0101 | 6.9930 | 6000 | 0.1231 | 0.7699 | 0.7720 | 0.7710 | 0.9770 | | 0.0085 | 7.5758 | 6500 | 0.1334 | 0.7546 | 0.7844 | 0.7692 | 0.9764 | | 0.0067 | 8.1585 | 7000 | 0.1381 | 0.7640 | 0.7878 | 0.7757 | 0.9768 | | 0.0059 | 8.7413 | 7500 | 0.1370 | 0.7650 | 0.7855 | 0.7751 | 0.9770 | | 0.0058 | 9.3240 | 8000 | 0.1505 | 0.7585 | 0.7790 | 0.7686 | 0.9768 | | 0.0053 | 9.9068 | 8500 | 0.1423 | 0.7604 | 0.7886 | 0.7743 | 0.9772 | | 0.0048 | 10.4895 | 9000 | 0.1480 | 0.7566 | 0.7957 | 0.7757 | 0.9770 | | 0.0037 | 11.0723 | 9500 | 0.1495 | 0.7602 | 0.7870 | 0.7734 | 0.9765 | | 0.0037 | 11.6550 | 10000 | 0.1519 | 0.7652 | 0.7787 | 0.7719 | 0.9773 | | 0.0034 | 12.2378 | 10500 | 0.1580 | 0.7654 | 0.7859 | 0.7755 | 0.9771 | | 0.0027 | 12.8205 | 11000 | 0.1589 | 0.7686 | 0.7806 | 0.7745 | 0.9770 | | 0.0026 | 13.4033 | 11500 | 0.1557 | 0.7749 | 0.7767 | 0.7758 | 0.9773 | | 0.0027 | 13.9860 | 12000 | 0.1613 | 0.7587 | 0.7875 | 0.7728 | 0.9769 | | 0.002 | 14.5688 | 12500 | 0.1765 | 0.7746 | 0.7767 | 0.7756 | 0.9771 | | 0.0023 | 15.1515 | 13000 | 0.1723 | 0.7674 | 0.7898 | 0.7784 | 0.9773 | | 0.0024 | 15.7343 | 13500 | 0.1594 | 0.7672 | 0.7856 | 0.7763 | 0.9772 | | 0.0015 | 16.3170 | 14000 | 0.1696 | 0.7576 | 0.7927 | 0.7747 | 0.9770 | | 0.0019 | 16.8998 | 14500 | 0.1641 | 0.7704 | 0.7857 | 0.7780 | 0.9778 | | 0.0016 | 17.4825 | 15000 | 0.1644 | 0.7711 | 0.7896 | 0.7802 | 0.9775 | | 0.0017 | 18.0653 | 15500 | 0.1769 | 0.7600 | 0.7938 | 0.7766 | 0.9772 | | 0.0014 | 18.6480 | 16000 | 0.1760 | 0.7642 | 0.7821 | 0.7730 | 0.9770 | | 0.0013 | 19.2308 | 16500 | 0.1705 | 0.7737 | 0.7824 | 0.7780 | 0.9776 | | 0.0013 | 19.8135 | 17000 | 0.1729 | 0.7756 | 0.7875 | 0.7815 | 0.9778 | | 0.0012 | 20.3963 | 17500 | 0.1758 | 0.7615 | 0.7935 | 0.7772 | 0.9777 | | 0.0012 | 20.9790 | 18000 | 0.1755 | 0.7692 | 0.7966 | 0.7826 | 0.9778 | | 0.001 | 21.5618 | 18500 | 0.1719 | 0.7716 | 0.7902 | 0.7808 | 0.9781 | | 0.0008 | 22.1445 | 19000 | 0.1739 | 0.7731 | 0.7914 | 0.7821 | 0.9782 | | 0.0008 | 22.7273 | 19500 | 0.1754 | 0.7667 | 0.7930 | 0.7796 | 0.9777 | | 0.0007 | 23.3100 | 20000 | 0.1837 | 0.7622 | 0.7938 | 0.7777 | 0.9776 | | 0.0006 | 23.8928 | 20500 | 0.1783 | 0.7757 | 0.7914 | 0.7835 | 0.9780 | | 0.0005 | 24.4755 | 21000 | 0.1831 | 0.7782 | 0.7905 | 0.7843 | 0.9779 | | 0.0007 | 25.0583 | 21500 | 0.1799 | 0.7727 | 0.7944 | 0.7834 | 0.9781 | | 0.0005 | 25.6410 | 22000 | 0.1828 | 0.7743 | 0.7944 | 0.7842 | 0.9782 | | 0.0005 | 26.2238 | 22500 | 0.1850 | 0.7642 | 0.8012 | 0.7823 | 0.9779 | | 0.0004 | 26.8065 | 23000 | 0.1868 | 0.7765 | 0.7894 | 0.7829 | 0.9781 | | 0.0004 | 27.3893 | 23500 | 0.1915 | 0.7759 | 0.7979 | 0.7867 | 0.9779 | | 0.0003 | 27.9720 | 24000 | 0.1880 | 0.7817 | 0.7956 | 0.7886 | 0.9783 | | 0.0003 | 28.5548 | 24500 | 0.1886 | 0.7795 | 0.7935 | 0.7864 | 0.9782 | | 0.0004 | 29.1375 | 25000 | 0.1892 | 0.7749 | 0.7996 | 0.7870 | 0.9782 | | 0.0004 | 29.7203 | 25500 | 0.1899 | 0.7789 | 0.7960 | 0.7874 | 0.9782 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1