--- 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_half55 results: [] --- # scenario-non-kd-po-ner-full-mdeberta_data-univner_half55 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: 0.1857 - Precision: 0.7753 - Recall: 0.7967 - F1: 0.7859 - Accuracy: 0.9781 ## 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: 55 - 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 | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.2478 | 0.5828 | 500 | 0.1339 | 0.4725 | 0.6165 | 0.5350 | 0.9540 | | 0.1025 | 1.1655 | 1000 | 0.1049 | 0.6273 | 0.7213 | 0.6710 | 0.9664 | | 0.071 | 1.7483 | 1500 | 0.0967 | 0.6465 | 0.7769 | 0.7058 | 0.9698 | | 0.048 | 2.3310 | 2000 | 0.0946 | 0.7123 | 0.7788 | 0.7441 | 0.9744 | | 0.0392 | 2.9138 | 2500 | 0.0989 | 0.7245 | 0.7705 | 0.7467 | 0.9745 | | 0.0266 | 3.4965 | 3000 | 0.1055 | 0.7467 | 0.7653 | 0.7559 | 0.9759 | | 0.0247 | 4.0793 | 3500 | 0.1095 | 0.7402 | 0.7798 | 0.7595 | 0.9758 | | 0.0171 | 4.6620 | 4000 | 0.1124 | 0.7518 | 0.7842 | 0.7677 | 0.9765 | | 0.0156 | 5.2448 | 4500 | 0.1127 | 0.7432 | 0.7945 | 0.7680 | 0.9767 | | 0.013 | 5.8275 | 5000 | 0.1167 | 0.7529 | 0.7787 | 0.7656 | 0.9760 | | 0.01 | 6.4103 | 5500 | 0.1262 | 0.7467 | 0.7909 | 0.7682 | 0.9763 | | 0.01 | 6.9930 | 6000 | 0.1357 | 0.7492 | 0.7807 | 0.7646 | 0.9757 | | 0.0076 | 7.5758 | 6500 | 0.1310 | 0.7500 | 0.7940 | 0.7714 | 0.9767 | | 0.007 | 8.1585 | 7000 | 0.1412 | 0.7446 | 0.7882 | 0.7658 | 0.9761 | | 0.006 | 8.7413 | 7500 | 0.1484 | 0.7539 | 0.7821 | 0.7677 | 0.9768 | | 0.0056 | 9.3240 | 8000 | 0.1475 | 0.7769 | 0.7693 | 0.7731 | 0.9775 | | 0.0053 | 9.9068 | 8500 | 0.1399 | 0.7633 | 0.7794 | 0.7713 | 0.9773 | | 0.0048 | 10.4895 | 9000 | 0.1433 | 0.7526 | 0.7938 | 0.7726 | 0.9767 | | 0.004 | 11.0723 | 9500 | 0.1476 | 0.7731 | 0.7842 | 0.7786 | 0.9774 | | 0.0034 | 11.6550 | 10000 | 0.1473 | 0.7671 | 0.7917 | 0.7792 | 0.9774 | | 0.0036 | 12.2378 | 10500 | 0.1570 | 0.7512 | 0.7915 | 0.7708 | 0.9765 | | 0.003 | 12.8205 | 11000 | 0.1534 | 0.7689 | 0.7807 | 0.7748 | 0.9772 | | 0.0025 | 13.4033 | 11500 | 0.1633 | 0.7748 | 0.7833 | 0.7790 | 0.9772 | | 0.0029 | 13.9860 | 12000 | 0.1590 | 0.7561 | 0.7938 | 0.7745 | 0.9768 | | 0.0027 | 14.5688 | 12500 | 0.1614 | 0.7598 | 0.8035 | 0.7810 | 0.9775 | | 0.0023 | 15.1515 | 13000 | 0.1629 | 0.7731 | 0.7947 | 0.7837 | 0.9780 | | 0.0022 | 15.7343 | 13500 | 0.1582 | 0.7776 | 0.7908 | 0.7841 | 0.9779 | | 0.0019 | 16.3170 | 14000 | 0.1699 | 0.7605 | 0.8020 | 0.7807 | 0.9776 | | 0.002 | 16.8998 | 14500 | 0.1602 | 0.7670 | 0.7898 | 0.7782 | 0.9773 | | 0.0015 | 17.4825 | 15000 | 0.1716 | 0.7690 | 0.7956 | 0.7821 | 0.9779 | | 0.0017 | 18.0653 | 15500 | 0.1721 | 0.7653 | 0.7917 | 0.7782 | 0.9772 | | 0.0013 | 18.6480 | 16000 | 0.1743 | 0.7724 | 0.7902 | 0.7812 | 0.9778 | | 0.0014 | 19.2308 | 16500 | 0.1756 | 0.7625 | 0.8029 | 0.7822 | 0.9775 | | 0.0013 | 19.8135 | 17000 | 0.1800 | 0.7598 | 0.8003 | 0.7795 | 0.9768 | | 0.0009 | 20.3963 | 17500 | 0.1737 | 0.7718 | 0.7957 | 0.7835 | 0.9779 | | 0.0012 | 20.9790 | 18000 | 0.1709 | 0.7628 | 0.7993 | 0.7806 | 0.9775 | | 0.0009 | 21.5618 | 18500 | 0.1824 | 0.7721 | 0.8003 | 0.7860 | 0.9778 | | 0.0008 | 22.1445 | 19000 | 0.1859 | 0.7578 | 0.8005 | 0.7786 | 0.9772 | | 0.0008 | 22.7273 | 19500 | 0.1793 | 0.7774 | 0.7914 | 0.7843 | 0.9781 | | 0.0009 | 23.3100 | 20000 | 0.1797 | 0.7713 | 0.7908 | 0.7809 | 0.9780 | | 0.0007 | 23.8928 | 20500 | 0.1811 | 0.7616 | 0.7989 | 0.7798 | 0.9777 | | 0.0006 | 24.4755 | 21000 | 0.1831 | 0.7811 | 0.7889 | 0.7850 | 0.9782 | | 0.0006 | 25.0583 | 21500 | 0.1874 | 0.7644 | 0.8006 | 0.7821 | 0.9776 | | 0.0006 | 25.6410 | 22000 | 0.1840 | 0.7709 | 0.7937 | 0.7821 | 0.9777 | | 0.0005 | 26.2238 | 22500 | 0.1867 | 0.7719 | 0.7989 | 0.7852 | 0.9781 | | 0.0005 | 26.8065 | 23000 | 0.1826 | 0.7781 | 0.7878 | 0.7829 | 0.9782 | | 0.0004 | 27.3893 | 23500 | 0.1865 | 0.7719 | 0.8018 | 0.7866 | 0.9782 | | 0.0005 | 27.9720 | 24000 | 0.1871 | 0.7733 | 0.7987 | 0.7858 | 0.9781 | | 0.0004 | 28.5548 | 24500 | 0.1856 | 0.7770 | 0.7973 | 0.7870 | 0.9784 | | 0.0004 | 29.1375 | 25000 | 0.1854 | 0.7728 | 0.7967 | 0.7846 | 0.9781 | | 0.0003 | 29.7203 | 25500 | 0.1857 | 0.7753 | 0.7967 | 0.7859 | 0.9781 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1