--- 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-xlmr_data-univner_half55 results: [] --- # scenario-non-kd-po-ner-full-xlmr_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: 0.1639 - Precision: 0.8020 - Recall: 0.8084 - F1: 0.8052 - Accuracy: 0.9798 ## 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 | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0755 | 0.5828 | 500 | 0.0755 | 0.7536 | 0.7986 | 0.7754 | 0.9776 | | 0.0412 | 1.1655 | 1000 | 0.0813 | 0.7809 | 0.7912 | 0.7860 | 0.9783 | | 0.0296 | 1.7483 | 1500 | 0.0840 | 0.7778 | 0.8042 | 0.7908 | 0.9788 | | 0.02 | 2.3310 | 2000 | 0.0938 | 0.7895 | 0.8042 | 0.7968 | 0.9791 | | 0.0182 | 2.9138 | 2500 | 0.0984 | 0.7760 | 0.7937 | 0.7847 | 0.9777 | | 0.0131 | 3.4965 | 3000 | 0.1027 | 0.7937 | 0.8016 | 0.7976 | 0.9791 | | 0.0119 | 4.0793 | 3500 | 0.1057 | 0.7955 | 0.7895 | 0.7925 | 0.9785 | | 0.0092 | 4.6620 | 4000 | 0.1141 | 0.7852 | 0.7855 | 0.7853 | 0.9780 | | 0.0085 | 5.2448 | 4500 | 0.1148 | 0.7781 | 0.8173 | 0.7972 | 0.9787 | | 0.0078 | 5.8275 | 5000 | 0.1116 | 0.8016 | 0.7834 | 0.7924 | 0.9790 | | 0.0063 | 6.4103 | 5500 | 0.1147 | 0.7951 | 0.8041 | 0.7996 | 0.9795 | | 0.0063 | 6.9930 | 6000 | 0.1211 | 0.7885 | 0.8032 | 0.7958 | 0.9791 | | 0.0048 | 7.5758 | 6500 | 0.1206 | 0.7957 | 0.8038 | 0.7997 | 0.9794 | | 0.0053 | 8.1585 | 7000 | 0.1313 | 0.8020 | 0.7979 | 0.7999 | 0.9789 | | 0.0044 | 8.7413 | 7500 | 0.1250 | 0.8067 | 0.7930 | 0.7998 | 0.9793 | | 0.0041 | 9.3240 | 8000 | 0.1293 | 0.7933 | 0.8045 | 0.7989 | 0.9789 | | 0.004 | 9.9068 | 8500 | 0.1255 | 0.8019 | 0.8029 | 0.8024 | 0.9798 | | 0.0032 | 10.4895 | 9000 | 0.1303 | 0.8018 | 0.8025 | 0.8021 | 0.9794 | | 0.0029 | 11.0723 | 9500 | 0.1367 | 0.7926 | 0.8121 | 0.8023 | 0.9796 | | 0.0029 | 11.6550 | 10000 | 0.1362 | 0.8021 | 0.7992 | 0.8006 | 0.9795 | | 0.0026 | 12.2378 | 10500 | 0.1369 | 0.8011 | 0.8081 | 0.8046 | 0.9794 | | 0.0028 | 12.8205 | 11000 | 0.1408 | 0.7972 | 0.8010 | 0.7991 | 0.9791 | | 0.0018 | 13.4033 | 11500 | 0.1502 | 0.7928 | 0.8093 | 0.8009 | 0.9788 | | 0.0024 | 13.9860 | 12000 | 0.1519 | 0.7828 | 0.8162 | 0.7991 | 0.9786 | | 0.002 | 14.5688 | 12500 | 0.1452 | 0.7958 | 0.8055 | 0.8006 | 0.9793 | | 0.0019 | 15.1515 | 13000 | 0.1498 | 0.7976 | 0.8068 | 0.8022 | 0.9789 | | 0.0018 | 15.7343 | 13500 | 0.1494 | 0.7998 | 0.8051 | 0.8024 | 0.9790 | | 0.0016 | 16.3170 | 14000 | 0.1466 | 0.7947 | 0.8098 | 0.8022 | 0.9790 | | 0.0015 | 16.8998 | 14500 | 0.1488 | 0.7897 | 0.8146 | 0.8019 | 0.9788 | | 0.0014 | 17.4825 | 15000 | 0.1535 | 0.7979 | 0.8149 | 0.8063 | 0.9794 | | 0.0016 | 18.0653 | 15500 | 0.1567 | 0.7935 | 0.8072 | 0.8003 | 0.9790 | | 0.0012 | 18.6480 | 16000 | 0.1483 | 0.8011 | 0.8052 | 0.8031 | 0.9795 | | 0.0011 | 19.2308 | 16500 | 0.1506 | 0.7951 | 0.8106 | 0.8027 | 0.9797 | | 0.0009 | 19.8135 | 17000 | 0.1552 | 0.8057 | 0.8035 | 0.8046 | 0.9797 | | 0.0007 | 20.3963 | 17500 | 0.1566 | 0.8007 | 0.8045 | 0.8026 | 0.9794 | | 0.0011 | 20.9790 | 18000 | 0.1528 | 0.8072 | 0.8036 | 0.8054 | 0.9798 | | 0.0008 | 21.5618 | 18500 | 0.1592 | 0.7966 | 0.8046 | 0.8006 | 0.9789 | | 0.0006 | 22.1445 | 19000 | 0.1582 | 0.8021 | 0.8059 | 0.8040 | 0.9794 | | 0.0006 | 22.7273 | 19500 | 0.1667 | 0.7953 | 0.8104 | 0.8028 | 0.9789 | | 0.0007 | 23.3100 | 20000 | 0.1618 | 0.8067 | 0.8028 | 0.8047 | 0.9795 | | 0.0006 | 23.8928 | 20500 | 0.1632 | 0.8004 | 0.8046 | 0.8025 | 0.9795 | | 0.0006 | 24.4755 | 21000 | 0.1661 | 0.7889 | 0.8140 | 0.8012 | 0.9787 | | 0.0006 | 25.0583 | 21500 | 0.1629 | 0.8034 | 0.8097 | 0.8066 | 0.9795 | | 0.0006 | 25.6410 | 22000 | 0.1630 | 0.8075 | 0.8070 | 0.8072 | 0.9799 | | 0.0005 | 26.2238 | 22500 | 0.1636 | 0.7975 | 0.8165 | 0.8069 | 0.9796 | | 0.0004 | 26.8065 | 23000 | 0.1614 | 0.8037 | 0.8113 | 0.8075 | 0.9800 | | 0.0003 | 27.3893 | 23500 | 0.1645 | 0.8024 | 0.8093 | 0.8058 | 0.9797 | | 0.0003 | 27.9720 | 24000 | 0.1637 | 0.8073 | 0.8038 | 0.8055 | 0.9798 | | 0.0003 | 28.5548 | 24500 | 0.1638 | 0.8025 | 0.8072 | 0.8049 | 0.9796 | | 0.0003 | 29.1375 | 25000 | 0.1633 | 0.8016 | 0.8093 | 0.8054 | 0.9797 | | 0.0003 | 29.7203 | 25500 | 0.1639 | 0.8020 | 0.8084 | 0.8052 | 0.9798 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1