--- base_model: haryoaw/scenario-TCR-NER_data-univner_full library_name: transformers license: mit metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer model-index: - name: scenario-kd-scr-ner-full_data-univner_full44 results: [] --- # scenario-kd-scr-ner-full_data-univner_full44 This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_full](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_full) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1033 - Precision: 0.6036 - Recall: 0.5441 - F1: 0.5723 - Accuracy: 0.9593 ## 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 | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 2.8555 | 0.2910 | 500 | 2.5101 | 0.1888 | 0.0407 | 0.0669 | 0.9233 | | 2.1564 | 0.5821 | 1000 | 2.1629 | 0.2303 | 0.1529 | 0.1838 | 0.9272 | | 1.9176 | 0.8731 | 1500 | 2.0551 | 0.2484 | 0.1326 | 0.1729 | 0.9290 | | 1.7645 | 1.1641 | 2000 | 1.9667 | 0.2914 | 0.1539 | 0.2015 | 0.9319 | | 1.6699 | 1.4552 | 2500 | 1.8455 | 0.2770 | 0.2391 | 0.2566 | 0.9342 | | 1.5836 | 1.7462 | 3000 | 1.8413 | 0.3525 | 0.2388 | 0.2847 | 0.9377 | | 1.4981 | 2.0373 | 3500 | 1.6842 | 0.3698 | 0.2897 | 0.3249 | 0.9398 | | 1.3481 | 2.3283 | 4000 | 1.6502 | 0.3867 | 0.3320 | 0.3573 | 0.9405 | | 1.3432 | 2.6193 | 4500 | 1.6815 | 0.3763 | 0.3334 | 0.3536 | 0.9382 | | 1.2954 | 2.9104 | 5000 | 1.5667 | 0.4099 | 0.3443 | 0.3742 | 0.9431 | | 1.1925 | 3.2014 | 5500 | 1.5220 | 0.4337 | 0.3594 | 0.3931 | 0.9441 | | 1.1588 | 3.4924 | 6000 | 1.5354 | 0.4016 | 0.3821 | 0.3916 | 0.9428 | | 1.107 | 3.7835 | 6500 | 1.4844 | 0.4572 | 0.3718 | 0.4101 | 0.9456 | | 1.0738 | 4.0745 | 7000 | 1.4503 | 0.4181 | 0.4041 | 0.4110 | 0.9465 | | 0.9979 | 4.3655 | 7500 | 1.4415 | 0.4712 | 0.3787 | 0.4199 | 0.9472 | | 0.9833 | 4.6566 | 8000 | 1.4303 | 0.4696 | 0.4158 | 0.4411 | 0.9475 | | 0.9564 | 4.9476 | 8500 | 1.4136 | 0.4310 | 0.4250 | 0.4280 | 0.9481 | | 0.8779 | 5.2386 | 9000 | 1.3971 | 0.4514 | 0.4465 | 0.4489 | 0.9495 | | 0.8511 | 5.5297 | 9500 | 1.3609 | 0.4661 | 0.4161 | 0.4397 | 0.9495 | | 0.849 | 5.8207 | 10000 | 1.3403 | 0.5161 | 0.4224 | 0.4646 | 0.9508 | | 0.8182 | 6.1118 | 10500 | 1.3515 | 0.4611 | 0.4581 | 0.4596 | 0.9507 | | 0.76 | 6.4028 | 11000 | 1.3629 | 0.4871 | 0.4484 | 0.4670 | 0.9515 | | 0.7494 | 6.6938 | 11500 | 1.3188 | 0.4907 | 0.4812 | 0.4859 | 0.9526 | | 0.7363 | 6.9849 | 12000 | 1.3117 | 0.4692 | 0.4425 | 0.4555 | 0.9518 | | 0.6894 | 7.2759 | 12500 | 1.3309 | 0.5193 | 0.4308 | 0.4709 | 0.9526 | | 0.6688 | 7.5669 | 13000 | 1.3295 | 0.5067 | 0.4526 | 0.4781 | 0.9529 | | 0.6628 | 7.8580 | 13500 | 1.2883 | 0.5212 | 0.4920 | 0.5062 | 0.9542 | | 0.6274 | 8.1490 | 14000 | 1.2968 | 0.5284 | 0.4878 | 0.5073 | 0.9544 | | 0.6066 | 8.4400 | 14500 | 1.2572 | 0.5216 | 0.4942 | 0.5075 | 0.9543 | | 0.6126 | 8.7311 | 15000 | 1.2623 | 0.5105 | 0.5167 | 0.5136 | 0.9548 | | 0.5929 | 9.0221 | 15500 | 1.2700 | 0.5223 | 0.4940 | 0.5077 | 0.9548 | | 0.5614 | 9.3132 | 16000 | 1.2609 | 0.5307 | 0.5054 | 0.5177 | 0.9552 | | 0.5557 | 9.6042 | 16500 | 1.2618 | 0.5590 | 0.4766 | 0.5145 | 0.9552 | | 0.5526 | 9.8952 | 17000 | 1.2479 | 0.5451 | 0.4975 | 0.5202 | 0.9556 | | 0.526 | 10.1863 | 17500 | 1.2370 | 0.5432 | 0.5211 | 0.5320 | 0.9566 | | 0.5102 | 10.4773 | 18000 | 1.2283 | 0.5435 | 0.5232 | 0.5331 | 0.9563 | | 0.5163 | 10.7683 | 18500 | 1.2373 | 0.5523 | 0.5279 | 0.5398 | 0.9562 | | 0.4977 | 11.0594 | 19000 | 1.2457 | 0.5610 | 0.5028 | 0.5303 | 0.9564 | | 0.4829 | 11.3504 | 19500 | 1.2389 | 0.5677 | 0.5268 | 0.5465 | 0.9572 | | 0.4692 | 11.6414 | 20000 | 1.2132 | 0.5599 | 0.5198 | 0.5391 | 0.9570 | | 0.4749 | 11.9325 | 20500 | 1.2180 | 0.5531 | 0.5377 | 0.5453 | 0.9565 | | 0.4533 | 12.2235 | 21000 | 1.2167 | 0.5562 | 0.5193 | 0.5371 | 0.9569 | | 0.4446 | 12.5146 | 21500 | 1.2015 | 0.5489 | 0.5331 | 0.5409 | 0.9568 | | 0.447 | 12.8056 | 22000 | 1.2149 | 0.5598 | 0.5258 | 0.5422 | 0.9566 | | 0.4394 | 13.0966 | 22500 | 1.1838 | 0.5620 | 0.5376 | 0.5495 | 0.9570 | | 0.4245 | 13.3877 | 23000 | 1.1928 | 0.5910 | 0.5269 | 0.5571 | 0.9582 | | 0.4152 | 13.6787 | 23500 | 1.1844 | 0.5571 | 0.5331 | 0.5449 | 0.9570 | | 0.4164 | 13.9697 | 24000 | 1.2065 | 0.5649 | 0.5304 | 0.5471 | 0.9572 | | 0.397 | 14.2608 | 24500 | 1.1761 | 0.5779 | 0.5304 | 0.5531 | 0.9572 | | 0.3952 | 14.5518 | 25000 | 1.1791 | 0.5659 | 0.5379 | 0.5515 | 0.9575 | | 0.3973 | 14.8428 | 25500 | 1.2108 | 0.5868 | 0.5262 | 0.5548 | 0.9575 | | 0.3906 | 15.1339 | 26000 | 1.1774 | 0.5684 | 0.5568 | 0.5625 | 0.9581 | | 0.3781 | 15.4249 | 26500 | 1.1943 | 0.5897 | 0.5337 | 0.5603 | 0.9579 | | 0.3723 | 15.7159 | 27000 | 1.1733 | 0.5578 | 0.5519 | 0.5548 | 0.9571 | | 0.3705 | 16.0070 | 27500 | 1.1785 | 0.5711 | 0.5403 | 0.5553 | 0.9578 | | 0.3563 | 16.2980 | 28000 | 1.1837 | 0.5760 | 0.5356 | 0.5551 | 0.9580 | | 0.3542 | 16.5891 | 28500 | 1.1748 | 0.5918 | 0.5195 | 0.5533 | 0.9580 | | 0.3603 | 16.8801 | 29000 | 1.1675 | 0.5874 | 0.5429 | 0.5643 | 0.9585 | | 0.3518 | 17.1711 | 29500 | 1.1536 | 0.5918 | 0.5444 | 0.5671 | 0.9582 | | 0.343 | 17.4622 | 30000 | 1.1422 | 0.5899 | 0.5333 | 0.5602 | 0.9583 | | 0.3399 | 17.7532 | 30500 | 1.1619 | 0.5854 | 0.5258 | 0.5540 | 0.9581 | | 0.3355 | 18.0442 | 31000 | 1.1395 | 0.5846 | 0.5423 | 0.5627 | 0.9584 | | 0.3317 | 18.3353 | 31500 | 1.1426 | 0.5920 | 0.5465 | 0.5683 | 0.9584 | | 0.3284 | 18.6263 | 32000 | 1.1357 | 0.5834 | 0.5496 | 0.5660 | 0.9590 | | 0.3262 | 18.9173 | 32500 | 1.1450 | 0.5751 | 0.5403 | 0.5572 | 0.9583 | | 0.3215 | 19.2084 | 33000 | 1.1376 | 0.5822 | 0.5500 | 0.5656 | 0.9587 | | 0.3188 | 19.4994 | 33500 | 1.1514 | 0.5885 | 0.5442 | 0.5655 | 0.9587 | | 0.3172 | 19.7905 | 34000 | 1.1390 | 0.5908 | 0.5416 | 0.5651 | 0.9585 | | 0.3102 | 20.0815 | 34500 | 1.1351 | 0.5968 | 0.5367 | 0.5652 | 0.9587 | | 0.3109 | 20.3725 | 35000 | 1.1356 | 0.5980 | 0.5392 | 0.5671 | 0.9586 | | 0.3039 | 20.6636 | 35500 | 1.1291 | 0.6160 | 0.5187 | 0.5632 | 0.9587 | | 0.307 | 20.9546 | 36000 | 1.1421 | 0.6046 | 0.5423 | 0.5718 | 0.9588 | | 0.3043 | 21.2456 | 36500 | 1.1416 | 0.6020 | 0.5553 | 0.5777 | 0.9591 | | 0.2936 | 21.5367 | 37000 | 1.1234 | 0.6004 | 0.5475 | 0.5727 | 0.9591 | | 0.2984 | 21.8277 | 37500 | 1.1317 | 0.5894 | 0.5423 | 0.5649 | 0.9582 | | 0.2986 | 22.1187 | 38000 | 1.1294 | 0.5961 | 0.5468 | 0.5704 | 0.9590 | | 0.2885 | 22.4098 | 38500 | 1.1287 | 0.6151 | 0.5385 | 0.5742 | 0.9591 | | 0.2897 | 22.7008 | 39000 | 1.1261 | 0.5981 | 0.5507 | 0.5734 | 0.9590 | | 0.2897 | 22.9919 | 39500 | 1.1226 | 0.6051 | 0.5393 | 0.5703 | 0.9589 | | 0.2857 | 23.2829 | 40000 | 1.1248 | 0.6082 | 0.5353 | 0.5694 | 0.9591 | | 0.2819 | 23.5739 | 40500 | 1.1162 | 0.6230 | 0.5413 | 0.5793 | 0.9594 | | 0.2867 | 23.8650 | 41000 | 1.1145 | 0.6027 | 0.5435 | 0.5716 | 0.9591 | | 0.2796 | 24.1560 | 41500 | 1.1193 | 0.6025 | 0.5488 | 0.5744 | 0.9592 | | 0.2758 | 24.4470 | 42000 | 1.1114 | 0.6073 | 0.5529 | 0.5788 | 0.9593 | | 0.2779 | 24.7381 | 42500 | 1.1022 | 0.6036 | 0.5530 | 0.5772 | 0.9596 | | 0.2782 | 25.0291 | 43000 | 1.1104 | 0.6155 | 0.5434 | 0.5772 | 0.9593 | | 0.2723 | 25.3201 | 43500 | 1.1179 | 0.6139 | 0.5275 | 0.5674 | 0.9590 | | 0.276 | 25.6112 | 44000 | 1.1176 | 0.6099 | 0.5445 | 0.5753 | 0.9592 | | 0.2694 | 25.9022 | 44500 | 1.1124 | 0.6043 | 0.5386 | 0.5696 | 0.9591 | | 0.2723 | 26.1932 | 45000 | 1.1185 | 0.6068 | 0.5421 | 0.5726 | 0.9591 | | 0.2664 | 26.4843 | 45500 | 1.1090 | 0.6026 | 0.5455 | 0.5727 | 0.9592 | | 0.2675 | 26.7753 | 46000 | 1.1077 | 0.6022 | 0.5571 | 0.5787 | 0.9594 | | 0.2687 | 27.0664 | 46500 | 1.1059 | 0.6146 | 0.5353 | 0.5722 | 0.9593 | | 0.2635 | 27.3574 | 47000 | 1.1013 | 0.5965 | 0.5535 | 0.5742 | 0.9590 | | 0.2652 | 27.6484 | 47500 | 1.1031 | 0.6048 | 0.5340 | 0.5672 | 0.9588 | | 0.2657 | 27.9395 | 48000 | 1.1053 | 0.6074 | 0.5471 | 0.5757 | 0.9595 | | 0.2626 | 28.2305 | 48500 | 1.1000 | 0.6154 | 0.5452 | 0.5782 | 0.9595 | | 0.2596 | 28.5215 | 49000 | 1.1055 | 0.6012 | 0.5497 | 0.5743 | 0.9594 | | 0.2648 | 28.8126 | 49500 | 1.1101 | 0.6109 | 0.5454 | 0.5763 | 0.9593 | | 0.2597 | 29.1036 | 50000 | 1.1020 | 0.6181 | 0.5455 | 0.5796 | 0.9595 | | 0.2598 | 29.3946 | 50500 | 1.1045 | 0.608 | 0.5483 | 0.5766 | 0.9592 | | 0.2577 | 29.6857 | 51000 | 1.1024 | 0.6052 | 0.5559 | 0.5795 | 0.9593 | | 0.2622 | 29.9767 | 51500 | 1.1033 | 0.6036 | 0.5441 | 0.5723 | 0.9593 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1