--- 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_half44 results: [] --- # scenario-non-kd-po-ner-full-xlmr_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: 0.1451 - Precision: 0.8545 - Recall: 0.8580 - F1: 0.8562 - Accuracy: 0.9846 ## 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 | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0099 | 0.5828 | 500 | 0.0855 | 0.8429 | 0.8336 | 0.8382 | 0.9835 | | 0.0104 | 1.1655 | 1000 | 0.0903 | 0.8392 | 0.8524 | 0.8458 | 0.9841 | | 0.0085 | 1.7483 | 1500 | 0.0941 | 0.8319 | 0.8524 | 0.8420 | 0.9835 | | 0.0076 | 2.3310 | 2000 | 0.1037 | 0.8424 | 0.8443 | 0.8433 | 0.9832 | | 0.0071 | 2.9138 | 2500 | 0.0983 | 0.8252 | 0.8550 | 0.8399 | 0.9831 | | 0.007 | 3.4965 | 3000 | 0.0964 | 0.8389 | 0.8547 | 0.8467 | 0.9834 | | 0.0059 | 4.0793 | 3500 | 0.0988 | 0.8418 | 0.8510 | 0.8464 | 0.9839 | | 0.0051 | 4.6620 | 4000 | 0.1094 | 0.8410 | 0.8472 | 0.8441 | 0.9833 | | 0.0055 | 5.2448 | 4500 | 0.1039 | 0.8380 | 0.8521 | 0.8450 | 0.9834 | | 0.0043 | 5.8275 | 5000 | 0.1120 | 0.8416 | 0.8362 | 0.8389 | 0.9827 | | 0.0046 | 6.4103 | 5500 | 0.1148 | 0.8447 | 0.8450 | 0.8449 | 0.9833 | | 0.004 | 6.9930 | 6000 | 0.1135 | 0.8323 | 0.8491 | 0.8406 | 0.9832 | | 0.0036 | 7.5758 | 6500 | 0.1127 | 0.8556 | 0.8377 | 0.8465 | 0.9835 | | 0.0031 | 8.1585 | 7000 | 0.1192 | 0.8365 | 0.8489 | 0.8427 | 0.9835 | | 0.0029 | 8.7413 | 7500 | 0.1280 | 0.8403 | 0.8540 | 0.8471 | 0.9834 | | 0.0035 | 9.3240 | 8000 | 0.1272 | 0.8445 | 0.8371 | 0.8408 | 0.9831 | | 0.0031 | 9.9068 | 8500 | 0.1132 | 0.8556 | 0.8465 | 0.8510 | 0.9842 | | 0.0021 | 10.4895 | 9000 | 0.1302 | 0.8383 | 0.8512 | 0.8447 | 0.9835 | | 0.0023 | 11.0723 | 9500 | 0.1264 | 0.8347 | 0.8472 | 0.8409 | 0.9830 | | 0.0024 | 11.6550 | 10000 | 0.1191 | 0.8446 | 0.8523 | 0.8484 | 0.9837 | | 0.0021 | 12.2378 | 10500 | 0.1301 | 0.8419 | 0.8469 | 0.8444 | 0.9834 | | 0.0027 | 12.8205 | 11000 | 0.1231 | 0.8437 | 0.8541 | 0.8489 | 0.9840 | | 0.002 | 13.4033 | 11500 | 0.1329 | 0.8345 | 0.8482 | 0.8413 | 0.9828 | | 0.0017 | 13.9860 | 12000 | 0.1320 | 0.8418 | 0.8575 | 0.8495 | 0.9837 | | 0.0016 | 14.5688 | 12500 | 0.1298 | 0.8462 | 0.8439 | 0.8450 | 0.9836 | | 0.0016 | 15.1515 | 13000 | 0.1368 | 0.8440 | 0.8274 | 0.8356 | 0.9831 | | 0.0019 | 15.7343 | 13500 | 0.1281 | 0.8491 | 0.8453 | 0.8472 | 0.9837 | | 0.001 | 16.3170 | 14000 | 0.1348 | 0.8469 | 0.8523 | 0.8496 | 0.9839 | | 0.0014 | 16.8998 | 14500 | 0.1345 | 0.8405 | 0.8515 | 0.8460 | 0.9834 | | 0.001 | 17.4825 | 15000 | 0.1449 | 0.8449 | 0.8357 | 0.8403 | 0.9833 | | 0.0011 | 18.0653 | 15500 | 0.1414 | 0.8478 | 0.8541 | 0.8509 | 0.9840 | | 0.0013 | 18.6480 | 16000 | 0.1414 | 0.8486 | 0.8448 | 0.8466 | 0.9837 | | 0.001 | 19.2308 | 16500 | 0.1417 | 0.8522 | 0.8549 | 0.8535 | 0.9839 | | 0.0011 | 19.8135 | 17000 | 0.1400 | 0.8430 | 0.8474 | 0.8452 | 0.9835 | | 0.001 | 20.3963 | 17500 | 0.1369 | 0.8503 | 0.8498 | 0.8501 | 0.9836 | | 0.0007 | 20.9790 | 18000 | 0.1349 | 0.8512 | 0.8551 | 0.8532 | 0.9843 | | 0.001 | 21.5618 | 18500 | 0.1345 | 0.8532 | 0.8495 | 0.8514 | 0.9843 | | 0.0009 | 22.1445 | 19000 | 0.1397 | 0.8585 | 0.8420 | 0.8502 | 0.9843 | | 0.0004 | 22.7273 | 19500 | 0.1394 | 0.8522 | 0.8575 | 0.8548 | 0.9846 | | 0.0006 | 23.3100 | 20000 | 0.1433 | 0.8470 | 0.8576 | 0.8522 | 0.9843 | | 0.0005 | 23.8928 | 20500 | 0.1447 | 0.8526 | 0.8512 | 0.8519 | 0.9841 | | 0.0004 | 24.4755 | 21000 | 0.1418 | 0.8492 | 0.8547 | 0.8519 | 0.9843 | | 0.0004 | 25.0583 | 21500 | 0.1444 | 0.8546 | 0.8556 | 0.8551 | 0.9845 | | 0.0003 | 25.6410 | 22000 | 0.1458 | 0.8527 | 0.8554 | 0.8541 | 0.9843 | | 0.0004 | 26.2238 | 22500 | 0.1448 | 0.8541 | 0.8502 | 0.8521 | 0.9843 | | 0.0003 | 26.8065 | 23000 | 0.1449 | 0.8474 | 0.8579 | 0.8526 | 0.9842 | | 0.0004 | 27.3893 | 23500 | 0.1448 | 0.8553 | 0.8579 | 0.8566 | 0.9846 | | 0.0004 | 27.9720 | 24000 | 0.1427 | 0.8589 | 0.8527 | 0.8558 | 0.9844 | | 0.0002 | 28.5548 | 24500 | 0.1439 | 0.8541 | 0.8582 | 0.8561 | 0.9846 | | 0.0003 | 29.1375 | 25000 | 0.1446 | 0.8564 | 0.8560 | 0.8562 | 0.9847 | | 0.0002 | 29.7203 | 25500 | 0.1451 | 0.8545 | 0.8580 | 0.8562 | 0.9846 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1