--- library_name: transformers license: mit base_model: FacebookAI/xlm-roberta-base tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: scenario-non-kd-scr-ner-full-xlmr_data-univner_full66 results: [] --- # scenario-non-kd-scr-ner-full-xlmr_data-univner_full66 This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3798 - Precision: 0.5821 - Recall: 0.5864 - F1: 0.5842 - Accuracy: 0.9606 ## 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: 66 - 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 | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.3415 | 0.2910 | 500 | 0.2817 | 0.4535 | 0.1387 | 0.2124 | 0.9301 | | 0.2629 | 0.5821 | 1000 | 0.2498 | 0.3527 | 0.1915 | 0.2482 | 0.9340 | | 0.2318 | 0.8731 | 1500 | 0.2322 | 0.3468 | 0.2285 | 0.2755 | 0.9366 | | 0.2056 | 1.1641 | 2000 | 0.2234 | 0.3522 | 0.2851 | 0.3151 | 0.9380 | | 0.1827 | 1.4552 | 2500 | 0.2226 | 0.3487 | 0.3443 | 0.3465 | 0.9395 | | 0.1777 | 1.7462 | 3000 | 0.2044 | 0.4135 | 0.3391 | 0.3726 | 0.9419 | | 0.1627 | 2.0373 | 3500 | 0.2053 | 0.3898 | 0.3799 | 0.3848 | 0.9423 | | 0.1372 | 2.3283 | 4000 | 0.2020 | 0.4118 | 0.3959 | 0.4037 | 0.9434 | | 0.1294 | 2.6193 | 4500 | 0.1890 | 0.4132 | 0.4460 | 0.4289 | 0.9467 | | 0.1224 | 2.9104 | 5000 | 0.1756 | 0.4334 | 0.4686 | 0.4503 | 0.9480 | | 0.0947 | 3.2014 | 5500 | 0.1864 | 0.4487 | 0.5070 | 0.4761 | 0.9491 | | 0.0861 | 3.4924 | 6000 | 0.1806 | 0.5010 | 0.4972 | 0.4991 | 0.9533 | | 0.0815 | 3.7835 | 6500 | 0.1839 | 0.5021 | 0.4905 | 0.4963 | 0.9533 | | 0.0746 | 4.0745 | 7000 | 0.1943 | 0.4900 | 0.5006 | 0.4953 | 0.9534 | | 0.0574 | 4.3655 | 7500 | 0.2050 | 0.5221 | 0.4881 | 0.5045 | 0.9544 | | 0.0585 | 4.6566 | 8000 | 0.1908 | 0.5093 | 0.5351 | 0.5219 | 0.9552 | | 0.0565 | 4.9476 | 8500 | 0.1902 | 0.5107 | 0.5334 | 0.5218 | 0.9552 | | 0.0425 | 5.2386 | 9000 | 0.2168 | 0.5241 | 0.5351 | 0.5296 | 0.9565 | | 0.0412 | 5.5297 | 9500 | 0.2073 | 0.5717 | 0.5116 | 0.5400 | 0.9568 | | 0.0392 | 5.8207 | 10000 | 0.2052 | 0.5331 | 0.5406 | 0.5368 | 0.9561 | | 0.0362 | 6.1118 | 10500 | 0.2221 | 0.4957 | 0.5700 | 0.5303 | 0.9548 | | 0.0291 | 6.4028 | 11000 | 0.2298 | 0.5156 | 0.5431 | 0.5290 | 0.9559 | | 0.0274 | 6.6938 | 11500 | 0.2378 | 0.5018 | 0.5409 | 0.5206 | 0.9548 | | 0.0296 | 6.9849 | 12000 | 0.2342 | 0.5433 | 0.5408 | 0.5420 | 0.9571 | | 0.0201 | 7.2759 | 12500 | 0.2525 | 0.5167 | 0.5777 | 0.5455 | 0.9573 | | 0.0211 | 7.5669 | 13000 | 0.2469 | 0.5491 | 0.5413 | 0.5452 | 0.9577 | | 0.0218 | 7.8580 | 13500 | 0.2429 | 0.5509 | 0.5454 | 0.5481 | 0.9570 | | 0.0178 | 8.1490 | 14000 | 0.2578 | 0.5129 | 0.5468 | 0.5293 | 0.9559 | | 0.0153 | 8.4400 | 14500 | 0.2565 | 0.5540 | 0.5607 | 0.5573 | 0.9584 | | 0.0157 | 8.7311 | 15000 | 0.2661 | 0.5652 | 0.5317 | 0.5479 | 0.9579 | | 0.0158 | 9.0221 | 15500 | 0.2706 | 0.5403 | 0.5604 | 0.5501 | 0.9579 | | 0.012 | 9.3132 | 16000 | 0.2912 | 0.5543 | 0.5359 | 0.5449 | 0.9580 | | 0.0123 | 9.6042 | 16500 | 0.2804 | 0.5234 | 0.5784 | 0.5496 | 0.9573 | | 0.0124 | 9.8952 | 17000 | 0.2640 | 0.5384 | 0.5659 | 0.5518 | 0.9576 | | 0.0106 | 10.1863 | 17500 | 0.2812 | 0.5626 | 0.5481 | 0.5552 | 0.9582 | | 0.0094 | 10.4773 | 18000 | 0.2928 | 0.5317 | 0.5869 | 0.5579 | 0.9574 | | 0.0094 | 10.7683 | 18500 | 0.2820 | 0.5695 | 0.5377 | 0.5532 | 0.9583 | | 0.0098 | 11.0594 | 19000 | 0.2896 | 0.5526 | 0.5574 | 0.5550 | 0.9581 | | 0.0072 | 11.3504 | 19500 | 0.2952 | 0.5509 | 0.5832 | 0.5666 | 0.9584 | | 0.0078 | 11.6414 | 20000 | 0.2940 | 0.5288 | 0.5957 | 0.5603 | 0.9574 | | 0.0078 | 11.9325 | 20500 | 0.2972 | 0.5439 | 0.5634 | 0.5535 | 0.9579 | | 0.0061 | 12.2235 | 21000 | 0.3019 | 0.5683 | 0.5861 | 0.5770 | 0.9596 | | 0.0062 | 12.5146 | 21500 | 0.3057 | 0.5477 | 0.5640 | 0.5557 | 0.9582 | | 0.0065 | 12.8056 | 22000 | 0.3010 | 0.5546 | 0.5703 | 0.5623 | 0.9581 | | 0.0058 | 13.0966 | 22500 | 0.3143 | 0.5460 | 0.5836 | 0.5642 | 0.9589 | | 0.0051 | 13.3877 | 23000 | 0.3061 | 0.5576 | 0.5776 | 0.5674 | 0.9591 | | 0.0056 | 13.6787 | 23500 | 0.3028 | 0.5428 | 0.5813 | 0.5614 | 0.9582 | | 0.0054 | 13.9697 | 24000 | 0.3043 | 0.5553 | 0.5726 | 0.5638 | 0.9581 | | 0.0037 | 14.2608 | 24500 | 0.3197 | 0.5485 | 0.5901 | 0.5685 | 0.9588 | | 0.0043 | 14.5518 | 25000 | 0.3163 | 0.5730 | 0.5585 | 0.5656 | 0.9586 | | 0.0047 | 14.8428 | 25500 | 0.3160 | 0.5476 | 0.5813 | 0.5640 | 0.9587 | | 0.0036 | 15.1339 | 26000 | 0.3385 | 0.6042 | 0.5382 | 0.5693 | 0.9594 | | 0.0036 | 15.4249 | 26500 | 0.3352 | 0.5462 | 0.5786 | 0.5619 | 0.9591 | | 0.0033 | 15.7159 | 27000 | 0.3312 | 0.5505 | 0.5758 | 0.5629 | 0.9587 | | 0.0036 | 16.0070 | 27500 | 0.3457 | 0.5735 | 0.5553 | 0.5642 | 0.9594 | | 0.0027 | 16.2980 | 28000 | 0.3351 | 0.5602 | 0.5703 | 0.5652 | 0.9589 | | 0.0031 | 16.5891 | 28500 | 0.3375 | 0.5714 | 0.5451 | 0.5579 | 0.9589 | | 0.0033 | 16.8801 | 29000 | 0.3349 | 0.5621 | 0.5814 | 0.5716 | 0.9590 | | 0.0024 | 17.1711 | 29500 | 0.3422 | 0.5545 | 0.5869 | 0.5703 | 0.9595 | | 0.0024 | 17.4622 | 30000 | 0.3313 | 0.5552 | 0.6018 | 0.5775 | 0.9588 | | 0.0025 | 17.7532 | 30500 | 0.3302 | 0.5683 | 0.5832 | 0.5757 | 0.9595 | | 0.0023 | 18.0442 | 31000 | 0.3387 | 0.5555 | 0.5845 | 0.5696 | 0.9591 | | 0.0022 | 18.3353 | 31500 | 0.3519 | 0.5757 | 0.5497 | 0.5624 | 0.9591 | | 0.0019 | 18.6263 | 32000 | 0.3471 | 0.5574 | 0.5888 | 0.5727 | 0.9592 | | 0.0022 | 18.9173 | 32500 | 0.3429 | 0.5632 | 0.5882 | 0.5754 | 0.9597 | | 0.0017 | 19.2084 | 33000 | 0.3576 | 0.5673 | 0.5765 | 0.5719 | 0.9599 | | 0.0019 | 19.4994 | 33500 | 0.3459 | 0.5637 | 0.5791 | 0.5713 | 0.9593 | | 0.0017 | 19.7905 | 34000 | 0.3516 | 0.5643 | 0.5686 | 0.5664 | 0.9593 | | 0.0015 | 20.0815 | 34500 | 0.3632 | 0.5790 | 0.5764 | 0.5777 | 0.9599 | | 0.0015 | 20.3725 | 35000 | 0.3528 | 0.5731 | 0.5791 | 0.5761 | 0.9598 | | 0.0015 | 20.6636 | 35500 | 0.3560 | 0.5582 | 0.5788 | 0.5684 | 0.9589 | | 0.0015 | 20.9546 | 36000 | 0.3525 | 0.5698 | 0.5770 | 0.5734 | 0.9593 | | 0.0012 | 21.2456 | 36500 | 0.3562 | 0.5723 | 0.5741 | 0.5732 | 0.9597 | | 0.0013 | 21.5367 | 37000 | 0.3584 | 0.5690 | 0.5679 | 0.5684 | 0.9595 | | 0.0013 | 21.8277 | 37500 | 0.3598 | 0.5547 | 0.6047 | 0.5786 | 0.9593 | | 0.0011 | 22.1187 | 38000 | 0.3639 | 0.5676 | 0.5814 | 0.5744 | 0.9598 | | 0.0008 | 22.4098 | 38500 | 0.3594 | 0.5576 | 0.5881 | 0.5724 | 0.9590 | | 0.001 | 22.7008 | 39000 | 0.3661 | 0.5696 | 0.5786 | 0.5740 | 0.9597 | | 0.001 | 22.9919 | 39500 | 0.3595 | 0.5621 | 0.5905 | 0.5760 | 0.9597 | | 0.0008 | 23.2829 | 40000 | 0.3634 | 0.5700 | 0.5813 | 0.5756 | 0.9603 | | 0.0008 | 23.5739 | 40500 | 0.3619 | 0.5790 | 0.5700 | 0.5745 | 0.9597 | | 0.001 | 23.8650 | 41000 | 0.3704 | 0.5839 | 0.5666 | 0.5751 | 0.9599 | | 0.001 | 24.1560 | 41500 | 0.3639 | 0.5679 | 0.5923 | 0.5798 | 0.9597 | | 0.0008 | 24.4470 | 42000 | 0.3688 | 0.5703 | 0.5773 | 0.5738 | 0.9594 | | 0.0007 | 24.7381 | 42500 | 0.3794 | 0.5712 | 0.5803 | 0.5757 | 0.9600 | | 0.0007 | 25.0291 | 43000 | 0.3754 | 0.5807 | 0.5662 | 0.5733 | 0.9597 | | 0.0006 | 25.3201 | 43500 | 0.3732 | 0.5809 | 0.5866 | 0.5837 | 0.9602 | | 0.0007 | 25.6112 | 44000 | 0.3795 | 0.5940 | 0.5550 | 0.5739 | 0.9598 | | 0.0008 | 25.9022 | 44500 | 0.3721 | 0.5729 | 0.5843 | 0.5786 | 0.9599 | | 0.0004 | 26.1932 | 45000 | 0.3773 | 0.5790 | 0.5734 | 0.5762 | 0.9601 | | 0.0005 | 26.4843 | 45500 | 0.3811 | 0.5788 | 0.5713 | 0.5750 | 0.9600 | | 0.0005 | 26.7753 | 46000 | 0.3787 | 0.5757 | 0.5901 | 0.5828 | 0.9603 | | 0.0005 | 27.0664 | 46500 | 0.3766 | 0.5740 | 0.5817 | 0.5779 | 0.9601 | | 0.0004 | 27.3574 | 47000 | 0.3786 | 0.5758 | 0.5800 | 0.5779 | 0.9602 | | 0.0004 | 27.6484 | 47500 | 0.3800 | 0.5755 | 0.5866 | 0.5810 | 0.9603 | | 0.0004 | 27.9395 | 48000 | 0.3824 | 0.5843 | 0.5752 | 0.5798 | 0.9603 | | 0.0004 | 28.2305 | 48500 | 0.3836 | 0.5829 | 0.5739 | 0.5784 | 0.9603 | | 0.0002 | 28.5215 | 49000 | 0.3813 | 0.5894 | 0.5804 | 0.5849 | 0.9607 | | 0.0004 | 28.8126 | 49500 | 0.3817 | 0.5824 | 0.5852 | 0.5838 | 0.9604 | | 0.0004 | 29.1036 | 50000 | 0.3816 | 0.5814 | 0.5816 | 0.5815 | 0.9604 | | 0.0003 | 29.3946 | 50500 | 0.3800 | 0.5804 | 0.5865 | 0.5834 | 0.9605 | | 0.0003 | 29.6857 | 51000 | 0.3794 | 0.5831 | 0.5864 | 0.5847 | 0.9606 | | 0.0002 | 29.9767 | 51500 | 0.3798 | 0.5821 | 0.5864 | 0.5842 | 0.9606 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1