--- base_model: FacebookAI/xlm-roberta-base library_name: transformers license: mit metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer model-index: - name: scenario-non-kd-scr-ner-full-xlmr_data-univner_full55 results: [] --- # scenario-non-kd-scr-ner-full-xlmr_data-univner_full55 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: 0.3862 - Precision: 0.5807 - Recall: 0.5843 - F1: 0.5825 - Accuracy: 0.9598 ## 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 | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.3373 | 0.2910 | 500 | 0.2831 | 0.3902 | 0.1327 | 0.1981 | 0.9297 | | 0.2602 | 0.5821 | 1000 | 0.2620 | 0.4136 | 0.1627 | 0.2336 | 0.9337 | | 0.2313 | 0.8731 | 1500 | 0.2253 | 0.3380 | 0.2978 | 0.3166 | 0.9366 | | 0.2057 | 1.1641 | 2000 | 0.2288 | 0.3553 | 0.2601 | 0.3003 | 0.9388 | | 0.185 | 1.4552 | 2500 | 0.2033 | 0.3717 | 0.3418 | 0.3561 | 0.9405 | | 0.177 | 1.7462 | 3000 | 0.2021 | 0.3938 | 0.3770 | 0.3852 | 0.9421 | | 0.1625 | 2.0373 | 3500 | 0.2133 | 0.4051 | 0.3373 | 0.3681 | 0.9433 | | 0.1456 | 2.3283 | 4000 | 0.1992 | 0.4114 | 0.3841 | 0.3973 | 0.9441 | | 0.1334 | 2.6193 | 4500 | 0.1943 | 0.4074 | 0.4027 | 0.4051 | 0.9434 | | 0.1254 | 2.9104 | 5000 | 0.1859 | 0.4299 | 0.4351 | 0.4325 | 0.9482 | | 0.1063 | 3.2014 | 5500 | 0.1881 | 0.4969 | 0.4431 | 0.4685 | 0.9498 | | 0.0934 | 3.4924 | 6000 | 0.1894 | 0.4551 | 0.4862 | 0.4701 | 0.9492 | | 0.0911 | 3.7835 | 6500 | 0.1792 | 0.4762 | 0.4985 | 0.4871 | 0.9506 | | 0.0793 | 4.0745 | 7000 | 0.2058 | 0.5031 | 0.4683 | 0.4851 | 0.9528 | | 0.0642 | 4.3655 | 7500 | 0.2084 | 0.5126 | 0.4744 | 0.4928 | 0.9535 | | 0.0642 | 4.6566 | 8000 | 0.1847 | 0.5117 | 0.5045 | 0.5081 | 0.9536 | | 0.0598 | 4.9476 | 8500 | 0.1801 | 0.5147 | 0.5565 | 0.5348 | 0.9547 | | 0.0473 | 5.2386 | 9000 | 0.2131 | 0.5039 | 0.5474 | 0.5247 | 0.9547 | | 0.042 | 5.5297 | 9500 | 0.2062 | 0.5186 | 0.5361 | 0.5272 | 0.9560 | | 0.0429 | 5.8207 | 10000 | 0.2226 | 0.5290 | 0.5335 | 0.5312 | 0.9564 | | 0.0407 | 6.1118 | 10500 | 0.2236 | 0.5211 | 0.5429 | 0.5318 | 0.9553 | | 0.0326 | 6.4028 | 11000 | 0.2162 | 0.5193 | 0.5696 | 0.5433 | 0.9559 | | 0.0317 | 6.6938 | 11500 | 0.2267 | 0.4859 | 0.5773 | 0.5277 | 0.9538 | | 0.0311 | 6.9849 | 12000 | 0.2260 | 0.5119 | 0.5483 | 0.5295 | 0.9565 | | 0.0225 | 7.2759 | 12500 | 0.2352 | 0.4992 | 0.5851 | 0.5387 | 0.9553 | | 0.0236 | 7.5669 | 13000 | 0.2443 | 0.5564 | 0.5516 | 0.5540 | 0.9579 | | 0.0229 | 7.8580 | 13500 | 0.2339 | 0.5063 | 0.5666 | 0.5347 | 0.9554 | | 0.02 | 8.1490 | 14000 | 0.2553 | 0.5432 | 0.5673 | 0.5550 | 0.9581 | | 0.0177 | 8.4400 | 14500 | 0.2617 | 0.5457 | 0.5555 | 0.5506 | 0.9570 | | 0.0175 | 8.7311 | 15000 | 0.2634 | 0.5615 | 0.5569 | 0.5592 | 0.9584 | | 0.016 | 9.0221 | 15500 | 0.2674 | 0.5336 | 0.5669 | 0.5497 | 0.9572 | | 0.0137 | 9.3132 | 16000 | 0.2717 | 0.5077 | 0.5599 | 0.5326 | 0.9553 | | 0.0133 | 9.6042 | 16500 | 0.2714 | 0.5058 | 0.6154 | 0.5552 | 0.9557 | | 0.0137 | 9.8952 | 17000 | 0.2750 | 0.5386 | 0.5791 | 0.5582 | 0.9580 | | 0.0116 | 10.1863 | 17500 | 0.2720 | 0.5377 | 0.5755 | 0.5560 | 0.9580 | | 0.0104 | 10.4773 | 18000 | 0.2801 | 0.5321 | 0.5842 | 0.5569 | 0.9572 | | 0.0105 | 10.7683 | 18500 | 0.2857 | 0.5421 | 0.5747 | 0.5579 | 0.9575 | | 0.0118 | 11.0594 | 19000 | 0.2921 | 0.5556 | 0.5304 | 0.5427 | 0.9578 | | 0.0071 | 11.3504 | 19500 | 0.2876 | 0.5719 | 0.5536 | 0.5626 | 0.9582 | | 0.0081 | 11.6414 | 20000 | 0.2966 | 0.5636 | 0.5533 | 0.5584 | 0.9585 | | 0.0084 | 11.9325 | 20500 | 0.2968 | 0.5445 | 0.5517 | 0.5481 | 0.9576 | | 0.0069 | 12.2235 | 21000 | 0.3180 | 0.5551 | 0.5595 | 0.5573 | 0.9585 | | 0.0064 | 12.5146 | 21500 | 0.3099 | 0.5369 | 0.5800 | 0.5576 | 0.9581 | | 0.0073 | 12.8056 | 22000 | 0.3092 | 0.5694 | 0.5537 | 0.5615 | 0.9589 | | 0.0064 | 13.0966 | 22500 | 0.3255 | 0.5518 | 0.5490 | 0.5504 | 0.9583 | | 0.0056 | 13.3877 | 23000 | 0.3044 | 0.5564 | 0.5696 | 0.5630 | 0.9583 | | 0.0052 | 13.6787 | 23500 | 0.3074 | 0.5504 | 0.5729 | 0.5614 | 0.9581 | | 0.0053 | 13.9697 | 24000 | 0.3103 | 0.5709 | 0.5644 | 0.5677 | 0.9584 | | 0.0049 | 14.2608 | 24500 | 0.3124 | 0.5621 | 0.5851 | 0.5733 | 0.9589 | | 0.0048 | 14.5518 | 25000 | 0.3123 | 0.5741 | 0.5711 | 0.5726 | 0.9592 | | 0.0044 | 14.8428 | 25500 | 0.3238 | 0.5392 | 0.5685 | 0.5534 | 0.9581 | | 0.0042 | 15.1339 | 26000 | 0.3214 | 0.5449 | 0.5801 | 0.5620 | 0.9582 | | 0.0033 | 15.4249 | 26500 | 0.3239 | 0.5335 | 0.5845 | 0.5578 | 0.9576 | | 0.0039 | 15.7159 | 27000 | 0.3313 | 0.5606 | 0.5617 | 0.5612 | 0.9584 | | 0.0038 | 16.0070 | 27500 | 0.3274 | 0.5657 | 0.5556 | 0.5606 | 0.9585 | | 0.0028 | 16.2980 | 28000 | 0.3344 | 0.5490 | 0.5838 | 0.5658 | 0.9587 | | 0.0033 | 16.5891 | 28500 | 0.3311 | 0.5716 | 0.5693 | 0.5704 | 0.9591 | | 0.003 | 16.8801 | 29000 | 0.3299 | 0.5534 | 0.5836 | 0.5681 | 0.9582 | | 0.003 | 17.1711 | 29500 | 0.3449 | 0.5593 | 0.5636 | 0.5614 | 0.9587 | | 0.0026 | 17.4622 | 30000 | 0.3365 | 0.5607 | 0.5861 | 0.5731 | 0.9589 | | 0.0025 | 17.7532 | 30500 | 0.3399 | 0.5717 | 0.5793 | 0.5755 | 0.9592 | | 0.0027 | 18.0442 | 31000 | 0.3357 | 0.5498 | 0.5861 | 0.5674 | 0.9583 | | 0.0021 | 18.3353 | 31500 | 0.3448 | 0.5554 | 0.5809 | 0.5678 | 0.9586 | | 0.0023 | 18.6263 | 32000 | 0.3544 | 0.5393 | 0.5718 | 0.5551 | 0.9581 | | 0.002 | 18.9173 | 32500 | 0.3465 | 0.5700 | 0.5597 | 0.5648 | 0.9592 | | 0.002 | 19.2084 | 33000 | 0.3295 | 0.5610 | 0.5954 | 0.5777 | 0.9591 | | 0.0018 | 19.4994 | 33500 | 0.3415 | 0.5357 | 0.5937 | 0.5632 | 0.9573 | | 0.0018 | 19.7905 | 34000 | 0.3609 | 0.5609 | 0.5513 | 0.5561 | 0.9586 | | 0.0018 | 20.0815 | 34500 | 0.3604 | 0.5748 | 0.5654 | 0.5701 | 0.9593 | | 0.0016 | 20.3725 | 35000 | 0.3507 | 0.5721 | 0.5839 | 0.5779 | 0.9593 | | 0.0017 | 20.6636 | 35500 | 0.3457 | 0.5628 | 0.5952 | 0.5785 | 0.9589 | | 0.0015 | 20.9546 | 36000 | 0.3447 | 0.5632 | 0.5921 | 0.5773 | 0.9593 | | 0.0013 | 21.2456 | 36500 | 0.3491 | 0.5606 | 0.5940 | 0.5768 | 0.9589 | | 0.0013 | 21.5367 | 37000 | 0.3557 | 0.5597 | 0.5836 | 0.5714 | 0.9590 | | 0.0011 | 21.8277 | 37500 | 0.3603 | 0.5698 | 0.5810 | 0.5753 | 0.9595 | | 0.0012 | 22.1187 | 38000 | 0.3604 | 0.5721 | 0.5813 | 0.5766 | 0.9597 | | 0.001 | 22.4098 | 38500 | 0.3628 | 0.5591 | 0.5852 | 0.5718 | 0.9592 | | 0.0012 | 22.7008 | 39000 | 0.3599 | 0.5721 | 0.5825 | 0.5772 | 0.9596 | | 0.001 | 22.9919 | 39500 | 0.3596 | 0.5804 | 0.5884 | 0.5844 | 0.9601 | | 0.0008 | 23.2829 | 40000 | 0.3640 | 0.5844 | 0.5830 | 0.5837 | 0.9601 | | 0.0009 | 23.5739 | 40500 | 0.3747 | 0.5763 | 0.5739 | 0.5751 | 0.9596 | | 0.0008 | 23.8650 | 41000 | 0.3788 | 0.5967 | 0.5666 | 0.5813 | 0.9599 | | 0.0009 | 24.1560 | 41500 | 0.3742 | 0.5613 | 0.5908 | 0.5757 | 0.9592 | | 0.0008 | 24.4470 | 42000 | 0.3764 | 0.5744 | 0.5763 | 0.5753 | 0.9595 | | 0.001 | 24.7381 | 42500 | 0.3759 | 0.5891 | 0.5732 | 0.5811 | 0.9599 | | 0.0006 | 25.0291 | 43000 | 0.3713 | 0.5740 | 0.5940 | 0.5838 | 0.9597 | | 0.0008 | 25.3201 | 43500 | 0.3679 | 0.5800 | 0.5917 | 0.5858 | 0.9600 | | 0.0006 | 25.6112 | 44000 | 0.3791 | 0.5844 | 0.5768 | 0.5806 | 0.9600 | | 0.0006 | 25.9022 | 44500 | 0.3770 | 0.5732 | 0.5763 | 0.5747 | 0.9594 | | 0.0005 | 26.1932 | 45000 | 0.3751 | 0.5870 | 0.5868 | 0.5869 | 0.9602 | | 0.0004 | 26.4843 | 45500 | 0.3879 | 0.5863 | 0.5631 | 0.5745 | 0.9599 | | 0.0005 | 26.7753 | 46000 | 0.3818 | 0.5746 | 0.5832 | 0.5788 | 0.9596 | | 0.0004 | 27.0664 | 46500 | 0.3815 | 0.5727 | 0.5781 | 0.5754 | 0.9594 | | 0.0004 | 27.3574 | 47000 | 0.3763 | 0.5794 | 0.5894 | 0.5843 | 0.9600 | | 0.0005 | 27.6484 | 47500 | 0.3842 | 0.5691 | 0.5773 | 0.5732 | 0.9593 | | 0.0005 | 27.9395 | 48000 | 0.3867 | 0.5836 | 0.5778 | 0.5807 | 0.9598 | | 0.0004 | 28.2305 | 48500 | 0.3832 | 0.5735 | 0.5869 | 0.5801 | 0.9596 | | 0.0003 | 28.5215 | 49000 | 0.3834 | 0.5797 | 0.5858 | 0.5827 | 0.9598 | | 0.0004 | 28.8126 | 49500 | 0.3851 | 0.5807 | 0.5855 | 0.5831 | 0.9599 | | 0.0003 | 29.1036 | 50000 | 0.3850 | 0.5780 | 0.5845 | 0.5812 | 0.9597 | | 0.0003 | 29.3946 | 50500 | 0.3838 | 0.5801 | 0.5859 | 0.5830 | 0.9598 | | 0.0002 | 29.6857 | 51000 | 0.3874 | 0.5860 | 0.5793 | 0.5826 | 0.9600 | | 0.0002 | 29.9767 | 51500 | 0.3862 | 0.5807 | 0.5843 | 0.5825 | 0.9598 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1