--- 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-half-xlmr_data-univner_full44 results: [] --- # scenario-non-kd-scr-ner-half-xlmr_data-univner_full44 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: 0.3603 - Precision: 0.5290 - Recall: 0.5350 - F1: 0.5320 - Accuracy: 0.9557 ## 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 | |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.3576 | 0.2910 | 500 | 0.2944 | 0.4546 | 0.0903 | 0.1507 | 0.9285 | | 0.2752 | 0.5821 | 1000 | 0.2516 | 0.2788 | 0.1799 | 0.2187 | 0.9317 | | 0.2421 | 0.8731 | 1500 | 0.2433 | 0.3406 | 0.2018 | 0.2535 | 0.9349 | | 0.2184 | 1.1641 | 2000 | 0.2271 | 0.3200 | 0.2548 | 0.2837 | 0.9368 | | 0.2079 | 1.4552 | 2500 | 0.2195 | 0.3445 | 0.2835 | 0.3110 | 0.9378 | | 0.1943 | 1.7462 | 3000 | 0.2126 | 0.3641 | 0.2946 | 0.3257 | 0.9400 | | 0.183 | 2.0373 | 3500 | 0.2067 | 0.3467 | 0.3354 | 0.3410 | 0.9394 | | 0.1609 | 2.3283 | 4000 | 0.2107 | 0.3788 | 0.3251 | 0.3499 | 0.9414 | | 0.1644 | 2.6193 | 4500 | 0.2114 | 0.3478 | 0.3389 | 0.3433 | 0.9395 | | 0.1586 | 2.9104 | 5000 | 0.2053 | 0.3758 | 0.3559 | 0.3656 | 0.9414 | | 0.147 | 3.2014 | 5500 | 0.2029 | 0.4010 | 0.3751 | 0.3877 | 0.9430 | | 0.1423 | 3.4924 | 6000 | 0.2043 | 0.4021 | 0.3747 | 0.3879 | 0.9437 | | 0.1363 | 3.7835 | 6500 | 0.2080 | 0.4074 | 0.3496 | 0.3763 | 0.9436 | | 0.133 | 4.0745 | 7000 | 0.2049 | 0.4037 | 0.3919 | 0.3977 | 0.9439 | | 0.1227 | 4.3655 | 7500 | 0.2048 | 0.4163 | 0.3976 | 0.4068 | 0.9441 | | 0.1214 | 4.6566 | 8000 | 0.2034 | 0.4082 | 0.3984 | 0.4032 | 0.9439 | | 0.1198 | 4.9476 | 8500 | 0.1960 | 0.4205 | 0.4249 | 0.4227 | 0.9452 | | 0.1058 | 5.2386 | 9000 | 0.2107 | 0.4228 | 0.4048 | 0.4137 | 0.9459 | | 0.103 | 5.5297 | 9500 | 0.1999 | 0.4451 | 0.4268 | 0.4358 | 0.9461 | | 0.1017 | 5.8207 | 10000 | 0.2005 | 0.4308 | 0.4313 | 0.4310 | 0.9468 | | 0.0956 | 6.1118 | 10500 | 0.2008 | 0.4388 | 0.4535 | 0.4460 | 0.9473 | | 0.0848 | 6.4028 | 11000 | 0.2039 | 0.4301 | 0.4711 | 0.4496 | 0.9467 | | 0.0834 | 6.6938 | 11500 | 0.2040 | 0.4535 | 0.4669 | 0.4601 | 0.9490 | | 0.08 | 6.9849 | 12000 | 0.2021 | 0.4517 | 0.4753 | 0.4632 | 0.9495 | | 0.0714 | 7.2759 | 12500 | 0.2095 | 0.4691 | 0.4604 | 0.4647 | 0.9503 | | 0.0691 | 7.5669 | 13000 | 0.2165 | 0.4749 | 0.4425 | 0.4581 | 0.9509 | | 0.0676 | 7.8580 | 13500 | 0.2174 | 0.4795 | 0.4513 | 0.4650 | 0.9512 | | 0.0608 | 8.1490 | 14000 | 0.2157 | 0.4833 | 0.4812 | 0.4822 | 0.9516 | | 0.0574 | 8.4400 | 14500 | 0.2145 | 0.4707 | 0.4937 | 0.4819 | 0.9512 | | 0.06 | 8.7311 | 15000 | 0.2190 | 0.4862 | 0.4969 | 0.4915 | 0.9514 | | 0.0555 | 9.0221 | 15500 | 0.2291 | 0.4840 | 0.4679 | 0.4758 | 0.9519 | | 0.0491 | 9.3132 | 16000 | 0.2285 | 0.4845 | 0.4888 | 0.4866 | 0.9519 | | 0.0481 | 9.6042 | 16500 | 0.2325 | 0.4934 | 0.4799 | 0.4865 | 0.9523 | | 0.0476 | 9.8952 | 17000 | 0.2297 | 0.4678 | 0.5099 | 0.4879 | 0.9516 | | 0.042 | 10.1863 | 17500 | 0.2336 | 0.4962 | 0.5012 | 0.4987 | 0.9524 | | 0.0399 | 10.4773 | 18000 | 0.2368 | 0.5054 | 0.5024 | 0.5039 | 0.9530 | | 0.0432 | 10.7683 | 18500 | 0.2408 | 0.5064 | 0.4885 | 0.4973 | 0.9529 | | 0.0371 | 11.0594 | 19000 | 0.2471 | 0.4870 | 0.5122 | 0.4993 | 0.9530 | | 0.0345 | 11.3504 | 19500 | 0.2485 | 0.4988 | 0.5077 | 0.5032 | 0.9532 | | 0.0345 | 11.6414 | 20000 | 0.2533 | 0.5035 | 0.4918 | 0.4976 | 0.9533 | | 0.0342 | 11.9325 | 20500 | 0.2524 | 0.4906 | 0.5115 | 0.5008 | 0.9528 | | 0.0301 | 12.2235 | 21000 | 0.2562 | 0.4987 | 0.5014 | 0.5000 | 0.9531 | | 0.0293 | 12.5146 | 21500 | 0.2572 | 0.5046 | 0.5113 | 0.5080 | 0.9532 | | 0.0282 | 12.8056 | 22000 | 0.2633 | 0.5034 | 0.4972 | 0.5003 | 0.9537 | | 0.0283 | 13.0966 | 22500 | 0.2680 | 0.5014 | 0.5119 | 0.5066 | 0.9532 | | 0.0257 | 13.3877 | 23000 | 0.2685 | 0.4985 | 0.5185 | 0.5083 | 0.9537 | | 0.0245 | 13.6787 | 23500 | 0.2735 | 0.5104 | 0.5165 | 0.5134 | 0.9541 | | 0.0243 | 13.9697 | 24000 | 0.2811 | 0.4987 | 0.5157 | 0.5070 | 0.9534 | | 0.0215 | 14.2608 | 24500 | 0.2769 | 0.5021 | 0.5299 | 0.5156 | 0.9538 | | 0.0207 | 14.5518 | 25000 | 0.2748 | 0.4976 | 0.5425 | 0.5191 | 0.9532 | | 0.0224 | 14.8428 | 25500 | 0.2835 | 0.5190 | 0.5151 | 0.5170 | 0.9545 | | 0.0204 | 15.1339 | 26000 | 0.2845 | 0.5022 | 0.5195 | 0.5107 | 0.9541 | | 0.0186 | 15.4249 | 26500 | 0.2922 | 0.5177 | 0.5057 | 0.5116 | 0.9541 | | 0.0185 | 15.7159 | 27000 | 0.2888 | 0.5236 | 0.5210 | 0.5223 | 0.9546 | | 0.018 | 16.0070 | 27500 | 0.2892 | 0.5029 | 0.5354 | 0.5187 | 0.9540 | | 0.0152 | 16.2980 | 28000 | 0.2992 | 0.5166 | 0.5219 | 0.5192 | 0.9547 | | 0.0159 | 16.5891 | 28500 | 0.3011 | 0.5127 | 0.5232 | 0.5179 | 0.9545 | | 0.0159 | 16.8801 | 29000 | 0.3051 | 0.5135 | 0.5172 | 0.5153 | 0.9545 | | 0.015 | 17.1711 | 29500 | 0.3000 | 0.5170 | 0.5233 | 0.5201 | 0.9544 | | 0.0144 | 17.4622 | 30000 | 0.3049 | 0.5045 | 0.5180 | 0.5111 | 0.9543 | | 0.0144 | 17.7532 | 30500 | 0.3040 | 0.5066 | 0.5470 | 0.5260 | 0.9545 | | 0.0131 | 18.0442 | 31000 | 0.3145 | 0.5144 | 0.5214 | 0.5179 | 0.9547 | | 0.0119 | 18.3353 | 31500 | 0.3129 | 0.5150 | 0.5351 | 0.5249 | 0.9546 | | 0.013 | 18.6263 | 32000 | 0.3156 | 0.5113 | 0.5308 | 0.5208 | 0.9544 | | 0.0121 | 18.9173 | 32500 | 0.3242 | 0.5334 | 0.5129 | 0.5229 | 0.9551 | | 0.0115 | 19.2084 | 33000 | 0.3194 | 0.5244 | 0.5327 | 0.5285 | 0.9554 | | 0.0118 | 19.4994 | 33500 | 0.3195 | 0.5137 | 0.5396 | 0.5263 | 0.9546 | | 0.0107 | 19.7905 | 34000 | 0.3209 | 0.5107 | 0.5416 | 0.5257 | 0.9544 | | 0.0095 | 20.0815 | 34500 | 0.3266 | 0.5235 | 0.5361 | 0.5298 | 0.9550 | | 0.01 | 20.3725 | 35000 | 0.3252 | 0.5167 | 0.5370 | 0.5267 | 0.9549 | | 0.01 | 20.6636 | 35500 | 0.3272 | 0.5177 | 0.5354 | 0.5264 | 0.9549 | | 0.0095 | 20.9546 | 36000 | 0.3290 | 0.5171 | 0.5328 | 0.5248 | 0.9550 | | 0.0089 | 21.2456 | 36500 | 0.3316 | 0.5255 | 0.5348 | 0.5301 | 0.9556 | | 0.0085 | 21.5367 | 37000 | 0.3361 | 0.5258 | 0.5333 | 0.5295 | 0.9553 | | 0.0089 | 21.8277 | 37500 | 0.3336 | 0.5320 | 0.5227 | 0.5273 | 0.9553 | | 0.009 | 22.1187 | 38000 | 0.3368 | 0.5287 | 0.5263 | 0.5275 | 0.9555 | | 0.0069 | 22.4098 | 38500 | 0.3374 | 0.5194 | 0.5325 | 0.5259 | 0.9553 | | 0.0082 | 22.7008 | 39000 | 0.3367 | 0.5161 | 0.5376 | 0.5266 | 0.9552 | | 0.0079 | 22.9919 | 39500 | 0.3362 | 0.5170 | 0.5385 | 0.5275 | 0.9549 | | 0.0075 | 23.2829 | 40000 | 0.3408 | 0.5204 | 0.5309 | 0.5256 | 0.9552 | | 0.0062 | 23.5739 | 40500 | 0.3469 | 0.5194 | 0.5284 | 0.5239 | 0.9551 | | 0.0074 | 23.8650 | 41000 | 0.3394 | 0.5206 | 0.5409 | 0.5306 | 0.9553 | | 0.0065 | 24.1560 | 41500 | 0.3424 | 0.5163 | 0.5429 | 0.5293 | 0.9553 | | 0.0061 | 24.4470 | 42000 | 0.3466 | 0.5263 | 0.5330 | 0.5296 | 0.9550 | | 0.0065 | 24.7381 | 42500 | 0.3490 | 0.5297 | 0.5318 | 0.5308 | 0.9556 | | 0.0065 | 25.0291 | 43000 | 0.3523 | 0.5241 | 0.5344 | 0.5292 | 0.9553 | | 0.0056 | 25.3201 | 43500 | 0.3485 | 0.5287 | 0.5348 | 0.5317 | 0.9551 | | 0.0061 | 25.6112 | 44000 | 0.3515 | 0.5187 | 0.5490 | 0.5334 | 0.9552 | | 0.0059 | 25.9022 | 44500 | 0.3559 | 0.5254 | 0.5292 | 0.5273 | 0.9554 | | 0.0052 | 26.1932 | 45000 | 0.3521 | 0.5292 | 0.5340 | 0.5316 | 0.9555 | | 0.0051 | 26.4843 | 45500 | 0.3545 | 0.5222 | 0.5403 | 0.5311 | 0.9556 | | 0.0057 | 26.7753 | 46000 | 0.3551 | 0.5249 | 0.5374 | 0.5311 | 0.9554 | | 0.0055 | 27.0664 | 46500 | 0.3534 | 0.5198 | 0.5491 | 0.5341 | 0.9554 | | 0.0047 | 27.3574 | 47000 | 0.3572 | 0.5245 | 0.5318 | 0.5281 | 0.9556 | | 0.0054 | 27.6484 | 47500 | 0.3566 | 0.5290 | 0.5374 | 0.5332 | 0.9557 | | 0.0045 | 27.9395 | 48000 | 0.3560 | 0.5269 | 0.5405 | 0.5336 | 0.9554 | | 0.0053 | 28.2305 | 48500 | 0.3587 | 0.5244 | 0.5373 | 0.5308 | 0.9556 | | 0.0048 | 28.5215 | 49000 | 0.3605 | 0.5268 | 0.5353 | 0.5310 | 0.9555 | | 0.0043 | 28.8126 | 49500 | 0.3569 | 0.5243 | 0.5385 | 0.5313 | 0.9553 | | 0.0049 | 29.1036 | 50000 | 0.3585 | 0.5251 | 0.5370 | 0.5310 | 0.9555 | | 0.0045 | 29.3946 | 50500 | 0.3591 | 0.5277 | 0.5359 | 0.5317 | 0.9555 | | 0.0046 | 29.6857 | 51000 | 0.3598 | 0.5260 | 0.5347 | 0.5303 | 0.9555 | | 0.0045 | 29.9767 | 51500 | 0.3603 | 0.5290 | 0.5350 | 0.5320 | 0.9557 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1