--- license: mit base_model: microsoft/Multilingual-MiniLM-L12-H384 tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: ner-coin results: [] --- # ner-coin This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0820 - Precision: 0.9583 - Recall: 0.9664 - F1: 0.9623 - Accuracy: 0.9953 ## 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: 5e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 4 | 0.7480 | 0.0 | 0.0 | 0.0 | 0.8800 | | No log | 2.0 | 8 | 0.5628 | 0.0 | 0.0 | 0.0 | 0.8800 | | No log | 3.0 | 12 | 0.4862 | 0.0 | 0.0 | 0.0 | 0.8800 | | No log | 4.0 | 16 | 0.4488 | 0.0 | 0.0 | 0.0 | 0.8800 | | No log | 5.0 | 20 | 0.4199 | 1.0 | 0.2017 | 0.3357 | 0.9025 | | No log | 6.0 | 24 | 0.3671 | 1.0 | 0.3866 | 0.5576 | 0.9231 | | No log | 7.0 | 28 | 0.3227 | 0.9 | 0.7563 | 0.8219 | 0.9569 | | No log | 8.0 | 32 | 0.3000 | 0.8333 | 0.8403 | 0.8368 | 0.9625 | | No log | 9.0 | 36 | 0.2802 | 0.8919 | 0.8319 | 0.8609 | 0.9691 | | No log | 10.0 | 40 | 0.2654 | 0.8909 | 0.8235 | 0.8559 | 0.9700 | | No log | 11.0 | 44 | 0.2565 | 0.8443 | 0.8655 | 0.8548 | 0.9691 | | No log | 12.0 | 48 | 0.2418 | 0.8957 | 0.8655 | 0.8803 | 0.9756 | | No log | 13.0 | 52 | 0.2283 | 0.8983 | 0.8908 | 0.8945 | 0.9794 | | No log | 14.0 | 56 | 0.2149 | 0.888 | 0.9328 | 0.9098 | 0.9841 | | No log | 15.0 | 60 | 0.2216 | 0.9115 | 0.8655 | 0.8879 | 0.9775 | | No log | 16.0 | 64 | 0.2106 | 0.9052 | 0.8824 | 0.8936 | 0.9794 | | No log | 17.0 | 68 | 0.1997 | 0.8828 | 0.9496 | 0.9150 | 0.9850 | | No log | 18.0 | 72 | 0.1926 | 0.8828 | 0.9496 | 0.9150 | 0.9850 | | No log | 19.0 | 76 | 0.1840 | 0.8846 | 0.9664 | 0.9237 | 0.9878 | | No log | 20.0 | 80 | 0.1801 | 0.8788 | 0.9748 | 0.9243 | 0.9878 | | No log | 21.0 | 84 | 0.1737 | 0.8976 | 0.9580 | 0.9268 | 0.9888 | | No log | 22.0 | 88 | 0.1778 | 0.9008 | 0.9160 | 0.9083 | 0.9850 | | No log | 23.0 | 92 | 0.1651 | 0.8915 | 0.9664 | 0.9274 | 0.9888 | | No log | 24.0 | 96 | 0.1672 | 0.8788 | 0.9748 | 0.9243 | 0.9878 | | No log | 25.0 | 100 | 0.1614 | 0.8788 | 0.9748 | 0.9243 | 0.9878 | | No log | 26.0 | 104 | 0.1537 | 0.8923 | 0.9748 | 0.9317 | 0.9897 | | No log | 27.0 | 108 | 0.1489 | 0.8923 | 0.9748 | 0.9317 | 0.9897 | | No log | 28.0 | 112 | 0.1446 | 0.8992 | 0.9748 | 0.9355 | 0.9906 | | No log | 29.0 | 116 | 0.1417 | 0.8992 | 0.9748 | 0.9355 | 0.9906 | | No log | 30.0 | 120 | 0.1425 | 0.912 | 0.9580 | 0.9344 | 0.9906 | | No log | 31.0 | 124 | 0.1369 | 0.9915 | 0.9832 | 0.9873 | 0.9972 | | No log | 32.0 | 128 | 0.1347 | 0.9675 | 1.0 | 0.9835 | 0.9963 | | No log | 33.0 | 132 | 0.1323 | 0.9754 | 1.0 | 0.9876 | 0.9972 | | No log | 34.0 | 136 | 0.1308 | 0.9754 | 1.0 | 0.9876 | 0.9972 | | No log | 35.0 | 140 | 0.1308 | 0.9669 | 0.9832 | 0.975 | 0.9953 | | No log | 36.0 | 144 | 0.1278 | 0.9669 | 0.9832 | 0.975 | 0.9953 | | No log | 37.0 | 148 | 0.1265 | 0.9583 | 0.9664 | 0.9623 | 0.9944 | | No log | 38.0 | 152 | 0.1291 | 0.9569 | 0.9328 | 0.9447 | 0.9906 | | No log | 39.0 | 156 | 0.1281 | 0.9569 | 0.9328 | 0.9447 | 0.9906 | | No log | 40.0 | 160 | 0.1263 | 0.9569 | 0.9328 | 0.9447 | 0.9906 | | No log | 41.0 | 164 | 0.1222 | 0.9576 | 0.9496 | 0.9536 | 0.9925 | | No log | 42.0 | 168 | 0.1167 | 0.9667 | 0.9748 | 0.9707 | 0.9953 | | No log | 43.0 | 172 | 0.1165 | 0.9664 | 0.9664 | 0.9664 | 0.9944 | | No log | 44.0 | 176 | 0.1195 | 0.9569 | 0.9328 | 0.9447 | 0.9906 | | No log | 45.0 | 180 | 0.1186 | 0.9737 | 0.9328 | 0.9528 | 0.9925 | | No log | 46.0 | 184 | 0.1166 | 0.9569 | 0.9328 | 0.9447 | 0.9906 | | No log | 47.0 | 188 | 0.1123 | 0.95 | 0.9580 | 0.9540 | 0.9925 | | No log | 48.0 | 192 | 0.1100 | 0.95 | 0.9580 | 0.9540 | 0.9925 | | No log | 49.0 | 196 | 0.1086 | 0.95 | 0.9580 | 0.9540 | 0.9925 | | No log | 50.0 | 200 | 0.1077 | 0.95 | 0.9580 | 0.9540 | 0.9925 | | No log | 51.0 | 204 | 0.1073 | 0.95 | 0.9580 | 0.9540 | 0.9925 | | No log | 52.0 | 208 | 0.1066 | 0.95 | 0.9580 | 0.9540 | 0.9925 | | No log | 53.0 | 212 | 0.1054 | 0.95 | 0.9580 | 0.9540 | 0.9925 | | No log | 54.0 | 216 | 0.1075 | 0.9496 | 0.9496 | 0.9496 | 0.9906 | | No log | 55.0 | 220 | 0.1084 | 0.9496 | 0.9496 | 0.9496 | 0.9906 | | No log | 56.0 | 224 | 0.1065 | 0.9576 | 0.9496 | 0.9536 | 0.9916 | | No log | 57.0 | 228 | 0.1057 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 58.0 | 232 | 0.1053 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 59.0 | 236 | 0.1043 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 60.0 | 240 | 0.1033 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 61.0 | 244 | 0.1024 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 62.0 | 248 | 0.1003 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 63.0 | 252 | 0.1039 | 0.9268 | 0.9580 | 0.9421 | 0.9906 | | No log | 64.0 | 256 | 0.1084 | 0.9194 | 0.9580 | 0.9383 | 0.9888 | | No log | 65.0 | 260 | 0.1062 | 0.912 | 0.9580 | 0.9344 | 0.9888 | | No log | 66.0 | 264 | 0.0981 | 0.9344 | 0.9580 | 0.9461 | 0.9916 | | No log | 67.0 | 268 | 0.0960 | 0.9576 | 0.9496 | 0.9536 | 0.9916 | | No log | 68.0 | 272 | 0.0961 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 69.0 | 276 | 0.0951 | 0.9573 | 0.9412 | 0.9492 | 0.9916 | | No log | 70.0 | 280 | 0.0952 | 0.9652 | 0.9328 | 0.9487 | 0.9916 | | No log | 71.0 | 284 | 0.0950 | 0.9652 | 0.9328 | 0.9487 | 0.9916 | | No log | 72.0 | 288 | 0.0943 | 0.9652 | 0.9328 | 0.9487 | 0.9916 | | No log | 73.0 | 292 | 0.0935 | 0.9652 | 0.9328 | 0.9487 | 0.9916 | | No log | 74.0 | 296 | 0.0928 | 0.9652 | 0.9328 | 0.9487 | 0.9916 | | No log | 75.0 | 300 | 0.0922 | 0.9652 | 0.9328 | 0.9487 | 0.9916 | | No log | 76.0 | 304 | 0.0902 | 0.9655 | 0.9412 | 0.9532 | 0.9925 | | No log | 77.0 | 308 | 0.0885 | 0.9658 | 0.9496 | 0.9576 | 0.9934 | | No log | 78.0 | 312 | 0.0869 | 0.9658 | 0.9496 | 0.9576 | 0.9934 | | No log | 79.0 | 316 | 0.0858 | 0.9580 | 0.9580 | 0.9580 | 0.9925 | | No log | 80.0 | 320 | 0.0853 | 0.9580 | 0.9580 | 0.9580 | 0.9925 | | No log | 81.0 | 324 | 0.0852 | 0.9583 | 0.9664 | 0.9623 | 0.9934 | | No log | 82.0 | 328 | 0.0850 | 0.9583 | 0.9664 | 0.9623 | 0.9934 | | No log | 83.0 | 332 | 0.0848 | 0.9583 | 0.9664 | 0.9623 | 0.9934 | | No log | 84.0 | 336 | 0.0846 | 0.9583 | 0.9664 | 0.9623 | 0.9934 | | No log | 85.0 | 340 | 0.0843 | 0.9583 | 0.9664 | 0.9623 | 0.9944 | | No log | 86.0 | 344 | 0.0841 | 0.9583 | 0.9664 | 0.9623 | 0.9944 | | No log | 87.0 | 348 | 0.0839 | 0.9583 | 0.9664 | 0.9623 | 0.9944 | | No log | 88.0 | 352 | 0.0835 | 0.9583 | 0.9664 | 0.9623 | 0.9944 | | No log | 89.0 | 356 | 0.0831 | 0.9583 | 0.9664 | 0.9623 | 0.9944 | | No log | 90.0 | 360 | 0.0828 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 91.0 | 364 | 0.0825 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 92.0 | 368 | 0.0824 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 93.0 | 372 | 0.0822 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 94.0 | 376 | 0.0822 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 95.0 | 380 | 0.0821 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 96.0 | 384 | 0.0821 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 97.0 | 388 | 0.0820 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 98.0 | 392 | 0.0820 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 99.0 | 396 | 0.0820 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | | No log | 100.0 | 400 | 0.0820 | 0.9583 | 0.9664 | 0.9623 | 0.9953 | ### Framework versions - Transformers 4.40.2 - Pytorch 2.1.0+cu121 - Datasets 2.14.5 - Tokenizers 0.19.1