modernbert_punctuation_64

This model is a fine-tuned version of answerdotai/ModernBERT-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0562
  • Accuracy: 0.9795
  • Precision O: 0.9906
  • Recall O: 0.9920
  • F1 O: 0.9913
  • Precision Comma: 0.8441
  • Recall Comma: 0.8277
  • F1 Comma: 0.8358
  • Precision Period: 0.9066
  • Recall Period: 0.9025
  • F1 Period: 0.9045
  • Precision Question: 0.8309
  • Recall Question: 0.8
  • F1 Question: 0.8151
  • Precision Exclamation: 0.0
  • Recall Exclamation: 0.0
  • F1 Exclamation: 0.0
  • Precision Macro: 0.8930
  • Recall Macro: 0.8805
  • F1 Macro: 0.8867

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: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 512
  • total_eval_batch_size: 128
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision O Recall O F1 O Precision Comma Recall Comma F1 Comma Precision Period Recall Period F1 Period Precision Question Recall Question F1 Question Precision Exclamation Recall Exclamation F1 Exclamation Precision Macro Recall Macro F1 Macro
0.106 0.0212 100 0.1072 0.9607 0.9768 0.9882 0.9825 0.7357 0.6049 0.6639 0.8364 0.8113 0.8237 0.7550 0.6429 0.6944 0.0 0.0 0.0 0.8260 0.7618 0.7911
0.0706 0.0423 200 0.0790 0.9705 0.9844 0.9901 0.9872 0.7848 0.7370 0.7601 0.8859 0.8420 0.8634 0.7722 0.7457 0.7587 0.0 0.0 0.0 0.8568 0.8287 0.8424
0.0661 0.0635 300 0.0733 0.9721 0.9872 0.9887 0.9880 0.7973 0.7606 0.7785 0.8599 0.8811 0.8704 0.7945 0.74 0.7663 0.0 0.0 0.0 0.8597 0.8426 0.8508
0.0619 0.0846 400 0.0695 0.9731 0.9870 0.9898 0.9884 0.7907 0.7818 0.7862 0.8976 0.8553 0.8759 0.7816 0.7771 0.7794 0.0 0.0 0.0 0.8642 0.8510 0.8575
0.0597 0.1058 500 0.0681 0.9736 0.9867 0.9906 0.9886 0.8144 0.7615 0.7871 0.8752 0.8810 0.8781 0.8496 0.6457 0.7338 0.0 0.0 0.0 0.8815 0.8197 0.8469
0.0587 0.1269 600 0.0662 0.9744 0.9867 0.9912 0.9889 0.8193 0.7661 0.7918 0.8863 0.8769 0.8815 0.8581 0.7086 0.7762 0.0 0.0 0.0 0.8876 0.8357 0.8596
0.0563 0.1481 700 0.0645 0.9750 0.9882 0.9903 0.9893 0.8140 0.7882 0.8009 0.8815 0.8838 0.8826 0.8526 0.6943 0.7654 0.0 0.0 0.0 0.8841 0.8392 0.8595
0.0574 0.1692 800 0.0645 0.9748 0.9892 0.9893 0.9893 0.7818 0.8231 0.8019 0.9108 0.8561 0.8826 0.8384 0.7857 0.8112 0.0 0.0 0.0 0.8801 0.8635 0.8712
0.056 0.1904 900 0.0639 0.9751 0.9868 0.9917 0.9892 0.8136 0.7814 0.7972 0.9089 0.8631 0.8854 0.8682 0.7343 0.7957 0.0 0.0 0.0 0.8944 0.8426 0.8669
0.055 0.2116 1000 0.0639 0.9749 0.9887 0.9899 0.9893 0.8051 0.7957 0.8004 0.8860 0.8797 0.8829 0.8293 0.7771 0.8024 0.0 0.0 0.0 0.8773 0.8606 0.8687
0.0535 0.2327 1100 0.0615 0.9763 0.9886 0.9910 0.9898 0.8268 0.7941 0.8102 0.8896 0.8886 0.8891 0.8293 0.7771 0.8024 0.0 0.0 0.0 0.8836 0.8627 0.8728
0.0552 0.2539 1200 0.0621 0.9756 0.9880 0.9910 0.9895 0.8206 0.7863 0.8031 0.8920 0.8808 0.8864 0.8218 0.7771 0.7988 0.0 0.0 0.0 0.8806 0.8588 0.8694
0.0539 0.2750 1300 0.0614 0.9753 0.9874 0.9915 0.9894 0.8233 0.7762 0.7990 0.8936 0.8767 0.8850 0.8103 0.8057 0.8080 0.0 0.0 0.0 0.8787 0.8625 0.8704
0.0521 0.2962 1400 0.0599 0.9767 0.9885 0.9918 0.9901 0.8346 0.7913 0.8124 0.8923 0.8859 0.8891 0.8218 0.7771 0.7988 0.0 0.0 0.0 0.8843 0.8615 0.8726
0.053 0.3173 1500 0.0602 0.9761 0.9907 0.9890 0.9898 0.7982 0.8286 0.8131 0.8930 0.8889 0.8910 0.8219 0.7514 0.7851 0.0 0.0 0.0 0.8759 0.8645 0.8697
0.0522 0.3385 1600 0.0604 0.9762 0.9869 0.9927 0.9898 0.8401 0.7717 0.8045 0.9053 0.8772 0.8910 0.7540 0.8057 0.7790 0.0 0.0 0.0 0.8716 0.8618 0.8661
0.0511 0.3596 1700 0.0594 0.9768 0.9886 0.9917 0.9901 0.8252 0.8002 0.8125 0.9017 0.8842 0.8929 0.8616 0.7114 0.7793 0.0 0.0 0.0 0.8943 0.8468 0.8687
0.0516 0.3808 1800 0.0592 0.9763 0.9870 0.9926 0.9898 0.8446 0.7693 0.8052 0.8983 0.8823 0.8902 0.7827 0.8029 0.7927 0.0 0.0 0.0 0.8782 0.8618 0.8695
0.052 0.4019 1900 0.0587 0.9766 0.9896 0.9906 0.9901 0.8106 0.8155 0.8130 0.9017 0.8792 0.8903 0.8269 0.7914 0.8088 0.0 0.0 0.0 0.8822 0.8692 0.8755
0.0498 0.4231 2000 0.0585 0.9769 0.9894 0.9909 0.9902 0.8253 0.8073 0.8162 0.8934 0.8911 0.8923 0.8235 0.76 0.7905 0.0 0.0 0.0 0.8829 0.8623 0.8723
0.0504 0.4443 2100 0.0582 0.9770 0.9868 0.9935 0.9901 0.8502 0.7762 0.8115 0.9105 0.8740 0.8919 0.8222 0.8057 0.8139 0.0 0.0 0.0 0.8924 0.8623 0.8768
0.0513 0.4654 2200 0.0575 0.9773 0.9885 0.9922 0.9903 0.8409 0.7927 0.8161 0.8987 0.8887 0.8937 0.7971 0.7743 0.7855 0.0 0.0 0.0 0.8813 0.8620 0.8714
0.0516 0.4866 2300 0.0588 0.9767 0.9862 0.9938 0.9900 0.8520 0.7641 0.8056 0.9107 0.8742 0.8921 0.8318 0.7771 0.8035 0.0 0.0 0.0 0.8952 0.8523 0.8728
0.0514 0.5077 2400 0.0575 0.9773 0.9885 0.9922 0.9903 0.8406 0.7898 0.8144 0.8966 0.8941 0.8953 0.8292 0.7629 0.7946 0.0 0.0 0.0 0.8887 0.8597 0.8737
0.0501 0.5289 2500 0.0574 0.9771 0.9885 0.9919 0.9902 0.8217 0.8121 0.8169 0.9198 0.8688 0.8936 0.8154 0.7571 0.7852 0.0 0.0 0.0 0.8863 0.8575 0.8715
0.0503 0.5500 2600 0.0570 0.9777 0.9888 0.9922 0.9905 0.8431 0.7941 0.8179 0.8983 0.8973 0.8978 0.8359 0.7714 0.8024 0.0 0.0 0.0 0.8915 0.8638 0.8771
0.0507 0.5712 2700 0.0567 0.9776 0.9895 0.9915 0.9905 0.8374 0.8007 0.8186 0.8902 0.9016 0.8958 0.8253 0.7829 0.8035 0.0 0.0 0.0 0.8856 0.8692 0.8771
0.0505 0.5923 2800 0.0564 0.9776 0.9881 0.9926 0.9903 0.8420 0.7936 0.8171 0.9074 0.8883 0.8977 0.8553 0.76 0.8048 0.0 0.0 0.0 0.8982 0.8586 0.8775
0.0508 0.6135 2900 0.0565 0.9775 0.9906 0.9905 0.9906 0.8078 0.8357 0.8215 0.9131 0.8773 0.8949 0.7955 0.8 0.7977 0.0 0.0 0.0 0.8767 0.8759 0.8762
0.049 0.6347 3000 0.0567 0.9777 0.9903 0.9907 0.9905 0.8203 0.8264 0.8234 0.8993 0.8941 0.8967 0.8768 0.6914 0.7732 0.0 0.0 0.0 0.8967 0.8507 0.8709
0.049 0.6558 3100 0.0563 0.9779 0.9899 0.9914 0.9907 0.8325 0.8125 0.8224 0.8999 0.8949 0.8974 0.7971 0.7971 0.7971 0.0 0.0 0.0 0.8799 0.8740 0.8769
0.0503 0.6770 3200 0.0560 0.9780 0.9901 0.9912 0.9907 0.8301 0.8185 0.8243 0.8997 0.8968 0.8983 0.8182 0.7714 0.7941 0.0 0.0 0.0 0.8845 0.8695 0.8768
0.0497 0.6981 3300 0.0557 0.9778 0.9885 0.9925 0.9905 0.8387 0.7996 0.8187 0.9087 0.8861 0.8972 0.8505 0.78 0.8137 0.0 0.0 0.0 0.8966 0.8645 0.8800
0.0484 0.7193 3400 0.0556 0.9780 0.9887 0.9925 0.9906 0.8487 0.7945 0.8207 0.9005 0.8967 0.8986 0.8218 0.7771 0.7988 0.0 0.0 0.0 0.8899 0.8652 0.8772
0.0486 0.7404 3500 0.0553 0.9779 0.9896 0.9917 0.9906 0.8292 0.8201 0.8246 0.9067 0.8838 0.8951 0.8548 0.74 0.7933 0.0 0.0 0.0 0.8950 0.8589 0.8759
0.0489 0.7616 3600 0.0549 0.9780 0.9896 0.9917 0.9907 0.8431 0.8058 0.8240 0.8922 0.9011 0.8966 0.8252 0.7686 0.7959 0.0 0.0 0.0 0.8875 0.8668 0.8768
0.0492 0.7827 3700 0.0556 0.9777 0.9882 0.9927 0.9905 0.8565 0.7823 0.8177 0.8922 0.9002 0.8962 0.8201 0.7686 0.7935 0.0 0.0 0.0 0.8893 0.8609 0.8745
0.0487 0.8039 3800 0.0556 0.9780 0.9874 0.9936 0.9905 0.8572 0.7821 0.8179 0.9126 0.8883 0.9003 0.8333 0.7857 0.8088 0.0 0.0 0.0 0.8976 0.8624 0.8794
0.0468 0.8250 3900 0.0553 0.9780 0.9900 0.9912 0.9906 0.8390 0.8087 0.8236 0.8881 0.9060 0.8970 0.8338 0.7743 0.8030 0.0 0.0 0.0 0.8878 0.8701 0.8785
0.0484 0.8462 4000 0.0556 0.9780 0.9886 0.9928 0.9907 0.8455 0.7999 0.8221 0.9043 0.8849 0.8945 0.8375 0.7657 0.8 0.0 0.0 0.0 0.8940 0.8608 0.8768
0.048 0.8674 4100 0.0551 0.9779 0.9908 0.9906 0.9907 0.8292 0.8223 0.8257 0.8883 0.9027 0.8955 0.8253 0.7829 0.8035 0.0 0.0 0.0 0.8834 0.8746 0.8788
0.0469 0.8885 4200 0.0548 0.9783 0.9897 0.9919 0.9908 0.8353 0.8176 0.8264 0.9059 0.8895 0.8976 0.8323 0.78 0.8053 0.0 0.0 0.0 0.8908 0.8698 0.8800
0.0475 0.9097 4300 0.0542 0.9783 0.9899 0.9918 0.9908 0.8399 0.8150 0.8273 0.8990 0.8948 0.8969 0.8103 0.8057 0.8080 0.0 0.0 0.0 0.8848 0.8768 0.8808
0.0469 0.9308 4400 0.0545 0.9783 0.9896 0.9918 0.9907 0.8338 0.8189 0.8263 0.9110 0.8884 0.8996 0.8110 0.7971 0.8040 0.0 0.0 0.0 0.8864 0.8741 0.8802
0.0492 0.9520 4500 0.0543 0.9783 0.9905 0.9911 0.9908 0.8366 0.8207 0.8286 0.8908 0.9040 0.8973 0.8279 0.7286 0.7751 0.0 0.0 0.0 0.8865 0.8611 0.8729
0.0483 0.9731 4600 0.0542 0.9784 0.9899 0.9918 0.9908 0.8467 0.8070 0.8264 0.8933 0.9065 0.8999 0.7994 0.7743 0.7866 0.0 0.0 0.0 0.8823 0.8699 0.8759
0.0471 0.9943 4700 0.0537 0.9788 0.9892 0.9926 0.9909 0.8444 0.8137 0.8288 0.9127 0.8894 0.9009 0.8469 0.7743 0.8090 0.0 0.0 0.0 0.8983 0.8675 0.8824
0.0409 1.0154 4800 0.0548 0.9783 0.9908 0.9908 0.9908 0.8241 0.8315 0.8278 0.9042 0.8959 0.9000 0.8193 0.7771 0.7977 0.0 0.0 0.0 0.8846 0.8738 0.8791
0.0414 1.0366 4900 0.0550 0.9783 0.9893 0.9922 0.9908 0.8363 0.8175 0.8268 0.9132 0.8835 0.8981 0.8221 0.7657 0.7929 0.0 0.0 0.0 0.8902 0.8647 0.8771
0.0397 1.0578 5000 0.0542 0.9786 0.9893 0.9924 0.9909 0.8442 0.8140 0.8288 0.9099 0.8900 0.8999 0.8131 0.7829 0.7977 0.0 0.0 0.0 0.8891 0.8698 0.8793
0.0407 1.0789 5100 0.0547 0.9786 0.9898 0.9923 0.9910 0.8409 0.8132 0.8268 0.9061 0.8929 0.8994 0.8145 0.8029 0.8086 0.0 0.0 0.0 0.8878 0.8753 0.8815
0.0399 1.1001 5200 0.0546 0.9784 0.9896 0.9921 0.9909 0.8432 0.8077 0.8250 0.9008 0.8998 0.9003 0.8288 0.7886 0.8082 0.0 0.0 0.0 0.8906 0.8720 0.8811
0.0407 1.1212 5300 0.0549 0.9782 0.9885 0.9930 0.9907 0.8438 0.8043 0.8236 0.9142 0.8810 0.8973 0.8481 0.7657 0.8048 0.0 0.0 0.0 0.8986 0.8610 0.8791
0.0398 1.1424 5400 0.0546 0.9786 0.9899 0.9919 0.9909 0.8455 0.8125 0.8287 0.8982 0.9016 0.8999 0.8239 0.7886 0.8058 0.0 0.0 0.0 0.8894 0.8736 0.8813
0.0405 1.1635 5500 0.0543 0.9787 0.9908 0.9912 0.9910 0.8324 0.8281 0.8302 0.9012 0.9003 0.9007 0.8382 0.8143 0.8261 0.0 0.0 0.0 0.8906 0.8835 0.8870
0.0413 1.1847 5600 0.0542 0.9787 0.9906 0.9914 0.9910 0.8375 0.8226 0.8300 0.8997 0.9014 0.9006 0.7917 0.8143 0.8028 0.0 0.0 0.0 0.8799 0.8824 0.8811
0.0402 1.2058 5700 0.0545 0.9784 0.9898 0.9919 0.9908 0.8420 0.8071 0.8242 0.8988 0.9046 0.9017 0.8348 0.7943 0.8141 0.0 0.0 0.0 0.8914 0.8745 0.8827
0.0403 1.2270 5800 0.0548 0.9786 0.9891 0.9927 0.9909 0.8457 0.8085 0.8267 0.9088 0.8921 0.9004 0.8709 0.7514 0.8067 0.0 0.0 0.0 0.9036 0.8612 0.8812
0.0402 1.2481 5900 0.0544 0.9787 0.9899 0.9921 0.9910 0.8459 0.8124 0.8288 0.9001 0.9 0.9001 0.8249 0.7943 0.8093 0.0 0.0 0.0 0.8902 0.8747 0.8823
0.0405 1.2693 6000 0.0541 0.9789 0.9902 0.9918 0.9910 0.8390 0.8243 0.8316 0.9070 0.8975 0.9022 0.8228 0.7829 0.8023 0.0 0.0 0.0 0.8898 0.8741 0.8818
0.0406 1.2905 6100 0.0540 0.9786 0.9896 0.9922 0.9909 0.8403 0.8200 0.8300 0.9122 0.8886 0.9002 0.8099 0.7914 0.8006 0.0 0.0 0.0 0.8880 0.8730 0.8804
0.0396 1.3116 6200 0.0536 0.9786 0.9906 0.9913 0.9910 0.8324 0.8278 0.8301 0.9022 0.8975 0.8998 0.8258 0.7857 0.8053 0.0 0.0 0.0 0.8877 0.8756 0.8815
0.0396 1.3328 6300 0.0531 0.9793 0.9900 0.9923 0.9912 0.8454 0.8231 0.8341 0.9090 0.8960 0.9025 0.8536 0.7829 0.8167 0.0 0.0 0.0 0.8995 0.8736 0.8861
0.0401 1.3539 6400 0.0532 0.9789 0.9895 0.9925 0.9910 0.8437 0.8179 0.8306 0.9103 0.8921 0.9011 0.8633 0.74 0.7969 0.0 0.0 0.0 0.9017 0.8606 0.8799
0.0393 1.3751 6500 0.0539 0.9789 0.9897 0.9923 0.9910 0.8411 0.8205 0.8307 0.9130 0.8894 0.9010 0.8147 0.7914 0.8029 0.0 0.0 0.0 0.8896 0.8734 0.8814
0.0395 1.3962 6600 0.0530 0.9786 0.9900 0.9920 0.9910 0.8414 0.8177 0.8294 0.9004 0.8957 0.8981 0.8253 0.7829 0.8035 0.0 0.0 0.0 0.8893 0.8721 0.8805
0.0398 1.4174 6700 0.0533 0.9789 0.9898 0.9923 0.9910 0.8547 0.8077 0.8305 0.8953 0.9057 0.9005 0.8063 0.8086 0.8074 0.0 0.0 0.0 0.8865 0.8786 0.8824
0.0398 1.4385 6800 0.0526 0.9793 0.9898 0.9926 0.9912 0.8560 0.8138 0.8344 0.9017 0.9024 0.9020 0.8225 0.7943 0.8081 0.0 0.0 0.0 0.8925 0.8758 0.8839
0.039 1.4597 6900 0.0528 0.9792 0.9894 0.9929 0.9912 0.8465 0.8192 0.8326 0.9186 0.8873 0.9027 0.8303 0.7829 0.8059 0.0 0.0 0.0 0.8962 0.8706 0.8831
0.0391 1.4809 7000 0.0536 0.9788 0.9902 0.9917 0.9910 0.8328 0.8282 0.8305 0.9128 0.8924 0.9025 0.8269 0.7914 0.8088 0.0 0.0 0.0 0.8907 0.8759 0.8832
0.04 1.5020 7100 0.0533 0.9789 0.9903 0.9919 0.9911 0.8399 0.8224 0.8311 0.9072 0.8956 0.9013 0.8044 0.8343 0.8191 0.0 0.0 0.0 0.8854 0.8860 0.8856
0.0391 1.5232 7200 0.0532 0.9791 0.9889 0.9934 0.9911 0.8606 0.7981 0.8282 0.9065 0.8986 0.9025 0.8328 0.7829 0.8071 0.0 0.0 0.0 0.8972 0.8682 0.8822
0.0392 1.5443 7300 0.0537 0.9788 0.9900 0.9920 0.9910 0.8518 0.8069 0.8287 0.8921 0.9109 0.9014 0.8134 0.7971 0.8052 0.0 0.0 0.0 0.8868 0.8767 0.8816
0.0399 1.5655 7400 0.0535 0.9790 0.9909 0.9912 0.9911 0.8253 0.8419 0.8335 0.9160 0.8921 0.9039 0.8313 0.7886 0.8094 0.0 0.0 0.0 0.8909 0.8784 0.8845
0.0397 1.5866 7500 0.0528 0.9793 0.9911 0.9913 0.9912 0.8365 0.8378 0.8372 0.9042 0.9021 0.9031 0.8442 0.7743 0.8077 0.0 0.0 0.0 0.8940 0.8764 0.8848
0.0386 1.6078 7600 0.0529 0.9791 0.9899 0.9922 0.9911 0.8456 0.8199 0.8326 0.9069 0.8983 0.9025 0.8471 0.7914 0.8183 0.0 0.0 0.0 0.8974 0.8754 0.8861
0.0395 1.6289 7700 0.0530 0.9793 0.9904 0.9921 0.9913 0.8487 0.8183 0.8332 0.8994 0.9067 0.9030 0.8222 0.8057 0.8139 0.0 0.0 0.0 0.8902 0.8807 0.8853
0.039 1.6501 7800 0.0526 0.9794 0.9901 0.9923 0.9912 0.8421 0.8287 0.8353 0.9169 0.8913 0.9039 0.8304 0.7971 0.8134 0.0 0.0 0.0 0.8948 0.8774 0.8860
0.0389 1.6713 7900 0.0527 0.9791 0.9899 0.9924 0.9912 0.8432 0.8230 0.8330 0.9121 0.8900 0.9009 0.8274 0.7943 0.8105 0.0 0.0 0.0 0.8932 0.8749 0.8839
0.0388 1.6924 8000 0.0522 0.9794 0.9905 0.9921 0.9913 0.8453 0.8273 0.8362 0.9062 0.8998 0.9030 0.8324 0.8086 0.8203 0.0 0.0 0.0 0.8936 0.8819 0.8877
0.0395 1.7136 8100 0.0524 0.9796 0.9900 0.9926 0.9913 0.8507 0.8200 0.8351 0.9111 0.9003 0.9057 0.8358 0.8 0.8175 0.0 0.0 0.0 0.8969 0.8782 0.8874
0.039 1.7347 8200 0.0525 0.9794 0.9907 0.9918 0.9913 0.8406 0.8319 0.8363 0.9058 0.8992 0.9025 0.8421 0.7771 0.8083 0.0 0.0 0.0 0.8948 0.8750 0.8846
0.0399 1.7559 8300 0.0519 0.9794 0.9899 0.9926 0.9913 0.8512 0.8173 0.8339 0.9077 0.8989 0.9033 0.8232 0.8114 0.8173 0.0 0.0 0.0 0.8930 0.8801 0.8864
0.0379 1.7770 8400 0.0524 0.9793 0.9898 0.9927 0.9913 0.8453 0.8230 0.8340 0.9149 0.8889 0.9017 0.8328 0.7829 0.8071 0.0 0.0 0.0 0.8957 0.8719 0.8835
0.0391 1.7982 8500 0.0517 0.9794 0.9903 0.9924 0.9913 0.8507 0.8212 0.8357 0.9034 0.8997 0.9015 0.8143 0.8143 0.8143 0.0 0.0 0.0 0.8897 0.8819 0.8857
0.0396 1.8193 8600 0.0520 0.9793 0.9904 0.9920 0.9912 0.8449 0.8236 0.8341 0.9054 0.9022 0.9038 0.8434 0.8 0.8211 0.0 0.0 0.0 0.8960 0.8795 0.8876
0.0381 1.8405 8700 0.0520 0.9793 0.9902 0.9922 0.9912 0.8478 0.8191 0.8332 0.9037 0.9014 0.9026 0.8230 0.8371 0.8300 0.0 0.0 0.0 0.8912 0.8874 0.8892
0.039 1.8616 8800 0.0523 0.9795 0.9902 0.9925 0.9913 0.8499 0.8230 0.8362 0.9068 0.8971 0.9019 0.8407 0.8143 0.8273 0.0 0.0 0.0 0.8969 0.8817 0.8892
0.0385 1.8828 8900 0.0518 0.9795 0.9902 0.9923 0.9913 0.8483 0.8242 0.8361 0.9081 0.8987 0.9034 0.8392 0.82 0.8295 0.0 0.0 0.0 0.8964 0.8838 0.8901
0.0388 1.9040 9000 0.0519 0.9794 0.9901 0.9924 0.9913 0.8458 0.8246 0.8350 0.9108 0.8954 0.9031 0.8373 0.7943 0.8152 0.0 0.0 0.0 0.8960 0.8767 0.8862
0.0386 1.9251 9100 0.0519 0.9794 0.9907 0.9918 0.9912 0.8444 0.8293 0.8368 0.9030 0.9016 0.9023 0.8294 0.8057 0.8174 0.0 0.0 0.0 0.8919 0.8821 0.8869
0.0389 1.9463 9200 0.0518 0.9794 0.9909 0.9916 0.9912 0.8370 0.8388 0.8379 0.9102 0.8959 0.9030 0.8445 0.7914 0.8171 0.0 0.0 0.0 0.8956 0.8794 0.8873
0.0387 1.9674 9300 0.0517 0.9796 0.9902 0.9926 0.9914 0.8509 0.8218 0.8361 0.9086 0.8992 0.9039 0.8318 0.7914 0.8111 0.0 0.0 0.0 0.8954 0.8763 0.8856
0.0386 1.9886 9400 0.0515 0.9797 0.9906 0.9922 0.9914 0.8494 0.8252 0.8371 0.9045 0.9049 0.9047 0.8314 0.8029 0.8169 0.0 0.0 0.0 0.8940 0.8813 0.8875
0.03 2.0097 9500 0.0549 0.9793 0.9910 0.9917 0.9913 0.8391 0.8330 0.8360 0.9029 0.8994 0.9012 0.8419 0.7914 0.8159 0.0 0.0 0.0 0.8937 0.8789 0.8861
0.0292 2.0309 9600 0.0555 0.9793 0.9906 0.9920 0.9913 0.8441 0.8258 0.8348 0.9032 0.9006 0.9019 0.8235 0.8 0.8116 0.0 0.0 0.0 0.8904 0.8796 0.8849
0.03 2.0520 9700 0.0555 0.9793 0.9902 0.9923 0.9913 0.8432 0.8250 0.8340 0.9111 0.8949 0.9029 0.8323 0.7943 0.8129 0.0 0.0 0.0 0.8942 0.8766 0.8853
0.0289 2.0732 9800 0.0560 0.9792 0.9904 0.9919 0.9912 0.8440 0.8244 0.8341 0.9043 0.9017 0.9030 0.8184 0.8114 0.8149 0.0 0.0 0.0 0.8893 0.8824 0.8858
0.03 2.0944 9900 0.0558 0.9792 0.9912 0.9913 0.9912 0.8317 0.8393 0.8355 0.9077 0.8976 0.9026 0.8140 0.8 0.8069 0.0 0.0 0.0 0.8861 0.8821 0.8841
0.03 2.1155 10000 0.0557 0.9792 0.9904 0.9921 0.9912 0.8418 0.8263 0.8340 0.9075 0.8975 0.9025 0.8204 0.7829 0.8012 0.0 0.0 0.0 0.8900 0.8747 0.8822
0.029 2.1367 10100 0.0562 0.9793 0.9905 0.9920 0.9912 0.8402 0.8277 0.8339 0.9097 0.8971 0.9034 0.8251 0.8086 0.8167 0.0 0.0 0.0 0.8913 0.8813 0.8863
0.0288 2.1578 10200 0.0563 0.9792 0.9905 0.9919 0.9912 0.8417 0.8256 0.8336 0.9040 0.8989 0.9015 0.8348 0.7943 0.8141 0.0 0.0 0.0 0.8928 0.8777 0.8851
0.0296 2.1790 10300 0.0555 0.9793 0.9907 0.9918 0.9913 0.8415 0.8279 0.8346 0.9061 0.9017 0.9039 0.8187 0.8 0.8092 0.0 0.0 0.0 0.8892 0.8804 0.8848
0.029 2.2001 10400 0.0559 0.9791 0.9910 0.9914 0.9912 0.8326 0.8356 0.8341 0.9084 0.8978 0.9031 0.8103 0.8057 0.8080 0.0 0.0 0.0 0.8856 0.8826 0.8841
0.0288 2.2213 10500 0.0565 0.9792 0.9910 0.9914 0.9912 0.8336 0.8328 0.8332 0.9066 0.8998 0.9032 0.8190 0.8143 0.8166 0.0 0.0 0.0 0.8876 0.8846 0.8861
0.0285 2.2424 10600 0.0565 0.9792 0.9903 0.9921 0.9912 0.8484 0.8173 0.8326 0.8997 0.9065 0.9031 0.8214 0.7886 0.8047 0.0 0.0 0.0 0.8900 0.8761 0.8829
0.0291 2.2636 10700 0.0563 0.9792 0.9911 0.9913 0.9912 0.8356 0.8329 0.8342 0.9014 0.9036 0.9025 0.8323 0.7943 0.8129 0.0 0.0 0.0 0.8901 0.8805 0.8852
0.0282 2.2847 10800 0.0565 0.9793 0.9908 0.9916 0.9912 0.8439 0.8251 0.8344 0.8987 0.9086 0.9036 0.8225 0.7943 0.8081 0.0 0.0 0.0 0.8890 0.8799 0.8843
0.0288 2.3059 10900 0.0562 0.9796 0.9907 0.9920 0.9913 0.8466 0.8262 0.8363 0.9035 0.9062 0.9048 0.8323 0.7943 0.8129 0.0 0.0 0.0 0.8933 0.8797 0.8863
0.0286 2.3271 11000 0.0559 0.9797 0.9904 0.9925 0.9914 0.8485 0.8250 0.8366 0.9075 0.9017 0.9046 0.8491 0.7714 0.8084 0.0 0.0 0.0 0.8989 0.8727 0.8853
0.0284 2.3482 11100 0.0569 0.9796 0.9907 0.9920 0.9913 0.8446 0.8274 0.8359 0.9071 0.9040 0.9055 0.8299 0.7943 0.8117 0.0 0.0 0.0 0.8931 0.8794 0.8861
0.029 2.3694 11200 0.0564 0.9794 0.9904 0.9922 0.9913 0.8461 0.8227 0.8342 0.9073 0.9024 0.9048 0.8140 0.8 0.8069 0.0 0.0 0.0 0.8894 0.8793 0.8843
0.0285 2.3905 11300 0.0564 0.9794 0.9908 0.9919 0.9913 0.8407 0.8275 0.8341 0.9053 0.9030 0.9042 0.8323 0.7943 0.8129 0.0 0.0 0.0 0.8923 0.8792 0.8856
0.0286 2.4117 11400 0.0562 0.9795 0.9908 0.9919 0.9913 0.8409 0.8328 0.8368 0.9091 0.8984 0.9037 0.8279 0.7971 0.8122 0.0 0.0 0.0 0.8921 0.8801 0.8860
0.0289 2.4328 11500 0.0562 0.9795 0.9905 0.9921 0.9913 0.8446 0.8274 0.8359 0.9087 0.9006 0.9046 0.8265 0.8029 0.8145 0.0 0.0 0.0 0.8926 0.8808 0.8866
0.0284 2.4540 11600 0.0561 0.9794 0.9908 0.9918 0.9913 0.8424 0.8281 0.8352 0.9045 0.9025 0.9035 0.8227 0.8086 0.8156 0.0 0.0 0.0 0.8901 0.8828 0.8864
0.0289 2.4751 11700 0.0562 0.9794 0.9907 0.9918 0.9912 0.8412 0.8279 0.8345 0.9055 0.9036 0.9046 0.8309 0.8 0.8151 0.0 0.0 0.0 0.8921 0.8808 0.8864
0.0295 2.4963 11800 0.0564 0.9795 0.9906 0.9921 0.9913 0.8427 0.8279 0.8353 0.9083 0.8992 0.9037 0.8324 0.8086 0.8203 0.0 0.0 0.0 0.8935 0.8819 0.8877
0.0283 2.5175 11900 0.0562 0.9792 0.9906 0.9919 0.9912 0.8399 0.8263 0.8331 0.9063 0.9014 0.9039 0.8389 0.7886 0.8130 0.0 0.0 0.0 0.8939 0.8770 0.8853
0.0284 2.5386 12000 0.0560 0.9794 0.9908 0.9918 0.9913 0.8407 0.8307 0.8357 0.9070 0.9016 0.9043 0.8314 0.8029 0.8169 0.0 0.0 0.0 0.8925 0.8817 0.8870
0.0278 2.5598 12100 0.0562 0.9795 0.9906 0.9920 0.9913 0.8417 0.8285 0.8350 0.9087 0.9010 0.9048 0.8404 0.7971 0.8182 0.0 0.0 0.0 0.8953 0.8796 0.8873
0.0284 2.5809 12200 0.0564 0.9794 0.9905 0.9921 0.9913 0.8457 0.8240 0.8347 0.9046 0.9021 0.9033 0.8192 0.8029 0.8110 0.0 0.0 0.0 0.8900 0.8803 0.8851
0.0284 2.6021 12300 0.0562 0.9795 0.9906 0.9921 0.9913 0.8438 0.8273 0.8354 0.9067 0.9006 0.9036 0.8429 0.7971 0.8194 0.0 0.0 0.0 0.8960 0.8793 0.8874
0.0286 2.6232 12400 0.0562 0.9795 0.9905 0.9921 0.9913 0.8451 0.8254 0.8351 0.9069 0.9016 0.9042 0.8289 0.8029 0.8157 0.0 0.0 0.0 0.8928 0.8805 0.8866
0.0285 2.6444 12500 0.0561 0.9795 0.9908 0.9919 0.9914 0.8427 0.8294 0.8360 0.9057 0.9030 0.9044 0.8289 0.8029 0.8157 0.0 0.0 0.0 0.8921 0.8818 0.8869
0.0282 2.6655 12600 0.0563 0.9794 0.9906 0.9920 0.9913 0.8439 0.8263 0.8350 0.9063 0.9030 0.9047 0.8254 0.7971 0.8110 0.0 0.0 0.0 0.8915 0.8796 0.8855
0.0282 2.6867 12700 0.0562 0.9794 0.9905 0.9921 0.9913 0.8437 0.8260 0.8348 0.9065 0.9008 0.9037 0.8378 0.7971 0.8170 0.0 0.0 0.0 0.8947 0.8790 0.8867
0.0284 2.7078 12800 0.0561 0.9795 0.9905 0.9922 0.9913 0.8467 0.8251 0.8358 0.9062 0.9021 0.9041 0.8353 0.7971 0.8158 0.0 0.0 0.0 0.8947 0.8791 0.8868
0.0289 2.7290 12900 0.0560 0.9796 0.9906 0.9921 0.9913 0.8457 0.8269 0.8362 0.9065 0.9033 0.9049 0.8408 0.8 0.8199 0.0 0.0 0.0 0.8959 0.8806 0.8881
0.0283 2.7502 13000 0.0562 0.9795 0.9907 0.9920 0.9913 0.8439 0.8278 0.8357 0.9058 0.9038 0.9048 0.8408 0.8 0.8199 0.0 0.0 0.0 0.8953 0.8809 0.8880
0.029 2.7713 13100 0.0562 0.9796 0.9906 0.9920 0.9913 0.8449 0.8279 0.8363 0.9067 0.9030 0.9049 0.8363 0.8029 0.8192 0.0 0.0 0.0 0.8947 0.8815 0.8879
0.0281 2.7925 13200 0.0563 0.9795 0.9906 0.9921 0.9913 0.8457 0.8263 0.8359 0.9064 0.9035 0.9049 0.8333 0.8 0.8163 0.0 0.0 0.0 0.8940 0.8805 0.8871
0.0277 2.8136 13300 0.0563 0.9795 0.9907 0.9919 0.9913 0.8441 0.8286 0.8363 0.9058 0.9041 0.9050 0.8358 0.8 0.8175 0.0 0.0 0.0 0.8941 0.8812 0.8875
0.0287 2.8348 13400 0.0562 0.9795 0.9907 0.9919 0.9913 0.8430 0.8290 0.8359 0.9066 0.9032 0.9049 0.8358 0.8 0.8175 0.0 0.0 0.0 0.8940 0.8810 0.8874
0.0286 2.8559 13500 0.0562 0.9796 0.9907 0.9919 0.9913 0.8433 0.8293 0.8362 0.9064 0.9041 0.9053 0.8353 0.7971 0.8158 0.0 0.0 0.0 0.8939 0.8806 0.8871
0.0287 2.8771 13600 0.0562 0.9795 0.9906 0.9919 0.9913 0.8440 0.8282 0.8360 0.9066 0.9032 0.9049 0.8328 0.7971 0.8146 0.0 0.0 0.0 0.8935 0.8801 0.8867
0.0284 2.8982 13700 0.0562 0.9795 0.9906 0.9920 0.9913 0.8444 0.8275 0.8359 0.9064 0.9035 0.9049 0.8304 0.7971 0.8134 0.0 0.0 0.0 0.8929 0.8800 0.8864
0.028 2.9194 13800 0.0562 0.9795 0.9906 0.9920 0.9913 0.8437 0.8274 0.8355 0.9065 0.9022 0.9044 0.8304 0.7971 0.8134 0.0 0.0 0.0 0.8928 0.8797 0.8861
0.0279 2.9406 13900 0.0562 0.9795 0.9906 0.9920 0.9913 0.8441 0.8277 0.8358 0.9066 0.9025 0.9045 0.8309 0.8 0.8151 0.0 0.0 0.0 0.8930 0.8805 0.8867
0.028 2.9617 14000 0.0562 0.9795 0.9906 0.9920 0.9913 0.8442 0.8277 0.8358 0.9066 0.9025 0.9045 0.8309 0.8 0.8151 0.0 0.0 0.0 0.8931 0.8805 0.8867
0.0288 2.9829 14100 0.0562 0.9795 0.9906 0.9920 0.9913 0.8441 0.8277 0.8358 0.9066 0.9025 0.9045 0.8309 0.8 0.8151 0.0 0.0 0.0 0.8930 0.8805 0.8867

Framework versions

  • Transformers 4.49.0.dev0
  • Pytorch 2.6.0+cu124
  • Datasets 3.3.0
  • Tokenizers 0.21.0
Downloads last month
6
Safetensors
Model size
396M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for whooray/modernbert_punctuation_64

Finetuned
(75)
this model