--- license: mit base_model: roberta-base tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: results results: [] --- # results This model is a fine-tuned version of [roberta-base](https://huggingface.co./roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6970 - Accuracy: 0.7288 - F1: 0.7229 ## 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: 1e-05 - train_batch_size: 16 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| | 1.108 | 0.02 | 10 | 1.1080 | 0.2174 | 0.1291 | | 1.1078 | 0.05 | 20 | 1.1070 | 0.2214 | 0.1295 | | 1.1054 | 0.07 | 30 | 1.1045 | 0.2409 | 0.1356 | | 1.1127 | 0.1 | 40 | 1.0994 | 0.3112 | 0.2653 | | 1.0924 | 0.12 | 50 | 1.0923 | 0.5664 | 0.5046 | | 1.0844 | 0.15 | 60 | 1.0841 | 0.6120 | 0.4647 | | 1.074 | 0.17 | 70 | 1.0756 | 0.6120 | 0.4647 | | 1.0725 | 0.19 | 80 | 1.0660 | 0.6120 | 0.4647 | | 1.0546 | 0.22 | 90 | 1.0541 | 0.6120 | 0.4647 | | 1.0407 | 0.24 | 100 | 1.0401 | 0.6120 | 0.4647 | | 1.0107 | 0.27 | 110 | 1.0227 | 0.6120 | 0.4647 | | 1.0217 | 0.29 | 120 | 1.0030 | 0.6120 | 0.4647 | | 0.9785 | 0.32 | 130 | 0.9774 | 0.6120 | 0.4647 | | 1.0076 | 0.34 | 140 | 0.9498 | 0.6120 | 0.4647 | | 0.9475 | 0.36 | 150 | 0.9313 | 0.6120 | 0.4647 | | 0.8933 | 0.39 | 160 | 0.9104 | 0.6120 | 0.4647 | | 1.0152 | 0.41 | 170 | 0.9052 | 0.6120 | 0.4647 | | 1.0132 | 0.44 | 180 | 0.9086 | 0.6120 | 0.4647 | | 0.9295 | 0.46 | 190 | 0.9178 | 0.6120 | 0.4647 | | 0.9264 | 0.49 | 200 | 0.9104 | 0.6120 | 0.4647 | | 0.9901 | 0.51 | 210 | 0.9087 | 0.6120 | 0.4647 | | 0.9287 | 0.53 | 220 | 0.9140 | 0.6120 | 0.4647 | | 0.9729 | 0.56 | 230 | 0.9108 | 0.6120 | 0.4647 | | 1.0134 | 0.58 | 240 | 0.9184 | 0.6120 | 0.4647 | | 0.9293 | 0.61 | 250 | 0.9016 | 0.6120 | 0.4647 | | 0.9546 | 0.63 | 260 | 0.8928 | 0.6120 | 0.4647 | | 0.9028 | 0.66 | 270 | 0.8910 | 0.6120 | 0.4647 | | 0.8572 | 0.68 | 280 | 0.8872 | 0.6120 | 0.4647 | | 0.9085 | 0.7 | 290 | 0.8813 | 0.6120 | 0.4647 | | 0.9711 | 0.73 | 300 | 0.8845 | 0.6120 | 0.4647 | | 0.8595 | 0.75 | 310 | 0.8768 | 0.6120 | 0.4647 | | 0.8392 | 0.78 | 320 | 0.8635 | 0.6120 | 0.4647 | | 0.8645 | 0.8 | 330 | 0.8700 | 0.6120 | 0.4647 | | 0.886 | 0.83 | 340 | 0.8746 | 0.6120 | 0.4647 | | 0.9011 | 0.85 | 350 | 0.8624 | 0.6120 | 0.4647 | | 0.866 | 0.87 | 360 | 0.8375 | 0.6120 | 0.4647 | | 0.9093 | 0.9 | 370 | 0.8616 | 0.6120 | 0.4647 | | 0.8792 | 0.92 | 380 | 0.8254 | 0.6120 | 0.4647 | | 0.7503 | 0.95 | 390 | 0.8279 | 0.6120 | 0.4647 | | 0.8007 | 0.97 | 400 | 0.8319 | 0.6120 | 0.4647 | | 0.9182 | 1.0 | 410 | 0.8737 | 0.6120 | 0.4647 | | 0.89 | 1.02 | 420 | 0.8689 | 0.6120 | 0.4647 | | 0.8556 | 1.04 | 430 | 0.8321 | 0.6185 | 0.4917 | | 0.8988 | 1.07 | 440 | 0.8146 | 0.6263 | 0.4981 | | 0.8161 | 1.09 | 450 | 0.8289 | 0.6159 | 0.4735 | | 0.8428 | 1.12 | 460 | 0.8441 | 0.6237 | 0.4908 | | 0.8503 | 1.14 | 470 | 0.8284 | 0.6562 | 0.6118 | | 0.7648 | 1.17 | 480 | 0.8277 | 0.6224 | 0.5989 | | 0.8573 | 1.19 | 490 | 0.8402 | 0.6328 | 0.5723 | | 0.7526 | 1.21 | 500 | 0.8147 | 0.6367 | 0.6037 | | 0.8221 | 1.24 | 510 | 0.8205 | 0.6276 | 0.5986 | | 0.83 | 1.26 | 520 | 0.7885 | 0.6471 | 0.5935 | | 0.7811 | 1.29 | 530 | 0.7936 | 0.6497 | 0.6471 | | 0.7587 | 1.31 | 540 | 0.7992 | 0.6510 | 0.6003 | | 0.7823 | 1.33 | 550 | 0.7637 | 0.6589 | 0.6498 | | 0.806 | 1.36 | 560 | 0.7986 | 0.6510 | 0.5994 | | 0.6892 | 1.38 | 570 | 0.7657 | 0.6576 | 0.6338 | | 0.7004 | 1.41 | 580 | 0.7759 | 0.6628 | 0.6604 | | 0.76 | 1.43 | 590 | 0.7915 | 0.6497 | 0.6319 | | 0.7296 | 1.46 | 600 | 0.7696 | 0.6536 | 0.6543 | | 0.7777 | 1.48 | 610 | 0.7408 | 0.6615 | 0.6516 | | 0.689 | 1.5 | 620 | 0.7559 | 0.6732 | 0.6359 | | 0.7462 | 1.53 | 630 | 0.7471 | 0.6641 | 0.6622 | | 0.7586 | 1.55 | 640 | 0.7719 | 0.6602 | 0.6484 | | 0.7149 | 1.58 | 650 | 0.7450 | 0.6615 | 0.6556 | | 0.7634 | 1.6 | 660 | 0.7440 | 0.6615 | 0.6499 | | 0.6967 | 1.63 | 670 | 0.7679 | 0.6615 | 0.6295 | | 0.8081 | 1.65 | 680 | 0.7868 | 0.6497 | 0.6525 | | 0.7743 | 1.67 | 690 | 0.7756 | 0.6471 | 0.6513 | | 0.6511 | 1.7 | 700 | 0.7339 | 0.6966 | 0.6700 | | 0.7563 | 1.72 | 710 | 0.8288 | 0.6107 | 0.6282 | | 0.7533 | 1.75 | 720 | 0.7225 | 0.6784 | 0.6716 | | 0.6474 | 1.77 | 730 | 0.7119 | 0.7070 | 0.6915 | | 0.6677 | 1.8 | 740 | 0.7168 | 0.6992 | 0.6879 | | 0.6215 | 1.82 | 750 | 0.7381 | 0.6823 | 0.6725 | | 0.7862 | 1.84 | 760 | 0.8190 | 0.6380 | 0.6555 | | 0.661 | 1.87 | 770 | 0.7201 | 0.6953 | 0.6803 | | 0.6256 | 1.89 | 780 | 0.7576 | 0.6732 | 0.6558 | | 0.7411 | 1.92 | 790 | 0.8308 | 0.6263 | 0.6354 | | 0.5917 | 1.94 | 800 | 0.7480 | 0.6875 | 0.6627 | | 0.7315 | 1.97 | 810 | 0.7350 | 0.6862 | 0.6777 | | 0.7161 | 1.99 | 820 | 0.7271 | 0.6862 | 0.6789 | | 0.6705 | 2.01 | 830 | 0.7650 | 0.6888 | 0.6583 | | 0.6363 | 2.04 | 840 | 0.7582 | 0.6602 | 0.6668 | | 0.5478 | 2.06 | 850 | 0.7336 | 0.6875 | 0.6760 | | 0.5762 | 2.09 | 860 | 0.7453 | 0.6797 | 0.6756 | | 0.5043 | 2.11 | 870 | 0.7730 | 0.6706 | 0.6751 | | 0.6707 | 2.14 | 880 | 0.7607 | 0.6797 | 0.6795 | | 0.6797 | 2.16 | 890 | 0.7392 | 0.6966 | 0.6903 | | 0.5108 | 2.18 | 900 | 0.7410 | 0.6992 | 0.6777 | | 0.6752 | 2.21 | 910 | 0.7795 | 0.6641 | 0.6701 | | 0.5653 | 2.23 | 920 | 0.7427 | 0.6927 | 0.6897 | | 0.4893 | 2.26 | 930 | 0.7870 | 0.6719 | 0.6800 | | 0.6131 | 2.28 | 940 | 0.7231 | 0.6992 | 0.6908 | | 0.5764 | 2.31 | 950 | 0.7240 | 0.6784 | 0.6764 | | 0.5644 | 2.33 | 960 | 0.7325 | 0.6758 | 0.6808 | | 0.5864 | 2.35 | 970 | 0.7196 | 0.7083 | 0.7077 | | 0.5273 | 2.38 | 980 | 0.7491 | 0.6979 | 0.7000 | | 0.5442 | 2.4 | 990 | 0.7273 | 0.6979 | 0.6962 | | 0.5273 | 2.43 | 1000 | 0.7619 | 0.6940 | 0.6971 | | 0.5559 | 2.45 | 1010 | 0.7602 | 0.6927 | 0.6759 | | 0.5739 | 2.48 | 1020 | 0.8416 | 0.6510 | 0.6620 | | 0.6714 | 2.5 | 1030 | 0.7206 | 0.6901 | 0.6833 | | 0.4798 | 2.52 | 1040 | 0.7417 | 0.6966 | 0.6967 | | 0.5155 | 2.55 | 1050 | 0.7524 | 0.6836 | 0.6756 | | 0.665 | 2.57 | 1060 | 0.7805 | 0.6836 | 0.6851 | | 0.5047 | 2.6 | 1070 | 0.7259 | 0.7005 | 0.6911 | | 0.4928 | 2.62 | 1080 | 0.7296 | 0.7070 | 0.6989 | | 0.6354 | 2.65 | 1090 | 0.7149 | 0.7057 | 0.6942 | | 0.5179 | 2.67 | 1100 | 0.7392 | 0.7005 | 0.7025 | | 0.565 | 2.69 | 1110 | 0.9225 | 0.6211 | 0.6397 | | 0.568 | 2.72 | 1120 | 0.7576 | 0.6927 | 0.6620 | | 0.6313 | 2.74 | 1130 | 0.7672 | 0.6823 | 0.6870 | | 0.5991 | 2.77 | 1140 | 0.7014 | 0.6953 | 0.6949 | | 0.5064 | 2.79 | 1150 | 0.6919 | 0.7201 | 0.7108 | | 0.5132 | 2.82 | 1160 | 0.7176 | 0.7109 | 0.7122 | | 0.4623 | 2.84 | 1170 | 0.7508 | 0.7083 | 0.7116 | | 0.5912 | 2.86 | 1180 | 0.6912 | 0.7188 | 0.7097 | | 0.6299 | 2.89 | 1190 | 0.6937 | 0.7214 | 0.7108 | | 0.526 | 2.91 | 1200 | 0.8388 | 0.6680 | 0.6729 | | 0.6121 | 2.94 | 1210 | 0.7092 | 0.7227 | 0.7078 | | 0.505 | 2.96 | 1220 | 0.7108 | 0.7057 | 0.7069 | | 0.5917 | 2.99 | 1230 | 0.7166 | 0.6992 | 0.6991 | | 0.4392 | 3.01 | 1240 | 0.7017 | 0.7135 | 0.7125 | | 0.3661 | 3.03 | 1250 | 0.7366 | 0.7148 | 0.7077 | | 0.4179 | 3.06 | 1260 | 0.7762 | 0.7135 | 0.7123 | | 0.5012 | 3.08 | 1270 | 0.7817 | 0.6901 | 0.6943 | | 0.455 | 3.11 | 1280 | 0.7387 | 0.7031 | 0.7018 | | 0.45 | 3.13 | 1290 | 0.7666 | 0.6849 | 0.6895 | | 0.3803 | 3.16 | 1300 | 0.7289 | 0.7057 | 0.7055 | | 0.3249 | 3.18 | 1310 | 0.7702 | 0.7057 | 0.7057 | | 0.4053 | 3.2 | 1320 | 0.8736 | 0.6693 | 0.6762 | | 0.6543 | 3.23 | 1330 | 0.7545 | 0.7083 | 0.7046 | | 0.5145 | 3.25 | 1340 | 0.7623 | 0.7044 | 0.7065 | | 0.4317 | 3.28 | 1350 | 0.7426 | 0.7096 | 0.7085 | | 0.3173 | 3.3 | 1360 | 0.7538 | 0.7201 | 0.7088 | | 0.3904 | 3.33 | 1370 | 0.7851 | 0.6966 | 0.7013 | | 0.4739 | 3.35 | 1380 | 0.7529 | 0.7096 | 0.7090 | | 0.3597 | 3.37 | 1390 | 0.7475 | 0.7135 | 0.7049 | | 0.5589 | 3.4 | 1400 | 0.7390 | 0.7057 | 0.7068 | | 0.4127 | 3.42 | 1410 | 0.7603 | 0.6992 | 0.7039 | | 0.4193 | 3.45 | 1420 | 0.7565 | 0.7031 | 0.6982 | | 0.4774 | 3.47 | 1430 | 0.7831 | 0.6966 | 0.6999 | | 0.5156 | 3.5 | 1440 | 0.8372 | 0.6875 | 0.6948 | | 0.4646 | 3.52 | 1450 | 0.7770 | 0.7083 | 0.7079 | | 0.4435 | 3.54 | 1460 | 0.8211 | 0.6914 | 0.6981 | | 0.4664 | 3.57 | 1470 | 0.7730 | 0.7109 | 0.7116 | | 0.4468 | 3.59 | 1480 | 0.7884 | 0.6966 | 0.6972 | | 0.4693 | 3.62 | 1490 | 0.7881 | 0.7018 | 0.7049 | | 0.4677 | 3.64 | 1500 | 0.7521 | 0.7018 | 0.6935 | | 0.3911 | 3.67 | 1510 | 0.8343 | 0.6693 | 0.6750 | | 0.4981 | 3.69 | 1520 | 0.7461 | 0.7057 | 0.7003 | | 0.432 | 3.71 | 1530 | 0.7555 | 0.7227 | 0.7085 | | 0.5283 | 3.74 | 1540 | 0.8265 | 0.6497 | 0.6596 | | 0.4641 | 3.76 | 1550 | 0.7541 | 0.7005 | 0.6920 | | 0.42 | 3.79 | 1560 | 0.7664 | 0.6979 | 0.6916 | | 0.6015 | 3.81 | 1570 | 0.8471 | 0.6484 | 0.6541 | | 0.5301 | 3.83 | 1580 | 0.7240 | 0.6979 | 0.6946 | | 0.4583 | 3.86 | 1590 | 0.7755 | 0.6888 | 0.6921 | | 0.5194 | 3.88 | 1600 | 0.7334 | 0.7122 | 0.7088 | | 0.3624 | 3.91 | 1610 | 0.7659 | 0.6940 | 0.6951 | | 0.543 | 3.93 | 1620 | 0.7718 | 0.6992 | 0.7027 | | 0.3838 | 3.96 | 1630 | 0.7798 | 0.6940 | 0.6994 | | 0.4389 | 3.98 | 1640 | 0.7479 | 0.7201 | 0.7159 | | 0.3009 | 4.0 | 1650 | 0.7924 | 0.7031 | 0.7035 | | 0.3812 | 4.03 | 1660 | 0.8021 | 0.7201 | 0.7186 | | 0.3271 | 4.05 | 1670 | 0.8095 | 0.7188 | 0.7180 | | 0.2551 | 4.08 | 1680 | 0.8355 | 0.7083 | 0.7107 | | 0.3143 | 4.1 | 1690 | 0.8294 | 0.7096 | 0.7109 | | 0.4337 | 4.13 | 1700 | 0.8897 | 0.6823 | 0.6873 | | 0.5192 | 4.15 | 1710 | 0.8754 | 0.6758 | 0.6819 | | 0.278 | 4.17 | 1720 | 0.8021 | 0.7096 | 0.7061 | | 0.2782 | 4.2 | 1730 | 0.8350 | 0.6992 | 0.7031 | | 0.2952 | 4.22 | 1740 | 0.8248 | 0.6966 | 0.6998 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0