--- license: apache-2.0 base_model: microsoft/swinv2-tiny-patch4-window8-256 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swinv2-tiny-patch4-window8-256-mineral results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.24666666666666667 --- # swinv2-tiny-patch4-window8-256-mineral This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 5.2045 - Accuracy: 0.2467 ## 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: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:------:|:----:|:---------------:|:--------:| | 5.692 | 0.96 | 18 | 5.6904 | 0.0017 | | 5.6759 | 1.97 | 37 | 5.6829 | 0.0017 | | 5.6699 | 2.99 | 56 | 5.6722 | 0.0033 | | 5.6484 | 4.0 | 75 | 5.6601 | 0.0033 | | 5.6355 | 4.96 | 93 | 5.6486 | 0.005 | | 5.6088 | 5.97 | 112 | 5.6375 | 0.0067 | | 5.5941 | 6.99 | 131 | 5.6268 | 0.0083 | | 5.5636 | 8.0 | 150 | 5.6131 | 0.0117 | | 5.5499 | 8.96 | 168 | 5.5987 | 0.0117 | | 5.5038 | 9.97 | 187 | 5.5798 | 0.0083 | | 5.437 | 10.99 | 206 | 5.5757 | 0.0133 | | 5.3642 | 12.0 | 225 | 5.5482 | 0.0133 | | 5.2877 | 12.96 | 243 | 5.5107 | 0.0183 | | 5.1992 | 13.97 | 262 | 5.4744 | 0.025 | | 5.0956 | 14.99 | 281 | 5.4006 | 0.0333 | | 4.9566 | 16.0 | 300 | 5.3490 | 0.0433 | | 4.8827 | 16.96 | 318 | 5.2856 | 0.0517 | | 4.7089 | 17.97 | 337 | 5.1565 | 0.075 | | 4.5187 | 18.99 | 356 | 5.0459 | 0.0817 | | 4.4164 | 20.0 | 375 | 4.9614 | 0.0983 | | 4.2402 | 20.96 | 393 | 4.8814 | 0.0983 | | 4.0046 | 21.97 | 412 | 4.7763 | 0.1167 | | 3.8336 | 22.99 | 431 | 4.6775 | 0.125 | | 3.6379 | 24.0 | 450 | 4.6089 | 0.14 | | 3.4647 | 24.96 | 468 | 4.5512 | 0.1433 | | 3.3663 | 25.97 | 487 | 4.4674 | 0.1533 | | 3.1445 | 26.99 | 506 | 4.4247 | 0.15 | | 3.0248 | 28.0 | 525 | 4.3519 | 0.1633 | | 2.8415 | 28.96 | 543 | 4.3256 | 0.1633 | | 2.6664 | 29.97 | 562 | 4.3015 | 0.18 | | 2.5225 | 30.99 | 581 | 4.2571 | 0.1867 | | 2.4433 | 32.0 | 600 | 4.2507 | 0.1833 | | 2.3169 | 32.96 | 618 | 4.2097 | 0.1933 | | 2.145 | 33.97 | 637 | 4.1741 | 0.1883 | | 2.0045 | 34.99 | 656 | 4.1681 | 0.1967 | | 1.9272 | 36.0 | 675 | 4.1376 | 0.2083 | | 1.7761 | 36.96 | 693 | 4.1391 | 0.1933 | | 1.7038 | 37.97 | 712 | 4.0957 | 0.205 | | 1.5902 | 38.99 | 731 | 4.1309 | 0.2067 | | 1.4921 | 40.0 | 750 | 4.1324 | 0.2033 | | 1.3552 | 40.96 | 768 | 4.1510 | 0.2067 | | 1.2597 | 41.97 | 787 | 4.1636 | 0.205 | | 1.2909 | 42.99 | 806 | 4.1422 | 0.2267 | | 1.1661 | 44.0 | 825 | 4.1553 | 0.21 | | 1.1031 | 44.96 | 843 | 4.1976 | 0.2167 | | 1.0203 | 45.97 | 862 | 4.1673 | 0.2183 | | 0.9883 | 46.99 | 881 | 4.1628 | 0.2167 | | 0.976 | 48.0 | 900 | 4.1852 | 0.2267 | | 0.8848 | 48.96 | 918 | 4.2108 | 0.2167 | | 0.8616 | 49.97 | 937 | 4.2583 | 0.2133 | | 0.8079 | 50.99 | 956 | 4.1821 | 0.23 | | 0.8256 | 52.0 | 975 | 4.2021 | 0.2217 | | 0.7439 | 52.96 | 993 | 4.2577 | 0.2167 | | 0.6863 | 53.97 | 1012 | 4.2398 | 0.225 | | 0.715 | 54.99 | 1031 | 4.2934 | 0.21 | | 0.6924 | 56.0 | 1050 | 4.2675 | 0.225 | | 0.6454 | 56.96 | 1068 | 4.2916 | 0.2117 | | 0.5688 | 57.97 | 1087 | 4.3216 | 0.2217 | | 0.5958 | 58.99 | 1106 | 4.3202 | 0.2133 | | 0.5834 | 60.0 | 1125 | 4.3022 | 0.2267 | | 0.5583 | 60.96 | 1143 | 4.3746 | 0.225 | | 0.565 | 61.97 | 1162 | 4.3334 | 0.215 | | 0.55 | 62.99 | 1181 | 4.3330 | 0.2217 | | 0.4972 | 64.0 | 1200 | 4.3866 | 0.2183 | | 0.4895 | 64.96 | 1218 | 4.3797 | 0.2267 | | 0.4537 | 65.97 | 1237 | 4.3761 | 0.2267 | | 0.4941 | 66.99 | 1256 | 4.4122 | 0.2317 | | 0.4422 | 68.0 | 1275 | 4.4636 | 0.2217 | | 0.3731 | 68.96 | 1293 | 4.4118 | 0.2217 | | 0.4338 | 69.97 | 1312 | 4.4002 | 0.2217 | | 0.4482 | 70.99 | 1331 | 4.4558 | 0.2233 | | 0.4206 | 72.0 | 1350 | 4.4238 | 0.23 | | 0.4009 | 72.96 | 1368 | 4.4717 | 0.2267 | | 0.4297 | 73.97 | 1387 | 4.5047 | 0.23 | | 0.4031 | 74.99 | 1406 | 4.4637 | 0.2233 | | 0.3489 | 76.0 | 1425 | 4.4878 | 0.2183 | | 0.4202 | 76.96 | 1443 | 4.4785 | 0.23 | | 0.3307 | 77.97 | 1462 | 4.4647 | 0.2267 | | 0.3919 | 78.99 | 1481 | 4.5011 | 0.2233 | | 0.3511 | 80.0 | 1500 | 4.4895 | 0.2367 | | 0.334 | 80.96 | 1518 | 4.4878 | 0.2283 | | 0.3958 | 81.97 | 1537 | 4.5025 | 0.2367 | | 0.316 | 82.99 | 1556 | 4.5792 | 0.2317 | | 0.3135 | 84.0 | 1575 | 4.4894 | 0.2333 | | 0.3292 | 84.96 | 1593 | 4.5495 | 0.235 | | 0.3116 | 85.97 | 1612 | 4.5069 | 0.2317 | | 0.3162 | 86.99 | 1631 | 4.5407 | 0.23 | | 0.3173 | 88.0 | 1650 | 4.5997 | 0.2217 | | 0.2857 | 88.96 | 1668 | 4.5476 | 0.2283 | | 0.2869 | 89.97 | 1687 | 4.5655 | 0.2217 | | 0.299 | 90.99 | 1706 | 4.5743 | 0.24 | | 0.3142 | 92.0 | 1725 | 4.5478 | 0.23 | | 0.3066 | 92.96 | 1743 | 4.5509 | 0.2367 | | 0.2542 | 93.97 | 1762 | 4.5452 | 0.225 | | 0.2707 | 94.99 | 1781 | 4.5017 | 0.225 | | 0.2781 | 96.0 | 1800 | 4.5425 | 0.23 | | 0.2611 | 96.96 | 1818 | 4.6214 | 0.2233 | | 0.2816 | 97.97 | 1837 | 4.5780 | 0.2233 | | 0.2698 | 98.99 | 1856 | 4.5237 | 0.225 | | 0.2568 | 100.0 | 1875 | 4.6262 | 0.2167 | | 0.2925 | 100.96 | 1893 | 4.6138 | 0.2133 | | 0.2542 | 101.97 | 1912 | 4.6329 | 0.22 | | 0.2276 | 102.99 | 1931 | 4.5854 | 0.23 | | 0.2701 | 104.0 | 1950 | 4.5662 | 0.2167 | | 0.2492 | 104.96 | 1968 | 4.6098 | 0.225 | | 0.2394 | 105.97 | 1987 | 4.6215 | 0.2333 | | 0.2409 | 106.99 | 2006 | 4.6277 | 0.2317 | | 0.2578 | 108.0 | 2025 | 4.6173 | 0.2267 | | 0.229 | 108.96 | 2043 | 4.6405 | 0.2283 | | 0.2438 | 109.97 | 2062 | 4.6041 | 0.2233 | | 0.2441 | 110.99 | 2081 | 4.6367 | 0.23 | | 0.2353 | 112.0 | 2100 | 4.5877 | 0.2467 | | 0.1876 | 112.96 | 2118 | 4.6518 | 0.2333 | | 0.1996 | 113.97 | 2137 | 4.6810 | 0.2367 | | 0.1908 | 114.99 | 2156 | 4.6483 | 0.245 | | 0.1905 | 116.0 | 2175 | 4.6117 | 0.22 | | 0.1995 | 116.96 | 2193 | 4.6283 | 0.2183 | | 0.2044 | 117.97 | 2212 | 4.6130 | 0.2283 | | 0.2156 | 118.99 | 2231 | 4.6729 | 0.2167 | | 0.2003 | 120.0 | 2250 | 4.6124 | 0.24 | | 0.1861 | 120.96 | 2268 | 4.6839 | 0.23 | | 0.2072 | 121.97 | 2287 | 4.7217 | 0.2267 | | 0.1973 | 122.99 | 2306 | 4.7596 | 0.23 | | 0.2191 | 124.0 | 2325 | 4.7394 | 0.2283 | | 0.1738 | 124.96 | 2343 | 4.7356 | 0.23 | | 0.1669 | 125.97 | 2362 | 4.7210 | 0.235 | | 0.1971 | 126.99 | 2381 | 4.6826 | 0.23 | | 0.1972 | 128.0 | 2400 | 4.7256 | 0.2233 | | 0.1794 | 128.96 | 2418 | 4.6589 | 0.235 | | 0.1894 | 129.97 | 2437 | 4.7391 | 0.2317 | | 0.1854 | 130.99 | 2456 | 4.7441 | 0.23 | | 0.1551 | 132.0 | 2475 | 4.7559 | 0.2233 | | 0.179 | 132.96 | 2493 | 4.7555 | 0.235 | | 0.2235 | 133.97 | 2512 | 4.7686 | 0.2183 | | 0.179 | 134.99 | 2531 | 4.7334 | 0.2283 | | 0.1595 | 136.0 | 2550 | 4.7324 | 0.2267 | | 0.1598 | 136.96 | 2568 | 4.7099 | 0.245 | | 0.178 | 137.97 | 2587 | 4.7363 | 0.2317 | | 0.1976 | 138.99 | 2606 | 4.7806 | 0.2217 | | 0.153 | 140.0 | 2625 | 4.8128 | 0.2267 | | 0.1946 | 140.96 | 2643 | 4.7925 | 0.2233 | | 0.1597 | 141.97 | 2662 | 4.8279 | 0.2117 | | 0.1515 | 142.99 | 2681 | 4.8203 | 0.2233 | | 0.2013 | 144.0 | 2700 | 4.7393 | 0.23 | | 0.1431 | 144.96 | 2718 | 4.7866 | 0.2367 | | 0.1864 | 145.97 | 2737 | 4.7730 | 0.2317 | | 0.1676 | 146.99 | 2756 | 4.8112 | 0.2333 | | 0.1502 | 148.0 | 2775 | 4.8374 | 0.215 | | 0.1584 | 148.96 | 2793 | 4.8600 | 0.2317 | | 0.1901 | 149.97 | 2812 | 4.8647 | 0.2167 | | 0.1347 | 150.99 | 2831 | 4.8073 | 0.215 | | 0.1859 | 152.0 | 2850 | 4.8766 | 0.2283 | | 0.1483 | 152.96 | 2868 | 4.8392 | 0.23 | | 0.149 | 153.97 | 2887 | 4.8734 | 0.215 | | 0.1411 | 154.99 | 2906 | 4.9380 | 0.2083 | | 0.1589 | 156.0 | 2925 | 4.8365 | 0.2367 | | 0.1608 | 156.96 | 2943 | 4.8053 | 0.23 | | 0.1759 | 157.97 | 2962 | 4.8690 | 0.2383 | | 0.142 | 158.99 | 2981 | 4.8490 | 0.23 | | 0.1433 | 160.0 | 3000 | 4.8658 | 0.2267 | | 0.1407 | 160.96 | 3018 | 4.8936 | 0.2267 | | 0.1442 | 161.97 | 3037 | 4.8534 | 0.235 | | 0.1669 | 162.99 | 3056 | 4.9050 | 0.2317 | | 0.1384 | 164.0 | 3075 | 4.8717 | 0.235 | | 0.1366 | 164.96 | 3093 | 4.8951 | 0.2317 | | 0.1428 | 165.97 | 3112 | 4.9253 | 0.225 | | 0.1376 | 166.99 | 3131 | 4.9108 | 0.22 | | 0.1238 | 168.0 | 3150 | 4.8965 | 0.2267 | | 0.1129 | 168.96 | 3168 | 4.8446 | 0.2317 | | 0.1296 | 169.97 | 3187 | 4.9100 | 0.2217 | | 0.1383 | 170.99 | 3206 | 4.8886 | 0.2333 | | 0.1511 | 172.0 | 3225 | 4.8883 | 0.235 | | 0.1426 | 172.96 | 3243 | 4.8783 | 0.2333 | | 0.1112 | 173.97 | 3262 | 4.9305 | 0.225 | | 0.1456 | 174.99 | 3281 | 4.8354 | 0.2417 | | 0.1343 | 176.0 | 3300 | 4.8553 | 0.225 | | 0.1133 | 176.96 | 3318 | 4.8739 | 0.2317 | | 0.1213 | 177.97 | 3337 | 4.8865 | 0.2333 | | 0.1309 | 178.99 | 3356 | 4.9231 | 0.22 | | 0.1197 | 180.0 | 3375 | 4.8976 | 0.2383 | | 0.1619 | 180.96 | 3393 | 4.8812 | 0.2383 | | 0.1254 | 181.97 | 3412 | 4.8260 | 0.225 | | 0.0934 | 182.99 | 3431 | 4.8645 | 0.2283 | | 0.1156 | 184.0 | 3450 | 4.8253 | 0.24 | | 0.1008 | 184.96 | 3468 | 4.8692 | 0.2467 | | 0.1273 | 185.97 | 3487 | 4.9049 | 0.24 | | 0.1352 | 186.99 | 3506 | 4.8660 | 0.2333 | | 0.1411 | 188.0 | 3525 | 4.8252 | 0.2333 | | 0.124 | 188.96 | 3543 | 4.8715 | 0.2317 | | 0.1121 | 189.97 | 3562 | 4.8768 | 0.24 | | 0.1337 | 190.99 | 3581 | 4.9004 | 0.2433 | | 0.106 | 192.0 | 3600 | 4.8300 | 0.2333 | | 0.1044 | 192.96 | 3618 | 4.7903 | 0.25 | | 0.1259 | 193.97 | 3637 | 4.8227 | 0.2267 | | 0.1182 | 194.99 | 3656 | 4.8286 | 0.2283 | | 0.1269 | 196.0 | 3675 | 4.8475 | 0.2467 | | 0.1304 | 196.96 | 3693 | 4.8759 | 0.2367 | | 0.1086 | 197.97 | 3712 | 4.8773 | 0.2283 | | 0.1184 | 198.99 | 3731 | 4.8875 | 0.2317 | | 0.114 | 200.0 | 3750 | 4.9083 | 0.2283 | | 0.1028 | 200.96 | 3768 | 4.8888 | 0.2283 | | 0.1355 | 201.97 | 3787 | 4.8358 | 0.23 | | 0.1038 | 202.99 | 3806 | 4.8567 | 0.23 | | 0.1122 | 204.0 | 3825 | 4.8578 | 0.2317 | | 0.0864 | 204.96 | 3843 | 4.9288 | 0.2333 | | 0.0969 | 205.97 | 3862 | 4.8940 | 0.2567 | | 0.0986 | 206.99 | 3881 | 4.8632 | 0.2483 | | 0.1291 | 208.0 | 3900 | 4.9114 | 0.2433 | | 0.1244 | 208.96 | 3918 | 4.9076 | 0.2483 | | 0.1112 | 209.97 | 3937 | 4.8954 | 0.245 | | 0.1032 | 210.99 | 3956 | 4.8885 | 0.2433 | | 0.0919 | 212.0 | 3975 | 4.9197 | 0.2433 | | 0.1153 | 212.96 | 3993 | 4.9020 | 0.25 | | 0.0978 | 213.97 | 4012 | 4.9312 | 0.2433 | | 0.1316 | 214.99 | 4031 | 4.9504 | 0.2417 | | 0.1222 | 216.0 | 4050 | 4.9403 | 0.2367 | | 0.1108 | 216.96 | 4068 | 4.8719 | 0.2483 | | 0.0996 | 217.97 | 4087 | 4.8812 | 0.24 | | 0.0907 | 218.99 | 4106 | 4.9203 | 0.25 | | 0.0974 | 220.0 | 4125 | 4.9728 | 0.2417 | | 0.1127 | 220.96 | 4143 | 4.9708 | 0.2467 | | 0.0891 | 221.97 | 4162 | 5.0154 | 0.2517 | | 0.0973 | 222.99 | 4181 | 4.9533 | 0.24 | | 0.0912 | 224.0 | 4200 | 4.9306 | 0.2333 | | 0.0971 | 224.96 | 4218 | 4.9873 | 0.2283 | | 0.1069 | 225.97 | 4237 | 4.9154 | 0.2433 | | 0.1163 | 226.99 | 4256 | 4.9178 | 0.2367 | | 0.1139 | 228.0 | 4275 | 4.9395 | 0.2383 | | 0.0816 | 228.96 | 4293 | 4.8986 | 0.2333 | | 0.0899 | 229.97 | 4312 | 4.9542 | 0.2517 | | 0.0984 | 230.99 | 4331 | 4.9305 | 0.2433 | | 0.0732 | 232.0 | 4350 | 4.9264 | 0.2417 | | 0.0947 | 232.96 | 4368 | 4.9676 | 0.235 | | 0.0826 | 233.97 | 4387 | 5.0179 | 0.235 | | 0.086 | 234.99 | 4406 | 4.9719 | 0.2283 | | 0.1055 | 236.0 | 4425 | 4.9457 | 0.235 | | 0.0872 | 236.96 | 4443 | 4.9355 | 0.2533 | | 0.0826 | 237.97 | 4462 | 4.9467 | 0.245 | | 0.081 | 238.99 | 4481 | 5.0036 | 0.245 | | 0.0746 | 240.0 | 4500 | 5.0125 | 0.245 | | 0.0725 | 240.96 | 4518 | 5.0061 | 0.2367 | | 0.1104 | 241.97 | 4537 | 5.0150 | 0.2483 | | 0.0885 | 242.99 | 4556 | 5.0063 | 0.2333 | | 0.0847 | 244.0 | 4575 | 4.9919 | 0.2383 | | 0.0751 | 244.96 | 4593 | 4.9881 | 0.2367 | | 0.0872 | 245.97 | 4612 | 5.0013 | 0.2383 | | 0.0771 | 246.99 | 4631 | 5.0273 | 0.235 | | 0.0941 | 248.0 | 4650 | 5.0507 | 0.2317 | | 0.116 | 248.96 | 4668 | 5.0491 | 0.245 | | 0.0733 | 249.97 | 4687 | 5.0391 | 0.24 | | 0.0821 | 250.99 | 4706 | 5.0231 | 0.235 | | 0.075 | 252.0 | 4725 | 5.0388 | 0.2317 | | 0.0885 | 252.96 | 4743 | 4.9838 | 0.2383 | | 0.0759 | 253.97 | 4762 | 4.9536 | 0.2433 | | 0.0773 | 254.99 | 4781 | 5.0145 | 0.2383 | | 0.0707 | 256.0 | 4800 | 5.0352 | 0.2217 | | 0.0861 | 256.96 | 4818 | 5.0295 | 0.2483 | | 0.0739 | 257.97 | 4837 | 5.0354 | 0.2433 | | 0.0822 | 258.99 | 4856 | 5.0563 | 0.245 | | 0.0681 | 260.0 | 4875 | 5.0407 | 0.245 | | 0.0872 | 260.96 | 4893 | 5.0511 | 0.2367 | | 0.079 | 261.97 | 4912 | 5.1087 | 0.23 | | 0.0733 | 262.99 | 4931 | 5.0523 | 0.225 | | 0.097 | 264.0 | 4950 | 5.0368 | 0.2317 | | 0.0669 | 264.96 | 4968 | 5.0501 | 0.2283 | | 0.0801 | 265.97 | 4987 | 5.0515 | 0.235 | | 0.0894 | 266.99 | 5006 | 5.0182 | 0.245 | | 0.0815 | 268.0 | 5025 | 5.0713 | 0.23 | | 0.0934 | 268.96 | 5043 | 5.0082 | 0.2417 | | 0.0728 | 269.97 | 5062 | 5.0473 | 0.23 | | 0.088 | 270.99 | 5081 | 5.0689 | 0.2267 | | 0.0706 | 272.0 | 5100 | 5.0403 | 0.2383 | | 0.0931 | 272.96 | 5118 | 5.0298 | 0.235 | | 0.0784 | 273.97 | 5137 | 5.0141 | 0.2367 | | 0.0831 | 274.99 | 5156 | 5.0314 | 0.2417 | | 0.0624 | 276.0 | 5175 | 5.0445 | 0.2383 | | 0.0819 | 276.96 | 5193 | 5.0632 | 0.2517 | | 0.0714 | 277.97 | 5212 | 5.0520 | 0.255 | | 0.0893 | 278.99 | 5231 | 5.0075 | 0.2533 | | 0.0777 | 280.0 | 5250 | 5.0122 | 0.24 | | 0.0686 | 280.96 | 5268 | 5.0477 | 0.2333 | | 0.0849 | 281.97 | 5287 | 5.0238 | 0.2433 | | 0.0969 | 282.99 | 5306 | 5.0061 | 0.2383 | | 0.0906 | 284.0 | 5325 | 5.0771 | 0.2517 | | 0.0843 | 284.96 | 5343 | 5.0882 | 0.2417 | | 0.0538 | 285.97 | 5362 | 5.0800 | 0.2467 | | 0.0678 | 286.99 | 5381 | 5.0976 | 0.2367 | | 0.0729 | 288.0 | 5400 | 5.0817 | 0.2333 | | 0.0922 | 288.96 | 5418 | 5.0955 | 0.2433 | | 0.0684 | 289.97 | 5437 | 5.0873 | 0.2467 | | 0.082 | 290.99 | 5456 | 5.1424 | 0.2383 | | 0.0798 | 292.0 | 5475 | 5.0631 | 0.2433 | | 0.0781 | 292.96 | 5493 | 5.0474 | 0.2517 | | 0.0857 | 293.97 | 5512 | 5.0502 | 0.2417 | | 0.0733 | 294.99 | 5531 | 5.0599 | 0.235 | | 0.072 | 296.0 | 5550 | 5.0549 | 0.2433 | | 0.101 | 296.96 | 5568 | 5.0783 | 0.24 | | 0.0982 | 297.97 | 5587 | 5.1048 | 0.24 | | 0.0782 | 298.99 | 5606 | 5.1096 | 0.235 | | 0.0654 | 300.0 | 5625 | 5.1158 | 0.2333 | | 0.0761 | 300.96 | 5643 | 5.0416 | 0.2383 | | 0.079 | 301.97 | 5662 | 5.1202 | 0.235 | | 0.0845 | 302.99 | 5681 | 5.1711 | 0.2333 | | 0.0718 | 304.0 | 5700 | 5.1572 | 0.2383 | | 0.0675 | 304.96 | 5718 | 5.1230 | 0.235 | | 0.0683 | 305.97 | 5737 | 5.1464 | 0.23 | | 0.0899 | 306.99 | 5756 | 5.0815 | 0.24 | | 0.0692 | 308.0 | 5775 | 5.0867 | 0.2367 | | 0.0843 | 308.96 | 5793 | 5.1006 | 0.2283 | | 0.0742 | 309.97 | 5812 | 5.0545 | 0.2317 | | 0.0689 | 310.99 | 5831 | 5.0509 | 0.2317 | | 0.0714 | 312.0 | 5850 | 5.0536 | 0.2367 | | 0.0669 | 312.96 | 5868 | 5.0488 | 0.2433 | | 0.0726 | 313.97 | 5887 | 5.0903 | 0.2433 | | 0.0509 | 314.99 | 5906 | 5.1158 | 0.2433 | | 0.062 | 316.0 | 5925 | 5.0651 | 0.2417 | | 0.0528 | 316.96 | 5943 | 5.0545 | 0.2467 | | 0.0627 | 317.97 | 5962 | 5.0730 | 0.2417 | | 0.0678 | 318.99 | 5981 | 5.0354 | 0.24 | | 0.0603 | 320.0 | 6000 | 5.0496 | 0.2483 | | 0.0703 | 320.96 | 6018 | 5.0788 | 0.2367 | | 0.0797 | 321.97 | 6037 | 5.1071 | 0.24 | | 0.0914 | 322.99 | 6056 | 5.0996 | 0.24 | | 0.0688 | 324.0 | 6075 | 5.0954 | 0.24 | | 0.0591 | 324.96 | 6093 | 5.1014 | 0.245 | | 0.0622 | 325.97 | 6112 | 5.0859 | 0.24 | | 0.0715 | 326.99 | 6131 | 5.0557 | 0.2533 | | 0.0483 | 328.0 | 6150 | 5.1148 | 0.2383 | | 0.0922 | 328.96 | 6168 | 5.1338 | 0.24 | | 0.0588 | 329.97 | 6187 | 5.1553 | 0.245 | | 0.0615 | 330.99 | 6206 | 5.1083 | 0.2483 | | 0.0508 | 332.0 | 6225 | 5.1167 | 0.245 | | 0.0691 | 332.96 | 6243 | 5.1116 | 0.2433 | | 0.0684 | 333.97 | 6262 | 5.1211 | 0.2417 | | 0.0519 | 334.99 | 6281 | 5.1481 | 0.2433 | | 0.0571 | 336.0 | 6300 | 5.1662 | 0.245 | | 0.038 | 336.96 | 6318 | 5.1616 | 0.245 | | 0.0589 | 337.97 | 6337 | 5.1507 | 0.2483 | | 0.0609 | 338.99 | 6356 | 5.1083 | 0.245 | | 0.0484 | 340.0 | 6375 | 5.1392 | 0.2417 | | 0.0842 | 340.96 | 6393 | 5.1476 | 0.2483 | | 0.0569 | 341.97 | 6412 | 5.1547 | 0.245 | | 0.0626 | 342.99 | 6431 | 5.1824 | 0.2383 | | 0.0399 | 344.0 | 6450 | 5.1972 | 0.2417 | | 0.0803 | 344.96 | 6468 | 5.1678 | 0.2433 | | 0.0533 | 345.97 | 6487 | 5.1815 | 0.2417 | | 0.0542 | 346.99 | 6506 | 5.1768 | 0.2383 | | 0.0624 | 348.0 | 6525 | 5.1759 | 0.2333 | | 0.055 | 348.96 | 6543 | 5.1954 | 0.2433 | | 0.0678 | 349.97 | 6562 | 5.1478 | 0.2417 | | 0.0557 | 350.99 | 6581 | 5.1236 | 0.24 | | 0.0581 | 352.0 | 6600 | 5.1462 | 0.245 | | 0.0509 | 352.96 | 6618 | 5.1428 | 0.235 | | 0.0636 | 353.97 | 6637 | 5.1659 | 0.24 | | 0.0671 | 354.99 | 6656 | 5.1583 | 0.24 | | 0.0768 | 356.0 | 6675 | 5.1143 | 0.2283 | | 0.0719 | 356.96 | 6693 | 5.1047 | 0.235 | | 0.0653 | 357.97 | 6712 | 5.1262 | 0.2467 | | 0.0646 | 358.99 | 6731 | 5.1456 | 0.245 | | 0.0466 | 360.0 | 6750 | 5.1514 | 0.2517 | | 0.0447 | 360.96 | 6768 | 5.1479 | 0.24 | | 0.0671 | 361.97 | 6787 | 5.1508 | 0.2383 | | 0.0618 | 362.99 | 6806 | 5.1520 | 0.2367 | | 0.0559 | 364.0 | 6825 | 5.1495 | 0.2367 | | 0.0745 | 364.96 | 6843 | 5.1606 | 0.235 | | 0.0542 | 365.97 | 6862 | 5.1888 | 0.235 | | 0.0737 | 366.99 | 6881 | 5.2100 | 0.2417 | | 0.0524 | 368.0 | 6900 | 5.2309 | 0.2317 | | 0.0548 | 368.96 | 6918 | 5.2278 | 0.2283 | | 0.0742 | 369.97 | 6937 | 5.1995 | 0.2383 | | 0.0512 | 370.99 | 6956 | 5.2024 | 0.24 | | 0.0529 | 372.0 | 6975 | 5.1839 | 0.24 | | 0.0647 | 372.96 | 6993 | 5.2155 | 0.2433 | | 0.055 | 373.97 | 7012 | 5.1983 | 0.2417 | | 0.0586 | 374.99 | 7031 | 5.1605 | 0.2467 | | 0.0619 | 376.0 | 7050 | 5.1739 | 0.24 | | 0.0462 | 376.96 | 7068 | 5.1929 | 0.2467 | | 0.0406 | 377.97 | 7087 | 5.2178 | 0.2467 | | 0.0578 | 378.99 | 7106 | 5.2028 | 0.2433 | | 0.0643 | 380.0 | 7125 | 5.1912 | 0.245 | | 0.0442 | 380.96 | 7143 | 5.2069 | 0.2417 | | 0.0642 | 381.97 | 7162 | 5.1740 | 0.2417 | | 0.0423 | 382.99 | 7181 | 5.1597 | 0.2417 | | 0.0663 | 384.0 | 7200 | 5.1497 | 0.2467 | | 0.0539 | 384.96 | 7218 | 5.1274 | 0.2467 | | 0.0426 | 385.97 | 7237 | 5.1322 | 0.24 | | 0.0489 | 386.99 | 7256 | 5.1582 | 0.2433 | | 0.0591 | 388.0 | 7275 | 5.1627 | 0.245 | | 0.0528 | 388.96 | 7293 | 5.1561 | 0.2483 | | 0.0666 | 389.97 | 7312 | 5.1548 | 0.2433 | | 0.053 | 390.99 | 7331 | 5.1537 | 0.2433 | | 0.0546 | 392.0 | 7350 | 5.1460 | 0.25 | | 0.0546 | 392.96 | 7368 | 5.1467 | 0.2467 | | 0.0334 | 393.97 | 7387 | 5.1394 | 0.25 | | 0.0548 | 394.99 | 7406 | 5.1488 | 0.2417 | | 0.0441 | 396.0 | 7425 | 5.1643 | 0.2467 | | 0.0476 | 396.96 | 7443 | 5.1578 | 0.255 | | 0.0602 | 397.97 | 7462 | 5.1754 | 0.2517 | | 0.0455 | 398.99 | 7481 | 5.1758 | 0.2533 | | 0.0364 | 400.0 | 7500 | 5.1471 | 0.255 | | 0.0479 | 400.96 | 7518 | 5.1424 | 0.2517 | | 0.052 | 401.97 | 7537 | 5.1626 | 0.245 | | 0.0521 | 402.99 | 7556 | 5.1680 | 0.2533 | | 0.0527 | 404.0 | 7575 | 5.1557 | 0.2517 | | 0.0534 | 404.96 | 7593 | 5.1781 | 0.2567 | | 0.0431 | 405.97 | 7612 | 5.1900 | 0.2533 | | 0.0506 | 406.99 | 7631 | 5.1651 | 0.2533 | | 0.043 | 408.0 | 7650 | 5.1529 | 0.2567 | | 0.0419 | 408.96 | 7668 | 5.1589 | 0.255 | | 0.0388 | 409.97 | 7687 | 5.1641 | 0.2567 | | 0.0601 | 410.99 | 7706 | 5.1679 | 0.2567 | | 0.0521 | 412.0 | 7725 | 5.1805 | 0.255 | | 0.0564 | 412.96 | 7743 | 5.1811 | 0.2517 | | 0.0395 | 413.97 | 7762 | 5.1670 | 0.2483 | | 0.0542 | 414.99 | 7781 | 5.1530 | 0.2517 | | 0.0482 | 416.0 | 7800 | 5.1599 | 0.2483 | | 0.0597 | 416.96 | 7818 | 5.1715 | 0.2517 | | 0.0579 | 417.97 | 7837 | 5.1748 | 0.2517 | | 0.0331 | 418.99 | 7856 | 5.1811 | 0.25 | | 0.045 | 420.0 | 7875 | 5.1903 | 0.25 | | 0.0424 | 420.96 | 7893 | 5.1830 | 0.2583 | | 0.0474 | 421.97 | 7912 | 5.1867 | 0.2567 | | 0.051 | 422.99 | 7931 | 5.1793 | 0.255 | | 0.0563 | 424.0 | 7950 | 5.1588 | 0.2517 | | 0.039 | 424.96 | 7968 | 5.1612 | 0.2483 | | 0.0722 | 425.97 | 7987 | 5.1692 | 0.2433 | | 0.0492 | 426.99 | 8006 | 5.1873 | 0.245 | | 0.0594 | 428.0 | 8025 | 5.1983 | 0.245 | | 0.0646 | 428.96 | 8043 | 5.2049 | 0.2483 | | 0.0412 | 429.97 | 8062 | 5.1985 | 0.25 | | 0.0493 | 430.99 | 8081 | 5.2013 | 0.24 | | 0.0582 | 432.0 | 8100 | 5.1916 | 0.2467 | | 0.0528 | 432.96 | 8118 | 5.1852 | 0.2483 | | 0.0432 | 433.97 | 8137 | 5.1820 | 0.25 | | 0.0313 | 434.99 | 8156 | 5.1844 | 0.2483 | | 0.048 | 436.0 | 8175 | 5.1884 | 0.2467 | | 0.0591 | 436.96 | 8193 | 5.1952 | 0.2467 | | 0.0379 | 437.97 | 8212 | 5.2027 | 0.25 | | 0.0355 | 438.99 | 8231 | 5.2032 | 0.2517 | | 0.0499 | 440.0 | 8250 | 5.1997 | 0.2533 | | 0.0464 | 440.96 | 8268 | 5.1866 | 0.255 | | 0.0455 | 441.97 | 8287 | 5.1744 | 0.255 | | 0.0429 | 442.99 | 8306 | 5.1745 | 0.2533 | | 0.0532 | 444.0 | 8325 | 5.1885 | 0.2483 | | 0.053 | 444.96 | 8343 | 5.1893 | 0.2517 | | 0.0453 | 445.97 | 8362 | 5.1899 | 0.2467 | | 0.0414 | 446.99 | 8381 | 5.1957 | 0.2433 | | 0.0449 | 448.0 | 8400 | 5.2016 | 0.2433 | | 0.0424 | 448.96 | 8418 | 5.2080 | 0.245 | | 0.0377 | 449.97 | 8437 | 5.2015 | 0.2417 | | 0.0448 | 450.99 | 8456 | 5.1974 | 0.2433 | | 0.0647 | 452.0 | 8475 | 5.1928 | 0.24 | | 0.0549 | 452.96 | 8493 | 5.1991 | 0.24 | | 0.0455 | 453.97 | 8512 | 5.1975 | 0.245 | | 0.0531 | 454.99 | 8531 | 5.1890 | 0.2417 | | 0.0476 | 456.0 | 8550 | 5.1756 | 0.245 | | 0.0366 | 456.96 | 8568 | 5.1726 | 0.2467 | | 0.0534 | 457.97 | 8587 | 5.1726 | 0.2467 | | 0.0521 | 458.99 | 8606 | 5.1757 | 0.2467 | | 0.042 | 460.0 | 8625 | 5.1777 | 0.2467 | | 0.0513 | 460.96 | 8643 | 5.1781 | 0.2483 | | 0.0463 | 461.97 | 8662 | 5.1803 | 0.25 | | 0.0563 | 462.99 | 8681 | 5.1841 | 0.2483 | | 0.0366 | 464.0 | 8700 | 5.1888 | 0.245 | | 0.0439 | 464.96 | 8718 | 5.1896 | 0.2467 | | 0.0645 | 465.97 | 8737 | 5.1916 | 0.2483 | | 0.0358 | 466.99 | 8756 | 5.1958 | 0.25 | | 0.0397 | 468.0 | 8775 | 5.1982 | 0.2467 | | 0.0498 | 468.96 | 8793 | 5.2001 | 0.245 | | 0.0597 | 469.97 | 8812 | 5.2035 | 0.245 | | 0.031 | 470.99 | 8831 | 5.2055 | 0.245 | | 0.0466 | 472.0 | 8850 | 5.2071 | 0.245 | | 0.0406 | 472.96 | 8868 | 5.2064 | 0.245 | | 0.047 | 473.97 | 8887 | 5.2062 | 0.2467 | | 0.0472 | 474.99 | 8906 | 5.2057 | 0.245 | | 0.0392 | 476.0 | 8925 | 5.2060 | 0.2467 | | 0.0314 | 476.96 | 8943 | 5.2054 | 0.2467 | | 0.0411 | 477.97 | 8962 | 5.2049 | 0.2467 | | 0.0427 | 478.99 | 8981 | 5.2046 | 0.2467 | | 0.0469 | 480.0 | 9000 | 5.2045 | 0.2467 | ### Framework versions - Transformers 4.31.0 - Pytorch 1.13.1 - Datasets 2.14.0 - Tokenizers 0.13.3