<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit-base_tobacco_bs_16_lr_2e-4_e_200_wr_0.01_wd_0.2
This model is a fine-tuned version of jordyvl/vit-base_tobacco on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0644
- Accuracy: 0.86
- Brier Loss: 0.2705
- Nll: 1.3085
- F1 Micro: 0.8600
- F1 Macro: 0.8552
- Ece: 0.1378
- Aurc: 0.0461
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 200
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc |
---|---|---|---|---|---|---|---|---|---|---|
No log | 0.96 | 12 | 0.7869 | 0.78 | 0.3223 | 1.3413 | 0.78 | 0.7402 | 0.2269 | 0.0782 |
No log | 2.0 | 25 | 0.9889 | 0.715 | 0.4300 | 1.9648 | 0.715 | 0.6881 | 0.2669 | 0.1397 |
No log | 2.96 | 37 | 0.7053 | 0.82 | 0.2995 | 1.2578 | 0.82 | 0.8270 | 0.2253 | 0.0758 |
No log | 4.0 | 50 | 0.7535 | 0.78 | 0.3225 | 1.3427 | 0.78 | 0.7395 | 0.2159 | 0.0616 |
No log | 4.96 | 62 | 0.8538 | 0.775 | 0.3634 | 1.5684 | 0.775 | 0.7523 | 0.2181 | 0.1149 |
No log | 6.0 | 75 | 0.7825 | 0.77 | 0.3557 | 1.3406 | 0.7700 | 0.7663 | 0.2136 | 0.0625 |
No log | 6.96 | 87 | 1.0777 | 0.67 | 0.4896 | 1.5465 | 0.67 | 0.6728 | 0.2540 | 0.1106 |
No log | 8.0 | 100 | 1.1030 | 0.73 | 0.4453 | 2.5744 | 0.7300 | 0.6939 | 0.2294 | 0.1423 |
No log | 8.96 | 112 | 1.0215 | 0.725 | 0.4339 | 2.0485 | 0.7250 | 0.7012 | 0.2348 | 0.1278 |
No log | 10.0 | 125 | 0.7940 | 0.795 | 0.3378 | 1.3057 | 0.795 | 0.7911 | 0.1828 | 0.0750 |
No log | 10.96 | 137 | 0.7648 | 0.82 | 0.2963 | 1.3907 | 0.82 | 0.8022 | 0.1597 | 0.0744 |
No log | 12.0 | 150 | 1.0755 | 0.74 | 0.4383 | 2.1271 | 0.74 | 0.7182 | 0.2281 | 0.0847 |
No log | 12.96 | 162 | 1.0091 | 0.775 | 0.3856 | 1.7383 | 0.775 | 0.7339 | 0.1969 | 0.1029 |
No log | 14.0 | 175 | 1.0531 | 0.77 | 0.4027 | 1.5532 | 0.7700 | 0.7592 | 0.2152 | 0.0888 |
No log | 14.96 | 187 | 1.0221 | 0.77 | 0.4027 | 1.5199 | 0.7700 | 0.7259 | 0.2059 | 0.1031 |
No log | 16.0 | 200 | 1.1795 | 0.735 | 0.4435 | 2.0739 | 0.735 | 0.7063 | 0.2262 | 0.1305 |
No log | 16.96 | 212 | 1.1560 | 0.745 | 0.4379 | 2.0155 | 0.745 | 0.7240 | 0.2207 | 0.1273 |
No log | 18.0 | 225 | 1.0635 | 0.76 | 0.4159 | 1.5491 | 0.76 | 0.7508 | 0.2124 | 0.0879 |
No log | 18.96 | 237 | 1.2639 | 0.73 | 0.4649 | 1.9828 | 0.7300 | 0.7276 | 0.2298 | 0.1079 |
No log | 20.0 | 250 | 1.0598 | 0.78 | 0.3866 | 1.5139 | 0.78 | 0.7676 | 0.1885 | 0.0914 |
No log | 20.96 | 262 | 0.8900 | 0.81 | 0.3241 | 1.8355 | 0.81 | 0.7925 | 0.1691 | 0.0648 |
No log | 22.0 | 275 | 1.0617 | 0.79 | 0.3788 | 1.8951 | 0.79 | 0.7783 | 0.1893 | 0.0676 |
No log | 22.96 | 287 | 1.0362 | 0.785 | 0.3646 | 1.9399 | 0.785 | 0.7653 | 0.1914 | 0.0816 |
No log | 24.0 | 300 | 1.1701 | 0.775 | 0.4060 | 2.1593 | 0.775 | 0.7718 | 0.2114 | 0.0842 |
No log | 24.96 | 312 | 1.0841 | 0.79 | 0.3799 | 1.8773 | 0.79 | 0.7795 | 0.2016 | 0.0775 |
No log | 26.0 | 325 | 1.0064 | 0.785 | 0.3650 | 1.7371 | 0.785 | 0.7674 | 0.1915 | 0.0813 |
No log | 26.96 | 337 | 0.8886 | 0.825 | 0.3114 | 1.4858 | 0.825 | 0.8116 | 0.1609 | 0.0636 |
No log | 28.0 | 350 | 1.1174 | 0.8 | 0.3751 | 1.9584 | 0.8000 | 0.7869 | 0.1928 | 0.0930 |
No log | 28.96 | 362 | 1.0922 | 0.8 | 0.3672 | 1.8702 | 0.8000 | 0.7673 | 0.1954 | 0.0771 |
No log | 30.0 | 375 | 1.0281 | 0.805 | 0.3506 | 1.6105 | 0.805 | 0.7809 | 0.1773 | 0.0936 |
No log | 30.96 | 387 | 0.9041 | 0.82 | 0.3210 | 1.3323 | 0.82 | 0.8148 | 0.1627 | 0.0651 |
No log | 32.0 | 400 | 1.1018 | 0.79 | 0.3804 | 1.9928 | 0.79 | 0.7962 | 0.1859 | 0.0574 |
No log | 32.96 | 412 | 1.1973 | 0.765 | 0.4156 | 1.4304 | 0.765 | 0.7682 | 0.2147 | 0.0760 |
No log | 34.0 | 425 | 1.0216 | 0.805 | 0.3605 | 1.4476 | 0.805 | 0.7864 | 0.1830 | 0.0633 |
No log | 34.96 | 437 | 1.2356 | 0.755 | 0.4237 | 1.9897 | 0.755 | 0.7350 | 0.2214 | 0.0890 |
No log | 36.0 | 450 | 1.0881 | 0.8 | 0.3757 | 1.3848 | 0.8000 | 0.7810 | 0.1960 | 0.0703 |
No log | 36.96 | 462 | 1.1133 | 0.795 | 0.3687 | 2.0286 | 0.795 | 0.7707 | 0.1790 | 0.0652 |
No log | 38.0 | 475 | 1.1243 | 0.78 | 0.3839 | 1.5683 | 0.78 | 0.7699 | 0.1905 | 0.0704 |
No log | 38.96 | 487 | 1.1351 | 0.785 | 0.3983 | 1.4970 | 0.785 | 0.7647 | 0.1969 | 0.0666 |
0.0934 | 40.0 | 500 | 1.2551 | 0.775 | 0.4089 | 2.0438 | 0.775 | 0.7688 | 0.2082 | 0.1007 |
0.0934 | 40.96 | 512 | 1.1739 | 0.775 | 0.4003 | 1.3286 | 0.775 | 0.7654 | 0.2056 | 0.0819 |
0.0934 | 42.0 | 525 | 1.0007 | 0.83 | 0.3207 | 1.2576 | 0.83 | 0.8345 | 0.1579 | 0.0677 |
0.0934 | 42.96 | 537 | 1.0509 | 0.805 | 0.3580 | 1.2330 | 0.805 | 0.7933 | 0.1884 | 0.0716 |
0.0934 | 44.0 | 550 | 1.0830 | 0.805 | 0.3537 | 1.7652 | 0.805 | 0.7871 | 0.1740 | 0.0688 |
0.0934 | 44.96 | 562 | 0.8544 | 0.83 | 0.2957 | 1.4716 | 0.83 | 0.8039 | 0.1560 | 0.0532 |
0.0934 | 46.0 | 575 | 1.0803 | 0.815 | 0.3549 | 1.5802 | 0.815 | 0.7951 | 0.1840 | 0.0691 |
0.0934 | 46.96 | 587 | 0.9441 | 0.815 | 0.3318 | 1.2883 | 0.815 | 0.7924 | 0.1709 | 0.0514 |
0.0934 | 48.0 | 600 | 0.9007 | 0.845 | 0.2765 | 1.3443 | 0.845 | 0.8353 | 0.1402 | 0.0539 |
0.0934 | 48.96 | 612 | 0.9601 | 0.84 | 0.2952 | 1.4755 | 0.8400 | 0.8306 | 0.1499 | 0.0565 |
0.0934 | 50.0 | 625 | 0.9801 | 0.84 | 0.2992 | 1.4646 | 0.8400 | 0.8306 | 0.1529 | 0.0559 |
0.0934 | 50.96 | 637 | 0.9747 | 0.845 | 0.2950 | 1.4544 | 0.845 | 0.8338 | 0.1526 | 0.0546 |
0.0934 | 52.0 | 650 | 0.9651 | 0.845 | 0.2895 | 1.4442 | 0.845 | 0.8338 | 0.1469 | 0.0537 |
0.0934 | 52.96 | 662 | 0.9583 | 0.85 | 0.2848 | 1.4367 | 0.85 | 0.8370 | 0.1465 | 0.0525 |
0.0934 | 54.0 | 675 | 0.9534 | 0.85 | 0.2805 | 1.4300 | 0.85 | 0.8370 | 0.1455 | 0.0514 |
0.0934 | 54.96 | 687 | 0.9503 | 0.855 | 0.2776 | 1.4252 | 0.855 | 0.8425 | 0.1408 | 0.0510 |
0.0934 | 56.0 | 700 | 0.9480 | 0.855 | 0.2754 | 1.4207 | 0.855 | 0.8425 | 0.1407 | 0.0506 |
0.0934 | 56.96 | 712 | 0.9471 | 0.855 | 0.2739 | 1.4175 | 0.855 | 0.8425 | 0.1442 | 0.0504 |
0.0934 | 58.0 | 725 | 0.9471 | 0.855 | 0.2729 | 1.4147 | 0.855 | 0.8442 | 0.1435 | 0.0501 |
0.0934 | 58.96 | 737 | 0.9474 | 0.855 | 0.2720 | 1.4125 | 0.855 | 0.8442 | 0.1432 | 0.0497 |
0.0934 | 60.0 | 750 | 0.9482 | 0.855 | 0.2713 | 1.4101 | 0.855 | 0.8442 | 0.1420 | 0.0497 |
0.0934 | 60.96 | 762 | 0.9490 | 0.855 | 0.2708 | 1.4082 | 0.855 | 0.8442 | 0.1421 | 0.0493 |
0.0934 | 62.0 | 775 | 0.9500 | 0.86 | 0.2703 | 1.4063 | 0.8600 | 0.8534 | 0.1411 | 0.0493 |
0.0934 | 62.96 | 787 | 0.9512 | 0.86 | 0.2702 | 1.4046 | 0.8600 | 0.8534 | 0.1410 | 0.0492 |
0.0934 | 64.0 | 800 | 0.9528 | 0.86 | 0.2699 | 1.4032 | 0.8600 | 0.8534 | 0.1408 | 0.0489 |
0.0934 | 64.96 | 812 | 0.9541 | 0.86 | 0.2697 | 1.3472 | 0.8600 | 0.8534 | 0.1349 | 0.0487 |
0.0934 | 66.0 | 825 | 0.9558 | 0.86 | 0.2696 | 1.3431 | 0.8600 | 0.8534 | 0.1408 | 0.0487 |
0.0934 | 66.96 | 837 | 0.9574 | 0.86 | 0.2697 | 1.3403 | 0.8600 | 0.8534 | 0.1405 | 0.0486 |
0.0934 | 68.0 | 850 | 0.9591 | 0.86 | 0.2698 | 1.3375 | 0.8600 | 0.8534 | 0.1402 | 0.0486 |
0.0934 | 68.96 | 862 | 0.9605 | 0.86 | 0.2698 | 1.3355 | 0.8600 | 0.8552 | 0.1394 | 0.0486 |
0.0934 | 70.0 | 875 | 0.9624 | 0.86 | 0.2698 | 1.3338 | 0.8600 | 0.8552 | 0.1394 | 0.0486 |
0.0934 | 70.96 | 887 | 0.9638 | 0.86 | 0.2700 | 1.3322 | 0.8600 | 0.8552 | 0.1397 | 0.0485 |
0.0934 | 72.0 | 900 | 0.9657 | 0.86 | 0.2701 | 1.3310 | 0.8600 | 0.8552 | 0.1397 | 0.0485 |
0.0934 | 72.96 | 912 | 0.9673 | 0.86 | 0.2702 | 1.3299 | 0.8600 | 0.8552 | 0.1397 | 0.0484 |
0.0934 | 74.0 | 925 | 0.9691 | 0.86 | 0.2703 | 1.3289 | 0.8600 | 0.8552 | 0.1397 | 0.0484 |
0.0934 | 74.96 | 937 | 0.9708 | 0.86 | 0.2704 | 1.3280 | 0.8600 | 0.8552 | 0.1398 | 0.0485 |
0.0934 | 76.0 | 950 | 0.9725 | 0.86 | 0.2706 | 1.3271 | 0.8600 | 0.8552 | 0.1398 | 0.0485 |
0.0934 | 76.96 | 962 | 0.9740 | 0.86 | 0.2707 | 1.3263 | 0.8600 | 0.8552 | 0.1398 | 0.0485 |
0.0934 | 78.0 | 975 | 0.9757 | 0.86 | 0.2707 | 1.3256 | 0.8600 | 0.8552 | 0.1383 | 0.0485 |
0.0934 | 78.96 | 987 | 0.9772 | 0.86 | 0.2708 | 1.3248 | 0.8600 | 0.8552 | 0.1357 | 0.0484 |
0.0038 | 80.0 | 1000 | 0.9789 | 0.86 | 0.2709 | 1.3243 | 0.8600 | 0.8552 | 0.1359 | 0.0485 |
0.0038 | 80.96 | 1012 | 0.9806 | 0.86 | 0.2710 | 1.3238 | 0.8600 | 0.8552 | 0.1360 | 0.0484 |
0.0038 | 82.0 | 1025 | 0.9820 | 0.86 | 0.2711 | 1.3232 | 0.8600 | 0.8552 | 0.1361 | 0.0482 |
0.0038 | 82.96 | 1037 | 0.9837 | 0.86 | 0.2712 | 1.3227 | 0.8600 | 0.8552 | 0.1361 | 0.0481 |
0.0038 | 84.0 | 1050 | 0.9853 | 0.86 | 0.2713 | 1.3222 | 0.8600 | 0.8552 | 0.1362 | 0.0480 |
0.0038 | 84.96 | 1062 | 0.9867 | 0.86 | 0.2713 | 1.3216 | 0.8600 | 0.8552 | 0.1363 | 0.0481 |
0.0038 | 86.0 | 1075 | 0.9883 | 0.86 | 0.2714 | 1.3212 | 0.8600 | 0.8552 | 0.1364 | 0.0479 |
0.0038 | 86.96 | 1087 | 0.9896 | 0.86 | 0.2714 | 1.3208 | 0.8600 | 0.8552 | 0.1365 | 0.0477 |
0.0038 | 88.0 | 1100 | 0.9911 | 0.86 | 0.2715 | 1.3203 | 0.8600 | 0.8552 | 0.1366 | 0.0478 |
0.0038 | 88.96 | 1112 | 0.9925 | 0.86 | 0.2715 | 1.3200 | 0.8600 | 0.8552 | 0.1369 | 0.0478 |
0.0038 | 90.0 | 1125 | 0.9940 | 0.86 | 0.2715 | 1.3196 | 0.8600 | 0.8552 | 0.1369 | 0.0477 |
0.0038 | 90.96 | 1137 | 0.9954 | 0.86 | 0.2715 | 1.3194 | 0.8600 | 0.8552 | 0.1369 | 0.0476 |
0.0038 | 92.0 | 1150 | 0.9968 | 0.86 | 0.2716 | 1.3190 | 0.8600 | 0.8552 | 0.1368 | 0.0476 |
0.0038 | 92.96 | 1162 | 0.9983 | 0.86 | 0.2716 | 1.3187 | 0.8600 | 0.8552 | 0.1368 | 0.0476 |
0.0038 | 94.0 | 1175 | 0.9996 | 0.86 | 0.2716 | 1.3184 | 0.8600 | 0.8552 | 0.1394 | 0.0476 |
0.0038 | 94.96 | 1187 | 1.0009 | 0.86 | 0.2716 | 1.3182 | 0.8600 | 0.8552 | 0.1393 | 0.0475 |
0.0038 | 96.0 | 1200 | 1.0023 | 0.86 | 0.2717 | 1.3179 | 0.8600 | 0.8552 | 0.1392 | 0.0475 |
0.0038 | 96.96 | 1212 | 1.0035 | 0.86 | 0.2717 | 1.3176 | 0.8600 | 0.8552 | 0.1391 | 0.0475 |
0.0038 | 98.0 | 1225 | 1.0049 | 0.86 | 0.2717 | 1.3175 | 0.8600 | 0.8552 | 0.1391 | 0.0474 |
0.0038 | 98.96 | 1237 | 1.0062 | 0.86 | 0.2717 | 1.3172 | 0.8600 | 0.8552 | 0.1391 | 0.0475 |
0.0038 | 100.0 | 1250 | 1.0075 | 0.86 | 0.2717 | 1.3169 | 0.8600 | 0.8552 | 0.1367 | 0.0475 |
0.0038 | 100.96 | 1262 | 1.0087 | 0.86 | 0.2717 | 1.3167 | 0.8600 | 0.8552 | 0.1368 | 0.0475 |
0.0038 | 102.0 | 1275 | 1.0099 | 0.86 | 0.2717 | 1.3164 | 0.8600 | 0.8552 | 0.1375 | 0.0474 |
0.0038 | 102.96 | 1287 | 1.0111 | 0.86 | 0.2717 | 1.3162 | 0.8600 | 0.8552 | 0.1376 | 0.0473 |
0.0038 | 104.0 | 1300 | 1.0122 | 0.86 | 0.2717 | 1.3159 | 0.8600 | 0.8552 | 0.1378 | 0.0471 |
0.0038 | 104.96 | 1312 | 1.0134 | 0.86 | 0.2716 | 1.3158 | 0.8600 | 0.8552 | 0.1378 | 0.0473 |
0.0038 | 106.0 | 1325 | 1.0146 | 0.86 | 0.2717 | 1.3155 | 0.8600 | 0.8552 | 0.1379 | 0.0472 |
0.0038 | 106.96 | 1337 | 1.0158 | 0.86 | 0.2717 | 1.3153 | 0.8600 | 0.8552 | 0.1379 | 0.0471 |
0.0038 | 108.0 | 1350 | 1.0169 | 0.86 | 0.2716 | 1.3151 | 0.8600 | 0.8552 | 0.1380 | 0.0471 |
0.0038 | 108.96 | 1362 | 1.0180 | 0.86 | 0.2716 | 1.3149 | 0.8600 | 0.8552 | 0.1381 | 0.0471 |
0.0038 | 110.0 | 1375 | 1.0191 | 0.86 | 0.2716 | 1.3146 | 0.8600 | 0.8552 | 0.1381 | 0.0471 |
0.0038 | 110.96 | 1387 | 1.0201 | 0.86 | 0.2716 | 1.3144 | 0.8600 | 0.8552 | 0.1382 | 0.0471 |
0.0038 | 112.0 | 1400 | 1.0211 | 0.86 | 0.2716 | 1.3142 | 0.8600 | 0.8552 | 0.1382 | 0.0470 |
0.0038 | 112.96 | 1412 | 1.0222 | 0.86 | 0.2716 | 1.3141 | 0.8600 | 0.8552 | 0.1382 | 0.0471 |
0.0038 | 114.0 | 1425 | 1.0233 | 0.86 | 0.2715 | 1.3139 | 0.8600 | 0.8552 | 0.1383 | 0.0470 |
0.0038 | 114.96 | 1437 | 1.0242 | 0.86 | 0.2715 | 1.3138 | 0.8600 | 0.8552 | 0.1383 | 0.0470 |
0.0038 | 116.0 | 1450 | 1.0253 | 0.86 | 0.2715 | 1.3136 | 0.8600 | 0.8552 | 0.1383 | 0.0469 |
0.0038 | 116.96 | 1462 | 1.0263 | 0.86 | 0.2715 | 1.3134 | 0.8600 | 0.8552 | 0.1383 | 0.0470 |
0.0038 | 118.0 | 1475 | 1.0273 | 0.86 | 0.2715 | 1.3133 | 0.8600 | 0.8552 | 0.1384 | 0.0470 |
0.0038 | 118.96 | 1487 | 1.0282 | 0.86 | 0.2714 | 1.3131 | 0.8600 | 0.8552 | 0.1384 | 0.0468 |
0.0006 | 120.0 | 1500 | 1.0292 | 0.86 | 0.2714 | 1.3130 | 0.8600 | 0.8552 | 0.1385 | 0.0468 |
0.0006 | 120.96 | 1512 | 1.0301 | 0.86 | 0.2714 | 1.3128 | 0.8600 | 0.8552 | 0.1385 | 0.0468 |
0.0006 | 122.0 | 1525 | 1.0311 | 0.86 | 0.2714 | 1.3127 | 0.8600 | 0.8552 | 0.1386 | 0.0467 |
0.0006 | 122.96 | 1537 | 1.0319 | 0.86 | 0.2714 | 1.3126 | 0.8600 | 0.8552 | 0.1386 | 0.0467 |
0.0006 | 124.0 | 1550 | 1.0329 | 0.86 | 0.2714 | 1.3124 | 0.8600 | 0.8552 | 0.1387 | 0.0467 |
0.0006 | 124.96 | 1562 | 1.0337 | 0.86 | 0.2713 | 1.3123 | 0.8600 | 0.8552 | 0.1393 | 0.0467 |
0.0006 | 126.0 | 1575 | 1.0346 | 0.86 | 0.2713 | 1.3122 | 0.8600 | 0.8552 | 0.1374 | 0.0466 |
0.0006 | 126.96 | 1587 | 1.0354 | 0.86 | 0.2713 | 1.3120 | 0.8600 | 0.8552 | 0.1375 | 0.0466 |
0.0006 | 128.0 | 1600 | 1.0363 | 0.86 | 0.2713 | 1.3119 | 0.8600 | 0.8552 | 0.1375 | 0.0467 |
0.0006 | 128.96 | 1612 | 1.0372 | 0.86 | 0.2713 | 1.3118 | 0.8600 | 0.8552 | 0.1375 | 0.0466 |
0.0006 | 130.0 | 1625 | 1.0380 | 0.86 | 0.2712 | 1.3117 | 0.8600 | 0.8552 | 0.1375 | 0.0466 |
0.0006 | 130.96 | 1637 | 1.0388 | 0.86 | 0.2712 | 1.3116 | 0.8600 | 0.8552 | 0.1375 | 0.0467 |
0.0006 | 132.0 | 1650 | 1.0396 | 0.86 | 0.2712 | 1.3115 | 0.8600 | 0.8552 | 0.1375 | 0.0465 |
0.0006 | 132.96 | 1662 | 1.0403 | 0.86 | 0.2712 | 1.3113 | 0.8600 | 0.8552 | 0.1375 | 0.0466 |
0.0006 | 134.0 | 1675 | 1.0411 | 0.86 | 0.2712 | 1.3113 | 0.8600 | 0.8552 | 0.1376 | 0.0466 |
0.0006 | 134.96 | 1687 | 1.0419 | 0.86 | 0.2711 | 1.3112 | 0.8600 | 0.8552 | 0.1376 | 0.0466 |
0.0006 | 136.0 | 1700 | 1.0426 | 0.86 | 0.2711 | 1.3111 | 0.8600 | 0.8552 | 0.1376 | 0.0465 |
0.0006 | 136.96 | 1712 | 1.0433 | 0.86 | 0.2711 | 1.3110 | 0.8600 | 0.8552 | 0.1376 | 0.0465 |
0.0006 | 138.0 | 1725 | 1.0441 | 0.86 | 0.2711 | 1.3109 | 0.8600 | 0.8552 | 0.1376 | 0.0465 |
0.0006 | 138.96 | 1737 | 1.0448 | 0.86 | 0.2711 | 1.3108 | 0.8600 | 0.8552 | 0.1376 | 0.0465 |
0.0006 | 140.0 | 1750 | 1.0455 | 0.86 | 0.2710 | 1.3107 | 0.8600 | 0.8552 | 0.1377 | 0.0465 |
0.0006 | 140.96 | 1762 | 1.0461 | 0.86 | 0.2710 | 1.3106 | 0.8600 | 0.8552 | 0.1377 | 0.0465 |
0.0006 | 142.0 | 1775 | 1.0468 | 0.86 | 0.2710 | 1.3106 | 0.8600 | 0.8552 | 0.1377 | 0.0465 |
0.0006 | 142.96 | 1787 | 1.0474 | 0.86 | 0.2710 | 1.3105 | 0.8600 | 0.8552 | 0.1377 | 0.0465 |
0.0006 | 144.0 | 1800 | 1.0481 | 0.86 | 0.2710 | 1.3104 | 0.8600 | 0.8552 | 0.1377 | 0.0465 |
0.0006 | 144.96 | 1812 | 1.0487 | 0.86 | 0.2710 | 1.3103 | 0.8600 | 0.8552 | 0.1378 | 0.0465 |
0.0006 | 146.0 | 1825 | 1.0494 | 0.86 | 0.2709 | 1.3102 | 0.8600 | 0.8552 | 0.1378 | 0.0465 |
0.0006 | 146.96 | 1837 | 1.0500 | 0.86 | 0.2709 | 1.3102 | 0.8600 | 0.8552 | 0.1378 | 0.0465 |
0.0006 | 148.0 | 1850 | 1.0506 | 0.86 | 0.2709 | 1.3101 | 0.8600 | 0.8552 | 0.1378 | 0.0465 |
0.0006 | 148.96 | 1862 | 1.0511 | 0.86 | 0.2709 | 1.3100 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 150.0 | 1875 | 1.0517 | 0.86 | 0.2709 | 1.3099 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 150.96 | 1887 | 1.0523 | 0.86 | 0.2709 | 1.3099 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 152.0 | 1900 | 1.0529 | 0.86 | 0.2708 | 1.3098 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 152.96 | 1912 | 1.0534 | 0.86 | 0.2708 | 1.3097 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 154.0 | 1925 | 1.0539 | 0.86 | 0.2708 | 1.3096 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 154.96 | 1937 | 1.0544 | 0.86 | 0.2708 | 1.3096 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 156.0 | 1950 | 1.0550 | 0.86 | 0.2708 | 1.3095 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 156.96 | 1962 | 1.0554 | 0.86 | 0.2708 | 1.3094 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 158.0 | 1975 | 1.0559 | 0.86 | 0.2707 | 1.3094 | 0.8600 | 0.8552 | 0.1378 | 0.0464 |
0.0006 | 158.96 | 1987 | 1.0563 | 0.86 | 0.2707 | 1.3093 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 160.0 | 2000 | 1.0568 | 0.86 | 0.2707 | 1.3093 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 160.96 | 2012 | 1.0573 | 0.86 | 0.2707 | 1.3092 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 162.0 | 2025 | 1.0577 | 0.86 | 0.2707 | 1.3092 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 162.96 | 2037 | 1.0581 | 0.86 | 0.2707 | 1.3091 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 164.0 | 2050 | 1.0585 | 0.86 | 0.2707 | 1.3091 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 164.96 | 2062 | 1.0589 | 0.86 | 0.2707 | 1.3090 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 166.0 | 2075 | 1.0593 | 0.86 | 0.2707 | 1.3090 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 166.96 | 2087 | 1.0597 | 0.86 | 0.2706 | 1.3089 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 168.0 | 2100 | 1.0600 | 0.86 | 0.2706 | 1.3089 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 168.96 | 2112 | 1.0603 | 0.86 | 0.2706 | 1.3089 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 170.0 | 2125 | 1.0607 | 0.86 | 0.2706 | 1.3088 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 170.96 | 2137 | 1.0610 | 0.86 | 0.2706 | 1.3088 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 172.0 | 2150 | 1.0613 | 0.86 | 0.2706 | 1.3088 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 172.96 | 2162 | 1.0616 | 0.86 | 0.2706 | 1.3087 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 174.0 | 2175 | 1.0619 | 0.86 | 0.2706 | 1.3087 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 174.96 | 2187 | 1.0621 | 0.86 | 0.2706 | 1.3087 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 176.0 | 2200 | 1.0624 | 0.86 | 0.2706 | 1.3087 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 176.96 | 2212 | 1.0626 | 0.86 | 0.2706 | 1.3086 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 178.0 | 2225 | 1.0629 | 0.86 | 0.2706 | 1.3086 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 178.96 | 2237 | 1.0630 | 0.86 | 0.2706 | 1.3086 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 180.0 | 2250 | 1.0632 | 0.86 | 0.2706 | 1.3086 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 180.96 | 2262 | 1.0634 | 0.86 | 0.2706 | 1.3086 | 0.8600 | 0.8552 | 0.1378 | 0.0463 |
0.0004 | 182.0 | 2275 | 1.0636 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 182.96 | 2287 | 1.0637 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 184.0 | 2300 | 1.0639 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 184.96 | 2312 | 1.0640 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 186.0 | 2325 | 1.0641 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 186.96 | 2337 | 1.0642 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0462 |
0.0004 | 188.0 | 2350 | 1.0643 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0461 |
0.0004 | 188.96 | 2362 | 1.0643 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0461 |
0.0004 | 190.0 | 2375 | 1.0644 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0461 |
0.0004 | 190.96 | 2387 | 1.0644 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0461 |
0.0004 | 192.0 | 2400 | 1.0644 | 0.86 | 0.2705 | 1.3085 | 0.8600 | 0.8552 | 0.1378 | 0.0461 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.13.1
- Datasets 2.13.1
- Tokenizers 0.13.3