<!-- 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_lr5e-6_e_200
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: 0.7893
- Accuracy: 0.78
- Brier Loss: 0.3364
- Nll: 1.4430
- F1 Micro: 0.78
- F1 Macro: 0.7488
- Ece: 0.1922
- Aurc: 0.1018
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-06
- 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: 0.1
- 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 | 0.7450 | 0.815 | 0.3079 | 1.1882 | 0.815 | 0.7942 | 0.2383 | 0.0734 |
No log | 2.0 | 25 | 0.7440 | 0.815 | 0.3074 | 1.1877 | 0.815 | 0.7922 | 0.2303 | 0.0734 |
No log | 2.96 | 37 | 0.7429 | 0.81 | 0.3071 | 1.1883 | 0.81 | 0.7914 | 0.2367 | 0.0714 |
No log | 4.0 | 50 | 0.7463 | 0.815 | 0.3083 | 1.1912 | 0.815 | 0.7942 | 0.2334 | 0.0768 |
No log | 4.96 | 62 | 0.7453 | 0.815 | 0.3080 | 1.1927 | 0.815 | 0.7922 | 0.2224 | 0.0751 |
No log | 6.0 | 75 | 0.7416 | 0.81 | 0.3067 | 1.1870 | 0.81 | 0.7914 | 0.2232 | 0.0716 |
No log | 6.96 | 87 | 0.7420 | 0.81 | 0.3070 | 1.1858 | 0.81 | 0.7914 | 0.2309 | 0.0730 |
No log | 8.0 | 100 | 0.7409 | 0.81 | 0.3062 | 1.1879 | 0.81 | 0.7871 | 0.2186 | 0.0749 |
No log | 8.96 | 112 | 0.7444 | 0.815 | 0.3079 | 1.1984 | 0.815 | 0.8059 | 0.2342 | 0.0766 |
No log | 10.0 | 125 | 0.7445 | 0.81 | 0.3079 | 1.1918 | 0.81 | 0.7894 | 0.2353 | 0.0775 |
No log | 10.96 | 137 | 0.7451 | 0.81 | 0.3085 | 1.1888 | 0.81 | 0.7871 | 0.2319 | 0.0784 |
No log | 12.0 | 150 | 0.7411 | 0.805 | 0.3060 | 1.1914 | 0.805 | 0.7829 | 0.2186 | 0.0779 |
No log | 12.96 | 162 | 0.7406 | 0.815 | 0.3075 | 1.1967 | 0.815 | 0.8057 | 0.2472 | 0.0746 |
No log | 14.0 | 175 | 0.7360 | 0.805 | 0.3048 | 1.2494 | 0.805 | 0.7841 | 0.2383 | 0.0770 |
No log | 14.96 | 187 | 0.7331 | 0.81 | 0.3037 | 1.1896 | 0.81 | 0.7912 | 0.2306 | 0.0721 |
No log | 16.0 | 200 | 0.7345 | 0.81 | 0.3042 | 1.2488 | 0.81 | 0.7956 | 0.2064 | 0.0794 |
No log | 16.96 | 212 | 0.7329 | 0.815 | 0.3018 | 1.2595 | 0.815 | 0.8043 | 0.2331 | 0.0797 |
No log | 18.0 | 225 | 0.7354 | 0.795 | 0.3055 | 1.1743 | 0.795 | 0.7765 | 0.2154 | 0.0742 |
No log | 18.96 | 237 | 0.7282 | 0.805 | 0.3001 | 1.1920 | 0.805 | 0.7844 | 0.2444 | 0.0748 |
No log | 20.0 | 250 | 0.7225 | 0.805 | 0.2981 | 1.1804 | 0.805 | 0.7874 | 0.2041 | 0.0744 |
No log | 20.96 | 262 | 0.7250 | 0.81 | 0.3000 | 1.2516 | 0.81 | 0.7900 | 0.2148 | 0.0761 |
No log | 22.0 | 275 | 0.7252 | 0.81 | 0.3009 | 1.3033 | 0.81 | 0.7954 | 0.2375 | 0.0782 |
No log | 22.96 | 287 | 0.7293 | 0.8 | 0.3016 | 1.2557 | 0.8000 | 0.7796 | 0.2243 | 0.0810 |
No log | 24.0 | 300 | 0.7344 | 0.805 | 0.3057 | 1.3122 | 0.805 | 0.7853 | 0.2096 | 0.0815 |
No log | 24.96 | 312 | 0.7314 | 0.81 | 0.3044 | 1.2501 | 0.81 | 0.7909 | 0.2068 | 0.0808 |
No log | 26.0 | 325 | 0.7293 | 0.81 | 0.3036 | 1.3066 | 0.81 | 0.7909 | 0.2015 | 0.0804 |
No log | 26.96 | 337 | 0.7323 | 0.805 | 0.3042 | 1.3147 | 0.805 | 0.7853 | 0.2242 | 0.0827 |
No log | 28.0 | 350 | 0.7288 | 0.805 | 0.3029 | 1.3109 | 0.805 | 0.7853 | 0.1976 | 0.0826 |
No log | 28.96 | 362 | 0.7343 | 0.805 | 0.3058 | 1.3108 | 0.805 | 0.7853 | 0.2128 | 0.0851 |
No log | 30.0 | 375 | 0.7351 | 0.8 | 0.3062 | 1.3129 | 0.8000 | 0.7733 | 0.2088 | 0.0845 |
No log | 30.96 | 387 | 0.7301 | 0.8 | 0.3044 | 1.2452 | 0.8000 | 0.7733 | 0.2272 | 0.0836 |
No log | 32.0 | 400 | 0.7340 | 0.8 | 0.3055 | 1.3769 | 0.8000 | 0.7806 | 0.2207 | 0.0855 |
No log | 32.96 | 412 | 0.7322 | 0.805 | 0.3052 | 1.3132 | 0.805 | 0.7784 | 0.2470 | 0.0865 |
No log | 34.0 | 425 | 0.7301 | 0.8 | 0.3045 | 1.2543 | 0.8000 | 0.7733 | 0.2021 | 0.0863 |
No log | 34.96 | 437 | 0.7297 | 0.8 | 0.3046 | 1.3056 | 0.8000 | 0.7731 | 0.1886 | 0.0836 |
No log | 36.0 | 450 | 0.7326 | 0.805 | 0.3056 | 1.3102 | 0.805 | 0.7784 | 0.2256 | 0.0892 |
No log | 36.96 | 462 | 0.7311 | 0.8 | 0.3046 | 1.3681 | 0.8000 | 0.7733 | 0.2065 | 0.0880 |
No log | 38.0 | 475 | 0.7356 | 0.8 | 0.3077 | 1.3666 | 0.8000 | 0.7733 | 0.2034 | 0.0895 |
No log | 38.96 | 487 | 0.7302 | 0.8 | 0.3042 | 1.3114 | 0.8000 | 0.7733 | 0.1996 | 0.0894 |
0.1528 | 40.0 | 500 | 0.7289 | 0.805 | 0.3035 | 1.3669 | 0.805 | 0.7797 | 0.1951 | 0.0874 |
0.1528 | 40.96 | 512 | 0.7292 | 0.8 | 0.3037 | 1.3685 | 0.8000 | 0.7737 | 0.2103 | 0.0878 |
0.1528 | 42.0 | 525 | 0.7347 | 0.805 | 0.3077 | 1.3640 | 0.805 | 0.7784 | 0.2005 | 0.0894 |
0.1528 | 42.96 | 537 | 0.7343 | 0.805 | 0.3063 | 1.3684 | 0.805 | 0.7784 | 0.2055 | 0.0899 |
0.1528 | 44.0 | 550 | 0.7283 | 0.805 | 0.3038 | 1.3660 | 0.805 | 0.7797 | 0.2142 | 0.0881 |
0.1528 | 44.96 | 562 | 0.7325 | 0.805 | 0.3061 | 1.3658 | 0.805 | 0.7784 | 0.1967 | 0.0896 |
0.1528 | 46.0 | 575 | 0.7303 | 0.81 | 0.3049 | 1.3659 | 0.81 | 0.7844 | 0.1985 | 0.0883 |
0.1528 | 46.96 | 587 | 0.7321 | 0.805 | 0.3054 | 1.3657 | 0.805 | 0.7797 | 0.1925 | 0.0888 |
0.1528 | 48.0 | 600 | 0.7322 | 0.8 | 0.3054 | 1.3680 | 0.8000 | 0.7704 | 0.1837 | 0.0903 |
0.1528 | 48.96 | 612 | 0.7368 | 0.8 | 0.3079 | 1.3234 | 0.8000 | 0.7704 | 0.2111 | 0.0905 |
0.1528 | 50.0 | 625 | 0.7358 | 0.8 | 0.3074 | 1.3682 | 0.8000 | 0.7704 | 0.1971 | 0.0899 |
0.1528 | 50.96 | 637 | 0.7318 | 0.8 | 0.3054 | 1.3661 | 0.8000 | 0.7704 | 0.2111 | 0.0889 |
0.1528 | 52.0 | 650 | 0.7473 | 0.795 | 0.3133 | 1.3707 | 0.795 | 0.7660 | 0.2032 | 0.0954 |
0.1528 | 52.96 | 662 | 0.7299 | 0.805 | 0.3050 | 1.3631 | 0.805 | 0.7797 | 0.1977 | 0.0891 |
0.1528 | 54.0 | 675 | 0.7427 | 0.795 | 0.3116 | 1.3673 | 0.795 | 0.7644 | 0.2181 | 0.0923 |
0.1528 | 54.96 | 687 | 0.7371 | 0.8 | 0.3087 | 1.3648 | 0.8000 | 0.7704 | 0.1984 | 0.0902 |
0.1528 | 56.0 | 700 | 0.7399 | 0.8 | 0.3100 | 1.3671 | 0.8000 | 0.7704 | 0.2178 | 0.0920 |
0.1528 | 56.96 | 712 | 0.7420 | 0.8 | 0.3114 | 1.3671 | 0.8000 | 0.7689 | 0.2035 | 0.0925 |
0.1528 | 58.0 | 725 | 0.7380 | 0.8 | 0.3088 | 1.3646 | 0.8000 | 0.7704 | 0.2016 | 0.0916 |
0.1528 | 58.96 | 737 | 0.7390 | 0.8 | 0.3091 | 1.3671 | 0.8000 | 0.7704 | 0.2005 | 0.0921 |
0.1528 | 60.0 | 750 | 0.7370 | 0.8 | 0.3085 | 1.3651 | 0.8000 | 0.7704 | 0.1891 | 0.0908 |
0.1528 | 60.96 | 762 | 0.7388 | 0.8 | 0.3097 | 1.3622 | 0.8000 | 0.7704 | 0.2010 | 0.0906 |
0.1528 | 62.0 | 775 | 0.7403 | 0.795 | 0.3102 | 1.3691 | 0.795 | 0.7654 | 0.2142 | 0.0910 |
0.1528 | 62.96 | 787 | 0.7390 | 0.8 | 0.3088 | 1.3950 | 0.8000 | 0.7684 | 0.2058 | 0.0910 |
0.1528 | 64.0 | 800 | 0.7431 | 0.795 | 0.3110 | 1.3722 | 0.795 | 0.7656 | 0.1959 | 0.0914 |
0.1528 | 64.96 | 812 | 0.7429 | 0.8 | 0.3117 | 1.3673 | 0.8000 | 0.7704 | 0.1933 | 0.0925 |
0.1528 | 66.0 | 825 | 0.7419 | 0.8 | 0.3115 | 1.3663 | 0.8000 | 0.7704 | 0.1986 | 0.0913 |
0.1528 | 66.96 | 837 | 0.7434 | 0.8 | 0.3120 | 1.3672 | 0.8000 | 0.7704 | 0.1929 | 0.0927 |
0.1528 | 68.0 | 850 | 0.7414 | 0.8 | 0.3115 | 1.3649 | 0.8000 | 0.7704 | 0.1988 | 0.0923 |
0.1528 | 68.96 | 862 | 0.7448 | 0.8 | 0.3129 | 1.3685 | 0.8000 | 0.7704 | 0.2251 | 0.0928 |
0.1528 | 70.0 | 875 | 0.7450 | 0.8 | 0.3130 | 1.3657 | 0.8000 | 0.7704 | 0.1969 | 0.0934 |
0.1528 | 70.96 | 887 | 0.7464 | 0.8 | 0.3132 | 1.3686 | 0.8000 | 0.7704 | 0.1988 | 0.0946 |
0.1528 | 72.0 | 900 | 0.7465 | 0.8 | 0.3138 | 1.3682 | 0.8000 | 0.7707 | 0.2015 | 0.0935 |
0.1528 | 72.96 | 912 | 0.7471 | 0.8 | 0.3142 | 1.3685 | 0.8000 | 0.7696 | 0.2093 | 0.0936 |
0.1528 | 74.0 | 925 | 0.7476 | 0.8 | 0.3145 | 1.3685 | 0.8000 | 0.7704 | 0.2120 | 0.0942 |
0.1528 | 74.96 | 937 | 0.7433 | 0.8 | 0.3126 | 1.3655 | 0.8000 | 0.7696 | 0.1907 | 0.0918 |
0.1528 | 76.0 | 950 | 0.7519 | 0.8 | 0.3166 | 1.3683 | 0.8000 | 0.7704 | 0.2111 | 0.0949 |
0.1528 | 76.96 | 962 | 0.7485 | 0.8 | 0.3152 | 1.3679 | 0.8000 | 0.7696 | 0.2035 | 0.0942 |
0.1528 | 78.0 | 975 | 0.7496 | 0.8 | 0.3155 | 1.3716 | 0.8000 | 0.7704 | 0.1931 | 0.0940 |
0.1528 | 78.96 | 987 | 0.7513 | 0.8 | 0.3163 | 1.3684 | 0.8000 | 0.7704 | 0.1888 | 0.0952 |
0.1059 | 80.0 | 1000 | 0.7490 | 0.8 | 0.3157 | 1.3707 | 0.8000 | 0.7691 | 0.2118 | 0.0943 |
0.1059 | 80.96 | 1012 | 0.7482 | 0.8 | 0.3151 | 1.3687 | 0.8000 | 0.7696 | 0.2060 | 0.0945 |
0.1059 | 82.0 | 1025 | 0.7516 | 0.8 | 0.3163 | 1.3682 | 0.8000 | 0.7704 | 0.2248 | 0.0950 |
0.1059 | 82.96 | 1037 | 0.7527 | 0.8 | 0.3174 | 1.3660 | 0.8000 | 0.7707 | 0.2204 | 0.0948 |
0.1059 | 84.0 | 1050 | 0.7495 | 0.8 | 0.3156 | 1.3663 | 0.8000 | 0.7704 | 0.2067 | 0.0939 |
0.1059 | 84.96 | 1062 | 0.7506 | 0.8 | 0.3161 | 1.3659 | 0.8000 | 0.7707 | 0.2086 | 0.0947 |
0.1059 | 86.0 | 1075 | 0.7537 | 0.8 | 0.3179 | 1.3687 | 0.8000 | 0.7698 | 0.2001 | 0.0955 |
0.1059 | 86.96 | 1087 | 0.7525 | 0.8 | 0.3172 | 1.3693 | 0.8000 | 0.7696 | 0.2096 | 0.0947 |
0.1059 | 88.0 | 1100 | 0.7535 | 0.8 | 0.3175 | 1.3675 | 0.8000 | 0.7704 | 0.2091 | 0.0951 |
0.1059 | 88.96 | 1112 | 0.7525 | 0.8 | 0.3172 | 1.3680 | 0.8000 | 0.7696 | 0.2009 | 0.0946 |
0.1059 | 90.0 | 1125 | 0.7566 | 0.8 | 0.3190 | 1.3725 | 0.8000 | 0.7698 | 0.1881 | 0.0964 |
0.1059 | 90.96 | 1137 | 0.7578 | 0.8 | 0.3195 | 1.3726 | 0.8000 | 0.7704 | 0.1880 | 0.0968 |
0.1059 | 92.0 | 1150 | 0.7560 | 0.8 | 0.3186 | 1.3715 | 0.8000 | 0.7707 | 0.2095 | 0.0969 |
0.1059 | 92.96 | 1162 | 0.7623 | 0.795 | 0.3219 | 1.3765 | 0.795 | 0.7681 | 0.1907 | 0.0979 |
0.1059 | 94.0 | 1175 | 0.7567 | 0.8 | 0.3192 | 1.3709 | 0.8000 | 0.7698 | 0.2000 | 0.0953 |
0.1059 | 94.96 | 1187 | 0.7538 | 0.8 | 0.3181 | 1.3708 | 0.8000 | 0.7691 | 0.1986 | 0.0958 |
0.1059 | 96.0 | 1200 | 0.7530 | 0.8 | 0.3175 | 1.3725 | 0.8000 | 0.7693 | 0.2122 | 0.0958 |
0.1059 | 96.96 | 1212 | 0.7607 | 0.8 | 0.3207 | 1.3730 | 0.8000 | 0.7709 | 0.1906 | 0.0972 |
0.1059 | 98.0 | 1225 | 0.7647 | 0.79 | 0.3229 | 1.3411 | 0.79 | 0.7633 | 0.1889 | 0.0984 |
0.1059 | 98.96 | 1237 | 0.7568 | 0.79 | 0.3191 | 1.4425 | 0.79 | 0.7644 | 0.1911 | 0.0976 |
0.1059 | 100.0 | 1250 | 0.7586 | 0.8 | 0.3200 | 1.4486 | 0.8000 | 0.7696 | 0.2009 | 0.0952 |
0.1059 | 100.96 | 1262 | 0.7552 | 0.8 | 0.3192 | 1.3728 | 0.8000 | 0.7696 | 0.1962 | 0.0953 |
0.1059 | 102.0 | 1275 | 0.7601 | 0.8 | 0.3217 | 1.4309 | 0.8000 | 0.7691 | 0.2071 | 0.0969 |
0.1059 | 102.96 | 1287 | 0.7608 | 0.795 | 0.3213 | 1.3702 | 0.795 | 0.7668 | 0.2068 | 0.0967 |
0.1059 | 104.0 | 1300 | 0.7590 | 0.795 | 0.3202 | 1.3748 | 0.795 | 0.7668 | 0.1922 | 0.0967 |
0.1059 | 104.96 | 1312 | 0.7626 | 0.795 | 0.3222 | 1.3775 | 0.795 | 0.7673 | 0.1917 | 0.0974 |
0.1059 | 106.0 | 1325 | 0.7632 | 0.795 | 0.3228 | 1.3765 | 0.795 | 0.7664 | 0.2072 | 0.0977 |
0.1059 | 106.96 | 1337 | 0.7612 | 0.795 | 0.3223 | 1.3764 | 0.795 | 0.7666 | 0.2011 | 0.0974 |
0.1059 | 108.0 | 1350 | 0.7669 | 0.79 | 0.3246 | 1.3777 | 0.79 | 0.7639 | 0.2005 | 0.0981 |
0.1059 | 108.96 | 1362 | 0.7658 | 0.795 | 0.3238 | 1.3782 | 0.795 | 0.7673 | 0.2099 | 0.0983 |
0.1059 | 110.0 | 1375 | 0.7632 | 0.79 | 0.3232 | 1.3766 | 0.79 | 0.7639 | 0.2002 | 0.0978 |
0.1059 | 110.96 | 1387 | 0.7651 | 0.79 | 0.3236 | 1.3758 | 0.79 | 0.7580 | 0.2134 | 0.0980 |
0.1059 | 112.0 | 1400 | 0.7649 | 0.79 | 0.3235 | 1.3765 | 0.79 | 0.7583 | 0.1975 | 0.0982 |
0.1059 | 112.96 | 1412 | 0.7683 | 0.79 | 0.3253 | 1.3759 | 0.79 | 0.7639 | 0.1913 | 0.0986 |
0.1059 | 114.0 | 1425 | 0.7682 | 0.795 | 0.3253 | 1.3778 | 0.795 | 0.7668 | 0.1986 | 0.0984 |
0.1059 | 114.96 | 1437 | 0.7666 | 0.79 | 0.3245 | 1.3771 | 0.79 | 0.7639 | 0.1838 | 0.0976 |
0.1059 | 116.0 | 1450 | 0.7685 | 0.79 | 0.3255 | 1.3802 | 0.79 | 0.7639 | 0.1962 | 0.0988 |
0.1059 | 116.96 | 1462 | 0.7676 | 0.785 | 0.3249 | 1.3783 | 0.785 | 0.7554 | 0.2011 | 0.0991 |
0.1059 | 118.0 | 1475 | 0.7704 | 0.785 | 0.3262 | 1.3789 | 0.785 | 0.7516 | 0.2098 | 0.0995 |
0.1059 | 118.96 | 1487 | 0.7701 | 0.785 | 0.3262 | 1.3806 | 0.785 | 0.7554 | 0.2167 | 0.0991 |
0.0842 | 120.0 | 1500 | 0.7708 | 0.79 | 0.3267 | 1.3815 | 0.79 | 0.7639 | 0.1934 | 0.0990 |
0.0842 | 120.96 | 1512 | 0.7710 | 0.785 | 0.3265 | 1.3790 | 0.785 | 0.7516 | 0.1928 | 0.0995 |
0.0842 | 122.0 | 1525 | 0.7728 | 0.79 | 0.3274 | 1.3830 | 0.79 | 0.7639 | 0.1917 | 0.0996 |
0.0842 | 122.96 | 1537 | 0.7708 | 0.785 | 0.3267 | 1.3826 | 0.785 | 0.7554 | 0.2057 | 0.0992 |
0.0842 | 124.0 | 1550 | 0.7698 | 0.785 | 0.3262 | 1.3777 | 0.785 | 0.7554 | 0.2021 | 0.0996 |
0.0842 | 124.96 | 1562 | 0.7706 | 0.785 | 0.3267 | 1.3825 | 0.785 | 0.7554 | 0.1949 | 0.0994 |
0.0842 | 126.0 | 1575 | 0.7751 | 0.79 | 0.3290 | 1.3827 | 0.79 | 0.7639 | 0.1945 | 0.1002 |
0.0842 | 126.96 | 1587 | 0.7734 | 0.79 | 0.3282 | 1.3855 | 0.79 | 0.7639 | 0.1882 | 0.0998 |
0.0842 | 128.0 | 1600 | 0.7753 | 0.785 | 0.3290 | 1.3842 | 0.785 | 0.7554 | 0.1926 | 0.1006 |
0.0842 | 128.96 | 1612 | 0.7731 | 0.78 | 0.3278 | 1.3808 | 0.78 | 0.7488 | 0.2115 | 0.0994 |
0.0842 | 130.0 | 1625 | 0.7723 | 0.78 | 0.3276 | 1.3830 | 0.78 | 0.7486 | 0.2005 | 0.0994 |
0.0842 | 130.96 | 1637 | 0.7746 | 0.78 | 0.3287 | 1.3810 | 0.78 | 0.7488 | 0.2103 | 0.0999 |
0.0842 | 132.0 | 1650 | 0.7758 | 0.78 | 0.3291 | 1.3848 | 0.78 | 0.7488 | 0.2138 | 0.1004 |
0.0842 | 132.96 | 1662 | 0.7771 | 0.78 | 0.3299 | 1.3833 | 0.78 | 0.7488 | 0.2080 | 0.1007 |
0.0842 | 134.0 | 1675 | 0.7757 | 0.78 | 0.3295 | 1.3837 | 0.78 | 0.7488 | 0.2060 | 0.0999 |
0.0842 | 134.96 | 1687 | 0.7754 | 0.78 | 0.3292 | 1.3836 | 0.78 | 0.7488 | 0.2070 | 0.1001 |
0.0842 | 136.0 | 1700 | 0.7755 | 0.78 | 0.3294 | 1.3834 | 0.78 | 0.7488 | 0.2057 | 0.0999 |
0.0842 | 136.96 | 1712 | 0.7755 | 0.78 | 0.3295 | 1.3874 | 0.78 | 0.7488 | 0.1999 | 0.0998 |
0.0842 | 138.0 | 1725 | 0.7759 | 0.78 | 0.3296 | 1.4380 | 0.78 | 0.7488 | 0.2007 | 0.1002 |
0.0842 | 138.96 | 1737 | 0.7776 | 0.78 | 0.3303 | 1.3868 | 0.78 | 0.7488 | 0.2091 | 0.1002 |
0.0842 | 140.0 | 1750 | 0.7780 | 0.78 | 0.3304 | 1.3868 | 0.78 | 0.7488 | 0.2086 | 0.1005 |
0.0842 | 140.96 | 1762 | 0.7780 | 0.78 | 0.3306 | 1.3855 | 0.78 | 0.7488 | 0.2065 | 0.1001 |
0.0842 | 142.0 | 1775 | 0.7789 | 0.78 | 0.3311 | 1.3855 | 0.78 | 0.7488 | 0.2067 | 0.1003 |
0.0842 | 142.96 | 1787 | 0.7798 | 0.78 | 0.3314 | 1.3856 | 0.78 | 0.7488 | 0.2083 | 0.1010 |
0.0842 | 144.0 | 1800 | 0.7799 | 0.78 | 0.3315 | 1.3914 | 0.78 | 0.7488 | 0.2161 | 0.1004 |
0.0842 | 144.96 | 1812 | 0.7806 | 0.78 | 0.3317 | 1.3857 | 0.78 | 0.7488 | 0.2024 | 0.1008 |
0.0842 | 146.0 | 1825 | 0.7817 | 0.78 | 0.3322 | 1.3947 | 0.78 | 0.7488 | 0.2043 | 0.1009 |
0.0842 | 146.96 | 1837 | 0.7815 | 0.78 | 0.3324 | 1.3898 | 0.78 | 0.7488 | 0.2118 | 0.1006 |
0.0842 | 148.0 | 1850 | 0.7820 | 0.78 | 0.3326 | 1.3874 | 0.78 | 0.7488 | 0.2114 | 0.1008 |
0.0842 | 148.96 | 1862 | 0.7821 | 0.78 | 0.3327 | 1.4391 | 0.78 | 0.7488 | 0.2087 | 0.1006 |
0.0842 | 150.0 | 1875 | 0.7816 | 0.78 | 0.3324 | 1.4410 | 0.78 | 0.7488 | 0.2160 | 0.1006 |
0.0842 | 150.96 | 1887 | 0.7826 | 0.78 | 0.3328 | 1.3927 | 0.78 | 0.7488 | 0.2011 | 0.1007 |
0.0842 | 152.0 | 1900 | 0.7834 | 0.78 | 0.3332 | 1.4411 | 0.78 | 0.7488 | 0.1994 | 0.1009 |
0.0842 | 152.96 | 1912 | 0.7830 | 0.78 | 0.3331 | 1.4409 | 0.78 | 0.7488 | 0.1967 | 0.1008 |
0.0842 | 154.0 | 1925 | 0.7825 | 0.78 | 0.3329 | 1.4412 | 0.78 | 0.7488 | 0.2070 | 0.1008 |
0.0842 | 154.96 | 1937 | 0.7827 | 0.78 | 0.3332 | 1.4399 | 0.78 | 0.7488 | 0.2097 | 0.1007 |
0.0842 | 156.0 | 1950 | 0.7822 | 0.78 | 0.3329 | 1.4391 | 0.78 | 0.7488 | 0.1986 | 0.1006 |
0.0842 | 156.96 | 1962 | 0.7838 | 0.78 | 0.3335 | 1.4414 | 0.78 | 0.7488 | 0.1967 | 0.1007 |
0.0842 | 158.0 | 1975 | 0.7845 | 0.78 | 0.3337 | 1.3899 | 0.78 | 0.7488 | 0.2087 | 0.1008 |
0.0842 | 158.96 | 1987 | 0.7846 | 0.78 | 0.3340 | 1.4419 | 0.78 | 0.7488 | 0.2002 | 0.1007 |
0.0731 | 160.0 | 2000 | 0.7853 | 0.78 | 0.3343 | 1.4419 | 0.78 | 0.7488 | 0.1967 | 0.1010 |
0.0731 | 160.96 | 2012 | 0.7853 | 0.78 | 0.3343 | 1.4425 | 0.78 | 0.7488 | 0.1963 | 0.1012 |
0.0731 | 162.0 | 2025 | 0.7846 | 0.78 | 0.3341 | 1.4411 | 0.78 | 0.7488 | 0.1998 | 0.1008 |
0.0731 | 162.96 | 2037 | 0.7856 | 0.78 | 0.3345 | 1.4419 | 0.78 | 0.7488 | 0.2000 | 0.1011 |
0.0731 | 164.0 | 2050 | 0.7863 | 0.78 | 0.3348 | 1.4425 | 0.78 | 0.7488 | 0.1991 | 0.1014 |
0.0731 | 164.96 | 2062 | 0.7863 | 0.78 | 0.3349 | 1.4414 | 0.78 | 0.7488 | 0.1969 | 0.1013 |
0.0731 | 166.0 | 2075 | 0.7865 | 0.78 | 0.3349 | 1.4425 | 0.78 | 0.7488 | 0.1994 | 0.1015 |
0.0731 | 166.96 | 2087 | 0.7863 | 0.78 | 0.3349 | 1.4412 | 0.78 | 0.7488 | 0.1966 | 0.1015 |
0.0731 | 168.0 | 2100 | 0.7870 | 0.78 | 0.3352 | 1.4431 | 0.78 | 0.7488 | 0.1944 | 0.1016 |
0.0731 | 168.96 | 2112 | 0.7868 | 0.78 | 0.3351 | 1.4425 | 0.78 | 0.7488 | 0.1919 | 0.1017 |
0.0731 | 170.0 | 2125 | 0.7873 | 0.78 | 0.3354 | 1.4424 | 0.78 | 0.7488 | 0.1965 | 0.1017 |
0.0731 | 170.96 | 2137 | 0.7870 | 0.78 | 0.3352 | 1.4418 | 0.78 | 0.7488 | 0.2081 | 0.1014 |
0.0731 | 172.0 | 2150 | 0.7879 | 0.78 | 0.3356 | 1.4431 | 0.78 | 0.7488 | 0.1922 | 0.1017 |
0.0731 | 172.96 | 2162 | 0.7874 | 0.78 | 0.3355 | 1.4421 | 0.78 | 0.7488 | 0.1967 | 0.1015 |
0.0731 | 174.0 | 2175 | 0.7872 | 0.78 | 0.3355 | 1.4418 | 0.78 | 0.7488 | 0.1965 | 0.1016 |
0.0731 | 174.96 | 2187 | 0.7882 | 0.78 | 0.3358 | 1.4433 | 0.78 | 0.7488 | 0.1945 | 0.1017 |
0.0731 | 176.0 | 2200 | 0.7882 | 0.78 | 0.3358 | 1.4423 | 0.78 | 0.7488 | 0.1969 | 0.1016 |
0.0731 | 176.96 | 2212 | 0.7885 | 0.78 | 0.3361 | 1.4431 | 0.78 | 0.7488 | 0.1948 | 0.1017 |
0.0731 | 178.0 | 2225 | 0.7883 | 0.78 | 0.3359 | 1.4428 | 0.78 | 0.7488 | 0.1946 | 0.1017 |
0.0731 | 178.96 | 2237 | 0.7882 | 0.78 | 0.3359 | 1.4426 | 0.78 | 0.7488 | 0.1920 | 0.1017 |
0.0731 | 180.0 | 2250 | 0.7884 | 0.78 | 0.3360 | 1.4425 | 0.78 | 0.7488 | 0.2000 | 0.1016 |
0.0731 | 180.96 | 2262 | 0.7886 | 0.78 | 0.3361 | 1.4431 | 0.78 | 0.7488 | 0.1946 | 0.1017 |
0.0731 | 182.0 | 2275 | 0.7888 | 0.78 | 0.3362 | 1.4428 | 0.78 | 0.7488 | 0.1977 | 0.1016 |
0.0731 | 182.96 | 2287 | 0.7889 | 0.78 | 0.3362 | 1.4428 | 0.78 | 0.7488 | 0.1922 | 0.1017 |
0.0731 | 184.0 | 2300 | 0.7889 | 0.78 | 0.3362 | 1.4431 | 0.78 | 0.7488 | 0.1946 | 0.1017 |
0.0731 | 184.96 | 2312 | 0.7889 | 0.78 | 0.3362 | 1.4427 | 0.78 | 0.7488 | 0.1946 | 0.1017 |
0.0731 | 186.0 | 2325 | 0.7889 | 0.78 | 0.3362 | 1.4431 | 0.78 | 0.7488 | 0.1922 | 0.1018 |
0.0731 | 186.96 | 2337 | 0.7892 | 0.78 | 0.3364 | 1.4432 | 0.78 | 0.7488 | 0.1921 | 0.1017 |
0.0731 | 188.0 | 2350 | 0.7890 | 0.78 | 0.3363 | 1.4427 | 0.78 | 0.7488 | 0.1921 | 0.1017 |
0.0731 | 188.96 | 2362 | 0.7892 | 0.78 | 0.3364 | 1.4429 | 0.78 | 0.7488 | 0.1922 | 0.1017 |
0.0731 | 190.0 | 2375 | 0.7893 | 0.78 | 0.3364 | 1.4433 | 0.78 | 0.7488 | 0.1945 | 0.1017 |
0.0731 | 190.96 | 2387 | 0.7893 | 0.78 | 0.3364 | 1.4430 | 0.78 | 0.7488 | 0.1921 | 0.1017 |
0.0731 | 192.0 | 2400 | 0.7893 | 0.78 | 0.3364 | 1.4430 | 0.78 | 0.7488 | 0.1922 | 0.1018 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.13.1
- Datasets 2.13.1
- Tokenizers 0.13.3