--- tags: - masked-auto-encoding - generated_from_trainer model-index: - name: monospace-pixel-small results: [] --- # monospace-pixel-small This model is a fine-tuned version of [](https://huggingface.co/) on the wikipedia dataset. It achieves the following results on the evaluation set: - Loss: 0.2340 ## 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: 0.0003 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - total_train_batch_size: 512 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.05 - training_steps: 500000 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:------:|:---------------:| | 0.6779 | 0.02 | 1000 | 0.6512 | | 0.6505 | 0.05 | 2000 | 0.6479 | | 0.6475 | 0.07 | 3000 | 0.6461 | | 0.6464 | 0.09 | 4000 | 0.6451 | | 0.6455 | 0.12 | 5000 | 0.6444 | | 0.6448 | 0.14 | 6000 | 0.6439 | | 0.6222 | 0.16 | 7000 | 0.6123 | | 0.6019 | 0.19 | 8000 | 0.5873 | | 0.5838 | 0.21 | 9000 | 0.5689 | | 0.5612 | 0.23 | 10000 | 0.5473 | | 0.5428 | 0.26 | 11000 | 0.5301 | | 0.527 | 0.28 | 12000 | 0.5141 | | 0.5142 | 0.3 | 13000 | 0.5023 | | 0.5002 | 0.33 | 14000 | 0.4842 | | 0.4852 | 0.35 | 15000 | 0.4707 | | 0.4697 | 0.37 | 16000 | 0.4562 | | 0.459 | 0.4 | 17000 | 0.4430 | | 0.45 | 0.42 | 18000 | 0.4343 | | 0.4411 | 0.44 | 19000 | 0.4250 | | 0.4322 | 0.47 | 20000 | 0.4133 | | 0.4233 | 0.49 | 21000 | 0.4033 | | 0.4146 | 0.51 | 22000 | 0.3944 | | 0.4077 | 0.54 | 23000 | 0.3865 | | 0.4019 | 0.56 | 24000 | 0.3818 | | 0.3968 | 0.58 | 25000 | 0.3785 | | 0.392 | 0.61 | 26000 | 0.3732 | | 0.3869 | 0.63 | 27000 | 0.3670 | | 0.3828 | 0.65 | 28000 | 0.3616 | | 0.3786 | 0.68 | 29000 | 0.3613 | | 0.3751 | 0.7 | 30000 | 0.3555 | | 0.3713 | 0.72 | 31000 | 0.3529 | | 0.3681 | 0.75 | 32000 | 0.3517 | | 0.3656 | 0.77 | 33000 | 0.3477 | | 0.3626 | 0.79 | 34000 | 0.3423 | | 0.3601 | 0.82 | 35000 | 0.3443 | | 0.3577 | 0.84 | 36000 | 0.3400 | | 0.3555 | 0.86 | 37000 | 0.3369 | | 0.3532 | 0.89 | 38000 | 0.3357 | | 0.3514 | 0.91 | 39000 | 0.3329 | | 0.3493 | 0.93 | 40000 | 0.3323 | | 0.3477 | 0.96 | 41000 | 0.3314 | | 0.3459 | 0.98 | 42000 | 0.3256 | | 0.3441 | 1.0 | 43000 | 0.3270 | | 0.3424 | 1.03 | 44000 | 0.3216 | | 0.3408 | 1.05 | 45000 | 0.3245 | | 0.3394 | 1.07 | 46000 | 0.3232 | | 0.338 | 1.1 | 47000 | 0.3225 | | 0.3363 | 1.12 | 48000 | 0.3195 | | 0.3353 | 1.14 | 49000 | 0.3167 | | 0.3338 | 1.16 | 50000 | 0.3172 | | 0.3325 | 1.19 | 51000 | 0.3168 | | 0.3316 | 1.21 | 52000 | 0.3141 | | 0.3305 | 1.23 | 53000 | 0.3114 | | 0.3303 | 1.26 | 54000 | 0.3110 | | 0.3284 | 1.28 | 55000 | 0.3112 | | 0.3276 | 1.3 | 56000 | 0.3099 | | 0.3264 | 1.33 | 57000 | 0.3089 | | 0.3256 | 1.35 | 58000 | 0.3104 | | 0.3247 | 1.37 | 59000 | 0.3088 | | 0.3241 | 1.4 | 60000 | 0.3056 | | 0.3229 | 1.42 | 61000 | 0.3048 | | 0.3223 | 1.44 | 62000 | 0.3062 | | 0.3215 | 1.47 | 63000 | 0.3042 | | 0.3208 | 1.49 | 64000 | 0.3029 | | 0.3201 | 1.51 | 65000 | 0.3009 | | 0.3198 | 1.54 | 66000 | 0.3037 | | 0.3187 | 1.56 | 67000 | 0.3021 | | 0.3179 | 1.58 | 68000 | 0.2990 | | 0.3176 | 1.61 | 69000 | 0.3009 | | 0.3169 | 1.63 | 70000 | 0.3002 | | 0.3161 | 1.65 | 71000 | 0.2997 | | 0.3156 | 1.68 | 72000 | 0.2982 | | 0.3148 | 1.7 | 73000 | 0.2982 | | 0.3143 | 1.72 | 74000 | 0.2961 | | 0.3137 | 1.75 | 75000 | 0.2935 | | 0.3132 | 1.77 | 76000 | 0.2974 | | 0.313 | 1.79 | 77000 | 0.2965 | | 0.3147 | 1.82 | 78000 | 0.2947 | | 0.3118 | 1.84 | 79000 | 0.2940 | | 0.3113 | 1.86 | 80000 | 0.2935 | | 0.3109 | 1.89 | 81000 | 0.2936 | | 0.3103 | 1.91 | 82000 | 0.2913 | | 0.3102 | 1.93 | 83000 | 0.2955 | | 0.3096 | 1.96 | 84000 | 0.2917 | | 0.3093 | 1.98 | 85000 | 0.2931 | | 0.3084 | 2.0 | 86000 | 0.2907 | | 0.3086 | 2.03 | 87000 | 0.2908 | | 0.3077 | 2.05 | 88000 | 0.2881 | | 0.3087 | 2.07 | 89000 | 0.2878 | | 0.3065 | 2.1 | 90000 | 0.2883 | | 0.3063 | 2.12 | 91000 | 0.2891 | | 0.3057 | 2.14 | 92000 | 0.2866 | | 0.3066 | 2.17 | 93000 | 0.2894 | | 0.3048 | 2.19 | 94000 | 0.2859 | | 0.3051 | 2.21 | 95000 | 0.2881 | | 0.3041 | 2.24 | 96000 | 0.2859 | | 0.3039 | 2.26 | 97000 | 0.2837 | | 0.3032 | 2.28 | 98000 | 0.2860 | | 0.3039 | 2.31 | 99000 | 0.2858 | | 0.3025 | 2.33 | 100000 | 0.2849 | | 0.3023 | 2.35 | 101000 | 0.2857 | | 0.3024 | 2.38 | 102000 | 0.2879 | | 0.3018 | 2.4 | 103000 | 0.2866 | | 0.3015 | 2.42 | 104000 | 0.2861 | | 0.301 | 2.45 | 105000 | 0.2853 | | 0.3008 | 2.47 | 106000 | 0.2859 | | 0.3006 | 2.49 | 107000 | 0.2829 | | 0.3003 | 2.52 | 108000 | 0.2835 | | 0.2998 | 2.54 | 109000 | 0.2799 | | 0.3001 | 2.56 | 110000 | 0.2816 | | 0.2991 | 2.59 | 111000 | 0.2831 | | 0.2987 | 2.61 | 112000 | 0.2819 | | 0.2985 | 2.63 | 113000 | 0.2830 | | 0.2981 | 2.66 | 114000 | 0.2824 | | 0.2978 | 2.68 | 115000 | 0.2790 | | 0.2973 | 2.7 | 116000 | 0.2793 | | 0.2977 | 2.73 | 117000 | 0.2807 | | 0.2969 | 2.75 | 118000 | 0.2817 | | 0.2967 | 2.77 | 119000 | 0.2808 | | 0.2965 | 2.8 | 120000 | 0.2787 | | 0.2958 | 2.82 | 121000 | 0.2786 | | 0.2968 | 2.84 | 122000 | 0.2792 | | 0.2956 | 2.87 | 123000 | 0.2779 | | 0.2948 | 2.89 | 124000 | 0.2770 | | 0.2952 | 2.91 | 125000 | 0.2796 | | 0.2943 | 2.94 | 126000 | 0.2771 | | 0.2945 | 2.96 | 127000 | 0.2768 | | 0.2945 | 2.98 | 128000 | 0.2766 | | 0.2944 | 3.01 | 129000 | 0.2760 | | 0.2944 | 3.03 | 130000 | 0.2758 | | 0.2937 | 3.05 | 131000 | 0.2751 | | 0.2935 | 3.08 | 132000 | 0.2737 | | 0.2931 | 3.1 | 133000 | 0.2755 | | 0.2936 | 3.12 | 134000 | 0.2768 | | 0.2934 | 3.15 | 135000 | 0.2776 | | 0.2925 | 3.17 | 136000 | 0.2716 | | 0.2924 | 3.19 | 137000 | 0.2737 | | 0.2931 | 3.22 | 138000 | 0.2753 | | 0.2917 | 3.24 | 139000 | 0.2745 | | 0.2918 | 3.26 | 140000 | 0.2774 | | 0.2914 | 3.29 | 141000 | 0.2756 | | 0.2913 | 3.31 | 142000 | 0.2743 | | 0.2909 | 3.33 | 143000 | 0.2742 | | 0.2911 | 3.36 | 144000 | 0.2735 | | 0.2904 | 3.38 | 145000 | 0.2727 | | 0.2903 | 3.4 | 146000 | 0.2748 | | 0.2899 | 3.43 | 147000 | 0.2698 | | 0.2896 | 3.45 | 148000 | 0.2718 | | 0.2895 | 3.47 | 149000 | 0.2725 | | 0.2892 | 3.49 | 150000 | 0.2716 | | 0.2889 | 3.52 | 151000 | 0.2722 | | 0.289 | 3.54 | 152000 | 0.2718 | | 0.2888 | 3.56 | 153000 | 0.2718 | | 0.2887 | 3.59 | 154000 | 0.2725 | | 0.2888 | 3.61 | 155000 | 0.2710 | | 0.289 | 3.63 | 156000 | 0.2686 | | 0.2873 | 3.66 | 157000 | 0.2693 | | 0.2876 | 3.68 | 158000 | 0.2717 | | 0.2873 | 3.7 | 159000 | 0.2711 | | 0.2883 | 3.73 | 160000 | 0.2702 | | 0.287 | 3.75 | 161000 | 0.2717 | | 0.2868 | 3.77 | 162000 | 0.2690 | | 0.2869 | 3.8 | 163000 | 0.2686 | | 0.286 | 3.82 | 164000 | 0.2662 | | 0.286 | 3.84 | 165000 | 0.2697 | | 0.2859 | 3.87 | 166000 | 0.2704 | | 0.2858 | 3.89 | 167000 | 0.2678 | | 0.2854 | 3.91 | 168000 | 0.2670 | | 0.2853 | 3.94 | 169000 | 0.2691 | | 0.2849 | 3.96 | 170000 | 0.2683 | | 0.2858 | 3.98 | 171000 | 0.2663 | | 0.2846 | 4.01 | 172000 | 0.2714 | | 0.2846 | 4.03 | 173000 | 0.2669 | | 0.2844 | 4.05 | 174000 | 0.2691 | | 0.2839 | 4.08 | 175000 | 0.2685 | | 0.284 | 4.1 | 176000 | 0.2669 | | 0.2835 | 4.12 | 177000 | 0.2660 | | 0.2833 | 4.15 | 178000 | 0.2681 | | 0.2833 | 4.17 | 179000 | 0.2678 | | 0.2839 | 4.19 | 180000 | 0.2671 | | 0.2832 | 4.22 | 181000 | 0.2657 | | 0.2828 | 4.24 | 182000 | 0.2643 | | 0.2825 | 4.26 | 183000 | 0.2665 | | 0.2854 | 4.29 | 184000 | 0.2665 | | 0.2824 | 4.31 | 185000 | 0.2619 | | 0.2819 | 4.33 | 186000 | 0.2657 | | 0.2824 | 4.36 | 187000 | 0.2655 | | 0.2815 | 4.38 | 188000 | 0.2621 | | 0.2814 | 4.4 | 189000 | 0.2638 | | 0.2821 | 4.43 | 190000 | 0.2650 | | 0.281 | 4.45 | 191000 | 0.2648 | | 0.2812 | 4.47 | 192000 | 0.2635 | | 0.2809 | 4.5 | 193000 | 0.2629 | | 0.2809 | 4.52 | 194000 | 0.2643 | | 0.2805 | 4.54 | 195000 | 0.2625 | | 0.2806 | 4.57 | 196000 | 0.2639 | | 0.2805 | 4.59 | 197000 | 0.2628 | | 0.2799 | 4.61 | 198000 | 0.2629 | | 0.2802 | 4.64 | 199000 | 0.2624 | | 0.2799 | 4.66 | 200000 | 0.2646 | | 0.2796 | 4.68 | 201000 | 0.2606 | | 0.2796 | 4.71 | 202000 | 0.2641 | | 0.2795 | 4.73 | 203000 | 0.2627 | | 0.2793 | 4.75 | 204000 | 0.2612 | | 0.2789 | 4.78 | 205000 | 0.2591 | | 0.2789 | 4.8 | 206000 | 0.2602 | | 0.2789 | 4.82 | 207000 | 0.2611 | | 0.2787 | 4.85 | 208000 | 0.2650 | | 0.2784 | 4.87 | 209000 | 0.2615 | | 0.2782 | 4.89 | 210000 | 0.2624 | | 0.2783 | 4.92 | 211000 | 0.2621 | | 0.2781 | 4.94 | 212000 | 0.2614 | | 0.2779 | 4.96 | 213000 | 0.2598 | | 0.2776 | 4.99 | 214000 | 0.2595 | | 0.2774 | 5.01 | 215000 | 0.2608 | | 0.2782 | 5.03 | 216000 | 0.2615 | | 0.2779 | 5.06 | 217000 | 0.2626 | | 0.2768 | 5.08 | 218000 | 0.2594 | | 0.2774 | 5.1 | 219000 | 0.2606 | | 0.2767 | 5.13 | 220000 | 0.2606 | | 0.2763 | 5.15 | 221000 | 0.2605 | | 0.2766 | 5.17 | 222000 | 0.2599 | | 0.2763 | 5.2 | 223000 | 0.2582 | | 0.2764 | 5.22 | 224000 | 0.2606 | | 0.276 | 5.24 | 225000 | 0.2585 | | 0.2758 | 5.27 | 226000 | 0.2608 | | 0.2761 | 5.29 | 227000 | 0.2606 | | 0.2759 | 5.31 | 228000 | 0.2582 | | 0.2754 | 5.34 | 229000 | 0.2570 | | 0.2753 | 5.36 | 230000 | 0.2596 | | 0.2753 | 5.38 | 231000 | 0.2578 | | 0.2749 | 5.41 | 232000 | 0.2568 | | 0.2749 | 5.43 | 233000 | 0.2575 | | 0.2748 | 5.45 | 234000 | 0.2570 | | 0.2744 | 5.48 | 235000 | 0.2594 | | 0.2748 | 5.5 | 236000 | 0.2592 | | 0.2742 | 5.52 | 237000 | 0.2585 | | 0.2742 | 5.55 | 238000 | 0.2570 | | 0.2743 | 5.57 | 239000 | 0.2567 | | 0.274 | 5.59 | 240000 | 0.2570 | | 0.2739 | 5.62 | 241000 | 0.2584 | | 0.2738 | 5.64 | 242000 | 0.2564 | | 0.2737 | 5.66 | 243000 | 0.2559 | | 0.2732 | 5.69 | 244000 | 0.2552 | | 0.2733 | 5.71 | 245000 | 0.2560 | | 0.2733 | 5.73 | 246000 | 0.2555 | | 0.2732 | 5.76 | 247000 | 0.2539 | | 0.2732 | 5.78 | 248000 | 0.2552 | | 0.2729 | 5.8 | 249000 | 0.2535 | | 0.2728 | 5.82 | 250000 | 0.2543 | | 0.2729 | 5.85 | 251000 | 0.2555 | | 0.2723 | 5.87 | 252000 | 0.2528 | | 0.2722 | 5.89 | 253000 | 0.2557 | | 0.2722 | 5.92 | 254000 | 0.2576 | | 0.2718 | 5.94 | 255000 | 0.2552 | | 0.2715 | 5.96 | 256000 | 0.2557 | | 0.2725 | 5.99 | 257000 | 0.2527 | | 0.2717 | 6.01 | 258000 | 0.2517 | | 0.272 | 6.03 | 259000 | 0.2557 | | 0.2717 | 6.06 | 260000 | 0.2546 | | 0.2709 | 6.08 | 261000 | 0.2549 | | 0.2708 | 6.1 | 262000 | 0.2543 | | 0.2719 | 6.13 | 263000 | 0.2540 | | 0.2706 | 6.15 | 264000 | 0.2522 | | 0.2705 | 6.17 | 265000 | 0.2552 | | 0.2708 | 6.2 | 266000 | 0.2525 | | 0.2704 | 6.22 | 267000 | 0.2517 | | 0.2701 | 6.24 | 268000 | 0.2536 | | 0.2704 | 6.27 | 269000 | 0.2539 | | 0.2702 | 6.29 | 270000 | 0.2548 | | 0.2698 | 6.31 | 271000 | 0.2508 | | 0.2703 | 6.34 | 272000 | 0.2518 | | 0.2693 | 6.36 | 273000 | 0.2533 | | 0.2698 | 6.38 | 274000 | 0.2530 | | 0.2697 | 6.41 | 275000 | 0.2507 | | 0.2691 | 6.43 | 276000 | 0.2510 | | 0.2691 | 6.45 | 277000 | 0.2523 | | 0.2689 | 6.48 | 278000 | 0.2522 | | 0.2688 | 6.5 | 279000 | 0.2515 | | 0.2686 | 6.52 | 280000 | 0.2516 | | 0.2686 | 6.55 | 281000 | 0.2526 | | 0.2686 | 6.57 | 282000 | 0.2530 | | 0.2681 | 6.59 | 283000 | 0.2523 | | 0.2683 | 6.62 | 284000 | 0.2518 | | 0.268 | 6.64 | 285000 | 0.2508 | | 0.2683 | 6.66 | 286000 | 0.2502 | | 0.2681 | 6.69 | 287000 | 0.2507 | | 0.2681 | 6.71 | 288000 | 0.2518 | | 0.2679 | 6.73 | 289000 | 0.2504 | | 0.2675 | 6.76 | 290000 | 0.2505 | | 0.2679 | 6.78 | 291000 | 0.2502 | | 0.2675 | 6.8 | 292000 | 0.2517 | | 0.2672 | 6.83 | 293000 | 0.2517 | | 0.2673 | 6.85 | 294000 | 0.2483 | | 0.2671 | 6.87 | 295000 | 0.2483 | | 0.2669 | 6.9 | 296000 | 0.2523 | | 0.2666 | 6.92 | 297000 | 0.2494 | | 0.2664 | 6.94 | 298000 | 0.2497 | | 0.2953 | 6.97 | 299000 | 0.6473 | | 0.6483 | 6.99 | 300000 | 0.6471 | | 0.6477 | 7.01 | 301000 | 0.6461 | | 0.6471 | 7.04 | 302000 | 0.6455 | | 0.4659 | 7.06 | 303000 | 0.2599 | | 0.2707 | 7.08 | 304000 | 0.2535 | | 0.2681 | 7.11 | 305000 | 0.2525 | | 0.2678 | 7.13 | 306000 | 0.2504 | | 0.267 | 7.15 | 307000 | 0.2485 | | 0.2663 | 7.18 | 308000 | 0.2510 | | 0.266 | 7.2 | 309000 | 0.2499 | | 0.2658 | 7.22 | 310000 | 0.2481 | | 0.2656 | 7.25 | 311000 | 0.2481 | | 0.2653 | 7.27 | 312000 | 0.2519 | | 0.2652 | 7.29 | 313000 | 0.2483 | | 0.2654 | 7.32 | 314000 | 0.2468 | | 0.2653 | 7.34 | 315000 | 0.2493 | | 0.265 | 7.36 | 316000 | 0.2473 | | 0.2646 | 7.39 | 317000 | 0.2479 | | 0.2647 | 7.41 | 318000 | 0.2483 | | 0.2645 | 7.43 | 319000 | 0.2484 | | 0.2642 | 7.46 | 320000 | 0.2467 | | 0.2643 | 7.48 | 321000 | 0.2483 | | 0.2643 | 7.5 | 322000 | 0.2488 | | 0.2638 | 7.53 | 323000 | 0.2484 | | 0.2636 | 7.55 | 324000 | 0.2478 | | 0.2633 | 7.57 | 325000 | 0.2480 | | 0.2633 | 7.6 | 326000 | 0.2482 | | 0.2637 | 7.62 | 327000 | 0.2486 | | 0.2634 | 7.64 | 328000 | 0.2464 | | 0.2631 | 7.67 | 329000 | 0.2453 | | 0.2631 | 7.69 | 330000 | 0.2482 | | 0.263 | 7.71 | 331000 | 0.2436 | | 0.2631 | 7.74 | 332000 | 0.2457 | | 0.2629 | 7.76 | 333000 | 0.2470 | | 0.2626 | 7.78 | 334000 | 0.2488 | | 0.2626 | 7.81 | 335000 | 0.2465 | | 0.2623 | 7.83 | 336000 | 0.2481 | | 0.2624 | 7.85 | 337000 | 0.2449 | | 0.2623 | 7.88 | 338000 | 0.2460 | | 0.2626 | 7.9 | 339000 | 0.2447 | | 0.262 | 7.92 | 340000 | 0.2456 | | 0.2624 | 7.95 | 341000 | 0.2436 | | 0.2618 | 7.97 | 342000 | 0.2451 | | 0.2617 | 7.99 | 343000 | 0.2431 | | 0.2614 | 8.02 | 344000 | 0.2446 | | 0.2617 | 8.04 | 345000 | 0.2446 | | 0.2612 | 8.06 | 346000 | 0.2443 | | 0.261 | 8.08 | 347000 | 0.2445 | | 0.261 | 8.11 | 348000 | 0.2460 | | 0.261 | 8.13 | 349000 | 0.2420 | | 0.2608 | 8.15 | 350000 | 0.2434 | | 0.2607 | 8.18 | 351000 | 0.2465 | | 0.261 | 8.2 | 352000 | 0.2440 | | 0.2605 | 8.22 | 353000 | 0.2437 | | 0.2605 | 8.25 | 354000 | 0.2444 | | 0.2603 | 8.27 | 355000 | 0.2447 | | 0.2599 | 8.29 | 356000 | 0.2416 | | 0.2601 | 8.32 | 357000 | 0.2435 | | 0.26 | 8.34 | 358000 | 0.2428 | | 0.26 | 8.36 | 359000 | 0.2448 | | 0.2596 | 8.39 | 360000 | 0.2432 | | 0.2596 | 8.41 | 361000 | 0.2435 | | 0.2595 | 8.43 | 362000 | 0.2439 | | 0.2593 | 8.46 | 363000 | 0.2452 | | 0.2593 | 8.48 | 364000 | 0.2412 | | 0.2592 | 8.5 | 365000 | 0.2430 | | 0.2587 | 8.53 | 366000 | 0.2405 | | 0.2591 | 8.55 | 367000 | 0.2447 | | 0.2586 | 8.57 | 368000 | 0.2428 | | 0.259 | 8.6 | 369000 | 0.2415 | | 0.2588 | 8.62 | 370000 | 0.2388 | | 0.2585 | 8.64 | 371000 | 0.2436 | | 0.2582 | 8.67 | 372000 | 0.2406 | | 0.2583 | 8.69 | 373000 | 0.2428 | | 0.2585 | 8.71 | 374000 | 0.2433 | | 0.2578 | 8.74 | 375000 | 0.2411 | | 0.2582 | 8.76 | 376000 | 0.2427 | | 0.258 | 8.78 | 377000 | 0.2417 | | 0.2576 | 8.81 | 378000 | 0.2399 | | 0.2574 | 8.83 | 379000 | 0.2415 | | 0.2579 | 8.85 | 380000 | 0.2417 | | 0.2573 | 8.88 | 381000 | 0.2407 | | 0.2575 | 8.9 | 382000 | 0.2418 | | 0.2573 | 8.92 | 383000 | 0.2398 | | 0.2573 | 8.95 | 384000 | 0.2400 | | 0.2569 | 8.97 | 385000 | 0.2390 | | 0.2572 | 8.99 | 386000 | 0.2373 | | 0.2566 | 9.02 | 387000 | 0.2406 | | 0.2565 | 9.04 | 388000 | 0.2388 | | 0.2566 | 9.06 | 389000 | 0.2398 | | 0.2564 | 9.09 | 390000 | 0.2411 | | 0.2566 | 9.11 | 391000 | 0.2374 | | 0.2564 | 9.13 | 392000 | 0.2417 | | 0.2565 | 9.16 | 393000 | 0.2408 | | 0.2566 | 9.18 | 394000 | 0.2391 | | 0.2561 | 9.2 | 395000 | 0.2375 | | 0.2562 | 9.23 | 396000 | 0.2393 | | 0.256 | 9.25 | 397000 | 0.2419 | | 0.2561 | 9.27 | 398000 | 0.2420 | | 0.2554 | 9.3 | 399000 | 0.2418 | | 0.2559 | 9.32 | 400000 | 0.2379 | | 0.2555 | 9.34 | 401000 | 0.2394 | | 0.2553 | 9.37 | 402000 | 0.2388 | | 0.2553 | 9.39 | 403000 | 0.2373 | | 0.2553 | 9.41 | 404000 | 0.2365 | | 0.2555 | 9.44 | 405000 | 0.2398 | | 0.2553 | 9.46 | 406000 | 0.2392 | | 0.255 | 9.48 | 407000 | 0.2371 | | 0.2548 | 9.51 | 408000 | 0.2382 | | 0.2548 | 9.53 | 409000 | 0.2374 | | 0.2548 | 9.55 | 410000 | 0.2390 | | 0.2547 | 9.58 | 411000 | 0.2395 | | 0.2544 | 9.6 | 412000 | 0.2367 | | 0.2548 | 9.62 | 413000 | 0.2361 | | 0.2545 | 9.65 | 414000 | 0.2389 | | 0.2547 | 9.67 | 415000 | 0.2401 | | 0.2545 | 9.69 | 416000 | 0.2389 | | 0.2543 | 9.72 | 417000 | 0.2375 | | 0.2543 | 9.74 | 418000 | 0.2396 | | 0.2541 | 9.76 | 419000 | 0.2385 | | 0.2541 | 9.79 | 420000 | 0.2357 | | 0.2539 | 9.81 | 421000 | 0.2378 | | 0.254 | 9.83 | 422000 | 0.2355 | | 0.2537 | 9.86 | 423000 | 0.2358 | | 0.2536 | 9.88 | 424000 | 0.2361 | | 0.2534 | 9.9 | 425000 | 0.2385 | | 0.2534 | 9.93 | 426000 | 0.2372 | | 0.2535 | 9.95 | 427000 | 0.2362 | | 0.2535 | 9.97 | 428000 | 0.2361 | | 0.2532 | 10.0 | 429000 | 0.2369 | | 0.2533 | 10.02 | 430000 | 0.2366 | | 0.2529 | 10.04 | 431000 | 0.2381 | | 0.2532 | 10.07 | 432000 | 0.2370 | | 0.253 | 10.09 | 433000 | 0.2379 | | 0.2531 | 10.11 | 434000 | 0.2394 | | 0.2528 | 10.14 | 435000 | 0.2357 | | 0.253 | 10.16 | 436000 | 0.2384 | | 0.2525 | 10.18 | 437000 | 0.2387 | | 0.2526 | 10.21 | 438000 | 0.2344 | | 0.2527 | 10.23 | 439000 | 0.2362 | | 0.2528 | 10.25 | 440000 | 0.2371 | | 0.2525 | 10.28 | 441000 | 0.2355 | | 0.2521 | 10.3 | 442000 | 0.2365 | | 0.2523 | 10.32 | 443000 | 0.2356 | | 0.2523 | 10.35 | 444000 | 0.2366 | | 0.2519 | 10.37 | 445000 | 0.2352 | | 0.2523 | 10.39 | 446000 | 0.2358 | | 0.2521 | 10.41 | 447000 | 0.2341 | | 0.2519 | 10.44 | 448000 | 0.2375 | | 0.2519 | 10.46 | 449000 | 0.2350 | | 0.2519 | 10.48 | 450000 | 0.2356 | | 0.2518 | 10.51 | 451000 | 0.2345 | | 0.252 | 10.53 | 452000 | 0.2365 | | 0.2517 | 10.55 | 453000 | 0.2377 | | 0.2516 | 10.58 | 454000 | 0.2362 | | 0.2517 | 10.6 | 455000 | 0.2354 | | 0.2515 | 10.62 | 456000 | 0.2340 | | 0.2515 | 10.65 | 457000 | 0.2348 | | 0.2517 | 10.67 | 458000 | 0.2370 | | 0.2514 | 10.69 | 459000 | 0.2341 | | 0.2514 | 10.72 | 460000 | 0.2361 | | 0.2513 | 10.74 | 461000 | 0.2357 | | 0.2516 | 10.76 | 462000 | 0.2352 | | 0.2511 | 10.79 | 463000 | 0.2325 | | 0.2515 | 10.81 | 464000 | 0.2364 | | 0.2509 | 10.83 | 465000 | 0.2379 | | 0.2511 | 10.86 | 466000 | 0.2361 | | 0.2513 | 10.88 | 467000 | 0.2350 | | 0.2509 | 10.9 | 468000 | 0.2350 | | 0.2512 | 10.93 | 469000 | 0.2339 | | 0.2508 | 10.95 | 470000 | 0.2333 | | 0.2508 | 10.97 | 471000 | 0.2342 | | 0.2508 | 11.0 | 472000 | 0.2346 | | 0.2509 | 11.02 | 473000 | 0.2332 | | 0.2506 | 11.04 | 474000 | 0.2351 | | 0.2506 | 11.07 | 475000 | 0.2317 | | 0.2508 | 11.09 | 476000 | 0.2339 | | 0.2506 | 11.11 | 477000 | 0.2343 | | 0.2506 | 11.14 | 478000 | 0.2336 | | 0.2508 | 11.16 | 479000 | 0.2331 | | 0.2507 | 11.18 | 480000 | 0.2337 | | 0.2506 | 11.21 | 481000 | 0.2345 | | 0.2505 | 11.23 | 482000 | 0.2329 | | 0.2505 | 11.25 | 483000 | 0.2361 | | 0.2505 | 11.28 | 484000 | 0.2341 | | 0.2503 | 11.3 | 485000 | 0.2339 | | 0.2505 | 11.32 | 486000 | 0.2341 | | 0.2505 | 11.35 | 487000 | 0.2334 | | 0.2504 | 11.37 | 488000 | 0.2337 | | 0.2504 | 11.39 | 489000 | 0.2356 | | 0.2506 | 11.42 | 490000 | 0.2319 | | 0.2503 | 11.44 | 491000 | 0.2337 | | 0.2501 | 11.46 | 492000 | 0.2318 | | 0.2505 | 11.49 | 493000 | 0.2325 | | 0.2504 | 11.51 | 494000 | 0.2338 | | 0.2503 | 11.53 | 495000 | 0.2317 | | 0.2502 | 11.56 | 496000 | 0.2340 | | 0.25 | 11.58 | 497000 | 0.2341 | | 0.2502 | 11.6 | 498000 | 0.2324 | | 0.2504 | 11.63 | 499000 | 0.2360 | | 0.2501 | 11.65 | 500000 | 0.2346 | ### Framework versions - Transformers 4.17.0 - Pytorch 1.11.0 - Datasets 2.5.0 - Tokenizers 0.12.1