Upload add_sub_sorl_v1_abs16_K1_100K/metrics.json with huggingface_hub
Browse files
add_sub_sorl_v1_abs16_K1_100K/metrics.json
CHANGED
|
@@ -2530,416 +2530,477 @@
|
|
| 2530 |
"K": null,
|
| 2531 |
"mode": "sft",
|
| 2532 |
"n_digits": 6,
|
| 2533 |
-
"n_per_split":
|
| 2534 |
},
|
| 2535 |
"splits": {
|
| 2536 |
"add_S0": {
|
| 2537 |
"full_accuracy": 1.0,
|
| 2538 |
-
"
|
|
|
|
| 2539 |
"per_subtask": {
|
| 2540 |
"SA": {
|
| 2541 |
"accuracy": 1.0,
|
| 2542 |
-
"count":
|
| 2543 |
},
|
| 2544 |
"SS": {
|
| 2545 |
"accuracy": 1.0,
|
| 2546 |
-
"count":
|
| 2547 |
}
|
| 2548 |
}
|
| 2549 |
},
|
| 2550 |
"add_S1": {
|
| 2551 |
"full_accuracy": 1.0,
|
| 2552 |
-
"
|
|
|
|
| 2553 |
"per_subtask": {
|
| 2554 |
"SA": {
|
| 2555 |
"accuracy": 1.0,
|
| 2556 |
-
"count":
|
| 2557 |
},
|
| 2558 |
"SC": {
|
| 2559 |
"accuracy": 1.0,
|
| 2560 |
-
"count":
|
| 2561 |
},
|
| 2562 |
"SS": {
|
| 2563 |
"accuracy": 1.0,
|
| 2564 |
-
"count":
|
| 2565 |
},
|
| 2566 |
"UC": {
|
| 2567 |
"accuracy": 1.0,
|
| 2568 |
-
"count":
|
| 2569 |
}
|
| 2570 |
}
|
| 2571 |
},
|
| 2572 |
"add_S2": {
|
| 2573 |
"full_accuracy": 1.0,
|
| 2574 |
-
"
|
|
|
|
| 2575 |
"per_subtask": {
|
| 2576 |
"SA": {
|
| 2577 |
"accuracy": 1.0,
|
| 2578 |
-
"count":
|
| 2579 |
},
|
| 2580 |
"SC": {
|
| 2581 |
"accuracy": 1.0,
|
| 2582 |
-
"count":
|
| 2583 |
},
|
| 2584 |
"SS": {
|
| 2585 |
"accuracy": 1.0,
|
| 2586 |
-
"count":
|
| 2587 |
},
|
| 2588 |
"UC": {
|
| 2589 |
"accuracy": 1.0,
|
| 2590 |
-
"count":
|
| 2591 |
},
|
| 2592 |
"US": {
|
| 2593 |
"accuracy": 1.0,
|
| 2594 |
-
"count":
|
| 2595 |
}
|
| 2596 |
}
|
| 2597 |
},
|
| 2598 |
"add_S3": {
|
| 2599 |
-
"full_accuracy":
|
| 2600 |
-
"
|
|
|
|
| 2601 |
"per_subtask": {
|
| 2602 |
"SA": {
|
| 2603 |
"accuracy": 1.0,
|
| 2604 |
-
"count":
|
| 2605 |
},
|
| 2606 |
"SC": {
|
| 2607 |
"accuracy": 1.0,
|
| 2608 |
-
"count":
|
| 2609 |
},
|
| 2610 |
"SS": {
|
| 2611 |
"accuracy": 1.0,
|
| 2612 |
-
"count":
|
| 2613 |
},
|
| 2614 |
"UC": {
|
| 2615 |
-
"accuracy":
|
| 2616 |
-
"count":
|
| 2617 |
},
|
| 2618 |
"US": {
|
| 2619 |
"accuracy": 1.0,
|
| 2620 |
-
"count":
|
| 2621 |
}
|
| 2622 |
}
|
| 2623 |
},
|
| 2624 |
"add_S4": {
|
| 2625 |
-
"full_accuracy": 0.
|
| 2626 |
-
"
|
|
|
|
| 2627 |
"per_subtask": {
|
| 2628 |
"SA": {
|
| 2629 |
"accuracy": 1.0,
|
| 2630 |
-
"count":
|
| 2631 |
},
|
| 2632 |
"SC": {
|
| 2633 |
"accuracy": 1.0,
|
| 2634 |
-
"count":
|
| 2635 |
},
|
| 2636 |
"SS": {
|
| 2637 |
"accuracy": 1.0,
|
| 2638 |
-
"count":
|
| 2639 |
},
|
| 2640 |
"UC": {
|
| 2641 |
-
"accuracy": 0.
|
| 2642 |
-
"count":
|
| 2643 |
},
|
| 2644 |
"US": {
|
| 2645 |
-
"accuracy": 0.
|
| 2646 |
-
"count":
|
| 2647 |
}
|
| 2648 |
}
|
| 2649 |
},
|
| 2650 |
"add_S5": {
|
| 2651 |
-
"full_accuracy": 0.
|
| 2652 |
-
"
|
|
|
|
| 2653 |
"per_subtask": {
|
| 2654 |
"SA": {
|
| 2655 |
"accuracy": 1.0,
|
| 2656 |
-
"count":
|
| 2657 |
},
|
| 2658 |
"SC": {
|
| 2659 |
"accuracy": 1.0,
|
| 2660 |
-
"count":
|
| 2661 |
},
|
| 2662 |
"UC": {
|
| 2663 |
-
"accuracy": 0.
|
| 2664 |
-
"count":
|
| 2665 |
},
|
| 2666 |
"US": {
|
| 2667 |
-
"accuracy": 0.
|
| 2668 |
-
"count":
|
| 2669 |
}
|
| 2670 |
}
|
| 2671 |
},
|
| 2672 |
"add_S6": {
|
| 2673 |
-
"full_accuracy": 0.
|
| 2674 |
-
"
|
|
|
|
| 2675 |
"per_subtask": {
|
| 2676 |
"SC": {
|
| 2677 |
"accuracy": 1.0,
|
| 2678 |
-
"count":
|
| 2679 |
},
|
| 2680 |
"UC": {
|
| 2681 |
"accuracy": 0.94,
|
| 2682 |
-
"count":
|
| 2683 |
},
|
| 2684 |
"US": {
|
| 2685 |
-
"accuracy": 0.
|
| 2686 |
-
"count":
|
| 2687 |
}
|
| 2688 |
}
|
| 2689 |
},
|
| 2690 |
"add_random": {
|
| 2691 |
"full_accuracy": 1.0,
|
|
|
|
| 2692 |
"n_examples": 200,
|
| 2693 |
"per_subtask": {
|
| 2694 |
"SA": {
|
| 2695 |
"accuracy": 1.0,
|
| 2696 |
-
"count":
|
| 2697 |
},
|
| 2698 |
"SC": {
|
| 2699 |
"accuracy": 1.0,
|
| 2700 |
-
"count":
|
| 2701 |
},
|
| 2702 |
"SS": {
|
| 2703 |
"accuracy": 1.0,
|
| 2704 |
-
"count":
|
| 2705 |
},
|
| 2706 |
"UC": {
|
| 2707 |
"accuracy": 1.0,
|
| 2708 |
-
"count":
|
| 2709 |
},
|
| 2710 |
"US": {
|
| 2711 |
"accuracy": 1.0,
|
| 2712 |
-
"count":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2713 |
}
|
| 2714 |
}
|
| 2715 |
},
|
| 2716 |
"add_C3": {
|
| 2717 |
-
"full_accuracy":
|
| 2718 |
-
"
|
|
|
|
| 2719 |
"per_subtask": {
|
| 2720 |
"SA": {
|
| 2721 |
"accuracy": 1.0,
|
| 2722 |
-
"count":
|
| 2723 |
},
|
| 2724 |
"SC": {
|
| 2725 |
"accuracy": 1.0,
|
| 2726 |
-
"count":
|
| 2727 |
},
|
| 2728 |
"UC": {
|
| 2729 |
-
"accuracy":
|
| 2730 |
-
"count":
|
| 2731 |
},
|
| 2732 |
"US": {
|
| 2733 |
"accuracy": 1.0,
|
| 2734 |
-
"count":
|
| 2735 |
}
|
| 2736 |
}
|
| 2737 |
},
|
| 2738 |
"add_C4": {
|
| 2739 |
-
"full_accuracy": 0.
|
| 2740 |
-
"
|
|
|
|
| 2741 |
"per_subtask": {
|
| 2742 |
"SA": {
|
| 2743 |
-
"accuracy":
|
| 2744 |
-
"count":
|
| 2745 |
},
|
| 2746 |
"SC": {
|
| 2747 |
"accuracy": 1.0,
|
| 2748 |
-
"count":
|
| 2749 |
},
|
| 2750 |
"UC": {
|
| 2751 |
-
"accuracy": 0.
|
| 2752 |
-
"count":
|
| 2753 |
},
|
| 2754 |
"US": {
|
| 2755 |
-
"accuracy":
|
| 2756 |
-
"count":
|
| 2757 |
}
|
| 2758 |
}
|
| 2759 |
},
|
| 2760 |
"add_C5": {
|
| 2761 |
-
"full_accuracy": 0.
|
| 2762 |
-
"
|
|
|
|
| 2763 |
"per_subtask": {
|
| 2764 |
"SA": {
|
| 2765 |
"accuracy": 1.0,
|
| 2766 |
-
"count":
|
| 2767 |
},
|
| 2768 |
"SC": {
|
| 2769 |
"accuracy": 1.0,
|
| 2770 |
-
"count":
|
| 2771 |
},
|
| 2772 |
"UC": {
|
| 2773 |
-
"accuracy":
|
| 2774 |
-
"count":
|
| 2775 |
},
|
| 2776 |
"US": {
|
| 2777 |
-
"accuracy": 0.
|
| 2778 |
-
"count":
|
| 2779 |
}
|
| 2780 |
}
|
| 2781 |
},
|
| 2782 |
"add_C6": {
|
| 2783 |
"full_accuracy": 1.0,
|
| 2784 |
-
"
|
|
|
|
| 2785 |
"per_subtask": {
|
| 2786 |
"SC": {
|
| 2787 |
"accuracy": 1.0,
|
| 2788 |
-
"count":
|
| 2789 |
},
|
| 2790 |
"UC": {
|
| 2791 |
"accuracy": 1.0,
|
| 2792 |
-
"count":
|
| 2793 |
},
|
| 2794 |
"US": {
|
| 2795 |
"accuracy": 1.0,
|
| 2796 |
-
"count":
|
| 2797 |
}
|
| 2798 |
}
|
| 2799 |
},
|
| 2800 |
"sub_M0": {
|
| 2801 |
"full_accuracy": 1.0,
|
| 2802 |
-
"
|
|
|
|
| 2803 |
"per_subtask": {
|
| 2804 |
"MD": {
|
| 2805 |
"accuracy": 1.0,
|
| 2806 |
-
"count":
|
| 2807 |
},
|
| 2808 |
"ME": {
|
| 2809 |
"accuracy": 1.0,
|
| 2810 |
-
"count":
|
| 2811 |
}
|
| 2812 |
}
|
| 2813 |
},
|
| 2814 |
"sub_M1": {
|
| 2815 |
-
"full_accuracy":
|
| 2816 |
-
"
|
|
|
|
| 2817 |
"per_subtask": {
|
| 2818 |
"MD": {
|
| 2819 |
"accuracy": 1.0,
|
| 2820 |
-
"count":
|
| 2821 |
},
|
| 2822 |
"MB": {
|
| 2823 |
"accuracy": 1.0,
|
| 2824 |
-
"count":
|
| 2825 |
},
|
| 2826 |
"ME": {
|
| 2827 |
"accuracy": 1.0,
|
| 2828 |
-
"count":
|
| 2829 |
},
|
| 2830 |
"UB": {
|
| 2831 |
-
"accuracy":
|
| 2832 |
-
"count":
|
| 2833 |
}
|
| 2834 |
}
|
| 2835 |
},
|
| 2836 |
"sub_M2": {
|
| 2837 |
"full_accuracy": 1.0,
|
| 2838 |
-
"
|
|
|
|
| 2839 |
"per_subtask": {
|
| 2840 |
"MD": {
|
| 2841 |
"accuracy": 1.0,
|
| 2842 |
-
"count":
|
| 2843 |
},
|
| 2844 |
"MB": {
|
| 2845 |
"accuracy": 1.0,
|
| 2846 |
-
"count":
|
| 2847 |
},
|
| 2848 |
"ME": {
|
| 2849 |
"accuracy": 1.0,
|
| 2850 |
-
"count":
|
| 2851 |
},
|
| 2852 |
"UB": {
|
| 2853 |
"accuracy": 1.0,
|
| 2854 |
-
"count":
|
| 2855 |
},
|
| 2856 |
"UD": {
|
| 2857 |
"accuracy": 1.0,
|
| 2858 |
-
"count":
|
| 2859 |
}
|
| 2860 |
}
|
| 2861 |
},
|
| 2862 |
"sub_M3": {
|
| 2863 |
"full_accuracy": 1.0,
|
| 2864 |
-
"
|
|
|
|
| 2865 |
"per_subtask": {
|
| 2866 |
"MD": {
|
| 2867 |
"accuracy": 1.0,
|
| 2868 |
-
"count":
|
| 2869 |
},
|
| 2870 |
"MB": {
|
| 2871 |
"accuracy": 1.0,
|
| 2872 |
-
"count":
|
| 2873 |
},
|
| 2874 |
"ME": {
|
| 2875 |
"accuracy": 1.0,
|
| 2876 |
-
"count":
|
| 2877 |
},
|
| 2878 |
"UB": {
|
| 2879 |
"accuracy": 1.0,
|
| 2880 |
-
"count":
|
| 2881 |
},
|
| 2882 |
"UD": {
|
| 2883 |
"accuracy": 1.0,
|
| 2884 |
-
"count":
|
| 2885 |
}
|
| 2886 |
}
|
| 2887 |
},
|
| 2888 |
"sub_M4": {
|
| 2889 |
-
"full_accuracy": 0.
|
| 2890 |
-
"
|
|
|
|
| 2891 |
"per_subtask": {
|
| 2892 |
"MD": {
|
| 2893 |
"accuracy": 1.0,
|
| 2894 |
-
"count":
|
| 2895 |
},
|
| 2896 |
"MB": {
|
| 2897 |
"accuracy": 1.0,
|
| 2898 |
-
"count":
|
| 2899 |
},
|
| 2900 |
"UB": {
|
| 2901 |
-
"accuracy": 0.
|
| 2902 |
-
"count":
|
| 2903 |
},
|
| 2904 |
"UD": {
|
| 2905 |
-
"accuracy":
|
| 2906 |
-
"count":
|
| 2907 |
}
|
| 2908 |
}
|
| 2909 |
},
|
| 2910 |
"sub_M5": {
|
| 2911 |
-
"full_accuracy": 0.
|
| 2912 |
-
"
|
|
|
|
| 2913 |
"per_subtask": {
|
| 2914 |
"MD": {
|
| 2915 |
"accuracy": 1.0,
|
| 2916 |
-
"count":
|
| 2917 |
},
|
| 2918 |
"MB": {
|
| 2919 |
"accuracy": 1.0,
|
| 2920 |
-
"count":
|
| 2921 |
},
|
| 2922 |
"UB": {
|
| 2923 |
-
"accuracy": 0.
|
| 2924 |
-
"count":
|
| 2925 |
},
|
| 2926 |
"UD": {
|
| 2927 |
-
"accuracy": 0.
|
| 2928 |
-
"count":
|
| 2929 |
}
|
| 2930 |
}
|
| 2931 |
},
|
| 2932 |
"sub_random": {
|
| 2933 |
"full_accuracy": 1.0,
|
|
|
|
| 2934 |
"n_examples": 200,
|
| 2935 |
"per_subtask": {
|
| 2936 |
"MD": {
|
| 2937 |
"accuracy": 1.0,
|
| 2938 |
-
"count":
|
| 2939 |
},
|
| 2940 |
"MB": {
|
| 2941 |
"accuracy": 1.0,
|
| 2942 |
-
"count":
|
| 2943 |
},
|
| 2944 |
"ME": {
|
| 2945 |
"accuracy": 1.0,
|
|
@@ -2947,85 +3008,89 @@
|
|
| 2947 |
},
|
| 2948 |
"UB": {
|
| 2949 |
"accuracy": 1.0,
|
| 2950 |
-
"count":
|
| 2951 |
},
|
| 2952 |
"UD": {
|
| 2953 |
"accuracy": 1.0,
|
| 2954 |
-
"count":
|
| 2955 |
}
|
| 2956 |
}
|
| 2957 |
},
|
| 2958 |
"sub_B3": {
|
| 2959 |
-
"full_accuracy":
|
| 2960 |
-
"
|
|
|
|
| 2961 |
"per_subtask": {
|
| 2962 |
"MD": {
|
| 2963 |
"accuracy": 1.0,
|
| 2964 |
-
"count":
|
| 2965 |
},
|
| 2966 |
"MB": {
|
| 2967 |
"accuracy": 1.0,
|
| 2968 |
-
"count":
|
| 2969 |
},
|
| 2970 |
"UB": {
|
| 2971 |
-
"accuracy":
|
| 2972 |
-
"count":
|
| 2973 |
},
|
| 2974 |
"UD": {
|
| 2975 |
"accuracy": 1.0,
|
| 2976 |
-
"count":
|
| 2977 |
}
|
| 2978 |
}
|
| 2979 |
},
|
| 2980 |
"sub_B4": {
|
| 2981 |
"full_accuracy": 0.94,
|
| 2982 |
-
"
|
|
|
|
| 2983 |
"per_subtask": {
|
| 2984 |
"MD": {
|
| 2985 |
"accuracy": 1.0,
|
| 2986 |
-
"count":
|
| 2987 |
},
|
| 2988 |
"MB": {
|
| 2989 |
"accuracy": 1.0,
|
| 2990 |
-
"count":
|
| 2991 |
},
|
| 2992 |
"UB": {
|
| 2993 |
-
"accuracy": 0.
|
| 2994 |
-
"count":
|
| 2995 |
},
|
| 2996 |
"UD": {
|
| 2997 |
"accuracy": 1.0,
|
| 2998 |
-
"count":
|
| 2999 |
}
|
| 3000 |
}
|
| 3001 |
},
|
| 3002 |
"sub_B5": {
|
| 3003 |
"full_accuracy": 0.98,
|
| 3004 |
-
"
|
|
|
|
| 3005 |
"per_subtask": {
|
| 3006 |
"MD": {
|
| 3007 |
"accuracy": 1.0,
|
| 3008 |
-
"count":
|
| 3009 |
},
|
| 3010 |
"MB": {
|
| 3011 |
"accuracy": 1.0,
|
| 3012 |
-
"count":
|
| 3013 |
},
|
| 3014 |
"UB": {
|
| 3015 |
-
"accuracy": 0.
|
| 3016 |
-
"count":
|
| 3017 |
},
|
| 3018 |
"UD": {
|
| 3019 |
-
"accuracy":
|
| 3020 |
-
"count":
|
| 3021 |
}
|
| 3022 |
}
|
| 3023 |
}
|
| 3024 |
},
|
| 3025 |
"summary": {
|
| 3026 |
-
"overall_accuracy": 0.
|
| 3027 |
-
"
|
| 3028 |
-
"
|
|
|
|
| 3029 |
}
|
| 3030 |
},
|
| 3031 |
"sorl_eval": {
|
|
@@ -3034,416 +3099,477 @@
|
|
| 3034 |
"K": 1,
|
| 3035 |
"mode": "sorl",
|
| 3036 |
"n_digits": 6,
|
| 3037 |
-
"n_per_split":
|
| 3038 |
},
|
| 3039 |
"splits": {
|
| 3040 |
"add_S0": {
|
| 3041 |
"full_accuracy": 1.0,
|
| 3042 |
-
"
|
|
|
|
| 3043 |
"per_subtask": {
|
| 3044 |
"SA": {
|
| 3045 |
"accuracy": 1.0,
|
| 3046 |
-
"count":
|
| 3047 |
},
|
| 3048 |
"SS": {
|
| 3049 |
"accuracy": 1.0,
|
| 3050 |
-
"count":
|
| 3051 |
}
|
| 3052 |
}
|
| 3053 |
},
|
| 3054 |
"add_S1": {
|
| 3055 |
"full_accuracy": 1.0,
|
| 3056 |
-
"
|
|
|
|
| 3057 |
"per_subtask": {
|
| 3058 |
"SA": {
|
| 3059 |
"accuracy": 1.0,
|
| 3060 |
-
"count":
|
| 3061 |
},
|
| 3062 |
"SC": {
|
| 3063 |
"accuracy": 1.0,
|
| 3064 |
-
"count":
|
| 3065 |
},
|
| 3066 |
"SS": {
|
| 3067 |
"accuracy": 1.0,
|
| 3068 |
-
"count":
|
| 3069 |
},
|
| 3070 |
"UC": {
|
| 3071 |
"accuracy": 1.0,
|
| 3072 |
-
"count":
|
| 3073 |
}
|
| 3074 |
}
|
| 3075 |
},
|
| 3076 |
"add_S2": {
|
| 3077 |
"full_accuracy": 1.0,
|
| 3078 |
-
"
|
|
|
|
| 3079 |
"per_subtask": {
|
| 3080 |
"SA": {
|
| 3081 |
"accuracy": 1.0,
|
| 3082 |
-
"count":
|
| 3083 |
},
|
| 3084 |
"SC": {
|
| 3085 |
"accuracy": 1.0,
|
| 3086 |
-
"count":
|
| 3087 |
},
|
| 3088 |
"SS": {
|
| 3089 |
"accuracy": 1.0,
|
| 3090 |
-
"count":
|
| 3091 |
},
|
| 3092 |
"UC": {
|
| 3093 |
"accuracy": 1.0,
|
| 3094 |
-
"count":
|
| 3095 |
},
|
| 3096 |
"US": {
|
| 3097 |
"accuracy": 1.0,
|
| 3098 |
-
"count":
|
| 3099 |
}
|
| 3100 |
}
|
| 3101 |
},
|
| 3102 |
"add_S3": {
|
| 3103 |
"full_accuracy": 1.0,
|
| 3104 |
-
"
|
|
|
|
| 3105 |
"per_subtask": {
|
| 3106 |
"SA": {
|
| 3107 |
"accuracy": 1.0,
|
| 3108 |
-
"count":
|
| 3109 |
},
|
| 3110 |
"SC": {
|
| 3111 |
"accuracy": 1.0,
|
| 3112 |
-
"count":
|
| 3113 |
},
|
| 3114 |
"SS": {
|
| 3115 |
"accuracy": 1.0,
|
| 3116 |
-
"count":
|
| 3117 |
},
|
| 3118 |
"UC": {
|
| 3119 |
"accuracy": 1.0,
|
| 3120 |
-
"count":
|
| 3121 |
},
|
| 3122 |
"US": {
|
| 3123 |
"accuracy": 1.0,
|
| 3124 |
-
"count":
|
| 3125 |
}
|
| 3126 |
}
|
| 3127 |
},
|
| 3128 |
"add_S4": {
|
| 3129 |
"full_accuracy": 1.0,
|
| 3130 |
-
"
|
|
|
|
| 3131 |
"per_subtask": {
|
| 3132 |
"SA": {
|
| 3133 |
"accuracy": 1.0,
|
| 3134 |
-
"count":
|
| 3135 |
},
|
| 3136 |
"SC": {
|
| 3137 |
"accuracy": 1.0,
|
| 3138 |
-
"count":
|
| 3139 |
},
|
| 3140 |
"SS": {
|
| 3141 |
"accuracy": 1.0,
|
| 3142 |
-
"count":
|
| 3143 |
},
|
| 3144 |
"UC": {
|
| 3145 |
"accuracy": 1.0,
|
| 3146 |
-
"count":
|
| 3147 |
},
|
| 3148 |
"US": {
|
| 3149 |
"accuracy": 1.0,
|
| 3150 |
-
"count":
|
| 3151 |
}
|
| 3152 |
}
|
| 3153 |
},
|
| 3154 |
"add_S5": {
|
| 3155 |
-
"full_accuracy":
|
| 3156 |
-
"
|
|
|
|
| 3157 |
"per_subtask": {
|
| 3158 |
"SA": {
|
| 3159 |
"accuracy": 1.0,
|
| 3160 |
-
"count":
|
| 3161 |
},
|
| 3162 |
"SC": {
|
| 3163 |
"accuracy": 1.0,
|
| 3164 |
-
"count":
|
| 3165 |
},
|
| 3166 |
"UC": {
|
| 3167 |
-
"accuracy":
|
| 3168 |
-
"count":
|
| 3169 |
},
|
| 3170 |
"US": {
|
| 3171 |
"accuracy": 1.0,
|
| 3172 |
-
"count":
|
| 3173 |
}
|
| 3174 |
}
|
| 3175 |
},
|
| 3176 |
"add_S6": {
|
| 3177 |
"full_accuracy": 0.96,
|
| 3178 |
-
"
|
|
|
|
| 3179 |
"per_subtask": {
|
| 3180 |
"SC": {
|
| 3181 |
"accuracy": 1.0,
|
| 3182 |
-
"count":
|
| 3183 |
},
|
| 3184 |
"UC": {
|
| 3185 |
"accuracy": 0.96,
|
| 3186 |
-
"count":
|
| 3187 |
},
|
| 3188 |
"US": {
|
| 3189 |
-
"accuracy": 0.
|
| 3190 |
-
"count":
|
| 3191 |
}
|
| 3192 |
}
|
| 3193 |
},
|
| 3194 |
"add_random": {
|
| 3195 |
"full_accuracy": 1.0,
|
|
|
|
| 3196 |
"n_examples": 200,
|
| 3197 |
"per_subtask": {
|
| 3198 |
"SA": {
|
| 3199 |
"accuracy": 1.0,
|
| 3200 |
-
"count":
|
| 3201 |
},
|
| 3202 |
"SC": {
|
| 3203 |
"accuracy": 1.0,
|
| 3204 |
-
"count":
|
| 3205 |
},
|
| 3206 |
"SS": {
|
| 3207 |
"accuracy": 1.0,
|
| 3208 |
-
"count":
|
| 3209 |
},
|
| 3210 |
"UC": {
|
| 3211 |
"accuracy": 1.0,
|
| 3212 |
-
"count":
|
| 3213 |
},
|
| 3214 |
"US": {
|
| 3215 |
"accuracy": 1.0,
|
| 3216 |
-
"count":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3217 |
}
|
| 3218 |
}
|
| 3219 |
},
|
| 3220 |
"add_C3": {
|
| 3221 |
"full_accuracy": 1.0,
|
| 3222 |
-
"
|
|
|
|
| 3223 |
"per_subtask": {
|
| 3224 |
"SA": {
|
| 3225 |
"accuracy": 1.0,
|
| 3226 |
-
"count":
|
| 3227 |
},
|
| 3228 |
"SC": {
|
| 3229 |
"accuracy": 1.0,
|
| 3230 |
-
"count":
|
| 3231 |
},
|
| 3232 |
"UC": {
|
| 3233 |
"accuracy": 1.0,
|
| 3234 |
-
"count":
|
| 3235 |
},
|
| 3236 |
"US": {
|
| 3237 |
"accuracy": 1.0,
|
| 3238 |
-
"count":
|
| 3239 |
}
|
| 3240 |
}
|
| 3241 |
},
|
| 3242 |
"add_C4": {
|
| 3243 |
-
"full_accuracy":
|
| 3244 |
-
"
|
|
|
|
| 3245 |
"per_subtask": {
|
| 3246 |
"SA": {
|
| 3247 |
"accuracy": 1.0,
|
| 3248 |
-
"count":
|
| 3249 |
},
|
| 3250 |
"SC": {
|
| 3251 |
"accuracy": 1.0,
|
| 3252 |
-
"count":
|
| 3253 |
},
|
| 3254 |
"UC": {
|
| 3255 |
-
"accuracy":
|
| 3256 |
-
"count":
|
| 3257 |
},
|
| 3258 |
"US": {
|
| 3259 |
"accuracy": 1.0,
|
| 3260 |
-
"count":
|
| 3261 |
}
|
| 3262 |
}
|
| 3263 |
},
|
| 3264 |
"add_C5": {
|
| 3265 |
"full_accuracy": 1.0,
|
| 3266 |
-
"
|
|
|
|
| 3267 |
"per_subtask": {
|
| 3268 |
"SA": {
|
| 3269 |
"accuracy": 1.0,
|
| 3270 |
-
"count":
|
| 3271 |
},
|
| 3272 |
"SC": {
|
| 3273 |
"accuracy": 1.0,
|
| 3274 |
-
"count":
|
| 3275 |
},
|
| 3276 |
"UC": {
|
| 3277 |
"accuracy": 1.0,
|
| 3278 |
-
"count":
|
| 3279 |
},
|
| 3280 |
"US": {
|
| 3281 |
"accuracy": 1.0,
|
| 3282 |
-
"count":
|
| 3283 |
}
|
| 3284 |
}
|
| 3285 |
},
|
| 3286 |
"add_C6": {
|
| 3287 |
"full_accuracy": 1.0,
|
| 3288 |
-
"
|
|
|
|
| 3289 |
"per_subtask": {
|
| 3290 |
"SC": {
|
| 3291 |
"accuracy": 1.0,
|
| 3292 |
-
"count":
|
| 3293 |
},
|
| 3294 |
"UC": {
|
| 3295 |
"accuracy": 1.0,
|
| 3296 |
-
"count":
|
| 3297 |
},
|
| 3298 |
"US": {
|
| 3299 |
"accuracy": 1.0,
|
| 3300 |
-
"count":
|
| 3301 |
}
|
| 3302 |
}
|
| 3303 |
},
|
| 3304 |
"sub_M0": {
|
| 3305 |
"full_accuracy": 1.0,
|
| 3306 |
-
"
|
|
|
|
| 3307 |
"per_subtask": {
|
| 3308 |
"MD": {
|
| 3309 |
"accuracy": 1.0,
|
| 3310 |
-
"count":
|
| 3311 |
},
|
| 3312 |
"ME": {
|
| 3313 |
"accuracy": 1.0,
|
| 3314 |
-
"count":
|
| 3315 |
}
|
| 3316 |
}
|
| 3317 |
},
|
| 3318 |
"sub_M1": {
|
| 3319 |
"full_accuracy": 1.0,
|
| 3320 |
-
"
|
|
|
|
| 3321 |
"per_subtask": {
|
| 3322 |
"MD": {
|
| 3323 |
"accuracy": 1.0,
|
| 3324 |
-
"count":
|
| 3325 |
},
|
| 3326 |
"MB": {
|
| 3327 |
"accuracy": 1.0,
|
| 3328 |
-
"count":
|
| 3329 |
},
|
| 3330 |
"ME": {
|
| 3331 |
"accuracy": 1.0,
|
| 3332 |
-
"count":
|
| 3333 |
},
|
| 3334 |
"UB": {
|
| 3335 |
"accuracy": 1.0,
|
| 3336 |
-
"count":
|
| 3337 |
}
|
| 3338 |
}
|
| 3339 |
},
|
| 3340 |
"sub_M2": {
|
| 3341 |
"full_accuracy": 1.0,
|
| 3342 |
-
"
|
|
|
|
| 3343 |
"per_subtask": {
|
| 3344 |
"MD": {
|
| 3345 |
"accuracy": 1.0,
|
| 3346 |
-
"count":
|
| 3347 |
},
|
| 3348 |
"MB": {
|
| 3349 |
"accuracy": 1.0,
|
| 3350 |
-
"count":
|
| 3351 |
},
|
| 3352 |
"ME": {
|
| 3353 |
"accuracy": 1.0,
|
| 3354 |
-
"count":
|
| 3355 |
},
|
| 3356 |
"UB": {
|
| 3357 |
"accuracy": 1.0,
|
| 3358 |
-
"count":
|
| 3359 |
},
|
| 3360 |
"UD": {
|
| 3361 |
"accuracy": 1.0,
|
| 3362 |
-
"count":
|
| 3363 |
}
|
| 3364 |
}
|
| 3365 |
},
|
| 3366 |
"sub_M3": {
|
| 3367 |
"full_accuracy": 1.0,
|
| 3368 |
-
"
|
|
|
|
| 3369 |
"per_subtask": {
|
| 3370 |
"MD": {
|
| 3371 |
"accuracy": 1.0,
|
| 3372 |
-
"count":
|
| 3373 |
},
|
| 3374 |
"MB": {
|
| 3375 |
"accuracy": 1.0,
|
| 3376 |
-
"count":
|
| 3377 |
},
|
| 3378 |
"ME": {
|
| 3379 |
"accuracy": 1.0,
|
| 3380 |
-
"count":
|
| 3381 |
},
|
| 3382 |
"UB": {
|
| 3383 |
"accuracy": 1.0,
|
| 3384 |
-
"count":
|
| 3385 |
},
|
| 3386 |
"UD": {
|
| 3387 |
"accuracy": 1.0,
|
| 3388 |
-
"count":
|
| 3389 |
}
|
| 3390 |
}
|
| 3391 |
},
|
| 3392 |
"sub_M4": {
|
| 3393 |
"full_accuracy": 1.0,
|
| 3394 |
-
"
|
|
|
|
| 3395 |
"per_subtask": {
|
| 3396 |
"MD": {
|
| 3397 |
"accuracy": 1.0,
|
| 3398 |
-
"count":
|
| 3399 |
},
|
| 3400 |
"MB": {
|
| 3401 |
"accuracy": 1.0,
|
| 3402 |
-
"count":
|
| 3403 |
},
|
| 3404 |
"UB": {
|
| 3405 |
"accuracy": 1.0,
|
| 3406 |
-
"count":
|
| 3407 |
},
|
| 3408 |
"UD": {
|
| 3409 |
"accuracy": 1.0,
|
| 3410 |
-
"count":
|
| 3411 |
}
|
| 3412 |
}
|
| 3413 |
},
|
| 3414 |
"sub_M5": {
|
| 3415 |
-
"full_accuracy": 0.
|
| 3416 |
-
"
|
|
|
|
| 3417 |
"per_subtask": {
|
| 3418 |
"MD": {
|
| 3419 |
"accuracy": 1.0,
|
| 3420 |
-
"count":
|
| 3421 |
},
|
| 3422 |
"MB": {
|
| 3423 |
"accuracy": 1.0,
|
| 3424 |
-
"count":
|
| 3425 |
},
|
| 3426 |
"UB": {
|
| 3427 |
-
"accuracy": 0.
|
| 3428 |
-
"count":
|
| 3429 |
},
|
| 3430 |
"UD": {
|
| 3431 |
-
"accuracy":
|
| 3432 |
-
"count":
|
| 3433 |
}
|
| 3434 |
}
|
| 3435 |
},
|
| 3436 |
"sub_random": {
|
| 3437 |
"full_accuracy": 1.0,
|
|
|
|
| 3438 |
"n_examples": 200,
|
| 3439 |
"per_subtask": {
|
| 3440 |
"MD": {
|
| 3441 |
"accuracy": 1.0,
|
| 3442 |
-
"count":
|
| 3443 |
},
|
| 3444 |
"MB": {
|
| 3445 |
"accuracy": 1.0,
|
| 3446 |
-
"count":
|
| 3447 |
},
|
| 3448 |
"ME": {
|
| 3449 |
"accuracy": 1.0,
|
|
@@ -3451,85 +3577,89 @@
|
|
| 3451 |
},
|
| 3452 |
"UB": {
|
| 3453 |
"accuracy": 1.0,
|
| 3454 |
-
"count":
|
| 3455 |
},
|
| 3456 |
"UD": {
|
| 3457 |
"accuracy": 1.0,
|
| 3458 |
-
"count":
|
| 3459 |
}
|
| 3460 |
}
|
| 3461 |
},
|
| 3462 |
"sub_B3": {
|
| 3463 |
"full_accuracy": 1.0,
|
| 3464 |
-
"
|
|
|
|
| 3465 |
"per_subtask": {
|
| 3466 |
"MD": {
|
| 3467 |
"accuracy": 1.0,
|
| 3468 |
-
"count":
|
| 3469 |
},
|
| 3470 |
"MB": {
|
| 3471 |
"accuracy": 1.0,
|
| 3472 |
-
"count":
|
| 3473 |
},
|
| 3474 |
"UB": {
|
| 3475 |
"accuracy": 1.0,
|
| 3476 |
-
"count":
|
| 3477 |
},
|
| 3478 |
"UD": {
|
| 3479 |
"accuracy": 1.0,
|
| 3480 |
-
"count":
|
| 3481 |
}
|
| 3482 |
}
|
| 3483 |
},
|
| 3484 |
"sub_B4": {
|
| 3485 |
"full_accuracy": 1.0,
|
| 3486 |
-
"
|
|
|
|
| 3487 |
"per_subtask": {
|
| 3488 |
"MD": {
|
| 3489 |
"accuracy": 1.0,
|
| 3490 |
-
"count":
|
| 3491 |
},
|
| 3492 |
"MB": {
|
| 3493 |
"accuracy": 1.0,
|
| 3494 |
-
"count":
|
| 3495 |
},
|
| 3496 |
"UB": {
|
| 3497 |
"accuracy": 1.0,
|
| 3498 |
-
"count":
|
| 3499 |
},
|
| 3500 |
"UD": {
|
| 3501 |
"accuracy": 1.0,
|
| 3502 |
-
"count":
|
| 3503 |
}
|
| 3504 |
}
|
| 3505 |
},
|
| 3506 |
"sub_B5": {
|
| 3507 |
"full_accuracy": 1.0,
|
| 3508 |
-
"
|
|
|
|
| 3509 |
"per_subtask": {
|
| 3510 |
"MD": {
|
| 3511 |
"accuracy": 1.0,
|
| 3512 |
-
"count":
|
| 3513 |
},
|
| 3514 |
"MB": {
|
| 3515 |
"accuracy": 1.0,
|
| 3516 |
-
"count":
|
| 3517 |
},
|
| 3518 |
"UB": {
|
| 3519 |
"accuracy": 1.0,
|
| 3520 |
-
"count":
|
| 3521 |
},
|
| 3522 |
"UD": {
|
| 3523 |
"accuracy": 1.0,
|
| 3524 |
-
"count":
|
| 3525 |
}
|
| 3526 |
}
|
| 3527 |
}
|
| 3528 |
},
|
| 3529 |
"summary": {
|
| 3530 |
-
"overall_accuracy": 0.
|
| 3531 |
-
"
|
| 3532 |
-
"
|
|
|
|
| 3533 |
}
|
| 3534 |
},
|
| 3535 |
"sorl_overall_accuracy": 0.9945833333333334,
|
|
|
|
| 2530 |
"K": null,
|
| 2531 |
"mode": "sft",
|
| 2532 |
"n_digits": 6,
|
| 2533 |
+
"n_per_split": 50
|
| 2534 |
},
|
| 2535 |
"splits": {
|
| 2536 |
"add_S0": {
|
| 2537 |
"full_accuracy": 1.0,
|
| 2538 |
+
"digit_accuracy": 1.0,
|
| 2539 |
+
"n_examples": 50,
|
| 2540 |
"per_subtask": {
|
| 2541 |
"SA": {
|
| 2542 |
"accuracy": 1.0,
|
| 2543 |
+
"count": 295
|
| 2544 |
},
|
| 2545 |
"SS": {
|
| 2546 |
"accuracy": 1.0,
|
| 2547 |
+
"count": 55
|
| 2548 |
}
|
| 2549 |
}
|
| 2550 |
},
|
| 2551 |
"add_S1": {
|
| 2552 |
"full_accuracy": 1.0,
|
| 2553 |
+
"digit_accuracy": 1.0,
|
| 2554 |
+
"n_examples": 50,
|
| 2555 |
"per_subtask": {
|
| 2556 |
"SA": {
|
| 2557 |
"accuracy": 1.0,
|
| 2558 |
+
"count": 126
|
| 2559 |
},
|
| 2560 |
"SC": {
|
| 2561 |
"accuracy": 1.0,
|
| 2562 |
+
"count": 79
|
| 2563 |
},
|
| 2564 |
"SS": {
|
| 2565 |
"accuracy": 1.0,
|
| 2566 |
+
"count": 21
|
| 2567 |
},
|
| 2568 |
"UC": {
|
| 2569 |
"accuracy": 1.0,
|
| 2570 |
+
"count": 124
|
| 2571 |
}
|
| 2572 |
}
|
| 2573 |
},
|
| 2574 |
"add_S2": {
|
| 2575 |
"full_accuracy": 1.0,
|
| 2576 |
+
"digit_accuracy": 1.0,
|
| 2577 |
+
"n_examples": 50,
|
| 2578 |
"per_subtask": {
|
| 2579 |
"SA": {
|
| 2580 |
"accuracy": 1.0,
|
| 2581 |
+
"count": 75
|
| 2582 |
},
|
| 2583 |
"SC": {
|
| 2584 |
"accuracy": 1.0,
|
| 2585 |
+
"count": 62
|
| 2586 |
},
|
| 2587 |
"SS": {
|
| 2588 |
"accuracy": 1.0,
|
| 2589 |
+
"count": 39
|
| 2590 |
},
|
| 2591 |
"UC": {
|
| 2592 |
"accuracy": 1.0,
|
| 2593 |
+
"count": 111
|
| 2594 |
},
|
| 2595 |
"US": {
|
| 2596 |
"accuracy": 1.0,
|
| 2597 |
+
"count": 63
|
| 2598 |
}
|
| 2599 |
}
|
| 2600 |
},
|
| 2601 |
"add_S3": {
|
| 2602 |
+
"full_accuracy": 1.0,
|
| 2603 |
+
"digit_accuracy": 1.0,
|
| 2604 |
+
"n_examples": 50,
|
| 2605 |
"per_subtask": {
|
| 2606 |
"SA": {
|
| 2607 |
"accuracy": 1.0,
|
| 2608 |
+
"count": 60
|
| 2609 |
},
|
| 2610 |
"SC": {
|
| 2611 |
"accuracy": 1.0,
|
| 2612 |
+
"count": 57
|
| 2613 |
},
|
| 2614 |
"SS": {
|
| 2615 |
"accuracy": 1.0,
|
| 2616 |
+
"count": 19
|
| 2617 |
},
|
| 2618 |
"UC": {
|
| 2619 |
+
"accuracy": 1.0,
|
| 2620 |
+
"count": 104
|
| 2621 |
},
|
| 2622 |
"US": {
|
| 2623 |
"accuracy": 1.0,
|
| 2624 |
+
"count": 110
|
| 2625 |
}
|
| 2626 |
}
|
| 2627 |
},
|
| 2628 |
"add_S4": {
|
| 2629 |
+
"full_accuracy": 0.9,
|
| 2630 |
+
"digit_accuracy": 0.9828571428571429,
|
| 2631 |
+
"n_examples": 50,
|
| 2632 |
"per_subtask": {
|
| 2633 |
"SA": {
|
| 2634 |
"accuracy": 1.0,
|
| 2635 |
+
"count": 48
|
| 2636 |
},
|
| 2637 |
"SC": {
|
| 2638 |
"accuracy": 1.0,
|
| 2639 |
+
"count": 52
|
| 2640 |
},
|
| 2641 |
"SS": {
|
| 2642 |
"accuracy": 1.0,
|
| 2643 |
+
"count": 7
|
| 2644 |
},
|
| 2645 |
"UC": {
|
| 2646 |
+
"accuracy": 0.9438202247191011,
|
| 2647 |
+
"count": 89
|
| 2648 |
},
|
| 2649 |
"US": {
|
| 2650 |
+
"accuracy": 0.9935064935064936,
|
| 2651 |
+
"count": 154
|
| 2652 |
}
|
| 2653 |
}
|
| 2654 |
},
|
| 2655 |
"add_S5": {
|
| 2656 |
+
"full_accuracy": 0.58,
|
| 2657 |
+
"digit_accuracy": 0.8971428571428571,
|
| 2658 |
+
"n_examples": 50,
|
| 2659 |
"per_subtask": {
|
| 2660 |
"SA": {
|
| 2661 |
"accuracy": 1.0,
|
| 2662 |
+
"count": 50
|
| 2663 |
},
|
| 2664 |
"SC": {
|
| 2665 |
"accuracy": 1.0,
|
| 2666 |
+
"count": 50
|
| 2667 |
},
|
| 2668 |
"UC": {
|
| 2669 |
+
"accuracy": 0.72,
|
| 2670 |
+
"count": 50
|
| 2671 |
},
|
| 2672 |
"US": {
|
| 2673 |
+
"accuracy": 0.89,
|
| 2674 |
+
"count": 200
|
| 2675 |
}
|
| 2676 |
}
|
| 2677 |
},
|
| 2678 |
"add_S6": {
|
| 2679 |
+
"full_accuracy": 0.92,
|
| 2680 |
+
"digit_accuracy": 0.9685714285714285,
|
| 2681 |
+
"n_examples": 50,
|
| 2682 |
"per_subtask": {
|
| 2683 |
"SC": {
|
| 2684 |
"accuracy": 1.0,
|
| 2685 |
+
"count": 50
|
| 2686 |
},
|
| 2687 |
"UC": {
|
| 2688 |
"accuracy": 0.94,
|
| 2689 |
+
"count": 50
|
| 2690 |
},
|
| 2691 |
"US": {
|
| 2692 |
+
"accuracy": 0.968,
|
| 2693 |
+
"count": 250
|
| 2694 |
}
|
| 2695 |
}
|
| 2696 |
},
|
| 2697 |
"add_random": {
|
| 2698 |
"full_accuracy": 1.0,
|
| 2699 |
+
"digit_accuracy": 1.0,
|
| 2700 |
"n_examples": 200,
|
| 2701 |
"per_subtask": {
|
| 2702 |
"SA": {
|
| 2703 |
"accuracy": 1.0,
|
| 2704 |
+
"count": 431
|
| 2705 |
},
|
| 2706 |
"SC": {
|
| 2707 |
"accuracy": 1.0,
|
| 2708 |
+
"count": 316
|
| 2709 |
},
|
| 2710 |
"SS": {
|
| 2711 |
"accuracy": 1.0,
|
| 2712 |
+
"count": 39
|
| 2713 |
},
|
| 2714 |
"UC": {
|
| 2715 |
"accuracy": 1.0,
|
| 2716 |
+
"count": 560
|
| 2717 |
},
|
| 2718 |
"US": {
|
| 2719 |
"accuracy": 1.0,
|
| 2720 |
+
"count": 54
|
| 2721 |
+
}
|
| 2722 |
+
}
|
| 2723 |
+
},
|
| 2724 |
+
"add_C1": {
|
| 2725 |
+
"full_accuracy": 1.0,
|
| 2726 |
+
"digit_accuracy": 1.0,
|
| 2727 |
+
"n_examples": 50,
|
| 2728 |
+
"per_subtask": {
|
| 2729 |
+
"SA": {
|
| 2730 |
+
"accuracy": 1.0,
|
| 2731 |
+
"count": 250
|
| 2732 |
+
},
|
| 2733 |
+
"SC": {
|
| 2734 |
+
"accuracy": 1.0,
|
| 2735 |
+
"count": 50
|
| 2736 |
+
},
|
| 2737 |
+
"UC": {
|
| 2738 |
+
"accuracy": 1.0,
|
| 2739 |
+
"count": 50
|
| 2740 |
+
}
|
| 2741 |
+
}
|
| 2742 |
+
},
|
| 2743 |
+
"add_C2": {
|
| 2744 |
+
"full_accuracy": 1.0,
|
| 2745 |
+
"digit_accuracy": 1.0,
|
| 2746 |
+
"n_examples": 50,
|
| 2747 |
+
"per_subtask": {
|
| 2748 |
+
"SA": {
|
| 2749 |
+
"accuracy": 1.0,
|
| 2750 |
+
"count": 200
|
| 2751 |
+
},
|
| 2752 |
+
"SC": {
|
| 2753 |
+
"accuracy": 1.0,
|
| 2754 |
+
"count": 50
|
| 2755 |
+
},
|
| 2756 |
+
"UC": {
|
| 2757 |
+
"accuracy": 1.0,
|
| 2758 |
+
"count": 83
|
| 2759 |
+
},
|
| 2760 |
+
"US": {
|
| 2761 |
+
"accuracy": 1.0,
|
| 2762 |
+
"count": 17
|
| 2763 |
}
|
| 2764 |
}
|
| 2765 |
},
|
| 2766 |
"add_C3": {
|
| 2767 |
+
"full_accuracy": 1.0,
|
| 2768 |
+
"digit_accuracy": 1.0,
|
| 2769 |
+
"n_examples": 50,
|
| 2770 |
"per_subtask": {
|
| 2771 |
"SA": {
|
| 2772 |
"accuracy": 1.0,
|
| 2773 |
+
"count": 150
|
| 2774 |
},
|
| 2775 |
"SC": {
|
| 2776 |
"accuracy": 1.0,
|
| 2777 |
+
"count": 50
|
| 2778 |
},
|
| 2779 |
"UC": {
|
| 2780 |
+
"accuracy": 1.0,
|
| 2781 |
+
"count": 100
|
| 2782 |
},
|
| 2783 |
"US": {
|
| 2784 |
"accuracy": 1.0,
|
| 2785 |
+
"count": 50
|
| 2786 |
}
|
| 2787 |
}
|
| 2788 |
},
|
| 2789 |
"add_C4": {
|
| 2790 |
+
"full_accuracy": 0.9,
|
| 2791 |
+
"digit_accuracy": 0.9857142857142858,
|
| 2792 |
+
"n_examples": 50,
|
| 2793 |
"per_subtask": {
|
| 2794 |
"SA": {
|
| 2795 |
+
"accuracy": 1.0,
|
| 2796 |
+
"count": 100
|
| 2797 |
},
|
| 2798 |
"SC": {
|
| 2799 |
"accuracy": 1.0,
|
| 2800 |
+
"count": 50
|
| 2801 |
},
|
| 2802 |
"UC": {
|
| 2803 |
+
"accuracy": 0.9621212121212122,
|
| 2804 |
+
"count": 132
|
| 2805 |
},
|
| 2806 |
"US": {
|
| 2807 |
+
"accuracy": 1.0,
|
| 2808 |
+
"count": 68
|
| 2809 |
}
|
| 2810 |
}
|
| 2811 |
},
|
| 2812 |
"add_C5": {
|
| 2813 |
+
"full_accuracy": 0.98,
|
| 2814 |
+
"digit_accuracy": 0.9971428571428571,
|
| 2815 |
+
"n_examples": 50,
|
| 2816 |
"per_subtask": {
|
| 2817 |
"SA": {
|
| 2818 |
"accuracy": 1.0,
|
| 2819 |
+
"count": 50
|
| 2820 |
},
|
| 2821 |
"SC": {
|
| 2822 |
"accuracy": 1.0,
|
| 2823 |
+
"count": 50
|
| 2824 |
},
|
| 2825 |
"UC": {
|
| 2826 |
+
"accuracy": 1.0,
|
| 2827 |
+
"count": 146
|
| 2828 |
},
|
| 2829 |
"US": {
|
| 2830 |
+
"accuracy": 0.9903846153846154,
|
| 2831 |
+
"count": 104
|
| 2832 |
}
|
| 2833 |
}
|
| 2834 |
},
|
| 2835 |
"add_C6": {
|
| 2836 |
"full_accuracy": 1.0,
|
| 2837 |
+
"digit_accuracy": 1.0,
|
| 2838 |
+
"n_examples": 50,
|
| 2839 |
"per_subtask": {
|
| 2840 |
"SC": {
|
| 2841 |
"accuracy": 1.0,
|
| 2842 |
+
"count": 50
|
| 2843 |
},
|
| 2844 |
"UC": {
|
| 2845 |
"accuracy": 1.0,
|
| 2846 |
+
"count": 189
|
| 2847 |
},
|
| 2848 |
"US": {
|
| 2849 |
"accuracy": 1.0,
|
| 2850 |
+
"count": 111
|
| 2851 |
}
|
| 2852 |
}
|
| 2853 |
},
|
| 2854 |
"sub_M0": {
|
| 2855 |
"full_accuracy": 1.0,
|
| 2856 |
+
"digit_accuracy": 1.0,
|
| 2857 |
+
"n_examples": 50,
|
| 2858 |
"per_subtask": {
|
| 2859 |
"MD": {
|
| 2860 |
"accuracy": 1.0,
|
| 2861 |
+
"count": 303
|
| 2862 |
},
|
| 2863 |
"ME": {
|
| 2864 |
"accuracy": 1.0,
|
| 2865 |
+
"count": 47
|
| 2866 |
}
|
| 2867 |
}
|
| 2868 |
},
|
| 2869 |
"sub_M1": {
|
| 2870 |
+
"full_accuracy": 1.0,
|
| 2871 |
+
"digit_accuracy": 1.0,
|
| 2872 |
+
"n_examples": 50,
|
| 2873 |
"per_subtask": {
|
| 2874 |
"MD": {
|
| 2875 |
"accuracy": 1.0,
|
| 2876 |
+
"count": 141
|
| 2877 |
},
|
| 2878 |
"MB": {
|
| 2879 |
"accuracy": 1.0,
|
| 2880 |
+
"count": 72
|
| 2881 |
},
|
| 2882 |
"ME": {
|
| 2883 |
"accuracy": 1.0,
|
| 2884 |
+
"count": 18
|
| 2885 |
},
|
| 2886 |
"UB": {
|
| 2887 |
+
"accuracy": 1.0,
|
| 2888 |
+
"count": 119
|
| 2889 |
}
|
| 2890 |
}
|
| 2891 |
},
|
| 2892 |
"sub_M2": {
|
| 2893 |
"full_accuracy": 1.0,
|
| 2894 |
+
"digit_accuracy": 1.0,
|
| 2895 |
+
"n_examples": 50,
|
| 2896 |
"per_subtask": {
|
| 2897 |
"MD": {
|
| 2898 |
"accuracy": 1.0,
|
| 2899 |
+
"count": 112
|
| 2900 |
},
|
| 2901 |
"MB": {
|
| 2902 |
"accuracy": 1.0,
|
| 2903 |
+
"count": 53
|
| 2904 |
},
|
| 2905 |
"ME": {
|
| 2906 |
"accuracy": 1.0,
|
| 2907 |
+
"count": 47
|
| 2908 |
},
|
| 2909 |
"UB": {
|
| 2910 |
"accuracy": 1.0,
|
| 2911 |
+
"count": 85
|
| 2912 |
},
|
| 2913 |
"UD": {
|
| 2914 |
"accuracy": 1.0,
|
| 2915 |
+
"count": 53
|
| 2916 |
}
|
| 2917 |
}
|
| 2918 |
},
|
| 2919 |
"sub_M3": {
|
| 2920 |
"full_accuracy": 1.0,
|
| 2921 |
+
"digit_accuracy": 1.0,
|
| 2922 |
+
"n_examples": 50,
|
| 2923 |
"per_subtask": {
|
| 2924 |
"MD": {
|
| 2925 |
"accuracy": 1.0,
|
| 2926 |
+
"count": 97
|
| 2927 |
},
|
| 2928 |
"MB": {
|
| 2929 |
"accuracy": 1.0,
|
| 2930 |
+
"count": 51
|
| 2931 |
},
|
| 2932 |
"ME": {
|
| 2933 |
"accuracy": 1.0,
|
| 2934 |
+
"count": 27
|
| 2935 |
},
|
| 2936 |
"UB": {
|
| 2937 |
"accuracy": 1.0,
|
| 2938 |
+
"count": 74
|
| 2939 |
},
|
| 2940 |
"UD": {
|
| 2941 |
"accuracy": 1.0,
|
| 2942 |
+
"count": 101
|
| 2943 |
}
|
| 2944 |
}
|
| 2945 |
},
|
| 2946 |
"sub_M4": {
|
| 2947 |
+
"full_accuracy": 0.6,
|
| 2948 |
+
"digit_accuracy": 0.9428571428571428,
|
| 2949 |
+
"n_examples": 50,
|
| 2950 |
"per_subtask": {
|
| 2951 |
"MD": {
|
| 2952 |
"accuracy": 1.0,
|
| 2953 |
+
"count": 100
|
| 2954 |
},
|
| 2955 |
"MB": {
|
| 2956 |
"accuracy": 1.0,
|
| 2957 |
+
"count": 50
|
| 2958 |
},
|
| 2959 |
"UB": {
|
| 2960 |
+
"accuracy": 0.6,
|
| 2961 |
+
"count": 50
|
| 2962 |
},
|
| 2963 |
"UD": {
|
| 2964 |
+
"accuracy": 1.0,
|
| 2965 |
+
"count": 150
|
| 2966 |
}
|
| 2967 |
}
|
| 2968 |
},
|
| 2969 |
"sub_M5": {
|
| 2970 |
+
"full_accuracy": 0.42,
|
| 2971 |
+
"digit_accuracy": 0.8914285714285715,
|
| 2972 |
+
"n_examples": 50,
|
| 2973 |
"per_subtask": {
|
| 2974 |
"MD": {
|
| 2975 |
"accuracy": 1.0,
|
| 2976 |
+
"count": 50
|
| 2977 |
},
|
| 2978 |
"MB": {
|
| 2979 |
"accuracy": 1.0,
|
| 2980 |
+
"count": 50
|
| 2981 |
},
|
| 2982 |
"UB": {
|
| 2983 |
+
"accuracy": 0.7,
|
| 2984 |
+
"count": 50
|
| 2985 |
},
|
| 2986 |
"UD": {
|
| 2987 |
+
"accuracy": 0.885,
|
| 2988 |
+
"count": 200
|
| 2989 |
}
|
| 2990 |
}
|
| 2991 |
},
|
| 2992 |
"sub_random": {
|
| 2993 |
"full_accuracy": 1.0,
|
| 2994 |
+
"digit_accuracy": 1.0,
|
| 2995 |
"n_examples": 200,
|
| 2996 |
"per_subtask": {
|
| 2997 |
"MD": {
|
| 2998 |
"accuracy": 1.0,
|
| 2999 |
+
"count": 570
|
| 3000 |
},
|
| 3001 |
"MB": {
|
| 3002 |
"accuracy": 1.0,
|
| 3003 |
+
"count": 277
|
| 3004 |
},
|
| 3005 |
"ME": {
|
| 3006 |
"accuracy": 1.0,
|
|
|
|
| 3008 |
},
|
| 3009 |
"UB": {
|
| 3010 |
"accuracy": 1.0,
|
| 3011 |
+
"count": 471
|
| 3012 |
},
|
| 3013 |
"UD": {
|
| 3014 |
"accuracy": 1.0,
|
| 3015 |
+
"count": 29
|
| 3016 |
}
|
| 3017 |
}
|
| 3018 |
},
|
| 3019 |
"sub_B3": {
|
| 3020 |
+
"full_accuracy": 1.0,
|
| 3021 |
+
"digit_accuracy": 1.0,
|
| 3022 |
+
"n_examples": 50,
|
| 3023 |
"per_subtask": {
|
| 3024 |
"MD": {
|
| 3025 |
"accuracy": 1.0,
|
| 3026 |
+
"count": 150
|
| 3027 |
},
|
| 3028 |
"MB": {
|
| 3029 |
"accuracy": 1.0,
|
| 3030 |
+
"count": 50
|
| 3031 |
},
|
| 3032 |
"UB": {
|
| 3033 |
+
"accuracy": 1.0,
|
| 3034 |
+
"count": 101
|
| 3035 |
},
|
| 3036 |
"UD": {
|
| 3037 |
"accuracy": 1.0,
|
| 3038 |
+
"count": 49
|
| 3039 |
}
|
| 3040 |
}
|
| 3041 |
},
|
| 3042 |
"sub_B4": {
|
| 3043 |
"full_accuracy": 0.94,
|
| 3044 |
+
"digit_accuracy": 0.9914285714285714,
|
| 3045 |
+
"n_examples": 50,
|
| 3046 |
"per_subtask": {
|
| 3047 |
"MD": {
|
| 3048 |
"accuracy": 1.0,
|
| 3049 |
+
"count": 100
|
| 3050 |
},
|
| 3051 |
"MB": {
|
| 3052 |
"accuracy": 1.0,
|
| 3053 |
+
"count": 50
|
| 3054 |
},
|
| 3055 |
"UB": {
|
| 3056 |
+
"accuracy": 0.9752066115702479,
|
| 3057 |
+
"count": 121
|
| 3058 |
},
|
| 3059 |
"UD": {
|
| 3060 |
"accuracy": 1.0,
|
| 3061 |
+
"count": 79
|
| 3062 |
}
|
| 3063 |
}
|
| 3064 |
},
|
| 3065 |
"sub_B5": {
|
| 3066 |
"full_accuracy": 0.98,
|
| 3067 |
+
"digit_accuracy": 0.9971428571428571,
|
| 3068 |
+
"n_examples": 50,
|
| 3069 |
"per_subtask": {
|
| 3070 |
"MD": {
|
| 3071 |
"accuracy": 1.0,
|
| 3072 |
+
"count": 50
|
| 3073 |
},
|
| 3074 |
"MB": {
|
| 3075 |
"accuracy": 1.0,
|
| 3076 |
+
"count": 50
|
| 3077 |
},
|
| 3078 |
"UB": {
|
| 3079 |
+
"accuracy": 0.993421052631579,
|
| 3080 |
+
"count": 152
|
| 3081 |
},
|
| 3082 |
"UD": {
|
| 3083 |
+
"accuracy": 1.0,
|
| 3084 |
+
"count": 98
|
| 3085 |
}
|
| 3086 |
}
|
| 3087 |
}
|
| 3088 |
},
|
| 3089 |
"summary": {
|
| 3090 |
+
"overall_accuracy": 0.94,
|
| 3091 |
+
"digit_accuracy": 0.9883809523809524,
|
| 3092 |
+
"total_examples": 1500,
|
| 3093 |
+
"n_splits": 24
|
| 3094 |
}
|
| 3095 |
},
|
| 3096 |
"sorl_eval": {
|
|
|
|
| 3099 |
"K": 1,
|
| 3100 |
"mode": "sorl",
|
| 3101 |
"n_digits": 6,
|
| 3102 |
+
"n_per_split": 50
|
| 3103 |
},
|
| 3104 |
"splits": {
|
| 3105 |
"add_S0": {
|
| 3106 |
"full_accuracy": 1.0,
|
| 3107 |
+
"digit_accuracy": 1.0,
|
| 3108 |
+
"n_examples": 50,
|
| 3109 |
"per_subtask": {
|
| 3110 |
"SA": {
|
| 3111 |
"accuracy": 1.0,
|
| 3112 |
+
"count": 295
|
| 3113 |
},
|
| 3114 |
"SS": {
|
| 3115 |
"accuracy": 1.0,
|
| 3116 |
+
"count": 55
|
| 3117 |
}
|
| 3118 |
}
|
| 3119 |
},
|
| 3120 |
"add_S1": {
|
| 3121 |
"full_accuracy": 1.0,
|
| 3122 |
+
"digit_accuracy": 1.0,
|
| 3123 |
+
"n_examples": 50,
|
| 3124 |
"per_subtask": {
|
| 3125 |
"SA": {
|
| 3126 |
"accuracy": 1.0,
|
| 3127 |
+
"count": 126
|
| 3128 |
},
|
| 3129 |
"SC": {
|
| 3130 |
"accuracy": 1.0,
|
| 3131 |
+
"count": 79
|
| 3132 |
},
|
| 3133 |
"SS": {
|
| 3134 |
"accuracy": 1.0,
|
| 3135 |
+
"count": 21
|
| 3136 |
},
|
| 3137 |
"UC": {
|
| 3138 |
"accuracy": 1.0,
|
| 3139 |
+
"count": 124
|
| 3140 |
}
|
| 3141 |
}
|
| 3142 |
},
|
| 3143 |
"add_S2": {
|
| 3144 |
"full_accuracy": 1.0,
|
| 3145 |
+
"digit_accuracy": 1.0,
|
| 3146 |
+
"n_examples": 50,
|
| 3147 |
"per_subtask": {
|
| 3148 |
"SA": {
|
| 3149 |
"accuracy": 1.0,
|
| 3150 |
+
"count": 75
|
| 3151 |
},
|
| 3152 |
"SC": {
|
| 3153 |
"accuracy": 1.0,
|
| 3154 |
+
"count": 62
|
| 3155 |
},
|
| 3156 |
"SS": {
|
| 3157 |
"accuracy": 1.0,
|
| 3158 |
+
"count": 39
|
| 3159 |
},
|
| 3160 |
"UC": {
|
| 3161 |
"accuracy": 1.0,
|
| 3162 |
+
"count": 111
|
| 3163 |
},
|
| 3164 |
"US": {
|
| 3165 |
"accuracy": 1.0,
|
| 3166 |
+
"count": 63
|
| 3167 |
}
|
| 3168 |
}
|
| 3169 |
},
|
| 3170 |
"add_S3": {
|
| 3171 |
"full_accuracy": 1.0,
|
| 3172 |
+
"digit_accuracy": 1.0,
|
| 3173 |
+
"n_examples": 50,
|
| 3174 |
"per_subtask": {
|
| 3175 |
"SA": {
|
| 3176 |
"accuracy": 1.0,
|
| 3177 |
+
"count": 60
|
| 3178 |
},
|
| 3179 |
"SC": {
|
| 3180 |
"accuracy": 1.0,
|
| 3181 |
+
"count": 57
|
| 3182 |
},
|
| 3183 |
"SS": {
|
| 3184 |
"accuracy": 1.0,
|
| 3185 |
+
"count": 19
|
| 3186 |
},
|
| 3187 |
"UC": {
|
| 3188 |
"accuracy": 1.0,
|
| 3189 |
+
"count": 104
|
| 3190 |
},
|
| 3191 |
"US": {
|
| 3192 |
"accuracy": 1.0,
|
| 3193 |
+
"count": 110
|
| 3194 |
}
|
| 3195 |
}
|
| 3196 |
},
|
| 3197 |
"add_S4": {
|
| 3198 |
"full_accuracy": 1.0,
|
| 3199 |
+
"digit_accuracy": 1.0,
|
| 3200 |
+
"n_examples": 50,
|
| 3201 |
"per_subtask": {
|
| 3202 |
"SA": {
|
| 3203 |
"accuracy": 1.0,
|
| 3204 |
+
"count": 48
|
| 3205 |
},
|
| 3206 |
"SC": {
|
| 3207 |
"accuracy": 1.0,
|
| 3208 |
+
"count": 52
|
| 3209 |
},
|
| 3210 |
"SS": {
|
| 3211 |
"accuracy": 1.0,
|
| 3212 |
+
"count": 7
|
| 3213 |
},
|
| 3214 |
"UC": {
|
| 3215 |
"accuracy": 1.0,
|
| 3216 |
+
"count": 89
|
| 3217 |
},
|
| 3218 |
"US": {
|
| 3219 |
"accuracy": 1.0,
|
| 3220 |
+
"count": 154
|
| 3221 |
}
|
| 3222 |
}
|
| 3223 |
},
|
| 3224 |
"add_S5": {
|
| 3225 |
+
"full_accuracy": 1.0,
|
| 3226 |
+
"digit_accuracy": 1.0,
|
| 3227 |
+
"n_examples": 50,
|
| 3228 |
"per_subtask": {
|
| 3229 |
"SA": {
|
| 3230 |
"accuracy": 1.0,
|
| 3231 |
+
"count": 50
|
| 3232 |
},
|
| 3233 |
"SC": {
|
| 3234 |
"accuracy": 1.0,
|
| 3235 |
+
"count": 50
|
| 3236 |
},
|
| 3237 |
"UC": {
|
| 3238 |
+
"accuracy": 1.0,
|
| 3239 |
+
"count": 50
|
| 3240 |
},
|
| 3241 |
"US": {
|
| 3242 |
"accuracy": 1.0,
|
| 3243 |
+
"count": 200
|
| 3244 |
}
|
| 3245 |
}
|
| 3246 |
},
|
| 3247 |
"add_S6": {
|
| 3248 |
"full_accuracy": 0.96,
|
| 3249 |
+
"digit_accuracy": 0.9914285714285714,
|
| 3250 |
+
"n_examples": 50,
|
| 3251 |
"per_subtask": {
|
| 3252 |
"SC": {
|
| 3253 |
"accuracy": 1.0,
|
| 3254 |
+
"count": 50
|
| 3255 |
},
|
| 3256 |
"UC": {
|
| 3257 |
"accuracy": 0.96,
|
| 3258 |
+
"count": 50
|
| 3259 |
},
|
| 3260 |
"US": {
|
| 3261 |
+
"accuracy": 0.996,
|
| 3262 |
+
"count": 250
|
| 3263 |
}
|
| 3264 |
}
|
| 3265 |
},
|
| 3266 |
"add_random": {
|
| 3267 |
"full_accuracy": 1.0,
|
| 3268 |
+
"digit_accuracy": 1.0,
|
| 3269 |
"n_examples": 200,
|
| 3270 |
"per_subtask": {
|
| 3271 |
"SA": {
|
| 3272 |
"accuracy": 1.0,
|
| 3273 |
+
"count": 431
|
| 3274 |
},
|
| 3275 |
"SC": {
|
| 3276 |
"accuracy": 1.0,
|
| 3277 |
+
"count": 316
|
| 3278 |
},
|
| 3279 |
"SS": {
|
| 3280 |
"accuracy": 1.0,
|
| 3281 |
+
"count": 39
|
| 3282 |
},
|
| 3283 |
"UC": {
|
| 3284 |
"accuracy": 1.0,
|
| 3285 |
+
"count": 560
|
| 3286 |
},
|
| 3287 |
"US": {
|
| 3288 |
"accuracy": 1.0,
|
| 3289 |
+
"count": 54
|
| 3290 |
+
}
|
| 3291 |
+
}
|
| 3292 |
+
},
|
| 3293 |
+
"add_C1": {
|
| 3294 |
+
"full_accuracy": 1.0,
|
| 3295 |
+
"digit_accuracy": 1.0,
|
| 3296 |
+
"n_examples": 50,
|
| 3297 |
+
"per_subtask": {
|
| 3298 |
+
"SA": {
|
| 3299 |
+
"accuracy": 1.0,
|
| 3300 |
+
"count": 250
|
| 3301 |
+
},
|
| 3302 |
+
"SC": {
|
| 3303 |
+
"accuracy": 1.0,
|
| 3304 |
+
"count": 50
|
| 3305 |
+
},
|
| 3306 |
+
"UC": {
|
| 3307 |
+
"accuracy": 1.0,
|
| 3308 |
+
"count": 50
|
| 3309 |
+
}
|
| 3310 |
+
}
|
| 3311 |
+
},
|
| 3312 |
+
"add_C2": {
|
| 3313 |
+
"full_accuracy": 0.98,
|
| 3314 |
+
"digit_accuracy": 0.9971428571428571,
|
| 3315 |
+
"n_examples": 50,
|
| 3316 |
+
"per_subtask": {
|
| 3317 |
+
"SA": {
|
| 3318 |
+
"accuracy": 1.0,
|
| 3319 |
+
"count": 200
|
| 3320 |
+
},
|
| 3321 |
+
"SC": {
|
| 3322 |
+
"accuracy": 1.0,
|
| 3323 |
+
"count": 50
|
| 3324 |
+
},
|
| 3325 |
+
"UC": {
|
| 3326 |
+
"accuracy": 0.9879518072289156,
|
| 3327 |
+
"count": 83
|
| 3328 |
+
},
|
| 3329 |
+
"US": {
|
| 3330 |
+
"accuracy": 1.0,
|
| 3331 |
+
"count": 17
|
| 3332 |
}
|
| 3333 |
}
|
| 3334 |
},
|
| 3335 |
"add_C3": {
|
| 3336 |
"full_accuracy": 1.0,
|
| 3337 |
+
"digit_accuracy": 1.0,
|
| 3338 |
+
"n_examples": 50,
|
| 3339 |
"per_subtask": {
|
| 3340 |
"SA": {
|
| 3341 |
"accuracy": 1.0,
|
| 3342 |
+
"count": 150
|
| 3343 |
},
|
| 3344 |
"SC": {
|
| 3345 |
"accuracy": 1.0,
|
| 3346 |
+
"count": 50
|
| 3347 |
},
|
| 3348 |
"UC": {
|
| 3349 |
"accuracy": 1.0,
|
| 3350 |
+
"count": 100
|
| 3351 |
},
|
| 3352 |
"US": {
|
| 3353 |
"accuracy": 1.0,
|
| 3354 |
+
"count": 50
|
| 3355 |
}
|
| 3356 |
}
|
| 3357 |
},
|
| 3358 |
"add_C4": {
|
| 3359 |
+
"full_accuracy": 1.0,
|
| 3360 |
+
"digit_accuracy": 1.0,
|
| 3361 |
+
"n_examples": 50,
|
| 3362 |
"per_subtask": {
|
| 3363 |
"SA": {
|
| 3364 |
"accuracy": 1.0,
|
| 3365 |
+
"count": 100
|
| 3366 |
},
|
| 3367 |
"SC": {
|
| 3368 |
"accuracy": 1.0,
|
| 3369 |
+
"count": 50
|
| 3370 |
},
|
| 3371 |
"UC": {
|
| 3372 |
+
"accuracy": 1.0,
|
| 3373 |
+
"count": 132
|
| 3374 |
},
|
| 3375 |
"US": {
|
| 3376 |
"accuracy": 1.0,
|
| 3377 |
+
"count": 68
|
| 3378 |
}
|
| 3379 |
}
|
| 3380 |
},
|
| 3381 |
"add_C5": {
|
| 3382 |
"full_accuracy": 1.0,
|
| 3383 |
+
"digit_accuracy": 1.0,
|
| 3384 |
+
"n_examples": 50,
|
| 3385 |
"per_subtask": {
|
| 3386 |
"SA": {
|
| 3387 |
"accuracy": 1.0,
|
| 3388 |
+
"count": 50
|
| 3389 |
},
|
| 3390 |
"SC": {
|
| 3391 |
"accuracy": 1.0,
|
| 3392 |
+
"count": 50
|
| 3393 |
},
|
| 3394 |
"UC": {
|
| 3395 |
"accuracy": 1.0,
|
| 3396 |
+
"count": 146
|
| 3397 |
},
|
| 3398 |
"US": {
|
| 3399 |
"accuracy": 1.0,
|
| 3400 |
+
"count": 104
|
| 3401 |
}
|
| 3402 |
}
|
| 3403 |
},
|
| 3404 |
"add_C6": {
|
| 3405 |
"full_accuracy": 1.0,
|
| 3406 |
+
"digit_accuracy": 1.0,
|
| 3407 |
+
"n_examples": 50,
|
| 3408 |
"per_subtask": {
|
| 3409 |
"SC": {
|
| 3410 |
"accuracy": 1.0,
|
| 3411 |
+
"count": 50
|
| 3412 |
},
|
| 3413 |
"UC": {
|
| 3414 |
"accuracy": 1.0,
|
| 3415 |
+
"count": 189
|
| 3416 |
},
|
| 3417 |
"US": {
|
| 3418 |
"accuracy": 1.0,
|
| 3419 |
+
"count": 111
|
| 3420 |
}
|
| 3421 |
}
|
| 3422 |
},
|
| 3423 |
"sub_M0": {
|
| 3424 |
"full_accuracy": 1.0,
|
| 3425 |
+
"digit_accuracy": 1.0,
|
| 3426 |
+
"n_examples": 50,
|
| 3427 |
"per_subtask": {
|
| 3428 |
"MD": {
|
| 3429 |
"accuracy": 1.0,
|
| 3430 |
+
"count": 303
|
| 3431 |
},
|
| 3432 |
"ME": {
|
| 3433 |
"accuracy": 1.0,
|
| 3434 |
+
"count": 47
|
| 3435 |
}
|
| 3436 |
}
|
| 3437 |
},
|
| 3438 |
"sub_M1": {
|
| 3439 |
"full_accuracy": 1.0,
|
| 3440 |
+
"digit_accuracy": 1.0,
|
| 3441 |
+
"n_examples": 50,
|
| 3442 |
"per_subtask": {
|
| 3443 |
"MD": {
|
| 3444 |
"accuracy": 1.0,
|
| 3445 |
+
"count": 141
|
| 3446 |
},
|
| 3447 |
"MB": {
|
| 3448 |
"accuracy": 1.0,
|
| 3449 |
+
"count": 72
|
| 3450 |
},
|
| 3451 |
"ME": {
|
| 3452 |
"accuracy": 1.0,
|
| 3453 |
+
"count": 18
|
| 3454 |
},
|
| 3455 |
"UB": {
|
| 3456 |
"accuracy": 1.0,
|
| 3457 |
+
"count": 119
|
| 3458 |
}
|
| 3459 |
}
|
| 3460 |
},
|
| 3461 |
"sub_M2": {
|
| 3462 |
"full_accuracy": 1.0,
|
| 3463 |
+
"digit_accuracy": 1.0,
|
| 3464 |
+
"n_examples": 50,
|
| 3465 |
"per_subtask": {
|
| 3466 |
"MD": {
|
| 3467 |
"accuracy": 1.0,
|
| 3468 |
+
"count": 112
|
| 3469 |
},
|
| 3470 |
"MB": {
|
| 3471 |
"accuracy": 1.0,
|
| 3472 |
+
"count": 53
|
| 3473 |
},
|
| 3474 |
"ME": {
|
| 3475 |
"accuracy": 1.0,
|
| 3476 |
+
"count": 47
|
| 3477 |
},
|
| 3478 |
"UB": {
|
| 3479 |
"accuracy": 1.0,
|
| 3480 |
+
"count": 85
|
| 3481 |
},
|
| 3482 |
"UD": {
|
| 3483 |
"accuracy": 1.0,
|
| 3484 |
+
"count": 53
|
| 3485 |
}
|
| 3486 |
}
|
| 3487 |
},
|
| 3488 |
"sub_M3": {
|
| 3489 |
"full_accuracy": 1.0,
|
| 3490 |
+
"digit_accuracy": 1.0,
|
| 3491 |
+
"n_examples": 50,
|
| 3492 |
"per_subtask": {
|
| 3493 |
"MD": {
|
| 3494 |
"accuracy": 1.0,
|
| 3495 |
+
"count": 97
|
| 3496 |
},
|
| 3497 |
"MB": {
|
| 3498 |
"accuracy": 1.0,
|
| 3499 |
+
"count": 51
|
| 3500 |
},
|
| 3501 |
"ME": {
|
| 3502 |
"accuracy": 1.0,
|
| 3503 |
+
"count": 27
|
| 3504 |
},
|
| 3505 |
"UB": {
|
| 3506 |
"accuracy": 1.0,
|
| 3507 |
+
"count": 74
|
| 3508 |
},
|
| 3509 |
"UD": {
|
| 3510 |
"accuracy": 1.0,
|
| 3511 |
+
"count": 101
|
| 3512 |
}
|
| 3513 |
}
|
| 3514 |
},
|
| 3515 |
"sub_M4": {
|
| 3516 |
"full_accuracy": 1.0,
|
| 3517 |
+
"digit_accuracy": 1.0,
|
| 3518 |
+
"n_examples": 50,
|
| 3519 |
"per_subtask": {
|
| 3520 |
"MD": {
|
| 3521 |
"accuracy": 1.0,
|
| 3522 |
+
"count": 100
|
| 3523 |
},
|
| 3524 |
"MB": {
|
| 3525 |
"accuracy": 1.0,
|
| 3526 |
+
"count": 50
|
| 3527 |
},
|
| 3528 |
"UB": {
|
| 3529 |
"accuracy": 1.0,
|
| 3530 |
+
"count": 50
|
| 3531 |
},
|
| 3532 |
"UD": {
|
| 3533 |
"accuracy": 1.0,
|
| 3534 |
+
"count": 150
|
| 3535 |
}
|
| 3536 |
}
|
| 3537 |
},
|
| 3538 |
"sub_M5": {
|
| 3539 |
+
"full_accuracy": 0.9,
|
| 3540 |
+
"digit_accuracy": 0.9857142857142858,
|
| 3541 |
+
"n_examples": 50,
|
| 3542 |
"per_subtask": {
|
| 3543 |
"MD": {
|
| 3544 |
"accuracy": 1.0,
|
| 3545 |
+
"count": 50
|
| 3546 |
},
|
| 3547 |
"MB": {
|
| 3548 |
"accuracy": 1.0,
|
| 3549 |
+
"count": 50
|
| 3550 |
},
|
| 3551 |
"UB": {
|
| 3552 |
+
"accuracy": 0.9,
|
| 3553 |
+
"count": 50
|
| 3554 |
},
|
| 3555 |
"UD": {
|
| 3556 |
+
"accuracy": 1.0,
|
| 3557 |
+
"count": 200
|
| 3558 |
}
|
| 3559 |
}
|
| 3560 |
},
|
| 3561 |
"sub_random": {
|
| 3562 |
"full_accuracy": 1.0,
|
| 3563 |
+
"digit_accuracy": 1.0,
|
| 3564 |
"n_examples": 200,
|
| 3565 |
"per_subtask": {
|
| 3566 |
"MD": {
|
| 3567 |
"accuracy": 1.0,
|
| 3568 |
+
"count": 570
|
| 3569 |
},
|
| 3570 |
"MB": {
|
| 3571 |
"accuracy": 1.0,
|
| 3572 |
+
"count": 277
|
| 3573 |
},
|
| 3574 |
"ME": {
|
| 3575 |
"accuracy": 1.0,
|
|
|
|
| 3577 |
},
|
| 3578 |
"UB": {
|
| 3579 |
"accuracy": 1.0,
|
| 3580 |
+
"count": 471
|
| 3581 |
},
|
| 3582 |
"UD": {
|
| 3583 |
"accuracy": 1.0,
|
| 3584 |
+
"count": 29
|
| 3585 |
}
|
| 3586 |
}
|
| 3587 |
},
|
| 3588 |
"sub_B3": {
|
| 3589 |
"full_accuracy": 1.0,
|
| 3590 |
+
"digit_accuracy": 1.0,
|
| 3591 |
+
"n_examples": 50,
|
| 3592 |
"per_subtask": {
|
| 3593 |
"MD": {
|
| 3594 |
"accuracy": 1.0,
|
| 3595 |
+
"count": 150
|
| 3596 |
},
|
| 3597 |
"MB": {
|
| 3598 |
"accuracy": 1.0,
|
| 3599 |
+
"count": 50
|
| 3600 |
},
|
| 3601 |
"UB": {
|
| 3602 |
"accuracy": 1.0,
|
| 3603 |
+
"count": 101
|
| 3604 |
},
|
| 3605 |
"UD": {
|
| 3606 |
"accuracy": 1.0,
|
| 3607 |
+
"count": 49
|
| 3608 |
}
|
| 3609 |
}
|
| 3610 |
},
|
| 3611 |
"sub_B4": {
|
| 3612 |
"full_accuracy": 1.0,
|
| 3613 |
+
"digit_accuracy": 1.0,
|
| 3614 |
+
"n_examples": 50,
|
| 3615 |
"per_subtask": {
|
| 3616 |
"MD": {
|
| 3617 |
"accuracy": 1.0,
|
| 3618 |
+
"count": 100
|
| 3619 |
},
|
| 3620 |
"MB": {
|
| 3621 |
"accuracy": 1.0,
|
| 3622 |
+
"count": 50
|
| 3623 |
},
|
| 3624 |
"UB": {
|
| 3625 |
"accuracy": 1.0,
|
| 3626 |
+
"count": 121
|
| 3627 |
},
|
| 3628 |
"UD": {
|
| 3629 |
"accuracy": 1.0,
|
| 3630 |
+
"count": 79
|
| 3631 |
}
|
| 3632 |
}
|
| 3633 |
},
|
| 3634 |
"sub_B5": {
|
| 3635 |
"full_accuracy": 1.0,
|
| 3636 |
+
"digit_accuracy": 1.0,
|
| 3637 |
+
"n_examples": 50,
|
| 3638 |
"per_subtask": {
|
| 3639 |
"MD": {
|
| 3640 |
"accuracy": 1.0,
|
| 3641 |
+
"count": 50
|
| 3642 |
},
|
| 3643 |
"MB": {
|
| 3644 |
"accuracy": 1.0,
|
| 3645 |
+
"count": 50
|
| 3646 |
},
|
| 3647 |
"UB": {
|
| 3648 |
"accuracy": 1.0,
|
| 3649 |
+
"count": 152
|
| 3650 |
},
|
| 3651 |
"UD": {
|
| 3652 |
"accuracy": 1.0,
|
| 3653 |
+
"count": 98
|
| 3654 |
}
|
| 3655 |
}
|
| 3656 |
}
|
| 3657 |
},
|
| 3658 |
"summary": {
|
| 3659 |
+
"overall_accuracy": 0.9946666666666667,
|
| 3660 |
+
"digit_accuracy": 0.9991428571428571,
|
| 3661 |
+
"total_examples": 1500,
|
| 3662 |
+
"n_splits": 24
|
| 3663 |
}
|
| 3664 |
},
|
| 3665 |
"sorl_overall_accuracy": 0.9945833333333334,
|