{ "acc": 35.699999999999996, "acc_norm": 36.0, "categories": { "elementary_school_math_continuation::addition::grades_1_2::easy": { "acc": 28.125, "acc_norm": 28.125, "norm_correct": 36, "raw_correct": 36, "total": 128 }, "elementary_school_math_continuation::comparison::grades_2_3::medium": { "acc": 27.27272727272727, "acc_norm": 27.27272727272727, "norm_correct": 12, "raw_correct": 12, "total": 44 }, "elementary_school_math_continuation::comparison_difference::grades_2_3::medium": { "acc": 25.0, "acc_norm": 25.0, "norm_correct": 12, "raw_correct": 12, "total": 48 }, "elementary_school_math_continuation::data::grades_2_3::easy": { "acc": 23.25581395348837, "acc_norm": 25.581395348837212, "norm_correct": 11, "raw_correct": 10, "total": 43 }, "elementary_school_math_continuation::division::grades_3_4::medium": { "acc": 25.925925925925924, "acc_norm": 24.074074074074073, "norm_correct": 13, "raw_correct": 14, "total": 54 }, "elementary_school_math_continuation::fractions_counting::grades_3_4::medium": { "acc": 20.0, "acc_norm": 20.0, "norm_correct": 10, "raw_correct": 10, "total": 50 }, "elementary_school_math_continuation::geometry_area::grades_4_5::medium": { "acc": 51.92307692307693, "acc_norm": 53.84615384615385, "norm_correct": 28, "raw_correct": 27, "total": 52 }, "elementary_school_math_continuation::geometry_perimeter::grades_4_5::medium": { "acc": 62.22222222222222, "acc_norm": 62.22222222222222, "norm_correct": 28, "raw_correct": 28, "total": 45 }, "elementary_school_math_continuation::measurement::grades_2_3::easy": { "acc": 32.89473684210527, "acc_norm": 32.89473684210527, "norm_correct": 25, "raw_correct": 25, "total": 76 }, "elementary_school_math_continuation::money::grades_3_4::medium": { "acc": 29.6875, "acc_norm": 29.6875, "norm_correct": 19, "raw_correct": 19, "total": 64 }, "elementary_school_math_continuation::multiplication::grades_3_4::medium": { "acc": 51.35135135135135, "acc_norm": 52.702702702702695, "norm_correct": 39, "raw_correct": 38, "total": 74 }, "elementary_school_math_continuation::patterns::grades_3_4::medium": { "acc": 24.528301886792452, "acc_norm": 24.528301886792452, "norm_correct": 13, "raw_correct": 13, "total": 53 }, "elementary_school_math_continuation::subtraction::grades_1_2::easy": { "acc": 30.76923076923077, "acc_norm": 31.62393162393162, "norm_correct": 37, "raw_correct": 36, "total": 117 }, "elementary_school_math_continuation::time::grades_2_3::easy": { "acc": 100.0, "acc_norm": 100.0, "norm_correct": 55, "raw_correct": 55, "total": 55 }, "elementary_school_math_continuation::two_step_add_subtract::grades_2_3::medium": { "acc": 21.73913043478261, "acc_norm": 21.73913043478261, "norm_correct": 10, "raw_correct": 10, "total": 46 }, "elementary_school_math_continuation::two_step_addition::grades_2_3::medium": { "acc": 15.789473684210526, "acc_norm": 15.789473684210526, "norm_correct": 3, "raw_correct": 3, "total": 19 }, "elementary_school_math_continuation::two_step_subtraction::grades_2_3::medium": { "acc": 28.125, "acc_norm": 28.125, "norm_correct": 9, "raw_correct": 9, "total": 32 } }, "frost_evaluation": { "checkpoint": "D:\\llm\\hummingbird\\artifacts\\runs\\flightmix_10b_balanced_10m_muon_lrfix_20260921\\checkpoint-tokens-10000000000", "data_sha256": "bf8ab1a5193d52cdf0e05ff0b3ca226bdfcf416cb6e75562dcbe72e7e4559435", "dataset": "AxiomicLabs/Arithmark-3.0", "dataset_revision": "6f6e59dd9b7e2c63455f7af7f838f9ecc3d0a746", "device": "cuda", "evaluator_sha256": "09667e1ea05ecd8b91dbfea14a47365b555c72622afed9fc284c127ecd5e1bcd", "limit": null, "loop_count": 1, "numeric_serialization": "none", "precision": "bfloat16", "qk_norm_position": null, "tokenizer": "D:\\llm\\hummingbird\\artifacts\\runs\\e3_tokenizers\\tok_4k_digit" }, "norm_correct": 360, "raw_correct": 357, "timing": { "evaluation_seconds": 0.8658304999989923, "examples_per_second": 1154.9604685919055, "tokenization_seconds": 0.30124549998436123 }, "total": 1000 }