open-llm-leaderboard-old/details_Isotonic__smol_llama-4x220M-MoE
收藏数据集概述
数据集简介
该数据集是在模型Isotonic/smol_llama-4x220M-MoE的评估运行期间自动创建的,用于Open LLM Leaderboard。
数据集组成
- 数据集包含63个配置,每个配置对应一个评估任务。
- 数据集由1次运行创建,每个运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。
- "train"分割始终指向最新的结果。
- 额外的配置"results"存储所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Isotonic__smol_llama-4x220M-MoE", "harness_winogrande_5", split="train")
最新结果
以下是2024-02-09T18:30:34.238511运行的最新结果:
python { "all": { "acc": 0.2581976478783647, "acc_stderr": 0.0306923175559902, "acc_norm": 0.25926163229506716, "acc_norm_stderr": 0.03149291372668089, "mc1": 0.24969400244798043, "mc1_stderr": 0.015152286907148128, "mc2": 0.43919471641963714, "mc2_stderr": 0.015487105411782864 }, "harness|arc:challenge|25": { "acc": 0.2030716723549488, "acc_stderr": 0.011755899303705582, "acc_norm": 0.2508532423208191, "acc_norm_stderr": 0.01266819862131543 }, "harness|hellaswag|10": { "acc": 0.2800238996215893, "acc_stderr": 0.00448092945028156, "acc_norm": 0.2923720374427405, "acc_norm_stderr": 0.004539227260397018 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2074074074074074, "acc_stderr": 0.03502553170678316, "acc_norm": 0.2074074074074074, "acc_norm_stderr": 0.03502553170678316 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123387, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123387 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816503, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816503 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.23018867924528302, "acc_stderr": 0.025907897122408173, "acc_norm": 0.23018867924528302, "acc_norm_stderr": 0.025907897122408173 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.19444444444444445, "acc_stderr": 0.033096151770590054, "acc_norm": 0.19444444444444445, "acc_norm_stderr": 0.033096151770590054 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2774566473988439, "acc_stderr": 0.034140140070440354, "acc_norm": 0.2774566473988439, "acc_norm_stderr": 0.034140140070440354 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237655, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237655 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.19, "acc_stderr": 0.03942772444036622, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036622 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2553191489361702, "acc_stderr": 0.028504856470514185, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.028504856470514185 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.040493392977481425, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.040493392977481425 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2619047619047619, "acc_stderr": 0.022644212615525218, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.022644212615525218 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23015873015873015, "acc_stderr": 0.03764950879790606, "acc_norm": 0.23015873015873015, "acc_norm_stderr": 0.03764950879790606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.32903225806451614, "acc_stderr": 0.02672949906834996, "acc_norm": 0.32903225806451614, "acc_norm_stderr": 0.02672949906834996 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3054187192118227, "acc_stderr": 0.03240661565868408, "acc_norm": 0.3054187192118227, "acc_norm_stderr": 0.03240661565868408 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2606060606060606, "acc_stderr": 0.034277431758165236, "acc_norm": 0.2606060606060606, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21717171717171718, "acc_stderr": 0.029376616484945633, "acc_norm": 0.21717171717171718, "acc_norm_stderr": 0.029376616484945633 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.36787564766839376, "acc_stderr": 0.03480175668466036, "acc_norm": 0.36787564766839376, "acc_norm_stderr": 0.03480175668466036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.29743589743589743, "acc_stderr": 0.023177408131465932, "acc_norm": 0.29743589743589743, "acc_norm_stderr": 0.023177408131465932 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.02684205787383371, "acc_norm": 0.26296296296296295, "acc_norm_stderr": 0.02684205787383371 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3067226890756303, "acc_stderr": 0.029953823891887048, "acc_norm": 0.3067226890756303, "acc_norm_stderr": 0.029953823891887048 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.32450331125827814, "acc_stderr": 0.03822746937658754, "acc_norm": 0.32450331125827814, "acc_norm_stderr": 0.03822746937658754 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.3339449541284404, "acc_stderr": 0.020220554196736403, "acc_norm": 0.3339449541284404, "acc_norm_stderr": 0.020220554196736403 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.4722222222222222, "acc_stderr": 0.0340470532865388, "acc_norm": 0.4722222222222222, "acc_norm_stderr": 0.0340470532865388 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.27941176470588236, "acc_stderr": 0.031493281045079556, "acc_norm": 0.27941176470588236, "acc_norm_stderr": 0.031493281045079556 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.22784810126582278, "acc_stderr": 0.027303484599069415, "acc_norm": 0.22784810126582278, "acc_norm_stderr": 0.027303484599069415 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.242152466367713, "acc_stderr": 0.028751392398694755, "acc_norm": 0.242152466367713, "acc_norm_stderr": 0.028751392398694755 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.26717557251908397, "acc_stderr": 0.038808483010823944, "acc_norm": 0.26717557251908397, "acc_norm_stderr": 0.038808483010823944 }, "harness|hendrycksTest-international_law|5": { "acc": 0.23140495867768596, "acc_stderr": 0.03849856098794089, "acc_norm": 0.23140495867768596, "acc_norm_stderr": 0.03849856098794089 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.21296296296296297, "acc_stderr": 0.0395783547198098, "acc_norm": 0.21296296296296297, "acc_norm_stderr": 0.0395783547198098 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.22085889570552147, "acc_stderr": 0.032591773927421776, "acc_norm": 0.22085889570552147, "acc_norm_stderr": 0.032591773927421776 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.125, "acc_stderr": 0.03139045014587016, "acc_norm": 0.125, "acc_norm_stderr": 0.03139045014587016 }, "harness|hendrycksTest-management|5": { "acc": 0.2912621359223301, "acc_stderr": 0.04498676320572924, "acc_norm": 0.2912621359223301, "acc_norm_stderr": 0.04498676320572924 }, "harness|hendrycksTest-marketing|5": { "acc": 0.19230769230769232, "acc_stderr": 0.025819233256483703, "acc_norm": 0.19230769230769232, "acc_norm_stderr": 0.025819233256483703 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816507, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.27330779054916987, "acc_stderr": 0.015936681062628556, "acc_norm": 0.27330779054916987, "acc_norm_stderr": 0.015936681062628556 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.21098265895953758, "acc_stderr": 0.021966309947043124, "acc_norm": 0.21098265895953758, "acc_norm_stderr": 0.021966309947043124 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.2424581005586592, "acc_stderr": 0.014333522059217889, "acc_norm": 0.2424581005586592, "acc_norm_stderr": 0.014333522059217889 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.2973856209150327, "acc_stderr": 0.02617390850671858, "acc_norm": 0.2973856209150327, "acc_norm_stderr": 0.02617390850671858 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.2315112540192926, "acc_stderr": 0.023956532766639133, "acc_norm": 0.2315112540192926, "acc_norm_stderr": 0.023956532766639133 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.17592592592592593, "acc_stderr": 0.021185893615225156, "acc_norm": 0.17592592592592593, "acc_norm_stderr": 0.021185893615225156 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.2978723404255319, "acc_stderr": 0.027281608344469414, "acc_norm": 0.2978723404255319, "acc_norm_stderr": 0.027281608344469414 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.2405475880052151, "acc_stderr": 0.010916406735478949, "acc_norm": 0.2405475880052151, "acc_norm_stderr": 0.010916406735478949 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.4485294117647059, "acc_stderr": 0.030211479609121593, "acc_norm": 0.4485294117647059, "acc_norm_stderr": 0.030211479609121593 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.24836601307189543, "acc_stderr": 0.017479487001364764, "acc_norm": 0.24836601307189543, "acc_norm_stderr": 0.017479487001364764 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.2909090909090909, "acc_stderr": 0.04350271442923243, "acc_norm": 0.2909090909090909, "acc_norm_stderr": 0.04350271442923243 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.39183673469387753, "acc_stderr": 0.031251275910891656, "acc_norm": 0.39183673469387753, "acc_norm_stderr": 0.031251275910891656 }, "harness|hendrycksTest-sociology|5": { "acc": 0.21890547263681592, "acc_stderr": 0.029239174636647, "acc_norm": 0.21890547263681592, "acc_norm_stderr": 0.029239174636647 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-virology|5": { "acc": 0.1686746987951807, "acc_stderr": 0.029152009627856544, "acc_norm": 0.1686746987951807, "acc_norm_stderr": 0.029152009627856544 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.21052631578947367, "acc_stderr": 0.03126781714663179, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.03126781714663179 }, "harness|truthfulqa:mc|0": { "mc1": 0.24969400244798043, "mc1_stderr": 0.015152286907148128, "mc2": 0.43919471641963714, "mc2_stderr": 0.015487105411782864 }, "harness|winogrande|5": { "acc": 0.5122336227308603, "acc_stderr": 0.01404827882040562 }, "harness|gsm8k|5": { "acc": 0.001516300227445034, "acc_stderr": 0.001071779348549262 } }



