open-llm-leaderboard-old/details_BEE-spoke-data__smol_llama-220M-openhermes
收藏数据集概述
该数据集是在评估模型BEE-spoke-data/smol_llama-220M-openhermes在Open LLM Leaderboard上的自动创建的。
数据集组成
- 该数据集包含63个配置，每个配置对应一个评估任务。
- 数据集从1次运行中创建，每次运行可以在每个配置中找到一个特定的分割，分割名称使用运行的时间戳。
- "train"分割始终指向最新的结果。
- 一个额外的配置"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_BEE-spoke-data__smol_llama-220M-openhermes", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-04T11:14:24.402269运行的最新结果：
python { "all": { "acc": 0.26124152760742403, "acc_stderr": 0.030861921022096055, "acc_norm": 0.26204860049920253, "acc_norm_stderr": 0.03164810576117213, "mc1": 0.2460220318237454, "mc1_stderr": 0.015077219200662604, "mc2": 0.4308131121933828, "mc2_stderr": 0.015493567057293808 }, "harness|arc:challenge|25": { "acc": 0.2090443686006826, "acc_stderr": 0.011882746987406451, "acc_norm": 0.25170648464163825, "acc_norm_stderr": 0.012682496334042967 }, "harness|hellaswag|10": { "acc": 0.2811192989444334, "acc_stderr": 0.004486268470666339, "acc_norm": 0.28978291177056364, "acc_norm_stderr": 0.004527343651130807 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.17777777777777778, "acc_stderr": 0.033027898599017176, "acc_norm": 0.17777777777777778, "acc_norm_stderr": 0.033027898599017176 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21710526315789475, "acc_stderr": 0.033550453048829226, "acc_norm": 0.21710526315789475, "acc_norm_stderr": 0.033550453048829226 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.26037735849056604, "acc_stderr": 0.0270087660907081, "acc_norm": 0.26037735849056604, "acc_norm_stderr": 0.0270087660907081 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2708333333333333, "acc_stderr": 0.03716177437566016, "acc_norm": 0.2708333333333333, "acc_norm_stderr": 0.03716177437566016 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2832369942196532, "acc_stderr": 0.03435568056047875, "acc_norm": 0.2832369942196532, "acc_norm_stderr": 0.03435568056047875 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2425531914893617, "acc_stderr": 0.028020226271200217, "acc_norm": 0.2425531914893617, "acc_norm_stderr": 0.028020226271200217 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2689655172413793, "acc_stderr": 0.036951833116502325, "acc_norm": 0.2689655172413793, "acc_norm_stderr": 0.036951833116502325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24603174603174602, "acc_stderr": 0.022182037202948368, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.022182037202948368 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03333333333333337, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03333333333333337 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3096774193548387, "acc_stderr": 0.026302774983517418, "acc_norm": 0.3096774193548387, "acc_norm_stderr": 0.026302774983517418 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2512315270935961, "acc_stderr": 0.030516530732694436, "acc_norm": 0.2512315270935961, "acc_norm_stderr": 0.030516530732694436 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3090909090909091, "acc_stderr": 0.036085410115739666, "acc_norm": 0.3090909090909091, "acc_norm_stderr": 0.036085410115739666 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21212121212121213, "acc_stderr": 0.029126522834586815, "acc_norm": 0.21212121212121213, "acc_norm_stderr": 0.029126522834586815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.36787564766839376, "acc_stderr": 0.034801756684660366, "acc_norm": 0.36787564766839376, "acc_norm_stderr": 0.034801756684660366 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.358974358974359, "acc_stderr": 0.024321738484602368, "acc_norm": 0.358974358974359, "acc_norm_stderr": 0.024321738484602368 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.02671924
