open-llm-leaderboard-old/details_u-chom__ex-llm-e1
收藏数据集概述
该数据集是在对模型 u-chom/ex-llm-e1 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集由 63 个配置组成，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_u-chom__ex-llm-e1", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-09T14:50:53.053467 运行 的最新结果：
python { "all": { "acc": 0.39402023545271236, "acc_stderr": 0.03431633094943852, "acc_norm": 0.3992950895868925, "acc_norm_stderr": 0.03515648307530415, "mc1": 0.2631578947368421, "mc1_stderr": 0.015415241740237009, "mc2": 0.4200995329344425, "mc2_stderr": 0.01434315654117436 }, "harness|arc:challenge|25": { "acc": 0.35921501706484643, "acc_stderr": 0.014020224155839159, "acc_norm": 0.3993174061433447, "acc_norm_stderr": 0.014312094557946698 }, "harness|hellaswag|10": { "acc": 0.5060744871539534, "acc_stderr": 0.004989413158034801, "acc_norm": 0.6811392152957578, "acc_norm_stderr": 0.004650825168905203 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45925925925925926, "acc_stderr": 0.04304979692464242, "acc_norm": 0.45925925925925926, "acc_norm_stderr": 0.04304979692464242 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.04060127035236397, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.04060127035236397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.41509433962264153, "acc_stderr": 0.03032594578928611, "acc_norm": 0.41509433962264153, "acc_norm_stderr": 0.03032594578928611 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3680555555555556, "acc_stderr": 0.040329990539607195, "acc_norm": 0.3680555555555556, "acc_norm_stderr": 0.040329990539607195 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.31, "acc_stderr": 0.04648231987117317, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117317 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3699421965317919, "acc_stderr": 0.036812296333943194, "acc_norm": 0.3699421965317919, "acc_norm_stderr": 0.036812296333943194 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.33191489361702126, "acc_stderr": 0.030783736757745643, "acc_norm": 0.33191489361702126, "acc_norm_stderr": 0.030783736757745643 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.042270544512322004, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.042270544512322004 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3793103448275862, "acc_stderr": 0.040434618619167466, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.040434618619167466 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2830687830687831, "acc_stderr": 0.023201392938194974, "acc_norm": 0.2830687830687831, "acc_norm_stderr": 0.023201392938194974 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.041905964388711366, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.041905964388711366 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3709677419354839, "acc_stderr": 0.027480541887953593, "acc_norm": 0.3709677419354839, "acc_norm_stderr": 0.027480541887953593 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3251231527093596, "acc_stderr": 0.032957975663112704, "acc_norm": 0.3251231527093596, "acc_norm_stderr": 0.032957975663112704 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4727272727272727, "acc_stderr": 0.0389853160557942, "acc_norm": 0.4727272727272727, "acc_norm_stderr": 0.0389853160557942 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4444444444444444, "acc_stderr": 0.035402943770953675, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.035402943770953675 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5233160621761658, "acc_stderr": 0.03604513672442202, "acc_norm": 0.5233160621761658, "acc_norm_stderr": 0.03604513672442202 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.31025641025641026, "acc_stderr": 0.02345467488940429, "acc_norm": 0.31025641025641026, "acc_norm_stderr": 0.02345467488940429 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.02620276653465215, "acc_norm": 0.2444444444444444
