open-llm-leaderboard-old/details_raincandy-u__Quark-464M-v0.1.alpha
收藏数据集概述
数据集摘要
该数据集是在评估模型 raincandy-u/Quark-464M-v0.1.alpha 在 Open LLM Leaderboard 上的自动创建的。数据集由 63 个配置组成，每个配置对应一个评估任务。
数据集结构
- 配置数量：63 个配置
- 数据来源：1 次运行结果
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："results" 配置存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_raincandy-u__Quark-464M-v0.1.alpha", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-08T22:05:09.274304 运行的最新结果：
python { "all": { "acc": 0.34329376941671863, "acc_stderr": 0.03353985083625715, "acc_norm": 0.3471291215165508, "acc_norm_stderr": 0.03436001790346169, "mc1": 0.2582619339045288, "mc1_stderr": 0.015321821688476199, "mc2": 0.4184473207659332, "mc2_stderr": 0.015494640529105812 }, "harness|arc:challenge|25": { "acc": 0.2832764505119454, "acc_stderr": 0.013167478735134575, "acc_norm": 0.31399317406143346, "acc_norm_stderr": 0.013562691224726291 }, "harness|hellaswag|10": { "acc": 0.3745269866560446, "acc_stderr": 0.004830113797327045, "acc_norm": 0.4731129257120096, "acc_norm_stderr": 0.0049825618152141244 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2962962962962963, "acc_stderr": 0.039446241625011175, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.039446241625011175 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.40789473684210525, "acc_stderr": 0.03999309712777472, "acc_norm": 0.40789473684210525, "acc_norm_stderr": 0.03999309712777472 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.35, "acc_stderr": 0.04793724854411018, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411018 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.39622641509433965, "acc_stderr": 0.030102793781791194, "acc_norm": 0.39622641509433965, "acc_norm_stderr": 0.030102793781791194 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3194444444444444, "acc_stderr": 0.03899073687357336, "acc_norm": 0.3194444444444444, "acc_norm_stderr": 0.03899073687357336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.35, "acc_stderr": 0.04793724854411019, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411019 }, "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": 0.3583815028901734, "acc_stderr": 0.036563436533531585, "acc_norm": 0.3583815028901734, "acc_norm_stderr": 0.036563436533531585 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201942, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201942 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.251063829787234, "acc_stderr": 0.028346963777162462, "acc_norm": 0.251063829787234, "acc_norm_stderr": 0.028346963777162462 }, "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": 0.33793103448275863, "acc_stderr": 0.039417076320648906, "acc_norm": 0.33793103448275863, "acc_norm_stderr": 0.039417076320648906 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25132275132275134, "acc_stderr": 0.022340482339643898, "acc_norm": 0.25132275132275134, "acc_norm_stderr": 0.022340482339643898 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0404061017820884, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0404061017820884 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3419354838709677, "acc_stderr": 0.026985289576552725, "acc_norm": 0.3419354838709677, "acc_norm_stderr": 0.026985289576552725 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.31527093596059114, "acc_stderr": 0.03269080871970186, "acc_norm": 0.31527093596059114, "acc_norm_stderr": 0.03269080871970186 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.48484848484848486, "acc_stderr": 0.03902551007374449, "acc_norm": 0.48484848484848486, "acc_norm_stderr": 0.03902551007374449 }, "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": 0.43523316062176165, "acc_stderr": 0.03578038165008585, "acc_norm": 0.43523316062176165, "acc_norm_stderr": 0.03578038165008585 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.38461538461538464, "acc_stderr": 0.02466674491518722, "acc_norm": 0.38461538461538464, "acc_norm_stderr": 0.02466674491518722 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145668, "acc_norm": 0.2703703
