open-llm-leaderboard-old/details_AA051615__L0225
收藏数据集概述
数据集简介
该数据集是在模型 AA051615/L0225 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。
结果配置
一个额外的配置 "results" 存储了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_AA051615__L0225", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-01T05:21:12.964101 运行的最新结果：
python { "all": { "acc": 0.8192856560436336, "acc_stderr": 0.02522551022169272, "acc_norm": 0.8278237600056262, "acc_norm_stderr": 0.025630597996564967, "mc1": 0.3671970624235006, "mc1_stderr": 0.01687480500145318, "mc2": 0.5419063822595955, "mc2_stderr": 0.015465200826091909 }, "harness|arc:challenge|25": { "acc": 0.6356655290102389, "acc_stderr": 0.014063260279882419, "acc_norm": 0.681740614334471, "acc_norm_stderr": 0.013611993916971451 }, "harness|hellaswag|10": { "acc": 0.6269667396932882, "acc_stderr": 0.004826224784850442, "acc_norm": 0.8273252340171281, "acc_norm_stderr": 0.003771934042799158 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7925925925925926, "acc_stderr": 0.03502553170678318, "acc_norm": 0.7925925925925926, "acc_norm_stderr": 0.03502553170678318 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.025648341251693598, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.025648341251693598 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8905660377358491, "acc_stderr": 0.019213530010965436, "acc_norm": 0.8905660377358491, "acc_norm_stderr": 0.019213530010965436 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9583333333333334, "acc_stderr": 0.016710315802959983, "acc_norm": 0.9583333333333334, "acc_norm_stderr": 0.016710315802959983 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.65, "acc_stderr": 0.04793724854411021, "acc_norm": 0.65, "acc_norm_stderr": 0.04793724854411021 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.815028901734104, "acc_stderr": 0.029605623981771197, "acc_norm": 0.815028901734104, "acc_norm_stderr": 0.029605623981771197 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.04690650298201942, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.04690650298201942 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.89, "acc_stderr": 0.03144660377352201, "acc_norm": 0.89, "acc_norm_stderr": 0.03144660377352201 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8382978723404255, "acc_stderr": 0.024068505289695338, "acc_norm": 0.8382978723404255, "acc_norm_stderr": 0.024068505289695338 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6842105263157895, "acc_stderr": 0.043727482902780085, "acc_norm": 0.6842105263157895, "acc_norm_stderr": 0.043727482902780085 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8620689655172413, "acc_stderr": 0.028735632183908073, "acc_norm": 0.8620689655172413, "acc_norm_stderr": 0.028735632183908073 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7936507936507936, "acc_stderr": 0.02084229093011468, "acc_norm": 0.7936507936507936, "acc_norm_stderr": 0.02084229093011468 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6190476190476191, "acc_stderr": 0.04343525428949099, "acc_norm": 0.6190476190476191, "acc_norm_stderr": 0.04343525428949099 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9483870967741935, "acc_stderr": 0.012586144774300194, "acc_norm": 0.9483870967741935, "acc_norm_stderr": 0.012586144774300194 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.7389162561576355, "acc_stderr": 0.030903796952114468, "acc_norm": 0.7389162561576355, "acc_norm_stderr": 0.030903796952114468 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.86, "acc_stderr": 0.03487350880197771, "acc_norm": 0.86, "acc_norm_stderr": 0.03487350880197771 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.9090909090909091, "acc_stderr": 0.022448399923854286, "acc_norm": 0.9090909090909091, "acc_norm_stderr": 0.022448399923854286 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9545454545454546, "acc_stderr": 0.014840681800540868, "acc_norm": 0.9545454545454546, "acc_norm_stderr": 0.014840681800540868 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9844559585492227, "acc_stderr": 0.008927492715084352, "acc_norm": 0.9844559585492227, "acc_norm_stderr": 0.008927492715084352 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.882051282051282, "acc_stderr": 0.016353801778303395, "acc_norm": 0.882051282051282, "acc_norm_stderr": 0.016353801778303395 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5851851851851851, "acc_stderr": 0.030039842454069283, "acc_norm": 0.5851851851851851,
