open-llm-leaderboard-old/details_binbi__MoMo-70B-V1.2_1
收藏数据集概述
该数据集是在对模型 binbi/MoMo-70B-V1.2_1 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，每个运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。
- "train" 拆分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_binbi__MoMo-70B-V1.2_1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-23T05:09:38.161416 运行的最新结果：
python { "all": { "acc": 0.698588284419882, "acc_stderr": 0.0303909434575038, "acc_norm": 0.7024430426815292, "acc_norm_stderr": 0.03098225812650051, "mc1": 0.4357405140758874, "mc1_stderr": 0.017358345398863124, "mc2": 0.6130536296369835, "mc2_stderr": 0.01483068540330801 }, "harness|arc:challenge|25": { "acc": 0.6715017064846417, "acc_stderr": 0.013724978465537302, "acc_norm": 0.7090443686006825, "acc_norm_stderr": 0.01327307786590759 }, "harness|hellaswag|10": { "acc": 0.6775542720573591, "acc_stderr": 0.00466457278498559, "acc_norm": 0.8646683927504482, "acc_norm_stderr": 0.0034137831331580715 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595852, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595852 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8092105263157895, "acc_stderr": 0.031975658210325, "acc_norm": 0.8092105263157895, "acc_norm_stderr": 0.031975658210325 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7132075471698113, "acc_stderr": 0.027834912527544064, "acc_norm": 0.7132075471698113, "acc_norm_stderr": 0.027834912527544064 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8333333333333334, "acc_stderr": 0.031164899666948617, "acc_norm": 0.8333333333333334, "acc_norm_stderr": 0.031164899666948617 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.676595744680851, "acc_stderr": 0.030579442773610337, "acc_norm": 0.676595744680851, "acc_norm_stderr": 0.030579442773610337 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.04657047260594963, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.04028731532947558, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.04028731532947558 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42857142857142855, "acc_stderr": 0.025487187147859372, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.025487187147859372 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.49206349206349204, "acc_stderr": 0.044715725362943486, "acc_norm": 0.49206349206349204, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8290322580645161, "acc_stderr": 0.02141724293632159, "acc_norm": 0.8290322580645161, "acc_norm_stderr": 0.02141724293632159 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.541871921182266, "acc_stderr": 0.03505630140785741, "acc_norm": 0.541871921182266, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8303030303030303, "acc_stderr": 0.029311188674983137, "acc_norm": 0.8303030303030303, "acc_norm_stderr": 0.029311188674983137 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8838383838383839, "acc_stderr": 0.022828881775249377, "acc_norm": 0.8838383838383839, "acc_norm_stderr": 0.022828881775249377 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.927461139896373, "acc_stderr": 0.018718998520678178, "acc_norm": 0.927461139896373, "acc_norm_stderr": 0.018718998520678178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6897435897435897, "acc_stderr": 0.023454674889404288, "acc_norm": 0.6897435897435897, "acc_norm_stderr": 0.023454674889404288 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.02840653309060846, "acc_norm": 0.3185185185185185
