open-llm-leaderboard-old/details_Weyaxi__Einstein-openchat-7B
收藏数据集概述
数据集来源
该数据集是在评估模型 Weyaxi/Einstein-openchat-7B 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。数据集是从1次运行中创建的，每次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。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 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_Weyaxi__Einstein-openchat-7B", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-01-23T23:44:02.231759的运行：
python { "all": { "acc": 0.6416289994817496, "acc_stderr": 0.03222660852943186, "acc_norm": 0.6436221960309779, "acc_norm_stderr": 0.03287361714145995, "mc1": 0.3708690330477356, "mc1_stderr": 0.01690969358024882, "mc2": 0.5450984783622247, "mc2_stderr": 0.0153785526545658 }, "harness|arc:challenge|25": { "acc": 0.606655290102389, "acc_stderr": 0.014275101465693028, "acc_norm": 0.6510238907849829, "acc_norm_stderr": 0.0139289334613825 }, "harness|hellaswag|10": { "acc": 0.6452897829117705, "acc_stderr": 0.004774476498238618, "acc_norm": 0.8356901015733917, "acc_norm_stderr": 0.0036979923561244747 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6710526315789473, "acc_stderr": 0.03823428969926605, "acc_norm": 0.6710526315789473, "acc_norm_stderr": 0.03823428969926605 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7245283018867924, "acc_stderr": 0.027495663683724053, "acc_norm": 0.7245283018867924, "acc_norm_stderr": 0.027495663683724053 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7569444444444444, "acc_stderr": 0.03586879280080341, "acc_norm": 0.7569444444444444, "acc_norm_stderr": 0.03586879280080341 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247078, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247078 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3235294117647059, "acc_stderr": 0.046550104113196177, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.046550104113196177 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5574468085106383, "acc_stderr": 0.032469569197899575, "acc_norm": 0.5574468085106383, "acc_norm_stderr": 0.032469569197899575 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6206896551724138, "acc_stderr": 0.040434618619167466, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.040434618619167466 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41005291005291006, "acc_stderr": 0.025331202438944433, "acc_norm": 0.41005291005291006, "acc_norm_stderr": 0.025331202438944433 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7451612903225806, "acc_stderr": 0.02479011845933221, "acc_norm": 0.7451612903225806, "acc_norm_stderr": 0.02479011845933221 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.035179450386910616, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.035179450386910616 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.793939393939394, "acc_stderr": 0.03158415324047711, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.03158415324047711 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7575757575757576, "acc_stderr": 0.030532892233932026, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.030532892233932026 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758723, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758723 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6435897435897436, "acc_stderr": 0.02428314052946731, "acc_norm": 0.6435897435897436, "acc_norm_stderr": 0.02428314052946731 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083018, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.029116617606083018 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.634453781512605, "acc_stderr":
