open-llm-leaderboard-old/details_mahiatlinux__MasherAI-v6.1-7B-checkpoint3

该数据集是在评估模型mahiatlinux/MasherAI-v6.1-7B-checkpoint3时自动创建的，评估在Open LLM Leaderboard上进行。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行创建，每次运行的结果可以在每个配置的特定分割中找到，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，还有一个名为results的配置，存储了所有运行的聚合结果，用于在Open LLM Leaderboard上计算和显示聚合指标。

原始信息汇总

数据集概述

该数据集是在评估模型 mahiatlinux/MasherAI-v6.1-7B-checkpoint3 的过程中自动创建的，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。
• 数据集由 1 次运行创建，每个运行可以在每个配置中找到特定的分片，分片名称使用运行的时间戳。
• "train" 分片始终指向最新的结果。
• 额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示聚合指标在 Open LLM Leaderboard 上。

最新结果

以下是 2024-04-02T17:04:36.698077 运行的最新结果：

python { "all": { "acc": 0.6400093098031701, "acc_stderr": 0.03234073596353466, "acc_norm": 0.6401347220520796, "acc_norm_stderr": 0.03301463698448825, "mc1": 0.39412484700122397, "mc1_stderr": 0.017106588140700322, "mc2": 0.56204060143086, "mc2_stderr": 0.015214848754673627 }, "harness|arc:challenge|25": { "acc": 0.606655290102389, "acc_stderr": 0.014275101465693028, "acc_norm": 0.6373720136518771, "acc_norm_stderr": 0.014049106564955019 }, "harness|hellaswag|10": { "acc": 0.64070902210715, "acc_stderr": 0.004788120727316244, "acc_norm": 0.8406691894045011, "acc_norm_stderr": 0.00365236325328959 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.042320736951515885, "acc_norm": 0.6, "acc_norm_stderr": 0.042320736951515885 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7105263157894737, "acc_stderr": 0.03690677986137283, "acc_norm": 0.7105263157894737, "acc_norm_stderr": 0.03690677986137283 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7094339622641509, "acc_stderr": 0.02794321998933714, "acc_norm": 0.7094339622641509, "acc_norm_stderr": 0.02794321998933714 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "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": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.653179190751445, "acc_stderr": 0.036291466701596636, "acc_norm": 0.653179190751445, "acc_norm_stderr": 0.036291466701596636 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5446808510638298, "acc_stderr": 0.03255525359340355, "acc_norm": 0.5446808510638298, "acc_norm_stderr": 0.03255525359340355 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.04692008381368909, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.04692008381368909 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4417989417989418, "acc_stderr": 0.025576257061253833, "acc_norm": 0.4417989417989418, "acc_norm_stderr": 0.025576257061253833 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7645161290322581, "acc_stderr": 0.02413763242933771, "acc_norm": 0.7645161290322581, "acc_norm_stderr": 0.02413763242933771 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.032876667586034906, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.032876667586034906 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7929292929292929, "acc_stderr": 0.028869778460267042, "acc_norm": 0.7929292929292929, "acc_norm_stderr": 0.028869778460267042 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8497409326424871, "acc_stderr": 0.025787723180723872, "acc_norm": 0.8497409326424871, "acc_norm_stderr": 0.025787723180723872 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6461538461538462, "acc_stderr": 0.024243783994062153, "acc_norm": 0.6461538461538462, "acc_norm_stderr": 0.024243783994062153 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.028317533496066482, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.028317533496066482 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6470588235294118, "acc_stderr": 0.031041941304059285, "acc_norm": 0.6470