open-llm-leaderboard-old/details_osanseviero__mistral-instruct-slerp

该数据集是在模型[osanseviero/mistral-instruct-slerp](https://huggingface.co/osanseviero/mistral-instruct-slerp)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的，每次运行都可以在特定配置中找到，分割名称使用运行的时间戳。"train"分割始终指向最新结果。此外，"results"配置存储了所有运行的聚合结果，并用于计算和显示[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的聚合指标。

原始信息汇总

数据集概述

该数据集是在对模型 osanseviero/mistral-instruct-slerp 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 该数据集包含 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。
• 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。

最新结果

以下是 2024-01-10T19:39:10.172387 运行的最新结果：

python { "all": { "acc": 0.5514236008900887, "acc_stderr": 0.033791449375361236, "acc_norm": 0.5561976919598308, "acc_norm_stderr": 0.03449972215885168, "mc1": 0.41615667074663404, "mc1_stderr": 0.01725565750290304, "mc2": 0.5761316177255528, "mc2_stderr": 0.015724067025526787 }, "harness|arc:challenge|25": { "acc": 0.5349829351535836, "acc_stderr": 0.014575583922019672, "acc_norm": 0.5742320819112628, "acc_norm_stderr": 0.014449464278868814 }, "harness|hellaswag|10": { "acc": 0.5846444931288588, "acc_stderr": 0.004917761181740162, "acc_norm": 0.7834096793467437, "acc_norm_stderr": 0.00411079202343171 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.038607315993160904, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.038607315993160904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.660377358490566, "acc_stderr": 0.02914690474779833, "acc_norm": 0.660377358490566, "acc_norm_stderr": 0.02914690474779833 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6180555555555556, "acc_stderr": 0.04062990784146667, "acc_norm": 0.6180555555555556, "acc_norm_stderr": 0.04062990784146667 }, "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": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5549132947976878, "acc_stderr": 0.037894017602836484, "acc_norm": 0.5549132947976878, "acc_norm_stderr": 0.037894017602836484 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.047551296160629475, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.047551296160629475 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.451063829787234, "acc_stderr": 0.03252909619613197, "acc_norm": 0.451063829787234, "acc_norm_stderr": 0.03252909619613197 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.04615186962583703, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.04615186962583703 }, "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": 0.4074074074074074, "acc_stderr": 0.025305906241590632, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.025305906241590632 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.04343525428949098, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.04343525428949098 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4064516129032258, "acc_stderr": 0.02794172734625631, "acc_norm": 0.4064516129032258, "acc_norm_stderr": 0.02794172734625631 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4433497536945813, "acc_stderr": 0.03495334582162934, "acc_norm": 0.4433497536945813, "acc_norm_stderr": 0.03495334582162934 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6545454545454545, "acc_stderr": 0.03713158067481913, "acc_norm": 0.6545454545454545, "acc_norm_stderr": 0.03713158067481913 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7474747474747475, "acc_stderr": 0.030954055470365897, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8082901554404145, "acc_stderr": 0.028408953626245282, "acc_norm": 0.8082901554404145, "acc_norm_stderr": 0.028408953626245282 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4948717948717949, "acc_stderr": 0.025349672906838653, "acc_norm": 0.4948717948717949, "acc_norm_stderr": 0.025349672906838653 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.026719240783712173, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.026719240783712173 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5588235294