open-llm-leaderboard-old/details_AA051610__O0128
收藏数据集概述
数据集创建背景
该数据集是在对模型 AA051610/O0128 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集由 63 个配置组成，每个配置对应一个评估任务。数据集从 1 次运行中创建，每次运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。"train" 分割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 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_AA051610__O0128", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-28T17:02:36.892419 运行的最新结果：
python { "all": { "acc": 0.8273006081081993, "acc_stderr": 0.024663470781539607, "acc_norm": 0.8335369148949214, "acc_norm_stderr": 0.025075862506569718, "mc1": 0.43451652386780903, "mc1_stderr": 0.017352738749259564, "mc2": 0.6012752268438828, "mc2_stderr": 0.014979362035595621 }, "harness|arc:challenge|25": { "acc": 0.6552901023890785, "acc_stderr": 0.01388881628678211, "acc_norm": 0.6791808873720137, "acc_norm_stderr": 0.013640943091946528 }, "harness|hellaswag|10": { "acc": 0.6569408484365664, "acc_stderr": 0.004737608340163403, "acc_norm": 0.853415654252141, "acc_norm_stderr": 0.003529682285857263 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.8222222222222222, "acc_stderr": 0.033027898599017176, "acc_norm": 0.8222222222222222, "acc_norm_stderr": 0.033027898599017176 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.9013157894736842, "acc_stderr": 0.02427022773752271, "acc_norm": 0.9013157894736842, "acc_norm_stderr": 0.02427022773752271 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.82, "acc_stderr": 0.038612291966536955, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8641509433962264, "acc_stderr": 0.02108730862243985, "acc_norm": 0.8641509433962264, "acc_norm_stderr": 0.02108730862243985 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9722222222222222, "acc_stderr": 0.013742429025504266, "acc_norm": 0.9722222222222222, "acc_norm_stderr": 0.013742429025504266 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.57, "acc_stderr": 0.04975698519562427, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562427 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.8265895953757225, "acc_stderr": 0.02886810787497064, "acc_norm": 0.8265895953757225, "acc_norm_stderr": 0.02886810787497064 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.6470588235294118, "acc_stderr": 0.047551296160629475, "acc_norm": 0.6470588235294118, "acc_norm_stderr": 0.047551296160629475 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.86, "acc_stderr": 0.03487350880197771, "acc_norm": 0.86, "acc_norm_stderr": 0.03487350880197771 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8468085106382979, "acc_stderr": 0.023545179061675203, "acc_norm": 0.8468085106382979, "acc_norm_stderr": 0.023545179061675203 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.7105263157894737, "acc_stderr": 0.04266339443159394, "acc_norm": 0.7105263157894737, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8620689655172413, "acc_stderr": 0.028735632183908084, "acc_norm": 0.8620689655172413, "acc_norm_stderr": 0.028735632183908084 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.791005291005291, "acc_stderr": 0.020940481565334863, "acc_norm": 0.791005291005291, "acc_norm_stderr": 0.020940481565334863 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6507936507936508, "acc_stderr": 0.04263906892795131, "acc_norm": 0.6507936507936508, "acc_norm_stderr": 0.04263906892795131 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9419354838709677, "acc_stderr": 0.01330413811280927, "acc_norm": 0.9419354838709677, "acc_norm_stderr": 0.01330413811280927 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.7635467980295566, "acc_stderr": 0.029896114291733545, "acc_norm": 0.7635467980295566, "acc_norm_stderr": 0.029896114291733545 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.88, "acc_stderr": 0.03265986323710906, "acc_norm": 0.88, "acc_norm_stderr": 0.03265986323710906 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.9151515151515152, "acc_stderr": 0.021759385340835914, "acc_norm": 0.9151515151515152, "acc_norm_stderr": 0.021759385340835914 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9696969696969697, "acc_stderr": 0.012213156893572809, "acc_norm": 0.9696969696969697, "acc_norm_stderr": 0.012213156893572809 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9792746113989638, "acc_stderr": 0.010281417011909029, "acc_norm": 0.9792746113989638, "acc_norm_stderr": 0.010281417011909029 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8692307692307693, "acc_stderr": 0.017094072023289646, "acc_norm": 0.8692307692307693, "acc_norm_stderr": 0.017094072023289646 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.6111111111111112, "acc_stderr": 0.029723278961476664, "acc_norm": 0.6111111111111112,
