open-llm-leaderboard-old/details_indischepartij__MiniCPM-3B-Bacchus
收藏数据集概述
该数据集是在对模型 indischepartij/MiniCPM-3B-Bacchus 进行评估运行期间自动创建的。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，每次运行的详细信息可以在每个配置中找到，并以运行的时间戳命名。"train" 分割始终指向最新的结果。
数据集结构
配置
- results: 存储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。
加载数据
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_indischepartij__MiniCPM-3B-Bacchus", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-13T04:24:43.886690 运行的最新结果：
python { "all": { "acc": 0.5043816466809818, "acc_stderr": 0.034512563967863674, "acc_norm": 0.50707380697781, "acc_norm_stderr": 0.03522451893789315, "mc1": 0.2937576499388005, "mc1_stderr": 0.015945068581236614, "mc2": 0.43515598064870864, "mc2_stderr": 0.014518057161705074 }, "harness|arc:challenge|25": { "acc": 0.40102389078498296, "acc_stderr": 0.014322255790719869, "acc_norm": 0.4351535836177474, "acc_norm_stderr": 0.014487986197186045 }, "harness|hellaswag|10": { "acc": 0.5152360087631945, "acc_stderr": 0.004987464257999318, "acc_norm": 0.7045409281019717, "acc_norm_stderr": 0.004553164013379556 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4148148148148148, "acc_stderr": 0.042561937679014075, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.042561937679014075 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5526315789473685, "acc_stderr": 0.0404633688397825, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.0404633688397825 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5169811320754717, "acc_stderr": 0.030755120364119905, "acc_norm": 0.5169811320754717, "acc_norm_stderr": 0.030755120364119905 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5486111111111112, "acc_stderr": 0.04161402398403279, "acc_norm": 0.5486111111111112, "acc_norm_stderr": 0.04161402398403279 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "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": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.48554913294797686, "acc_stderr": 0.03810871630454764, "acc_norm": 0.48554913294797686, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201943, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201943 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39148936170212767, "acc_stderr": 0.031907012423268113, "acc_norm": 0.39148936170212767, "acc_norm_stderr": 0.031907012423268113 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.044346007015849245, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.044346007015849245 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728762, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728762 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.31746031746031744, "acc_stderr": 0.02397386199899207, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.02397386199899207 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30158730158730157, "acc_stderr": 0.04104947269903394, "acc_norm": 0.30158730158730157, "acc_norm_stderr": 0.04104947269903394 }, "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": 0.5935483870967742, "acc_stderr": 0.02794172734625631, "acc_norm": 0.5935483870967742, "acc_norm_stderr": 0.02794172734625631 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3645320197044335, "acc_stderr": 0.0338640574606209, "acc_norm": 0.3645320197044335, "acc_norm_stderr": 0.0338640574606209 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5454545454545454, "acc_stderr": 0.038881769216741004, "acc_norm": 0.5454545454545454, "acc_norm_stderr": 0.038881769216741004 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6414141414141414, "acc_stderr": 0.03416903640391522, "acc_norm": 0.6414141414141414, "acc_norm_stderr": 0.03416903640391522 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.694300518134715, "acc_stderr": 0.033248379397581594, "acc_norm": 0.694300518134715, "acc_norm_stderr": 0.033248379397581594 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.45897435897435895, "acc_stderr": 0.025265525491284295, "acc_norm": 0.45897435897435895, "acc_norm_stderr": 0.025265525491284295 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945287, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945287 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.525210084
