open-llm-leaderboard-old/details_jukofyork__Eurus-70b-nca-fixed
收藏数据集概述
数据集简介
该数据集是在对模型 jukofyork/Eurus-70b-nca-fixed 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：数据集从1次运行中创建，每个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。
- 分割类型：每个配置包含多个分割，其中 "train" 分割始终指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，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_jukofyork__Eurus-70b-nca-fixed", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-16T00:23:57.124428 运行的最新结果：
python { "all": { "acc": 0.5571686624748139, "acc_stderr": 0.03393519743668366, "acc_norm": 0.5596479287539352, "acc_norm_stderr": 0.03462936550397699, "mc1": 0.38555691554467564, "mc1_stderr": 0.017038839010591673, "mc2": 0.5442237600234209, "mc2_stderr": 0.015173822929244801 }, "harness|arc:challenge|25": { "acc": 0.5204778156996587, "acc_stderr": 0.01459913135303501, "acc_norm": 0.5563139931740614, "acc_norm_stderr": 0.014518421825670444 }, "harness|hellaswag|10": { "acc": 0.518621788488349, "acc_stderr": 0.004986319587524961, "acc_norm": 0.7237602071300537, "acc_norm_stderr": 0.00446223036398215 }, "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": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5723684210526315, "acc_stderr": 0.04026097083296564, "acc_norm": 0.5723684210526315, "acc_norm_stderr": 0.04026097083296564 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.539622641509434, "acc_stderr": 0.030676096599389177, "acc_norm": 0.539622641509434, "acc_norm_stderr": 0.030676096599389177 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5416666666666666, "acc_stderr": 0.041666666666666644, "acc_norm": 0.5416666666666666, "acc_norm_stderr": 0.041666666666666644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4797687861271676, "acc_stderr": 0.03809342081273958, "acc_norm": 0.4797687861271676, "acc_norm_stderr": 0.03809342081273958 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.04724007352383889, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383889 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4595744680851064, "acc_stderr": 0.03257901482099835, "acc_norm": 0.4595744680851064, "acc_norm_stderr": 0.03257901482099835 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.04685473041907789, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.04685473041907789 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42857142857142855, "acc_stderr": 0.025487187147859372, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.025487187147859372 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.49206349206349204, "acc_stderr": 0.044715725362943486, "acc_norm": 0.49206349206349204, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5483870967741935, "acc_stderr": 0.02831050034856839, "acc_norm": 0.5483870967741935, "acc_norm_stderr": 0.02831050034856839 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39408866995073893, "acc_stderr": 0.034381579670365446, "acc_norm": 0.39408866995073893, "acc_norm_stderr": 0.034381579670365446 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6565656565656566, "acc_stderr": 0.03383201223244442, "acc_norm": 0.6565656565656566, "acc_norm_stderr": 0.03383201223244442 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7823834196891192, "acc_stderr": 0.02977866303775296, "acc_norm": 0.7823834196891192, "acc_norm_stderr": 0.02977866303775296 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5358974358974359, "acc_stderr": 0.025285585990017848, "acc_norm": 0.5358974358974359, "acc_norm_stderr": 0.025285585990017848 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34444444444444444, "acc_stderr": 0.028972648884844267, "acc_norm": 0.34444444444444444,
