open-llm-leaderboard-old/details_indischepartij__MiniCPM-3B-OpenHermes-2.5-v2
收藏数据集概述
该数据集是在评估模型indischepartij/MiniCPM-3B-OpenHermes-2.5-v2在Open LLM Leaderboard上的运行过程中自动创建的。
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2次运行中创建，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。
- "train"分割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，用于计算和显示在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_indischepartij__MiniCPM-3B-OpenHermes-2.5-v2", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-02-12T20:03:47.867498的运行： python { "all": { "acc": 0.5274704484249705, "acc_stderr": 0.03438524173597624, "acc_norm": 0.532836900103673, "acc_norm_stderr": 0.035101557474168814, "mc1": 0.2864137086903305, "mc1_stderr": 0.015826142439502342, "mc2": 0.4227589065713519, "mc2_stderr": 0.014631323260578519 }, "harness|arc:challenge|25": { "acc": 0.4308873720136519, "acc_stderr": 0.014471133392642468, "acc_norm": 0.47440273037542663, "acc_norm_stderr": 0.014592230885298967 }, "harness|hellaswag|10": { "acc": 0.5351523600876319, "acc_stderr": 0.004977434505403354, "acc_norm": 0.7199761003784106, "acc_norm_stderr": 0.004480929450281562 }, "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": 0.43703703703703706, "acc_stderr": 0.04284958639753399, "acc_norm": 0.43703703703703706, "acc_norm_stderr": 0.04284958639753399 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6118421052631579, "acc_stderr": 0.03965842097512744, "acc_norm": 0.6118421052631579, "acc_norm_stderr": 0.03965842097512744 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5773584905660377, "acc_stderr": 0.03040233144576954, "acc_norm": 0.5773584905660377, "acc_norm_stderr": 0.03040233144576954 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04076663253918567, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04076663253918567 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5260115606936416, "acc_stderr": 0.03807301726504513, "acc_norm": 0.5260115606936416, "acc_norm_stderr": 0.03807301726504513 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.04897104952726367, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.04897104952726367 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4127659574468085, "acc_stderr": 0.03218471141400351, "acc_norm": 0.4127659574468085, "acc_norm_stderr": 0.03218471141400351 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.04462917535336936, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.04462917535336936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.46206896551724136, "acc_stderr": 0.041546596717075474, "acc_norm": 0.46206896551724136, "acc_norm_stderr": 0.041546596717075474 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35714285714285715, "acc_stderr": 0.02467786284133278, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.02467786284133278 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.35714285714285715, "acc_stderr": 0.04285714285714281, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.04285714285714281 }, "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": 0.6709677419354839, "acc_stderr": 0.02672949906834996, "acc_norm": 0.6709677419354839, "acc_norm_stderr": 0.02672949906834996 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5515151515151515, "acc_stderr": 0.038835659779569286, "acc_norm": 0.5515151515151515, "acc_norm_stderr": 0.038835659779569286 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7070707070707071, "acc_stderr": 0.03242497958178815, "acc_norm": 0.7070707070707071, "acc_norm_stderr": 0.03242497958178815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7202072538860104, "acc_stderr": 0.03239637046735704, "acc_norm": 0.7202072538860104, "acc_norm_stderr": 0.03239637046735704 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5025641025641026, "acc_stderr": 0.025350672979412202, "acc_norm": 0.5025641025641026, "acc_norm_stderr": 0.025350672979412202 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815635, "acc_norm": 0.3074074074074074, "acc_norm_stderr": 0.028133252578815635 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.56
