open-llm-leaderboard/details_llm-agents__tora-code-34b-v1.0
收藏数据集概述
数据集简介
该数据集是在评估模型 llm-agents/tora-code-34b-v1.0 在 Open LLM Leaderboard 上的自动创建的。数据集包含64个配置，每个配置对应一个评估任务。
数据集结构
数据集由3次运行结果组成，每次运行的结果可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。"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，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_llm-agents__tora-code-34b-v1.0", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-04T21:49:30.893930 运行 的最新结果：
python { "all": { "acc": 0.46739279777981946, "acc_stderr": 0.034410091993572804, "acc_norm": 0.4720435067546776, "acc_norm_stderr": 0.03515712357620925, "mc1": 0.26193390452876375, "mc1_stderr": 0.015392118805015034, "mc2": 0.39617813653906875, "mc2_stderr": 0.01499031262059852 }, "harness|arc:challenge|25": { "acc": 0.47440273037542663, "acc_stderr": 0.014592230885298962, "acc_norm": 0.5025597269624573, "acc_norm_stderr": 0.014611199329843784 }, "harness|hellaswag|10": { "acc": 0.5683130850428202, "acc_stderr": 0.0049429906231311166, "acc_norm": 0.754829715196176, "acc_norm_stderr": 0.004293089342105424 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3851851851851852, "acc_stderr": 0.042039210401562783, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.042039210401562783 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.040601270352363966, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4867924528301887, "acc_stderr": 0.030762134874500482, "acc_norm": 0.4867924528301887, "acc_norm_stderr": 0.030762134874500482 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4583333333333333, "acc_stderr": 0.04166666666666665, "acc_norm": 0.4583333333333333, "acc_norm_stderr": 0.04166666666666665 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4046242774566474, "acc_stderr": 0.03742461193887248, "acc_norm": 0.4046242774566474, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808778, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808778 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.046482319871173156, "acc_norm": 0.69, "acc_norm_stderr": 0.046482319871173156 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3872340425531915, "acc_stderr": 0.03184389265339525, "acc_norm": 0.3872340425531915, "acc_norm_stderr": 0.03184389265339525 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.35964912280701755, "acc_stderr": 0.04514496132873633, "acc_norm": 0.35964912280701755, "acc_norm_stderr": 0.04514496132873633 }, "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": 0.3333333333333333, "acc_stderr": 0.024278568024307706, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.024278568024307706 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5, "acc_stderr": 0.028444006199428714, "acc_norm": 0.5, "acc_norm_stderr": 0.028444006199428714 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.35467980295566504, "acc_stderr": 0.03366124489051448, "acc_norm": 0.35467980295566504, "acc_norm_stderr": 0.03366124489051448 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5757575757575758, "acc_stderr": 0.03859268142070264, "acc_norm": 0.5757575757575758, "acc_norm_stderr": 0.03859268142070264 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5707070707070707, "acc_stderr": 0.03526552724601199, "acc_norm": 0.5707070707070707, "acc_norm_stderr": 0.03526552724601199 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.616580310880829, "acc_stderr": 0.03508984236295342, "acc_norm": 0.616580310880829, "acc_norm_stderr": 0.03508984236295342 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.37435897435897436, "acc_stderr": 0.024537591572830513, "acc_norm": 0.37435897435897436, "acc_norm_stderr": 0.024537591572830513 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.0284934650910286, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0.0
