open-llm-leaderboard-old/details_MatthieuJ__ING_Triomphant_M2_SLERP
收藏数据集概述
该数据集是在对模型 MatthieuJ/ING_Triomphant_M2_SLERP 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，每个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。
额外配置
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 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_MatthieuJ__ING_Triomphant_M2_SLERP", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要：
python { "all": { "acc": 0.2422761423529656, "acc_stderr": 0.03043234014188226, "acc_norm": 0.24295694156694908, "acc_norm_stderr": 0.03124493158242312, "mc1": 0.23990208078335373, "mc1_stderr": 0.014948812679062137, "mc2": 0.48793467414350816, "mc2_stderr": 0.01648072614415625 }, "harness|arc:challenge|25": { "acc": 0.2098976109215017, "acc_stderr": 0.011900548748047442, "acc_norm": 0.2721843003412969, "acc_norm_stderr": 0.013006600406423702 }, "harness|hellaswag|10": { "acc": 0.2605058753236407, "acc_stderr": 0.004380136468543944, "acc_norm": 0.2644891455885282, "acc_norm_stderr": 0.004401594054604112 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.033556772163131424, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.033556772163131424 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19736842105263158, "acc_stderr": 0.03238981601699397, "acc_norm": 0.19736842105263158, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.23018867924528302, "acc_stderr": 0.025907897122408173, "acc_norm": 0.23018867924528302, "acc_norm_stderr": 0.025907897122408173 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.22916666666666666, "acc_stderr": 0.035146974678623884, "acc_norm": 0.22916666666666666, "acc_norm_stderr": 0.035146974678623884 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.17341040462427745, "acc_stderr": 0.02886810787497064, "acc_norm": 0.17341040462427745, "acc_norm_stderr": 0.02886810787497064 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364396, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364396 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.20425531914893616, "acc_stderr": 0.026355158413349424, "acc_norm": 0.20425531914893616, "acc_norm_stderr": 0.026355158413349424 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2896551724137931, "acc_stderr": 0.03780019230438014, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.03780019230438014 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2724867724867725, "acc_stderr": 0.02293097307163335, "acc_norm": 0.2724867724867725, "acc_norm_stderr": 0.02293097307163335 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23015873015873015, "acc_stderr": 0.037649508797906066, "acc_norm": 0.23015873015873015, "acc_norm_stderr": 0.037649508797906066 }, "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": 0.27741935483870966, "acc_stderr": 0.025470196835900055, "acc_norm": 0.27741935483870966, "acc_norm_stderr": 0.025470196835900055 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.24630541871921183, "acc_stderr": 0.030315099285617722, "acc_norm": 0.24630541871921183, "acc_norm_stderr": 0.030315099285617722 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21717171717171718, "acc_stderr": 0.02937661648494563, "acc_norm": 0.21717171717171718, "acc_norm_stderr": 0.02937661648494563 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.16580310880829016, "acc_stderr": 0.026839845022314415, "acc_norm": 0.16580310880829016, "acc_norm_stderr": 0.026839845022314415 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23846153846153847, "acc_stderr": 0.021606294494647724, "acc_norm": 0.23846153846153847, "acc_norm_stderr": 0.021606294494647724 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2222222222222222, "acc_stderr": 0.025348097468097838, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.025
