open-llm-leaderboard-old/details_Expert68__llama2_13b_instructed_version2
收藏数据集概述
数据集摘要
该数据集是在对模型 Expert68/llama2_13b_instructed_version2 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 64 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 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_Expert68__llama2_13b_instructed_version2_public", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2023-11-12T19:44:39.658427 的运行： python { "all": { "acc": 0.5535385938067054, "acc_stderr": 0.03382379046360409, "acc_norm": 0.5616374813808622, "acc_norm_stderr": 0.034597480068222046, "mc1": 0.31456548347613217, "mc1_stderr": 0.01625524199317918, "mc2": 0.46118545589659976, "mc2_stderr": 0.015483508114692393, "em": 0.007340604026845637, "em_stderr": 0.0008741896875345934, "f1": 0.07567323825503336, "f1_stderr": 0.0016747744191590948 }, "harness|arc:challenge|25": { "acc": 0.5631399317406144, "acc_stderr": 0.014494421584256519, "acc_norm": 0.6006825938566553, "acc_norm_stderr": 0.014312094557946705 }, "harness|hellaswag|10": { "acc": 0.6412069308902609, "acc_stderr": 0.004786660691181909, "acc_norm": 0.8404700258912567, "acc_norm_stderr": 0.003654212329516619 }, "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": 0.4740740740740741, "acc_stderr": 0.04313531696750574, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750574 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5460526315789473, "acc_stderr": 0.04051646342874142, "acc_norm": 0.5460526315789473, "acc_norm_stderr": 0.04051646342874142 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5924528301886792, "acc_stderr": 0.030242233800854494, "acc_norm": 0.5924528301886792, "acc_norm_stderr": 0.030242233800854494 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.625, "acc_stderr": 0.04048439222695598, "acc_norm": 0.625, "acc_norm_stderr": 0.04048439222695598 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "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": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5144508670520231, "acc_stderr": 0.03810871630454764, "acc_norm": 0.5144508670520231, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364397, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364397 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.451063829787234, "acc_stderr": 0.032529096196131965, "acc_norm": 0.451063829787234, "acc_norm_stderr": 0.032529096196131965 }, "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": 0.46206896551724136, "acc_stderr": 0.041546596717075474, "acc_norm": 0.46206896551724136, "acc_norm_stderr": 0.041546596717075474 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.32275132275132273, "acc_stderr": 0.024078943243597016, "acc_norm": 0.32275132275132273, "acc_norm_stderr": 0.024078943243597016 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.35714285714285715, "acc_stderr": 0.042857142857142816, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.042857142857142816 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6483870967741936, "acc_stderr": 0.02716253782694846, "acc_norm": 0.6483870967741936, "acc_norm_stderr": 0.02716253782694846 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43842364532019706, "acc_stderr": 0.03491207857486518, "acc_norm": 0.43842364532019706, "acc_norm_stderr": 0.03491207857486518 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.696969696969697, "acc_stderr": 0.03588624800091707, "acc_norm": 0.696969696969697, "acc_norm_stderr": 0.03588624800091707 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6717171717171717, "acc_stderr": 0.03345678422756776, "acc_norm": 0.6717171717171717, "acc_norm_stderr": 0.03345678422756776 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8238341968911918, "acc_stderr": 0.027493504244548057, "acc_norm": 0.8238341968911918, "acc_norm_stderr": 0.027493504244548057 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5153846153846153, "acc_stderr": 0.025339003010106515, "acc_norm": 0.5153846153846153, "acc_norm_stderr": 0.025339003010106515 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.02696242432
