open-llm-leaderboard-old/details_gagan3012__MetaModel_moe_multilingualv1
收藏数据集概述
数据集简介
该数据集是在评估模型 gagan3012/MetaModel_moe_multilingualv1 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行创建，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。
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_gagan3012__MetaModel_moe_multilingualv1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-08T03:30:47.395820 运行 的最新结果：
python { "all": { "acc": 0.6413050326508205, "acc_stderr": 0.03216999625951096, "acc_norm": 0.6434280464159652, "acc_norm_stderr": 0.032808286279978185, "mc1": 0.44063647490820074, "mc1_stderr": 0.017379697555437446, "mc2": 0.6122907163213582, "mc2_stderr": 0.015399869141225538 }, "harness|arc:challenge|25": { "acc": 0.636518771331058, "acc_stderr": 0.014056207319068285, "acc_norm": 0.6723549488054608, "acc_norm_stderr": 0.013715847940719337 }, "harness|hellaswag|10": { "acc": 0.6665006970722963, "acc_stderr": 0.004704996294145034, "acc_norm": 0.8473411670981876, "acc_norm_stderr": 0.0035892328893065324 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998904, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.02863723563980089, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.02863723563980089 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7638888888888888, "acc_stderr": 0.03551446610810826, "acc_norm": 0.7638888888888888, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "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": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105655, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105655 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909282, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5702127659574469, "acc_stderr": 0.03236214467715564, "acc_norm": 0.5702127659574469, "acc_norm_stderr": 0.03236214467715564 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555498, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555498 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3994708994708995, "acc_stderr": 0.02522545028406788, "acc_norm": 0.3994708994708995, "acc_norm_stderr": 0.02522545028406788 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7548387096774194, "acc_stderr": 0.02447224384089551, "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.02447224384089551 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.03515895551165698, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.03515895551165698 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.03317505930009181, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.03317505930009181 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.029126522834586818, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586818 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.02098685459328973, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.02098685459328973 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402538, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402538 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028593, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0.028493465091028593 }, "
