open-llm-leaderboard-old/details_Test157t__Pasta-PrimaMaid-7b
收藏数据集概述
数据集简介
该数据集是在模型 Test157t/Pasta-PrimaMaid-7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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 1 次运行创建，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。
结果配置
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_Test157t__Pasta-PrimaMaid-7b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-14T05:01:29.583377 运行的最新结果：
python { "all": { "acc": 0.634263599311872, "acc_stderr": 0.03256128363764394, "acc_norm": 0.6378018463193035, "acc_norm_stderr": 0.03320777359975318, "mc1": 0.48959608323133413, "mc1_stderr": 0.017499711430249264, "mc2": 0.6646812404946975, "mc2_stderr": 0.0151510838946931 }, "harness|arc:challenge|25": { "acc": 0.6416382252559727, "acc_stderr": 0.014012883334859857, "acc_norm": 0.6791808873720137, "acc_norm_stderr": 0.013640943091946535 }, "harness|hellaswag|10": { "acc": 0.6888070105556662, "acc_stderr": 0.004620353433075613, "acc_norm": 0.8617805218084047, "acc_norm_stderr": 0.0034442484997916595 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "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": 0.6513157894736842, "acc_stderr": 0.0387813988879761, "acc_norm": 0.6513157894736842, "acc_norm_stderr": 0.0387813988879761 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7056603773584905, "acc_stderr": 0.02804918631569525, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.02804918631569525 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.036563436533531585, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.036563436533531585 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.4298245614035088, "acc_stderr": 0.04657047260594963, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3915343915343915, "acc_stderr": 0.025138091388851105, "acc_norm": 0.3915343915343915, "acc_norm_stderr": 0.025138091388851105 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7548387096774194, "acc_stderr": 0.024472243840895518, "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.024472243840895518 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175008, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175008 }, "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": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.029857515673386414, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.029857515673386414 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758723, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758723 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6512820512820513, "acc_stderr": 0.024162780284017724, "acc_norm": 0.6512820512820513, "acc_norm_stderr": 0.024162780284017724 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37777777777777777, "acc_stderr": 0.029560707392465725, "acc_norm": 0.37777777777777777, "acc_norm_
