open-llm-leaderboard/details_nathan0__mpt_delta_tuned_model_v2
收藏数据集概述
数据集摘要
该数据集是在对模型 nathan0/mpt_delta_tuned_model_v2 进行评估运行期间自动创建的。数据集包含 61 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。此外，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。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_nathan0__mpt_delta_tuned_model_v2", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-08-29T16:16:19.015155 运行的最新结果： python { "all": { "acc": 0.2950832179561353, "acc_stderr": 0.0329561063051657, "acc_norm": 0.29907052345099405, "acc_norm_stderr": 0.03294521260985216, "mc1": 0.23623011015911874, "mc1_stderr": 0.014869755015871108, "mc2": 0.35471976554662815, "mc2_stderr": 0.013741277408130734 }, "harness|arc:challenge|25": { "acc": 0.45819112627986347, "acc_stderr": 0.014560220308714697, "acc_norm": 0.5068259385665529, "acc_norm_stderr": 0.014610029151379813 }, "harness|hellaswag|10": { "acc": 0.5774746066520613, "acc_stderr": 0.004929517011508221, "acc_norm": 0.7640908185620394, "acc_norm_stderr": 0.0042369801453443065 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2740740740740741, "acc_stderr": 0.03853254836552003, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.03853254836552003 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.2565789473684211, "acc_stderr": 0.0355418036802569, "acc_norm": 0.2565789473684211, "acc_norm_stderr": 0.0355418036802569 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3169811320754717, "acc_stderr": 0.028637235639800918, "acc_norm": 0.3169811320754717, "acc_norm_stderr": 0.028637235639800918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3055555555555556, "acc_stderr": 0.03852084696008534, "acc_norm": 0.3055555555555556, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "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": 0.21965317919075145, "acc_stderr": 0.03156809362703175, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.03156809362703175 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.31063829787234043, "acc_stderr": 0.03025123757921317, "acc_norm": 0.31063829787234043, "acc_norm_stderr": 0.03025123757921317 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.04303684033537314, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537314 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.31724137931034485, "acc_stderr": 0.03878352372138622, "acc_norm": 0.31724137931034485, "acc_norm_stderr": 0.03878352372138622 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.023919984164047736, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.023919984164047736 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.19047619047619047, "acc_stderr": 0.03512207412302052, "acc_norm": 0.19047619047619047, "acc_norm_stderr": 0.03512207412302052 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2903225806451613, "acc_stderr": 0.025822106119415898, "acc_norm": 0.2903225806451613, "acc_norm_stderr": 0.025822106119415898 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.26108374384236455, "acc_stderr": 0.03090379695211449, "acc_norm": 0.26108374384236455, "acc_norm_stderr": 0.03090379695211449 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03453131801885415, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03453131801885415 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.30303030303030304, "acc_stderr": 0.03274287914026868, "acc_norm": 0.30303030303030304, "acc_norm_stderr": 0.03274287914026868 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.31088082901554404, "acc_stderr": 0.03340361906276585, "acc_norm": 0.31088082901554404, "acc_norm_stderr": 0.03340361906276585 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.30512820512820515, "acc_stderr": 0.023346335293325887, "acc_norm": 0.30512820512820515, "acc_norm_stderr": 0.023346335293325887 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145675, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.027080372815145675 }, "harness|hendrycksTest-high_school_microeconomics
