open-llm-leaderboard-old/details_AmberYifan__test-spin-lora-iter2

该数据集是在模型[AmberYifan/test-spin-lora-iter2](https://huggingface.co/AmberYifan/test-spin-lora-iter2)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的，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命名。"train"分割始终指向最新的结果。此外，"results"配置存储了所有运行的聚合结果，并用于计算和显示[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的聚合指标。

原始信息汇总

数据集概述

该数据集是在模型 AmberYifan/test-spin-lora-iter2 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

数据集组成

• 数据集包含 63 个配置，每个配置对应一个评估任务。
• 数据集由 1 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。
• 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。

最新结果

以下是 2024-04-17T06:00:49.810983 运行的最新结果：

python { "all": { "acc": 0.5964365040950002, "acc_stderr": 0.03300982793155409, "acc_norm": 0.6027288407710951, "acc_norm_stderr": 0.03370048284799211, "mc1": 0.25458996328029376, "mc1_stderr": 0.01525011707915648, "mc2": 0.39708976819752134, "mc2_stderr": 0.01445465903433318 }, "harness|arc:challenge|25": { "acc": 0.5358361774744027, "acc_stderr": 0.014573813664735718, "acc_norm": 0.5708191126279863, "acc_norm_stderr": 0.014464085894870653 }, "harness|hellaswag|10": { "acc": 0.6060545708026289, "acc_stderr": 0.004876243842318606, "acc_norm": 0.8064130651264688, "acc_norm_stderr": 0.00394301397148711 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.04276349494376599, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.038607315993160904, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.038607315993160904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6566037735849056, "acc_stderr": 0.02922452646912479, "acc_norm": 0.6566037735849056, "acc_norm_stderr": 0.02922452646912479 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6875, "acc_stderr": 0.038760854559127644, "acc_norm": 0.6875, "acc_norm_stderr": 0.038760854559127644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6069364161849711, "acc_stderr": 0.03724249595817731, "acc_norm": 0.6069364161849711, "acc_norm_stderr": 0.03724249595817731 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077615, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077615 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036845, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5276595744680851, "acc_stderr": 0.03263597118409769, "acc_norm": 0.5276595744680851, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.37719298245614036, "acc_stderr": 0.04559522141958216, "acc_norm": 0.37719298245614036, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.04113914981189261, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.04113914981189261 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.025305906241590632, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.025305906241590632 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.04343525428949098, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.04343525428949098 }, "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": 0.7096774193548387, "acc_stderr": 0.025822106119415898, "acc_norm": 0.7096774193548387, "acc_norm_stderr": 0.025822106119415898 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7626262626262627, "acc_stderr": 0.030313710538198913, "acc_norm": 0.7626262626262627, "acc_norm_stderr": 0.030313710538198913 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8186528497409327, "acc_stderr": 0.02780703236068609, "acc_norm": 0.8186528497409327, "acc_norm_stderr": 0.02780703236068609 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5717948717948718, "acc_stderr": 0.025088301454694827, "acc_norm": 0.5717948717948718, "acc_norm_stderr": 0.025088301454694827 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.028820884666253255, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.028820884666253255 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6134453781512605, "acc_stderr": 0.03163145