open-llm-leaderboard-old/details_NovoCode__Tiger-DPO

该数据集是在Open LLM Leaderboard上对模型NovoCode/Tiger-DPO进行评估时自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。数据集由2次运行创建，每次运行在每个配置中作为一个特定的分割，train分割始终指向最新结果。此外，还有一个名为results的配置，存储了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。README文件还包含一个Python代码片段，用于加载运行中的详细信息，并提供了特定运行的最新结果。

原始信息汇总

数据集概述

该数据集是在对模型 NovoCode/Tiger-DPO 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 63 个配置，每个配置对应一个评估任务。
• 数据集从 2 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。

最新结果

以下是 2024-02-16T14:49:32.301206 运行 的最新结果：

python { "all": { "acc": 0.5958020167795036, "acc_stderr": 0.03336424247295358, "acc_norm": 0.6002192767446106, "acc_norm_stderr": 0.03404810463176771, "mc1": 0.32313341493268055, "mc1_stderr": 0.016371836286454604, "mc2": 0.507583773070451, "mc2_stderr": 0.014770823381787772 }, "harness|arc:challenge|25": { "acc": 0.43686006825938567, "acc_stderr": 0.014494421584256525, "acc_norm": 0.48208191126279865, "acc_norm_stderr": 0.01460200558549098 }, "harness|hellaswag|10": { "acc": 0.620991834295957, "acc_stderr": 0.004841486716855774, "acc_norm": 0.8181637124078869, "acc_norm_stderr": 0.0038492126228151665 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.03894734487013317, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.03894734487013317 }, "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": 0.6754716981132075, "acc_stderr": 0.02881561571343211, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.02881561571343211 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6388888888888888, "acc_stderr": 0.040166600304512336, "acc_norm": 0.6388888888888888, "acc_norm_stderr": 0.040166600304512336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.04999999999999999, "acc_norm": 0.45, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.037336266553835096, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.037336266553835096 }, "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": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.502127659574468, "acc_stderr": 0.032685726586674915, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.032685726586674915 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.046854730419077895, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.046854730419077895 }, "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": 0.3862433862433862, "acc_stderr": 0.025075981767601677, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.025075981767601677 }, "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": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6645161290322581, "acc_stderr": 0.026860206444724352, "acc_norm": 0.6645161290322581, "acc_norm_stderr": 0.026860206444724352 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7090909090909091, "acc_stderr": 0.03546563019624335, "acc_norm": 0.7090909090909091, "acc_norm_stderr": 0.03546563019624335 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7626262626262627, "acc_stderr": 0.0303137105381989, "acc_norm": 0.7626262626262627, "acc_norm_stderr": 0.0303137105381989 }, "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": 0.5846153846153846, "acc_stderr": 0.02498535492310234, "acc_norm": 0.5846153846153846, "acc_norm_stderr": 0.02498535492310234 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35555555555555557, "acc_stderr": 0.029185714949857413, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.029185714949857413 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6260504201680672, "acc_stderr":