open-llm-leaderboard-old/details_juhwanlee__gemma-7B-alpaca-case-0-2
收藏数据集概述
该数据集是在对模型 juhwanlee/gemma-7B-alpaca-case-0-2 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 1 次运行中创建，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。
- 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 2024-03-27T17:36:28.950988 运行的最新结果：
python { "all": { "acc": 0.6537877318833083, "acc_stderr": 0.032021213526731145, "acc_norm": 0.6579157109359254, "acc_norm_stderr": 0.03265621830608772, "mc1": 0.3329253365973072, "mc1_stderr": 0.016497402382012052, "mc2": 0.4763395167045897, "mc2_stderr": 0.015301264906928517 }, "harness|arc:challenge|25": { "acc": 0.5930034129692833, "acc_stderr": 0.01435639941800912, "acc_norm": 0.6220136518771331, "acc_norm_stderr": 0.014169664520303101 }, "harness|hellaswag|10": { "acc": 0.622585142401912, "acc_stderr": 0.004837493439874299, "acc_norm": 0.82194781915953, "acc_norm_stderr": 0.0038177482691077852 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5481481481481482, "acc_stderr": 0.04299268905480864, "acc_norm": 0.5481481481481482, "acc_norm_stderr": 0.04299268905480864 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7105263157894737, "acc_stderr": 0.03690677986137282, "acc_norm": 0.7105263157894737, "acc_norm_stderr": 0.03690677986137282 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6679245283018868, "acc_stderr": 0.02898545565233439, "acc_norm": 0.6679245283018868, "acc_norm_stderr": 0.02898545565233439 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.75, "acc_stderr": 0.03621034121889507, "acc_norm": 0.75, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6936416184971098, "acc_stderr": 0.03514942551267437, "acc_norm": 0.6936416184971098, "acc_norm_stderr": 0.03514942551267437 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6127659574468085, "acc_stderr": 0.03184389265339526, "acc_norm": 0.6127659574468085, "acc_norm_stderr": 0.03184389265339526 }, "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": 0.6413793103448275, "acc_stderr": 0.039966295748767186, "acc_norm": 0.6413793103448275, "acc_norm_stderr": 0.039966295748767186 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47354497354497355, "acc_stderr": 0.025715239811346758, "acc_norm": 0.47354497354497355, "acc_norm_stderr": 0.025715239811346758 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5396825396825397, "acc_stderr": 0.04458029125470973, "acc_norm": 0.5396825396825397, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8032258064516129, "acc_stderr": 0.02261640942074202, "acc_norm": 0.8032258064516129, "acc_norm_stderr": 0.02261640942074202 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8333333333333334, "acc_stderr": 0.026552207828215282, "acc_norm": 0.8333333333333334, "acc_norm_stderr": 0.026552207828215282 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121434, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121434 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6512820512820513, "acc_stderr": 0.024162780284017717, "acc_norm": 0.6512820512820513, "acc_norm_stderr": 0.024162780284017717 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.029723278961476668, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.029723278961476668 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6764705882352942, "acc_stderr": 0.03038835355188679, "acc_norm": 0.67647
