open-llm-leaderboard-old/details_google__recurrentgemma-2b-it
收藏数据集概述
该数据集是在对模型 google/recurrentgemma-2b-it 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 该数据集包含 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 2024-04-22T18:05:14.115065 运行 的最新结果：
python { "all": { "acc": 0.406071810296271, "acc_stderr": 0.0341471799569999, "acc_norm": 0.4096266355207132, "acc_norm_stderr": 0.034943481884173386, "mc1": 0.26560587515299877, "mc1_stderr": 0.015461027627253595, "mc2": 0.4280584691787138, "mc2_stderr": 0.016352318555575316 }, "harness|arc:challenge|25": { "acc": 0.2738907849829352, "acc_stderr": 0.013032004972989503, "acc_norm": 0.3097269624573379, "acc_norm_stderr": 0.01351205841523836 }, "harness|hellaswag|10": { "acc": 0.4583748257319259, "acc_stderr": 0.004972460206842304, "acc_norm": 0.5626369249153556, "acc_norm_stderr": 0.004950472918523317 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45185185185185184, "acc_stderr": 0.04299268905480864, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.04299268905480864 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3684210526315789, "acc_stderr": 0.03925523381052932, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.03925523381052932 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4981132075471698, "acc_stderr": 0.03077265364207567, "acc_norm": 0.4981132075471698, "acc_norm_stderr": 0.03077265364207567 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4513888888888889, "acc_stderr": 0.04161402398403279, "acc_norm": 0.4513888888888889, "acc_norm_stderr": 0.04161402398403279 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.42, "acc_stderr": 0.04960449637488583, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488583 }, "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": 0.4046242774566474, "acc_stderr": 0.03742461193887248, "acc_norm": 0.4046242774566474, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808778, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808778 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.30638297872340425, "acc_stderr": 0.03013590647851756, "acc_norm": 0.30638297872340425, "acc_norm_stderr": 0.03013590647851756 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436716, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436716 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728762, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728762 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.31216931216931215, "acc_stderr": 0.023865206836972606, "acc_norm": 0.31216931216931215, "acc_norm_stderr": 0.023865206836972606 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2698412698412698, "acc_stderr": 0.03970158273235173, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.03970158273235173 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.44193548387096776, "acc_stderr": 0.028251557906849745, "acc_norm": 0.44193548387096776, "acc_norm_stderr": 0.028251557906849745 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.03413963805906235, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.03413963805906235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3393939393939394, "acc_stderr": 0.036974422050315967, "acc_norm": 0.3393939393939394, "acc_norm_stderr": 0.036974422050315967 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5404040404040404, "acc_stderr": 0.035507024651313425, "acc_norm": 0.5404040404040404, "acc_norm_stderr": 0.035507024651313425 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5906735751295337, "acc_stderr": 0.03548608168860806, "acc_norm": 0.5906735751295337, "acc_norm_stderr": 0.03548608168860806 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4153846153846154, "acc_stderr": 0.024985354923102325, "acc_norm": 0.4153846153846154, "acc_norm_stderr": 0.024985354923102325 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085622 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3949579831932773, "acc_stderr": 0.031753678
