open-llm-leaderboard-old/details_Kquant03__Prokaryote-8x7B-bf16
收藏数据集概述
数据集创建背景
该数据集是在对模型 Kquant03/Prokaryote-8x7B-bf16 进行评估运行期间自动创建的,评估运行在 Open LLM Leaderboard 上进行。
数据集结构
- 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。
- 额外的 "results" 配置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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Kquant03__Prokaryote-8x7B-bf16", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果从运行 2024-01-18T20:11:57.513943 的数据:
python { "all": { "acc": 0.655551112846195, "acc_stderr": 0.03200857802460192, "acc_norm": 0.6550894523163624, "acc_norm_stderr": 0.03267273078447577, "mc1": 0.5397796817625459, "mc1_stderr": 0.017448017223960867, "mc2": 0.6778730144008733, "mc2_stderr": 0.015193091234587739 }, "harness|arc:challenge|25": { "acc": 0.7150170648464164, "acc_stderr": 0.013191348179838793, "acc_norm": 0.7372013651877133, "acc_norm_stderr": 0.012862523175351335 }, "harness|hellaswag|10": { "acc": 0.7167894841665007, "acc_stderr": 0.004496369742132105, "acc_norm": 0.8817964548894642, "acc_norm_stderr": 0.003221891726851491 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7056603773584905, "acc_stderr": 0.028049186315695255, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.028049186315695255 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7638888888888888, "acc_stderr": 0.03551446610810826, "acc_norm": 0.7638888888888888, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.048580835742663454, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663454 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108101, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108101 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878152, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878152 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41005291005291006, "acc_stderr": 0.02533120243894443, "acc_norm": 0.41005291005291006, "acc_norm_stderr": 0.02533120243894443 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7967741935483871, "acc_stderr": 0.022891687984554956, "acc_norm": 0.7967741935483871, "acc_norm_stderr": 0.022891687984554956 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175007, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175007 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.032876667586034906, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.032876667586034906 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8080808080808081, "acc_stderr": 0.028057791672989017, "acc_norm": 0.8080808080808081, "acc_norm_stderr": 0.028057791672989017 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8963730569948186, "acc_stderr": 0.02199531196364424, "acc_norm": 0.8963730569948186, "acc_norm_stderr": 0.02199531196364424 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.658974358974359, "acc_stderr": 0.024035489676335082, "acc_norm": 0.658974358974359, "acc_norm_stderr": 0.024035489676335082 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34444444444444444, "acc_stderr": 0.02897264888484427, "acc_norm": 0.34444444444444444, "acc_norm_stderr":



