open-llm-leaderboard-old/details_lodrick-the-lafted__Grafted-Llama2-2x70B
收藏数据集概述
该数据集是在对模型lodrick-the-lafted/Grafted-Llama2-2x70B进行评估时自动创建的，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。
- 数据集由1次运行创建，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。
- 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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_lodrick-the-lafted__Grafted-Llama2-2x70B", "harness_winogrande_5", split="train")
最新结果
以下是最新结果（注意可能有其他任务的结果，每个任务的结果可以在"results"和"latest"分割中找到）：
python { "all": { "acc": 0.7162400942995992, "acc_stderr": 0.029857485504267534, "acc_norm": 0.7199041020126216, "acc_norm_stderr": 0.030434480280872887, "mc1": 0.4920440636474908, "mc1_stderr": 0.01750128507455183, "mc2": 0.6649277907845683, "mc2_stderr": 0.014471158700072567 }, "harness|arc:challenge|25": { "acc": 0.6928327645051194, "acc_stderr": 0.013481034054980945, "acc_norm": 0.7261092150170648, "acc_norm_stderr": 0.013032004972989505 }, "harness|hellaswag|10": { "acc": 0.7223660625373431, "acc_stderr": 0.004469165728600332, "acc_norm": 0.8957379008165705, "acc_norm_stderr": 0.003049756910828993 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.042039210401562783, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.042039210401562783 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8223684210526315, "acc_stderr": 0.03110318238312338, "acc_norm": 0.8223684210526315, "acc_norm_stderr": 0.03110318238312338 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7433962264150943, "acc_stderr": 0.026880647889051982, "acc_norm": 0.7433962264150943, "acc_norm_stderr": 0.026880647889051982 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8263888888888888, "acc_stderr": 0.03167473383795718, "acc_norm": 0.8263888888888888, "acc_norm_stderr": 0.03167473383795718 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7167630057803468, "acc_stderr": 0.03435568056047875, "acc_norm": 0.7167630057803468, "acc_norm_stderr": 0.03435568056047875 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105654, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909281, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909281 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7148936170212766, "acc_stderr": 0.02951319662553935, "acc_norm": 0.7148936170212766, "acc_norm_stderr": 0.02951319662553935 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.04697085136647863, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.04697085136647863 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6620689655172414, "acc_stderr": 0.039417076320648906, "acc_norm": 0.6620689655172414, "acc_norm_stderr": 0.039417076320648906 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.48412698412698413, "acc_stderr": 0.02573833063941215, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.02573833063941215 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5158730158730159, "acc_stderr": 0.044698818540726076, "acc_norm": 0.5158730158730159, "acc_norm_stderr": 0.044698818540726076 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8354838709677419, "acc_stderr": 0.021090847745939303, "acc_norm": 0.8354838709677419, "acc_norm_stderr": 0.021090847745939303 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5467980295566502, "acc_stderr": 0.03502544650845872, "acc_norm": 0.5467980295566502, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.83, "acc_stderr": 0.0377525168068637, "acc_norm": 0.83, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8545454545454545, "acc_stderr": 0.027530196355066573, "acc_norm": 0.8545454545454545, "acc_norm_stderr": 0.027530196355066573 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8838383838383839, "acc_stderr": 0.022828881775249377, "acc_norm": 0.8838383838383839, "acc_norm_stderr": 0.022828881775249377 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.017426974154240528, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.017426974154240528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7230769230769231, "acc_stderr": 0.022688042352424994, "acc_norm": 0.7230769230769231, "acc_norm_stderr": 0.022688042352424994 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028597, "acc_norm": 0.322222222
