open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-126m-instruct
收藏数据集概述
该数据集是在对模型 AI-Sweden-Models/gpt-sw3-126m-instruct 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_AI-Sweden-Models__gpt-sw3-126m-instruct", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-06T17:24:12.655083 运行的最新结果：
python { "all": { "acc": 0.23830785704981358, "acc_stderr": 0.030091824926520686, "acc_norm": 0.23875634303781132, "acc_norm_stderr": 0.030838942303782275, "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299965, "mc2": 0.42647039245716606, "mc2_stderr": 0.014756647007334998 }, "harness|arc:challenge|25": { "acc": 0.20392491467576793, "acc_stderr": 0.011774262478702254, "acc_norm": 0.23378839590443687, "acc_norm_stderr": 0.012368225378507144 }, "harness|hellaswag|10": { "acc": 0.28360884285998805, "acc_stderr": 0.004498280244494508, "acc_norm": 0.29884485162318264, "acc_norm_stderr": 0.004568161710399553 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.03355677216313143, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.03355677216313143 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.20394736842105263, "acc_stderr": 0.03279000406310052, "acc_norm": 0.20394736842105263, "acc_norm_stderr": 0.03279000406310052 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2339622641509434, "acc_stderr": 0.02605529690115292, "acc_norm": 0.2339622641509434, "acc_norm_stderr": 0.02605529690115292 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749895, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749895 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.043898699568087785, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.043898699568087785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.02880998985410297, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.02880998985410297 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2689655172413793, "acc_stderr": 0.03695183311650232, "acc_norm": 0.2689655172413793, "acc_norm_stderr": 0.03695183311650232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.23809523809523808, "acc_stderr": 0.021935878081184756, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.021935878081184756 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.18253968253968253, "acc_stderr": 0.034550710191021475, "acc_norm": 0.18253968253968253, "acc_norm_stderr": 0.034550710191021475 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.23548387096774193, "acc_stderr": 0.024137632429337707, "acc_norm": 0.23548387096774193, "acc_norm_stderr": 0.024137632429337707 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.1921182266009852, "acc_stderr": 0.027719315709614778, "acc_norm": 0.1921182266009852, "acc_norm_stderr": 0.027719315709614778 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.20606060606060606, "acc_stderr": 0.03158415324047707, "acc_norm": 0.20606060606060606, "acc_norm_stderr": 0.03158415324047707 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.20202020202020202, "acc_stderr": 0.028606204289229876, "acc_norm": 0.20202020202020202, "acc_norm_stderr": 0.028606204289229876 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860667, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860667 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.20512820512820512, "acc_stderr": 0.02047323317355198, "acc_norm": 0.20512820512820512, "acc_norm_stderr": 0.02047323317355198 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.22592592592592592, "acc_stderr": 0.0
