open-llm-leaderboard-old/details_BEE-spoke-data__smol_llama-101M-GQA
收藏数据集概述
该数据集是在评估模型BEE-spoke-data/smol_llama-101M-GQA在Open LLM Leaderboard上的自动创建的。
数据集组成
- 数据集包含64个配置，每个配置对应一个评估任务。
- 数据集从2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，用于计算和显示在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_BEE-spoke-data__smol_llama-101M-GQA_public", "harness_winogrande_5", split="train")
最新结果
以下是最新结果从2023-11-18T22:28:51.599216的摘要：
python { "all": { "acc": 0.243457145392589, "acc_stderr": 0.030232451207481324, "acc_norm": 0.2440460125546807, "acc_norm_stderr": 0.03099855104029764, "mc1": 0.2484700122399021, "mc1_stderr": 0.01512742709652069, "mc2": 0.45801037294841895, "mc2_stderr": 0.01513659314586415, "em": 0.0016778523489932886, "em_stderr": 0.0004191330178826889, "f1": 0.03420931208053696, "f1_stderr": 0.0011030675027452802 }, "harness|arc:challenge|25": { "acc": 0.18088737201365188, "acc_stderr": 0.011248574467407024, "acc_norm": 0.23464163822525597, "acc_norm_stderr": 0.012383873560768675 }, "harness|hellaswag|10": { "acc": 0.2789285002987453, "acc_stderr": 0.004475557360359701, "acc_norm": 0.287293367855009, "acc_norm_stderr": 0.004515748192605715 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2740740740740741, "acc_stderr": 0.03853254836552004, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.03853254836552004 }, "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": 0.19, "acc_stderr": 0.03942772444036625, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22641509433962265, "acc_stderr": 0.025757559893106737, "acc_norm": 0.22641509433962265, "acc_norm_stderr": 0.025757559893106737 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2708333333333333, "acc_stderr": 0.037161774375660164, "acc_norm": 0.2708333333333333, "acc_norm_stderr": 0.037161774375660164 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.15, "acc_stderr": 0.035887028128263714, "acc_norm": 0.15, "acc_norm_stderr": 0.035887028128263714 }, "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": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.1907514450867052, "acc_stderr": 0.029957851329869337, "acc_norm": 0.1907514450867052, "acc_norm_stderr": 0.029957851329869337 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.23829787234042554, "acc_stderr": 0.02785125297388977, "acc_norm": 0.23829787234042554, "acc_norm_stderr": 0.02785125297388977 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.0404933929774814, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.0404933929774814 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135303, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135303 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.17989417989417988, "acc_stderr": 0.019782119832766426, "acc_norm": 0.17989417989417988, "acc_norm_stderr": 0.019782119832766426 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.24603174603174602, "acc_stderr": 0.038522733649243156, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.038522733649243156 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3064516129032258, "acc_stderr": 0.026226485652553873, "acc_norm": 0.3064516129032258, "acc_norm_stderr": 0.026226485652553873 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.0316185633535861, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.0316185633535861 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.16, "acc_stderr": 0.03684529491774709, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.03256866661681102, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.26262626262626265, "acc_stderr": 0.031353050095330855, "acc_norm": 0.26262626262626265, "acc_norm_stderr": 0.031353050095330855 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.34196891191709844, "acc_stderr": 0.03423465100104281, "acc_norm": 0.34196891191709844, "acc_norm_stderr": 0.03423465100104281 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.30256410256410254, "acc_stderr": 0.023290888053772725, "acc_norm": 0.3025
