open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-6.7b-v2-instruct
收藏数据集概述
数据集简介
该数据集是在对模型 AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct 进行评估时自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 数据集包含 64 个配置，每个配置对应一个评估任务。
- 数据集来自 1 次运行，每次运行在每个配置中都有一个特定的分割，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-sw3-6.7b-v2-instruct_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-18T21:04:21.939404 运行的最新结果：
python { "all": { "acc": 0.32058974654497724, "acc_stderr": 0.03287256745618845, "acc_norm": 0.3233939935906761, "acc_norm_stderr": 0.03364411678813401, "mc1": 0.26193390452876375, "mc1_stderr": 0.015392118805015023, "mc2": 0.4032485125499964, "mc2_stderr": 0.014292284301112663, "em": 0.22766359060402686, "em_stderr": 0.004294273453162853, "f1": 0.266680998322148, "f1_stderr": 0.00428696034436648 }, "harness|arc:challenge|25": { "acc": 0.3575085324232082, "acc_stderr": 0.014005494275916576, "acc_norm": 0.40784982935153585, "acc_norm_stderr": 0.014361097288449707 }, "harness|hellaswag|10": { "acc": 0.5046803425612428, "acc_stderr": 0.004989562798280523, "acc_norm": 0.6776538538139812, "acc_norm_stderr": 0.004664195159393912 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.362962962962963, "acc_stderr": 0.04153948404742398, "acc_norm": 0.362962962962963, "acc_norm_stderr": 0.04153948404742398 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.32894736842105265, "acc_stderr": 0.03823428969926604, "acc_norm": 0.32894736842105265, "acc_norm_stderr": 0.03823428969926604 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.33962264150943394, "acc_stderr": 0.029146904747798335, "acc_norm": 0.33962264150943394, "acc_norm_stderr": 0.029146904747798335 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3680555555555556, "acc_stderr": 0.04032999053960718, "acc_norm": 0.3680555555555556, "acc_norm_stderr": 0.04032999053960718 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3352601156069364, "acc_stderr": 0.03599586301247078, "acc_norm": 0.3352601156069364, "acc_norm_stderr": 0.03599586301247078 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.0433643270799318, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.0433643270799318 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3191489361702128, "acc_stderr": 0.030472973363380045, "acc_norm": 0.3191489361702128, "acc_norm_stderr": 0.030472973363380045 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.040493392977481404, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.040493392977481404 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.03724563619774634, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.03724563619774634 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.29894179894179895, "acc_stderr": 0.023577604791655805, "acc_norm": 0.29894179894179895, "acc_norm_stderr": 0.023577604791655805 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.039325376803928704, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.039325376803928704 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904276, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904276 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.1921182266009852, "acc_stderr": 0.027719315709614775, "acc_norm": 0.1921182266009852, "acc_norm_stderr": 0.027719315709614775 }, "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": 0.03697442205031596, "acc_norm": 0.3393939393939394, "acc_norm_stderr": 0.03697442205031596 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.31313131313131315, "acc_stderr": 0.03304205087813653, "acc_norm": 0.31313131313131315, "acc_norm_stderr": 0.03304205087813653 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.35233160621761656, "acc_stderr": 0.034474782864143565, "acc_norm": 0.35233160621761656, "acc_norm_stderr": 0.034474782864143565 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2564102564102564, "acc_stderr": 0.02213908110397155, "acc_norm": 0.2564102
