open-llm-leaderboard-old/details_cookinai__Blitz-v0.2
收藏数据集概述
该数据集是在模型cookinai/Blitz-v0.2在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。
数据集结构
数据集从1次运行中创建，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train"分片始终指向最新的结果。
此外，一个名为"results"的额外配置存储了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
以下是加载特定运行详细信息的示例代码：
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_cookinai__Blitz-v0.2", "harness_winogrande_5", split="train")
最新结果
以下是2024-03-09T19:10:33.087092运行的最新结果：
python { "all": { "acc": 0.6259373955029214, "acc_stderr": 0.032583230555173225, "acc_norm": 0.6323336636080772, "acc_norm_stderr": 0.0332497653182241, "mc1": 0.28518971848225216, "mc1_stderr": 0.015805827874454892, "mc2": 0.42713204934683263, "mc2_stderr": 0.014117274045734679 }, "harness|arc:challenge|25": { "acc": 0.5537542662116041, "acc_stderr": 0.01452670554853998, "acc_norm": 0.590443686006826, "acc_norm_stderr": 0.01437035863247244 }, "harness|hellaswag|10": { "acc": 0.6223859788886676, "acc_stderr": 0.004837995637638541, "acc_norm": 0.8300139414459271, "acc_norm_stderr": 0.0037485288878381204 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.042446332383532265, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.042446332383532265 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6513157894736842, "acc_stderr": 0.03878139888797611, "acc_norm": 0.6513157894736842, "acc_norm_stderr": 0.03878139888797611 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.02863723563980089, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.02863723563980089 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "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": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6358381502890174, "acc_stderr": 0.03669072477416907, "acc_norm": 0.6358381502890174, "acc_norm_stderr": 0.03669072477416907 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5829787234042553, "acc_stderr": 0.03223276266711712, "acc_norm": 0.5829787234042553, "acc_norm_stderr": 0.03223276266711712 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.041227371113703316, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4126984126984127, "acc_stderr": 0.025355741263055263, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.025355741263055263 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7548387096774194, "acc_stderr": 0.024472243840895514, "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.024472243840895514 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7757575757575758, "acc_stderr": 0.032568666616811015, "acc_norm": 0.7757575757575758, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.03074630074212451, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.03074630074212451 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8652849740932642, "acc_stderr": 0.024639789097709443, "acc_norm": 0.8652849740932642, "acc_norm_stderr": 0.024639789097709443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6641025641025641, "acc_stderr": 0.02394672474156397, "acc_norm": 0.6641025641025641, "acc_norm_stderr": 0.02394672474156397 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32592592592592595, "acc_stderr": 0.028578348365473072, "acc_norm": 0.32592592592592595, "acc
