open-llm-leaderboard-old/details_openaccess-ai-collective__grendel
收藏数据集概述
该数据集是在对模型 openaccess-ai-collective/grendel 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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 1 次运行中创建，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" 分割始终指向最新结果。
- 额外的 "results" 配置存储所有运行的聚合结果，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_openaccess-ai-collective__grendel_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-19T14:02:28.206445 运行的最新结果：
python { "all": { "acc": 0.5874222006151991, "acc_stderr": 0.03333785718767842, "acc_norm": 0.5935899001354114, "acc_norm_stderr": 0.034032890288055895, "mc1": 0.3659730722154223, "mc1_stderr": 0.016862941684088365, "mc2": 0.5267824071398005, "mc2_stderr": 0.015695608410958812, "em": 0.611996644295302, "em_stderr": 0.0049903604159338, "f1": 0.6469746224832212, "f1_stderr": 0.0047180171110879675 }, "harness|arc:challenge|25": { "acc": 0.5597269624573379, "acc_stderr": 0.01450676952480424, "acc_norm": 0.6049488054607508, "acc_norm_stderr": 0.014285898292938163 }, "harness|hellaswag|10": { "acc": 0.6158135829516033, "acc_stderr": 0.004854082479916909, "acc_norm": 0.7999402509460267, "acc_norm_stderr": 0.003992272261659567 }, "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": 0.5703703703703704, "acc_stderr": 0.04276349494376599, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6118421052631579, "acc_stderr": 0.03965842097512744, "acc_norm": 0.6118421052631579, "acc_norm_stderr": 0.03965842097512744 }, "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": 0.6339622641509434, "acc_stderr": 0.02964781353936525, "acc_norm": 0.6339622641509434, "acc_norm_stderr": 0.02964781353936525 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6875, "acc_stderr": 0.038760854559127644, "acc_norm": 0.6875, "acc_norm_stderr": 0.038760854559127644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6069364161849711, "acc_stderr": 0.037242495958177295, "acc_norm": 0.6069364161849711, "acc_norm_stderr": 0.037242495958177295 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "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": 0.502127659574468, "acc_stderr": 0.03268572658667492, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.046151869625837026, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.046151869625837026 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.041665675771015785, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.041665675771015785 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3994708994708995, "acc_stderr": 0.02522545028406788, "acc_norm": 0.3994708994708995, "acc_norm_stderr": 0.02522545028406788 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30952380952380953, "acc_stderr": 0.04134913018303316, "acc_norm": 0.30952380952380953, "acc_norm_stderr": 0.04134913018303316 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6903225806451613, "acc_stderr": 0.026302774983517414, "acc_norm": 0.6903225806451613, "acc_norm_stderr": 0.026302774983517414 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7575757575757576, "acc_stderr": 0.030532892233932026, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.030532892233932026 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8238341968911918, "acc_stderr": 0.027493504244548057, "acc_norm": 0.8238341968911918, "acc_norm_stderr": 0.027493504244548057 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5435897435897435, "acc_stderr": 0.0252544854247996, "acc_norm": 0.5435897435897435, "acc_norm_stderr": 0.0252544854247996 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29629629629
