open-llm-leaderboard-old/details_CHIH-HUNG__llama-2-7b-dolphin_10w-test
收藏数据集概述
数据集简介
该数据集是在评估模型CHIH-HUNG/llama-2-7b-dolphin_10w-test在Open LLM Leaderboard上的运行过程中自动创建的。
数据集结构
- 数据集包含61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_CHIH-HUNG__llama-2-7b-dolphin_10w-test", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是2023-08-30T02:39:30.336527运行的最新结果：
python { "all": { "acc": 0.441355572237513, "acc_stderr": 0.035230208768426426, "acc_norm": 0.44554035341923276, "acc_norm_stderr": 0.03522008237001183, "mc1": 0.2692778457772338, "mc1_stderr": 0.01552856663708728, "mc2": 0.42075433716694316, "mc2_stderr": 0.014621475505823845 }, "harness|arc:challenge|25": { "acc": 0.4684300341296928, "acc_stderr": 0.014582236460866977, "acc_norm": 0.5170648464163823, "acc_norm_stderr": 0.014602878388536597 }, "harness|hellaswag|10": { "acc": 0.5467038438558056, "acc_stderr": 0.004967965810199991, "acc_norm": 0.7449711212905795, "acc_norm_stderr": 0.004349866376068983 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4962962962962963, "acc_stderr": 0.04319223625811331, "acc_norm": 0.4962962962962963, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.42105263157894735, "acc_stderr": 0.040179012759817494, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.040179012759817494 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.49056603773584906, "acc_stderr": 0.0307673947078081, "acc_norm": 0.49056603773584906, "acc_norm_stderr": 0.0307673947078081 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4236111111111111, "acc_stderr": 0.04132125019723369, "acc_norm": 0.4236111111111111, "acc_norm_stderr": 0.04132125019723369 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.42196531791907516, "acc_stderr": 0.0376574669386515, "acc_norm": 0.42196531791907516, "acc_norm_stderr": 0.0376574669386515 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03708284662416542, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03708284662416542 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4085106382978723, "acc_stderr": 0.03213418026701576, "acc_norm": 0.4085106382978723, "acc_norm_stderr": 0.03213418026701576 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4206896551724138, "acc_stderr": 0.0411391498118926, "acc_norm": 0.4206896551724138, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2698412698412698, "acc_stderr": 0.02286083830923207, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.02286083830923207 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.03932537680392871, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.03932537680392871 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.45483870967741935, "acc_stderr": 0.028327743091561067, "acc_norm": 0.45483870967741935, "acc_norm_stderr": 0.028327743091561067 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3103448275862069, "acc_stderr": 0.03255086769970103, "acc_norm": 0.3103448275862069, "acc_norm_stderr": 0.03255086769970103 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5575757575757576, "acc_stderr": 0.03878372113711274, "acc_norm": 0.5575757575757576, "acc_norm_stderr": 0.03878372113711274 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5404040404040404, "acc_stderr": 0.035507024651313425, "acc_norm": 0.5404040404040404, "acc_norm_stderr": 0.035507024651313425 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5958549222797928, "acc_stderr": 0.0354150857888402, "acc_norm": 0.5958549222797928, "acc_norm_stderr": 0.0354150857888402 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4153846153846154, "acc_stderr": 0.024985354923102325, "acc_norm": 0.4153846153846154, "acc_norm_stderr": 0.024985354923102325 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.026962424325073828,
