open-llm-leaderboard/details_raincandy-u__Quark-464M-v0.2
收藏数据集概述
该数据集是在对模型 raincandy-u/Quark-464M-v0.2 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 63 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。
- 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 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_raincandy-u__Quark-464M-v0.2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-09T08:39:02.304022 运行的最新结果：
python { "all": { "acc": 0.3125584120923437, "acc_stderr": 0.032810288522301126, "acc_norm": 0.31507177497570615, "acc_norm_stderr": 0.03360115960632853, "mc1": 0.2827417380660955, "mc1_stderr": 0.015764770836777308, "mc2": 0.4388966108457062, "mc2_stderr": 0.015289903733660282 }, "harness|arc:challenge|25": { "acc": 0.26621160409556316, "acc_stderr": 0.012915774781523202, "acc_norm": 0.3046075085324232, "acc_norm_stderr": 0.013449522109932487 }, "harness|hellaswag|10": { "acc": 0.36367257518422624, "acc_stderr": 0.004800728138792369, "acc_norm": 0.44961163114917346, "acc_norm_stderr": 0.004964378762425237 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.35555555555555557, "acc_stderr": 0.04135176749720385, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.26973684210526316, "acc_stderr": 0.03611780560284898, "acc_norm": 0.26973684210526316, "acc_norm_stderr": 0.03611780560284898 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3018867924528302, "acc_stderr": 0.028254200344438665, "acc_norm": 0.3018867924528302, "acc_norm_stderr": 0.028254200344438665 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2658959537572254, "acc_stderr": 0.033687629322594295, "acc_norm": 0.2658959537572254, "acc_norm_stderr": 0.033687629322594295 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179962, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179962 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.28936170212765955, "acc_stderr": 0.029644006577009618, "acc_norm": 0.28936170212765955, "acc_norm_stderr": 0.029644006577009618 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436695, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436695 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3310344827586207, "acc_stderr": 0.03921545312467122, "acc_norm": 0.3310344827586207, "acc_norm_stderr": 0.03921545312467122 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.022019080012217897, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.022019080012217897 }, "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": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3419354838709677, "acc_stderr": 0.026985289576552735, "acc_norm": 0.3419354838709677, "acc_norm_stderr": 0.026985289576552735 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3054187192118227, "acc_stderr": 0.03240661565868408, "acc_norm": 0.3054187192118227, "acc_norm_stderr": 0.03240661565868408 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3151515151515151, "acc_stderr": 0.0362773057502241, "acc_norm": 0.3151515151515151, "acc_norm_stderr": 0.0362773057502241 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3181818181818182, "acc_stderr": 0.033184773338453315, "acc_norm": 0.3181818181818182, "acc_norm_stderr": 0.033184773338453315 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.32124352331606215, "acc_stderr": 0.033699508685490674, "acc_norm": 0.32124352331606215, "acc_norm_stderr": 0.033699508685490674 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2717948717948718, "acc_stderr": 0.022556551010132368, "acc_norm": 0.2717948717948718, "acc_norm_stderr": 0.022556551010132368 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23703703703703705, "acc_stderr": 0.025928876132
