open-llm-leaderboard-old/details_ToastyPigeon__smolphin-test-stack-sorted
收藏数据集概述
数据集来源
该数据集是在模型 ToastyPigeon/smolphin-test-stack-sorted 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集由1次运行创建。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。
- 训练分割："train" 分割始终指向最新的结果。
- 结果配置：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_ToastyPigeon__smolphin-test-stack-sorted", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-03-29T21:12:59.929577的运行： python { "all": { "acc": 0.2693886134221748, "acc_stderr": 0.03126598314102477, "acc_norm": 0.2709400437138604, "acc_norm_stderr": 0.03203501471283497, "mc1": 0.2386780905752754, "mc1_stderr": 0.014922629695456418, "mc2": 0.3747768935887674, "mc2_stderr": 0.013984674618562865 }, "harness|arc:challenge|25": { "acc": 0.2901023890784983, "acc_stderr": 0.013261573677520764, "acc_norm": 0.32337883959044367, "acc_norm_stderr": 0.01366942163001214 }, "harness|hellaswag|10": { "acc": 0.43905596494722166, "acc_stderr": 0.004952576863315216, "acc_norm": 0.5907189802828122, "acc_norm_stderr": 0.0049069629803282985 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.25925925925925924, "acc_stderr": 0.03785714465066654, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.03785714465066654 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17105263157894737, "acc_stderr": 0.030643607071677084, "acc_norm": 0.17105263157894737, "acc_norm_stderr": 0.030643607071677084 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2188679245283019, "acc_stderr": 0.02544786382510861, "acc_norm": 0.2188679245283019, "acc_norm_stderr": 0.02544786382510861 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2361111111111111, "acc_stderr": 0.03551446610810826, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.21965317919075145, "acc_stderr": 0.031568093627031744, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.031568093627031744 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.042801058373643966, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.042801058373643966 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.24680851063829787, "acc_stderr": 0.0281854413012341, "acc_norm": 0.24680851063829787, "acc_norm_stderr": 0.0281854413012341 }, "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": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.022418042891113942, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113942 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.040061680838488774, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.040061680838488774 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2806451612903226, "acc_stderr": 0.025560604721022902, "acc_norm": 0.2806451612903226, "acc_norm_stderr": 0.025560604721022902 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.30049261083743845, "acc_stderr": 0.03225799476233485, "acc_norm": 0.30049261083743845, "acc_norm_stderr": 0.03225799476233485 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.035014387062967806, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.035014387062967806 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2777777777777778, "acc_stderr": 0.03191178226713545, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.03191178226713545 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.21243523316062177, "acc_stderr": 0.029519282616817258, "acc_norm": 0.21243523316062177, "acc_norm_stderr": 0.029519282616817258 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.30256410256410254, "acc_stderr": 0.02329088805377272, "acc_norm": 0.30256410256410254, "acc_norm_stderr": 0.02329088805377272 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24814814814814815, "acc_stderr": 0.0263357394040558, "acc_norm": 0.24814814814814815, "acc_norm_stderr": 0.0263357394040558 }, "harness|hendrycksTest-high_school_microeconomics|5": {
