open-llm-leaderboard-old/details_mwitiderrick__open_llama_3b_glaive_code_v0.1
收藏数据集概述
数据集摘要
该数据集是在评估模型 mwitiderrick/open_llama_3b_glaive_code_v0.1 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含63个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63个配置
- 数据来源：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。
- 最新结果："train" 分割总是指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，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_mwitiderrick__open_llama_3b_glaive_code_v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-23T17:05:08.212858 运行的最新结果：
python { "all": { "acc": 0.2843747535406573, "acc_stderr": 0.031689110133124844, "acc_norm": 0.28633888958645765, "acc_norm_stderr": 0.03246963675970039, "mc1": 0.23623011015911874, "mc1_stderr": 0.014869755015871114, "mc2": 0.3585983664640556, "mc2_stderr": 0.013742745779138914 }, "harness|arc:challenge|25": { "acc": 0.3703071672354949, "acc_stderr": 0.01411129875167495, "acc_norm": 0.4069965870307167, "acc_norm_stderr": 0.014356399418009131 }, "harness|hellaswag|10": { "acc": 0.4971121290579566, "acc_stderr": 0.004989698183207831, "acc_norm": 0.6744672376020713, "acc_norm_stderr": 0.004676159299105414 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2814814814814815, "acc_stderr": 0.03885004245800254, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.03885004245800254 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21052631578947367, "acc_stderr": 0.03317672787533157, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.03317672787533157 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.29056603773584905, "acc_stderr": 0.027943219989337156, "acc_norm": 0.29056603773584905, "acc_norm_stderr": 0.027943219989337156 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3236994219653179, "acc_stderr": 0.035676037996391685, "acc_norm": 0.3236994219653179, "acc_norm_stderr": 0.035676037996391685 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617749, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617749 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3148936170212766, "acc_stderr": 0.030363582197238167, "acc_norm": 0.3148936170212766, "acc_norm_stderr": 0.030363582197238167 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.044346007015849245, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.044346007015849245 }, "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": 0.022418042891113932, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113932 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.20634920634920634, "acc_stderr": 0.03619604524124252, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.03619604524124252 }, "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": 0.2645161290322581, "acc_stderr": 0.02509189237885928, "acc_norm": 0.2645161290322581, "acc_norm_stderr": 0.02509189237885928 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.30049261083743845, "acc_stderr": 0.03225799476233484, "acc_norm": 0.30049261083743845, "acc_norm_stderr": 0.03225799476233484 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.15, "acc_stderr": 0.035887028128263714, "acc_norm": 0.15, "acc_norm_stderr": 0.035887028128263714 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.26666666666666666, "acc_stderr": 0.034531318018854146, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.034531318018854146 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.31313131313131315, "acc_stderr": 0.03304205087813653, "acc_norm": 0.31313131313131315, "acc_norm_stderr": 0.03304205087813653 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.27461139896373055, "acc_stderr": 0.03221024508041154, "acc_norm": 0.27461139896373055, "acc_norm_stderr": 0.03221024508041154 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.32564102564102565, "acc_stderr": 0.02375966576741229, "acc_norm": 0.32564102564102565, "acc_norm_stderr": 0.02375966576741229 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2518518518518518, "acc_stderr": 0.026466
