open-llm-leaderboard-old/details_uukuguy__speechless-coding-7b-16k-tora
收藏数据集概述
该数据集是在模型uukuguy/speechless-coding-7b-16k-tora的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。
- 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_uukuguy__speechless-coding-7b-16k-tora", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2023-12-09T15:50:40.789199的运行： python { "all": { "acc": 0.3931109615254218, "acc_stderr": 0.03416544865753528, "acc_norm": 0.3960835606892354, "acc_norm_stderr": 0.03491838760794626, "mc1": 0.29008567931456547, "mc1_stderr": 0.01588623687420952, "mc2": 0.4490702414317695, "mc2_stderr": 0.01493086789491207 }, "harness|arc:challenge|25": { "acc": 0.37457337883959047, "acc_stderr": 0.014144193471893446, "acc_norm": 0.4121160409556314, "acc_norm_stderr": 0.0143839153022254 }, "harness|hellaswag|10": { "acc": 0.4838677554272057, "acc_stderr": 0.004987183560792758, "acc_norm": 0.6444931288587931, "acc_norm_stderr": 0.004776883632722618 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.35555555555555557, "acc_stderr": 0.04135176749720386, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.32894736842105265, "acc_stderr": 0.03823428969926604, "acc_norm": 0.32894736842105265, "acc_norm_stderr": 0.03823428969926604 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.39622641509433965, "acc_stderr": 0.030102793781791194, "acc_norm": 0.39622641509433965, "acc_norm_stderr": 0.030102793781791194 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3472222222222222, "acc_stderr": 0.039812405437178615, "acc_norm": 0.3472222222222222, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.04461960433384739, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3352601156069364, "acc_stderr": 0.03599586301247077, "acc_norm": 0.3352601156069364, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.043364327079931785, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.043364327079931785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2936170212765957, "acc_stderr": 0.029771642712491227, "acc_norm": 0.2936170212765957, "acc_norm_stderr": 0.029771642712491227 }, "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": 0.3448275862068966, "acc_stderr": 0.03960933549451208, "acc_norm": 0.3448275862068966, "acc_norm_stderr": 0.03960933549451208 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2751322751322751, "acc_stderr": 0.023000086859068656, "acc_norm": 0.2751322751322751, "acc_norm_stderr": 0.023000086859068656 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3903225806451613, "acc_stderr": 0.027751256636969576, "acc_norm": 0.3903225806451613, "acc_norm_stderr": 0.027751256636969576 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3497536945812808, "acc_stderr": 0.03355400904969566, "acc_norm": 0.3497536945812808, "acc_norm_stderr": 0.03355400904969566 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.509090909090909, "acc_stderr": 0.03903698647748441, "acc_norm": 0.509090909090909, "acc_norm_stderr": 0.03903698647748441 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.47474747474747475, "acc_stderr": 0.03557806245087314, "acc_norm": 0.47474747474747475, "acc_norm_stderr": 0.03557806245087314 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.46113989637305697, "acc_stderr": 0.03597524411734578, "acc_norm": 0.46113989637305697, "acc_norm_stderr": 0.03597524411734578 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3717948717948718, "acc_stderr": 0.024503472557110946, "acc_norm": 0.3717948717948718, "acc_norm_stderr": 0.024503472557110946 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.027309140588230186, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.027309140588230186 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3949579831
