open-llm-leaderboard-old/details_G-reen__EXPERIMENT-SFT-m7b2-3-merged
收藏数据集概述
数据集摘要
该数据集是在模型G-reen/EXPERIMENT-SFT-m7b2-3-merged在Open LLM Leaderboard上的评估运行期间自动创建的。
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_G-reen__EXPERIMENT-SFT-m7b2-3-merged", "harness_winogrande_5", split="train")
最新结果
以下是2024-04-15T18:10:14.725613运行的最新结果：
python { "all": { "acc": 0.6200576482672442, "acc_stderr": 0.032801956185609916, "acc_norm": 0.6259658189852138, "acc_norm_stderr": 0.03347561676613824, "mc1": 0.2692778457772338, "mc1_stderr": 0.015528566637087288, "mc2": 0.40037750545294976, "mc2_stderr": 0.014055526424611808 }, "harness|arc:challenge|25": { "acc": 0.5622866894197952, "acc_stderr": 0.014497573881108285, "acc_norm": 0.5955631399317406, "acc_norm_stderr": 0.014342036483436177 }, "harness|hellaswag|10": { "acc": 0.6185022903804023, "acc_stderr": 0.0048476152164734524, "acc_norm": 0.8239394542919737, "acc_norm_stderr": 0.003800932770597754 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880263, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880263 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7152777777777778, "acc_stderr": 0.037738099906869334, "acc_norm": 0.7152777777777778, "acc_norm_stderr": 0.037738099906869334 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956913, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082636, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5404255319148936, "acc_stderr": 0.03257901482099835, "acc_norm": 0.5404255319148936, "acc_norm_stderr": 0.03257901482099835 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3994708994708995, "acc_stderr": 0.02522545028406788, "acc_norm": 0.3994708994708995, "acc_norm_stderr": 0.02522545028406788 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7354838709677419, "acc_stderr": 0.02509189237885928, "acc_norm": 0.7354838709677419, "acc_norm_stderr": 0.02509189237885928 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175007, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175007 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124495, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124495 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.844559585492228, "acc_stderr": 0.02614848346915331, "acc_norm": 0.844559585492228, "acc_norm_stderr": 0.02614848346915331 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5948717948717949, "acc_stderr": 0.02489047176993815, "acc_norm": 0.5948717948717949, "acc_norm_stderr": 0.02489047176993815 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524572, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661
