open-llm-leaderboard-old/details_Eric111__Snorkel-Mistral-PairRM-DPO-openchat-3.5-0106-laser
收藏数据集概述
该数据集是在模型Eric111/Snorkel-Mistral-PairRM-DPO-openchat-3.5-0106-laser在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集组成
- 数据集由63个配置组成，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。
加载数据集示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Eric111__Snorkel-Mistral-PairRM-DPO-openchat-3.5-0106-laser", "harness_winogrande_5", split="train")
最新结果
以下是最新结果来自2024-03-03T10:27:01.631861：
python { "all": { "acc": 0.633768698931629, "acc_stderr": 0.032572341720681644, "acc_norm": 0.636731606444033, "acc_norm_stderr": 0.03322408077039106, "mc1": 0.44920440636474906, "mc1_stderr": 0.017412941986115305, "mc2": 0.6169050471107633, "mc2_stderr": 0.015386024878556101 }, "harness|arc:challenge|25": { "acc": 0.6126279863481229, "acc_stderr": 0.01423587248790987, "acc_norm": 0.6732081911262798, "acc_norm_stderr": 0.013706665975587331 }, "harness|hellaswag|10": { "acc": 0.6499701254730134, "acc_stderr": 0.004760041843651489, "acc_norm": 0.8511252738498307, "acc_norm_stderr": 0.003552374531305202 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595852, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595852 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7171052631578947, "acc_stderr": 0.03665349695640767, "acc_norm": 0.7171052631578947, "acc_norm_stderr": 0.03665349695640767 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700918, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6358381502890174, "acc_stderr": 0.03669072477416907, "acc_norm": 0.6358381502890174, "acc_norm_stderr": 0.03669072477416907 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.0446196043338474, "acc_norm": 0.73, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5446808510638298, "acc_stderr": 0.03255525359340355, "acc_norm": 0.5446808510638298, "acc_norm_stderr": 0.03255525359340355 }, "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": 0.6, "acc_stderr": 0.04082482904638628, "acc_norm": 0.6, "acc_norm_stderr": 0.04082482904638628 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4444444444444444, "acc_stderr": 0.025591857761382182, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.025591857761382182 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4523809523809524, "acc_stderr": 0.044518079590553275, "acc_norm": 0.4523809523809524, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6903225806451613, "acc_stderr": 0.026302774983517418, "acc_norm": 0.6903225806451613, "acc_norm_stderr": 0.026302774983517418 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.0351452856217501, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.0351452856217501 }, "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": 0.806060606060606, "acc_stderr": 0.030874145136562076, "acc_norm": 0.806060606060606, "acc_norm_stderr": 0.030874145136562076 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.029126522834586815, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758723, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758723 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6358974358974359, "acc_stderr": 0.024396672985094767, "acc_norm": 0.6358974358974359, "acc_norm_stderr": 0.024396672985094767 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34444444444444444, "acc_stderr": 0.028972648884844267, "acc_norm": 0.34444444444444444, "
