open-llm-leaderboard-old/details_Technoculture__MT7Bi-alpha-dpo
收藏数据集概述
该数据集是在对模型 Technoculture/MT7Bi-alpha-dpo 进行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。每个运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。
- "train" 拆分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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Technoculture__MT7Bi-alpha-dpo", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-02T21:20:32.408861 运行的最新结果：
python { "all": { "acc": 0.5253447014480443, "acc_stderr": 0.034195124118131595, "acc_norm": 0.530565322003796, "acc_norm_stderr": 0.034921847920628496, "mc1": 0.2802937576499388, "mc1_stderr": 0.015723139524608767, "mc2": 0.43810210168491254, "mc2_stderr": 0.01497369498317419 }, "harness|arc:challenge|25": { "acc": 0.5085324232081911, "acc_stderr": 0.014609263165632186, "acc_norm": 0.5503412969283277, "acc_norm_stderr": 0.014537144444284738 }, "harness|hellaswag|10": { "acc": 0.570902210714997, "acc_stderr": 0.00493935814556132, "acc_norm": 0.7545309699263095, "acc_norm_stderr": 0.004294853999177863 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5111111111111111, "acc_stderr": 0.04318275491977976, "acc_norm": 0.5111111111111111, "acc_norm_stderr": 0.04318275491977976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4605263157894737, "acc_stderr": 0.04056242252249034, "acc_norm": 0.4605263157894737, "acc_norm_stderr": 0.04056242252249034 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6377358490566037, "acc_stderr": 0.029582245128384303, "acc_norm": 0.6377358490566037, "acc_norm_stderr": 0.029582245128384303 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5902777777777778, "acc_stderr": 0.04112490974670788, "acc_norm": 0.5902777777777778, "acc_norm_stderr": 0.04112490974670788 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4913294797687861, "acc_stderr": 0.03811890988940412, "acc_norm": 0.4913294797687861, "acc_norm_stderr": 0.03811890988940412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077615, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077615 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.44680851063829785, "acc_stderr": 0.032500536843658404, "acc_norm": 0.44680851063829785, "acc_norm_stderr": 0.032500536843658404 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3684210526315789, "acc_stderr": 0.04537815354939392, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939392 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.31746031746031744, "acc_stderr": 0.02397386199899208, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.02397386199899208 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0404061017820884, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0404061017820884 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5774193548387097, "acc_stderr": 0.02810096472427264, "acc_norm": 0.5774193548387097, "acc_norm_stderr": 0.02810096472427264 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4482758620689655, "acc_stderr": 0.034991131376767445, "acc_norm": 0.4482758620689655, "acc_norm_stderr": 0.034991131376767445 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7212121212121212, "acc_stderr": 0.03501438706296781, "acc_norm": 0.7212121212121212, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6616161616161617, "acc_stderr": 0.033711241426263014, "acc_norm": 0.6616161616161617, "acc_norm_stderr": 0.033711241426263014 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7202072538860104, "acc_stderr": 0.032396370467357036, "acc_norm": 0.7202072538860104, "acc_norm_stderr": 0.032396370467357036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4717948717948718, "acc_stderr": 0.025310639254933886, "acc_norm": 0.4717948717948718, "acc_norm_stderr": 0.025310639254933886 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340492, "acc_norm": 0.2851851851851852, "acc_norm_stderr":
