open-llm-leaderboard-old/details_shitshow123__mistral7b_sft_dpo
收藏数据集概述
数据集摘要
该数据集是在对模型 shitshow123/mistral7b_sft_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 "results" 配置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_shitshow123__mistral7b_sft_dpo", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-01-11T07:28:54.566656 的运行： python { "all": { "acc": 0.24115205900155798, "acc_stderr": 0.030240327476101683, "acc_norm": 0.24138243110295876, "acc_norm_stderr": 0.031046885606606598, "mc1": 0.2350061199510404, "mc1_stderr": 0.014843061507731608, "mc2": 0.4967512296032591, "mc2_stderr": 0.016399783558395026 }, "harness|arc:challenge|25": { "acc": 0.21075085324232082, "acc_stderr": 0.011918271754852184, "acc_norm": 0.27559726962457337, "acc_norm_stderr": 0.013057169655761838 }, "harness|hellaswag|10": { "acc": 0.25692093208524197, "acc_stderr": 0.004360424536145123, "acc_norm": 0.255327623979287, "acc_norm_stderr": 0.004351540603988566 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.31851851851851853, "acc_stderr": 0.040247784019771096, "acc_norm": 0.31851851851851853, "acc_norm_stderr": 0.040247784019771096 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.26973684210526316, "acc_stderr": 0.03611780560284898, "acc_norm": 0.26973684210526316, "acc_norm_stderr": 0.03611780560284898 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22641509433962265, "acc_stderr": 0.025757559893106748, "acc_norm": 0.22641509433962265, "acc_norm_stderr": 0.025757559893106748 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2023121387283237, "acc_stderr": 0.030631145539198816, "acc_norm": 0.2023121387283237, "acc_norm_stderr": 0.030631145539198816 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179962, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179962 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.20425531914893616, "acc_stderr": 0.026355158413349424, "acc_norm": 0.20425531914893616, "acc_norm_stderr": 0.026355158413349424 }, "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": 0.30344827586206896, "acc_stderr": 0.038312260488503336, "acc_norm": 0.30344827586206896, "acc_norm_stderr": 0.038312260488503336 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2275132275132275, "acc_stderr": 0.021591269407823792, "acc_norm": 0.2275132275132275, "acc_norm_stderr": 0.021591269407823792 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.24603174603174602, "acc_stderr": 0.03852273364924318, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.03852273364924318 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2, "acc_stderr": 0.022755204959542936, "acc_norm": 0.2, "acc_norm_stderr": 0.022755204959542936 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2561576354679803, "acc_stderr": 0.030712730070982592, "acc_norm": 0.2561576354679803, "acc_norm_stderr": 0.030712730070982592 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21212121212121213, "acc_stderr": 0.031922715695483, "acc_norm": 0.21212121212121213, "acc_norm_stderr": 0.031922715695483 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2222222222222222, "acc_stderr": 0.02962022787479048, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.02962022787479048 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.26424870466321243, "acc_stderr": 0.03182155050916648, "acc_norm": 0.26424870466321243, "acc_norm_stderr": 0.03182155050916648 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2282051282051282, "acc_stderr": 0.02127839386358628, "acc_norm": 0.2282051282051282, "acc_norm_stderr": 0.02127839386358628 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.21851851851851853, "acc_stderr": 0.02519575225182379, "acc_norm": 0.21851851851851853, "acc_norm_stderr": 0.02519575225182379 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.19747899159663865, "acc_stderr
