open-llm-leaderboard-old/details_prhegde__merge-aanaphi-phi2-orage-3b
收藏数据集概述
该数据集是在模型 prhegde/merge-aanaphi-phi2-orage-3b 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。
- 数据集由 1 次运行创建，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。
- 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_prhegde__merge-aanaphi-phi2-orage-3b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-27T17:35:10.155769 运行的最新结果：
python { "all": { "acc": 0.5859937000423633, "acc_stderr": 0.033791826841491235, "acc_norm": 0.5863090954968909, "acc_norm_stderr": 0.0344878566811999, "mc1": 0.37454100367197063, "mc1_stderr": 0.01694353512840533, "mc2": 0.5347439699782387, "mc2_stderr": 0.015582112074867115 }, "harness|arc:challenge|25": { "acc": 0.606655290102389, "acc_stderr": 0.014275101465693028, "acc_norm": 0.6356655290102389, "acc_norm_stderr": 0.014063260279882419 }, "harness|hellaswag|10": { "acc": 0.5912168890659231, "acc_stderr": 0.004906043613013398, "acc_norm": 0.7742481577375024, "acc_norm_stderr": 0.004172220554799385 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.42962962962962964, "acc_stderr": 0.04276349494376599, "acc_norm": 0.42962962962962964, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5855263157894737, "acc_stderr": 0.04008973785779205, "acc_norm": 0.5855263157894737, "acc_norm_stderr": 0.04008973785779205 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5924528301886792, "acc_stderr": 0.030242233800854494, "acc_norm": 0.5924528301886792, "acc_norm_stderr": 0.030242233800854494 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6388888888888888, "acc_stderr": 0.04016660030451233, "acc_norm": 0.6388888888888888, "acc_norm_stderr": 0.04016660030451233 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.037038511930995215, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.037038511930995215 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.049135952012744975, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.049135952012744975 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4851063829787234, "acc_stderr": 0.032671518489247764, "acc_norm": 0.4851063829787234, "acc_norm_stderr": 0.032671518489247764 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3508771929824561, "acc_stderr": 0.044895393502706986, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.044895393502706986 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.503448275862069, "acc_stderr": 0.04166567577101579, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4312169312169312, "acc_stderr": 0.025506481698138208, "acc_norm": 0.4312169312169312, "acc_norm_stderr": 0.025506481698138208 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6806451612903226, "acc_stderr": 0.026522709674667765, "acc_norm": 0.6806451612903226, "acc_norm_stderr": 0.026522709674667765 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6909090909090909, "acc_stderr": 0.036085410115739666, "acc_norm": 0.6909090909090909, "acc_norm_stderr": 0.036085410115739666 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7424242424242424, "acc_stderr": 0.03115626951964684, "acc_norm": 0.7424242424242424, "acc_norm_stderr": 0.03115626951964684 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7979274611398963, "acc_stderr": 0.028979089794296732, "acc_norm": 0.7979274611398963, "acc_norm_stderr": 0.028979089794296732 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6076923076923076, "acc_stderr": 0.02475600038213095, "acc_norm": 0.6076923076923076, "acc_norm_stderr": 0.02475600038213095 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.028406533090608473, "acc_norm": 0.31
