open-llm-leaderboard-old/details_frankenmerger__delta-4B-scientific
收藏数据集概述
该数据集是在对模型 frankenmerger/delta-4B-scientific 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_frankenmerger__delta-4B-scientific", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-11T05:03:53.088812 运行 的最新结果：
python { "all": { "acc": 0.5763611715340329, "acc_stderr": 0.03364415142924134, "acc_norm": 0.5787195840594358, "acc_norm_stderr": 0.034335728498316835, "mc1": 0.3317013463892289, "mc1_stderr": 0.016482148810241473, "mc2": 0.48388057912772253, "mc2_stderr": 0.015377864755358938 }, "harness|arc:challenge|25": { "acc": 0.5665529010238908, "acc_stderr": 0.014481376224558902, "acc_norm": 0.5938566552901023, "acc_norm_stderr": 0.014351656690097862 }, "harness|hellaswag|10": { "acc": 0.5517825134435371, "acc_stderr": 0.004962949784236048, "acc_norm": 0.7409878510256921, "acc_norm_stderr": 0.0043719695428145605 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4962962962962963, "acc_stderr": 0.04319223625811331, "acc_norm": 0.4962962962962963, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5657894736842105, "acc_stderr": 0.040335656678483205, "acc_norm": 0.5657894736842105, "acc_norm_stderr": 0.040335656678483205 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.569811320754717, "acc_stderr": 0.030471445867183235, "acc_norm": 0.569811320754717, "acc_norm_stderr": 0.030471445867183235 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6319444444444444, "acc_stderr": 0.04032999053960718, "acc_norm": 0.6319444444444444, "acc_norm_stderr": 0.04032999053960718 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5953757225433526, "acc_stderr": 0.03742461193887249, "acc_norm": 0.5953757225433526, "acc_norm_stderr": 0.03742461193887249 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201943, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201943 }, "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": 0.4765957446808511, "acc_stderr": 0.03265019475033582, "acc_norm": 0.4765957446808511, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.35964912280701755, "acc_stderr": 0.04514496132873634, "acc_norm": 0.35964912280701755, "acc_norm_stderr": 0.04514496132873634 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.041665675771015785, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.041665675771015785 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4417989417989418, "acc_stderr": 0.025576257061253833, "acc_norm": 0.4417989417989418, "acc_norm_stderr": 0.025576257061253833 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.04390259265377563, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.04390259265377563 }, "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": 0.7193548387096774, "acc_stderr": 0.02556060472102289, "acc_norm": 0.7193548387096774, "acc_norm_stderr": 0.02556060472102289 }, "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": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6666666666666666, "acc_stderr": 0.0368105086916155, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.0368105086916155 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7373737373737373, "acc_stderr": 0.03135305009533086, "acc_norm": 0.7373737373737373, "acc_norm_stderr": 0.03135305009533086 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7927461139896373, "acc_stderr": 0.02925282329180363, "acc_norm": 0.7927461139896373, "acc_norm_stderr": 0.02925282329180363 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6128205128205129, "acc_stderr": 0.024697216930878948, "acc_norm": 0.6128205128205129, "acc_norm_stderr": 0.024697216930878948 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.028406533090608463, "acc_norm": 0.31851851851851853, "acc_norm_stderr": 0.0284065330906
