open-llm-leaderboard-old/details_BFauber__lora_llama2-13b_10e5_r128_a64
收藏数据集概述
数据集摘要
该数据集是在对模型 BFauber/lora_llama2-13b_10e5_r128_a64 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_BFauber__lora_llama2-13b_10e5_r128_a64", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-02-10T01:12:24.322159 的运行： python { "all": { "acc": 0.5547782267581419, "acc_stderr": 0.03364758987723506, "acc_norm": 0.5605657594957815, "acc_norm_stderr": 0.034369652344960734, "mc1": 0.2582619339045288, "mc1_stderr": 0.0153218216884762, "mc2": 0.37196197837880757, "mc2_stderr": 0.013661684990590431 }, "harness|arc:challenge|25": { "acc": 0.5639931740614335, "acc_stderr": 0.014491225699230916, "acc_norm": 0.590443686006826, "acc_norm_stderr": 0.014370358632472434 }, "harness|hellaswag|10": { "acc": 0.6166102370045807, "acc_stderr": 0.004852182621274261, "acc_norm": 0.8227444732125074, "acc_norm_stderr": 0.00381104341202466 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5037037037037037, "acc_stderr": 0.04319223625811331, "acc_norm": 0.5037037037037037, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5394736842105263, "acc_stderr": 0.04056242252249033, "acc_norm": 0.5394736842105263, "acc_norm_stderr": 0.04056242252249033 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956913, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6415094339622641, "acc_stderr": 0.029514703583981765, "acc_norm": 0.6415094339622641, "acc_norm_stderr": 0.029514703583981765 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.625, "acc_stderr": 0.04048439222695598, "acc_norm": 0.625, "acc_norm_stderr": 0.04048439222695598 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5606936416184971, "acc_stderr": 0.037842719328874674, "acc_norm": 0.5606936416184971, "acc_norm_stderr": 0.037842719328874674 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.043364327079931785, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.043364327079931785 }, "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": 0.46382978723404256, "acc_stderr": 0.032600385118357715, "acc_norm": 0.46382978723404256, "acc_norm_stderr": 0.032600385118357715 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.04303684033537314, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537314 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.31216931216931215, "acc_stderr": 0.023865206836972606, "acc_norm": 0.31216931216931215, "acc_norm_stderr": 0.023865206836972606 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6709677419354839, "acc_stderr": 0.026729499068349958, "acc_norm": 0.6709677419354839, "acc_norm_stderr": 0.026729499068349958 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.03502544650845872, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6484848484848484, "acc_stderr": 0.037282069986826503, "acc_norm": 0.6484848484848484, "acc_norm_stderr": 0.037282069986826503 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6818181818181818, "acc_stderr": 0.0331847733384533, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.0331847733384533 }, "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": 0.5256410256410257, "acc_stderr": 0.02531764972644866, "acc_norm": 0.5256410256410257, "acc_norm_stderr": 0.02531764972644866 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028604, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0.028493465091028604 }, "harness|hendrycksTest-high_school_microeconomics|5": {
