open-llm-leaderboard-old/details_Sao10K__14B-Glacier-Stack
收藏数据集概述
数据集摘要
该数据集是在对模型 Sao10K/14B-Glacier-Stack 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_Sao10K__14B-Glacier-Stack", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-07T12:10:05.722795 运行的最新结果：
python { "all": { "acc": 0.6686145157496808, "acc_stderr": 0.03159509998777849, "acc_norm": 0.671765635485992, "acc_norm_stderr": 0.032228278305947135, "mc1": 0.5030599755201959, "mc1_stderr": 0.017503173260960625, "mc2": 0.6537435659083609, "mc2_stderr": 0.015546800478831346 }, "harness|arc:challenge|25": { "acc": 0.6834470989761092, "acc_stderr": 0.01359243151906808, "acc_norm": 0.7167235494880546, "acc_norm_stderr": 0.013167478735134575 }, "harness|hellaswag|10": { "acc": 0.7013543118900617, "acc_stderr": 0.0045672877757005625, "acc_norm": 0.8834893447520414, "acc_norm_stderr": 0.003201805872737069 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7631578947368421, "acc_stderr": 0.034597776068105365, "acc_norm": 0.7631578947368421, "acc_norm_stderr": 0.034597776068105365 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6867924528301886, "acc_stderr": 0.028544793319055326, "acc_norm": 0.6867924528301886, "acc_norm_stderr": 0.028544793319055326 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.0365634365335316, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.0365634365335316 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.049512182523962625, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.049512182523962625 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.625531914893617, "acc_stderr": 0.031639106653672915, "acc_norm": 0.625531914893617, "acc_norm_stderr": 0.031639106653672915 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.04697085136647863, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.04697085136647863 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370334, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370334 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5105820105820106, "acc_stderr": 0.02574554227604548, "acc_norm": 0.5105820105820106, "acc_norm_stderr": 0.02574554227604548 }, "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": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8258064516129032, "acc_stderr": 0.021576248184514587, "acc_norm": 0.8258064516129032, "acc_norm_stderr": 0.021576248184514587 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.035145285621750094, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.035145285621750094 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8242424242424242, "acc_stderr": 0.02972094300622445, "acc_norm": 0.8242424242424242, "acc_norm_stderr": 0.02972094300622445 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8585858585858586, "acc_stderr": 0.024825909793343336, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.024825909793343336 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.917098445595855, "acc_stderr": 0.01989934131572178, "acc_norm": 0.917098445595855, "acc_norm_stderr": 0.01989934131572178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6974358974358974, "acc_stderr": 0.02329088805377274, "acc_norm": 0.6974358974358974, "acc_norm_stderr": 0.02329088805377274 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.029723278961476664, "acc_norm": 0.38888888888888
