open-llm-leaderboard-old/details_one-man-army__una-neural-chat-v3-3-P1-OMA
收藏数据集概述
该数据集是在对模型 one-man-army/una-neural-chat-v3-3-P1-OMA 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" 配置存储所有运行结果的聚合，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_one-man-army__una-neural-chat-v3-3-P1-OMA", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-12T11:36:35.468608 运行的最新结果：
python { "all": { "acc": 0.636840960894971, "acc_stderr": 0.0325649293445393, "acc_norm": 0.6380848976326104, "acc_norm_stderr": 0.0332251069866789, "mc1": 0.4847001223990208, "mc1_stderr": 0.017495304473187902, "mc2": 0.6434691270555646, "mc2_stderr": 0.015146860071018828 }, "harness|arc:challenge|25": { "acc": 0.6390784982935154, "acc_stderr": 0.014034761386175456, "acc_norm": 0.6680887372013652, "acc_norm_stderr": 0.013760988200880543 }, "harness|hellaswag|10": { "acc": 0.6734714200358495, "acc_stderr": 0.004679847503411345, "acc_norm": 0.8591913961362279, "acc_norm_stderr": 0.0034711315448920418 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6513157894736842, "acc_stderr": 0.0387813988879761, "acc_norm": 0.6513157894736842, "acc_norm_stderr": 0.0387813988879761 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880267, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880267 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "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": 0.036563436533531585, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.036563436533531585 }, "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": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5574468085106383, "acc_stderr": 0.03246956919789958, "acc_norm": 0.5574468085106383, "acc_norm_stderr": 0.03246956919789958 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.43859649122807015, "acc_stderr": 0.04668000738510455, "acc_norm": 0.43859649122807015, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878152, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878152 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.02510742548113728, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.02510742548113728 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.044444444444444495, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.044444444444444495 }, "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": 0.7451612903225806, "acc_stderr": 0.024790118459332208, "acc_norm": 0.7451612903225806, "acc_norm_stderr": 0.024790118459332208 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4630541871921182, "acc_stderr": 0.035083705204426656, "acc_norm": 0.4630541871921182, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.033175059300091826, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.033175059300091826 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229872, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229872 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.023814477086593552, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.023814477086593552 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6333333333333333, "acc_stderr": 0.02443301646605246, "acc_norm": 0.6333333333333333, "acc_norm_stderr": 0.02443301646605246 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.0291166176060830
