open-llm-leaderboard-old/details_vicgalle__NeuralBeagle-11B-truthy
收藏数据集概述
该数据集是在对模型 vicgalle/NeuralBeagle-11B-truthy 进行评估运行期间自动创建的。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，每次运行的详细信息可以在每个配置中找到，并以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。
数据集结构
数据集包含以下配置：
harness_arc_challenge_25harness_gsm8k_5harness_hellaswag_10harness_hendrycksTest_5
每个配置包含多个分片，包括特定时间戳的分片和最新的分片。
数据加载示例
以下是加载数据集详细信息的示例代码：
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_vicgalle__NeuralBeagle-11B-truthy", "harness_winogrande_5", split="train")
最新结果
以下是来自 2024-02-11T19:27:37.984436 运行的最新结果：
python { "all": { "acc": 0.6342999713787871, "acc_stderr": 0.03262677892134931, "acc_norm": 0.6370739871356, "acc_norm_stderr": 0.03328660511823099, "mc1": 0.620563035495716, "mc1_stderr": 0.016987039266142968, "mc2": 0.7592110983636813, "mc2_stderr": 0.014145118687247313 }, "harness|arc:challenge|25": { "acc": 0.7056313993174061, "acc_stderr": 0.013318528460539419, "acc_norm": 0.7363481228668942, "acc_norm_stderr": 0.01287592915129705 }, "harness|hellaswag|10": { "acc": 0.6960764787890859, "acc_stderr": 0.004590100050198815, "acc_norm": 0.8786098386775543, "acc_norm_stderr": 0.003259127057668171 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595853, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.660377358490566, "acc_stderr": 0.02914690474779833, "acc_norm": 0.660377358490566, "acc_norm_stderr": 0.02914690474779833 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.75, "acc_stderr": 0.03621034121889507, "acc_norm": 0.75, "acc_norm_stderr": 0.03621034121889507 }, "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": 0.49, "acc_stderr": 0.05024183937956913, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.036146654241808254, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.036146654241808254 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.045126085985421276, "acc_norm": 0.72, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5234042553191489, "acc_stderr": 0.03265019475033582, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3968253968253968, "acc_stderr": 0.025197101074246483, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.025197101074246483 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4365079365079365, "acc_stderr": 0.04435932892851466, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.04435932892851466 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.04793724854411019, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7741935483870968, "acc_stderr": 0.023785577884181015, "acc_norm": 0.7741935483870968, "acc_norm_stderr": 0.023785577884181015 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885417, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885417 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7777777777777778, "acc_stderr": 0.029620227874790486, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.029620227874790486 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.02423353229775873, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.02423353229775873 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.658974358974359, "acc_stderr": 0.02403548967633508, "acc_norm": 0.658974358974359, "acc_norm_stderr": 0.02403548967633508 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.028317533496066482, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.028317533496066482 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6302521008403361, "acc_stderr": 0.03135709599613591, "acc_norm": 0.6302521008403361
