open-llm-leaderboard-old/details_ResplendentAI__Asherah_7B
收藏数据集概述
该数据集是在对模型 ResplendentAI/Asherah_7B 进行评估运行期间自动创建的，评估结果展示在 Open LLM Leaderboard 上。
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" 配置存储所有运行的聚合结果，用于计算和显示在 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_ResplendentAI__Asherah_7B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-22T02:44:56.997740 运行的最新结果：
python { "all": { "acc": 0.6428050024791003, "acc_stderr": 0.03251525193563222, "acc_norm": 0.6437054038596077, "acc_norm_stderr": 0.03317605264661184, "mc1": 0.401468788249694, "mc1_stderr": 0.017160273901693654, "mc2": 0.5806505512555615, "mc2_stderr": 0.015421807086988029 }, "harness|arc:challenge|25": { "acc": 0.6467576791808873, "acc_stderr": 0.013967822714840055, "acc_norm": 0.681740614334471, "acc_norm_stderr": 0.013611993916971451 }, "harness|hellaswag|10": { "acc": 0.6715793666600279, "acc_stderr": 0.004686789042445373, "acc_norm": 0.8604859589723163, "acc_norm_stderr": 0.003457740283785488 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.04153948404742398, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.04153948404742398 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6776315789473685, "acc_stderr": 0.03803510248351585, "acc_norm": 0.6776315789473685, "acc_norm_stderr": 0.03803510248351585 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.04960449637488583, "acc_norm": 0.58, "acc_norm_stderr": 0.04960449637488583 }, "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": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "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": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "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": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5829787234042553, "acc_stderr": 0.032232762667117124, "acc_norm": 0.5829787234042553, "acc_norm_stderr": 0.032232762667117124 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.04685473041907789, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.04685473041907789 }, "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": 0.42857142857142855, "acc_stderr": 0.02548718714785938, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.02548718714785938 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677171, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677171 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7741935483870968, "acc_stderr": 0.023785577884181012, "acc_norm": 0.7741935483870968, "acc_norm_stderr": 0.023785577884181012 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.0351760354036101, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.0351760354036101 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7676767676767676, "acc_stderr": 0.030088629490217487, "acc_norm": 0.7676767676767676, "acc_norm_stderr": 0.030088629490217487 }, "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": 0.6743589743589744, "acc_stderr": 0.02375966576741229, "acc_norm": 0.6743589743589744, "acc_norm_stderr": 0.02375966576741229 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34814814814814815, "acc_stderr": 0.029045600290616248, "acc_norm": 0.34814814814814815, "acc_norm_stderr": 0
