open-llm-leaderboard-old/details_lloorree__kssht-dahj-70b
收藏数据集概述
该数据集是在模型 lloorree/kssht-dahj-70b 的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 61 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。
- 一个额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示聚合指标在 Open LLM Leaderboard 上。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_lloorree__kssht-dahj-70b", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-09-18T23:50:58.093131 运行的最新结果：
python { "all": { "acc": 0.7033014017574061, "acc_stderr": 0.03081446175839962, "acc_norm": 0.7072547203046122, "acc_norm_stderr": 0.03078306684205309, "mc1": 0.42962056303549573, "mc1_stderr": 0.017329234580409098, "mc2": 0.5891645864509103, "mc2_stderr": 0.015115214729699759 }, "harness|arc:challenge|25": { "acc": 0.6612627986348123, "acc_stderr": 0.013830568927974332, "acc_norm": 0.7081911262798635, "acc_norm_stderr": 0.013284525292403515 }, "harness|hellaswag|10": { "acc": 0.6867157936666003, "acc_stderr": 0.0046288092584835265, "acc_norm": 0.8730332603067118, "acc_norm_stderr": 0.003322552829608905 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6592592592592592, "acc_stderr": 0.04094376269996793, "acc_norm": 0.6592592592592592, "acc_norm_stderr": 0.04094376269996793 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8289473684210527, "acc_stderr": 0.030643607071677098, "acc_norm": 0.8289473684210527, "acc_norm_stderr": 0.030643607071677098 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7283018867924528, "acc_stderr": 0.027377706624670713, "acc_norm": 0.7283018867924528, "acc_norm_stderr": 0.027377706624670713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.032166008088022675, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.032166008088022675 }, "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": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "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": 0.7021276595744681, "acc_stderr": 0.029896145682095455, "acc_norm": 0.7021276595744681, "acc_norm_stderr": 0.029896145682095455 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.0470070803355104, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.0470070803355104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6413793103448275, "acc_stderr": 0.03996629574876719, "acc_norm": 0.6413793103448275, "acc_norm_stderr": 0.03996629574876719 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4470899470899471, "acc_stderr": 0.025606723995777025, "acc_norm": 0.4470899470899471, "acc_norm_stderr": 0.025606723995777025 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5079365079365079, "acc_stderr": 0.044715725362943486, "acc_norm": 0.5079365079365079, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8193548387096774, "acc_stderr": 0.021886178567172534, "acc_norm": 0.8193548387096774, "acc_norm_stderr": 0.021886178567172534 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.541871921182266, "acc_stderr": 0.03505630140785741, "acc_norm": 0.541871921182266, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.02845038880528437, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.02845038880528437 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8636363636363636, "acc_stderr": 0.024450155973189835, "acc_norm": 0.8636363636363636, "acc_norm_stderr": 0.024450155973189835 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9326424870466321, "acc_stderr": 0.018088393839078912, "acc_norm": 0.9326424870466321, "acc_norm_stderr": 0.018088393839078912 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7282051282051282, "acc_stderr": 0.02255655101013236, "acc_norm": 0.7282051282051282, "acc_norm_stderr": 0.02255655101013236 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251972, "acc_norm": 0.35925925925925
