open-llm-leaderboard-old/details_Qwen__Qwen1.5-14B
收藏数据集概述
数据集名称
Evaluation run of Qwen/Qwen1.5-14B
数据集描述
该数据集是在模型 Qwen/Qwen1.5-14B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
数据集由 63 个配置组成，每个配置对应一个评估任务。数据集从 1 次运行中创建，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了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_Qwen__Qwen1.5-14B", "harness_winogrande_5", split="train")
最新结果
这些是最新结果，来自 2024-02-29T19:03:16.730634 的运行： python { "all": { "acc": 0.6898580043254386, "acc_stderr": 0.031398020923176104, "acc_norm": 0.6934211051671241, "acc_norm_stderr": 0.0320155860635579, "mc1": 0.3574051407588739, "mc1_stderr": 0.016776599676729398, "mc2": 0.5206092394796343, "mc2_stderr": 0.014914799486183409 }, "harness|arc:challenge|25": { "acc": 0.5221843003412969, "acc_stderr": 0.014597001927076133, "acc_norm": 0.5656996587030717, "acc_norm_stderr": 0.01448470304885736 }, "harness|hellaswag|10": { "acc": 0.6127265484963155, "acc_stderr": 0.004861314613286845, "acc_norm": 0.810794662417845, "acc_norm_stderr": 0.0039087117912434905 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.041716541613545426, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.041716541613545426 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7368421052631579, "acc_stderr": 0.03583496176361073, "acc_norm": 0.7368421052631579, "acc_norm_stderr": 0.03583496176361073 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909284, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7433962264150943, "acc_stderr": 0.026880647889051975, "acc_norm": 0.7433962264150943, "acc_norm_stderr": 0.026880647889051975 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7638888888888888, "acc_stderr": 0.03551446610810826, "acc_norm": 0.7638888888888888, "acc_norm_stderr": 0.03551446610810826 }, "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": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6936416184971098, "acc_stderr": 0.03514942551267439, "acc_norm": 0.6936416184971098, "acc_norm_stderr": 0.03514942551267439 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.49019607843137253, "acc_stderr": 0.04974229460422817, "acc_norm": 0.49019607843137253, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036846, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7063829787234043, "acc_stderr": 0.029771642712491227, "acc_norm": 0.7063829787234043, "acc_norm_stderr": 0.029771642712491227 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5526315789473685, "acc_stderr": 0.04677473004491199, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7310344827586207, "acc_stderr": 0.036951833116502325, "acc_norm": 0.7310344827586207, "acc_norm_stderr": 0.036951833116502325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.58994708994709, "acc_stderr": 0.02533120243894442, "acc_norm": 0.58994708994709, "acc_norm_stderr": 0.02533120243894442 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5555555555555556, "acc_stderr": 0.04444444444444449, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8451612903225807, "acc_stderr": 0.020579287326583227, "acc_norm": 0.8451612903225807, "acc_norm_stderr": 0.020579287326583227 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5960591133004927, "acc_stderr": 0.03452453903822031, "acc_norm": 0.5960591133004927, "acc_norm_stderr": 0.03452453903822031 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.028450388805284332, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.028450388805284332 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8686868686868687, "acc_stderr": 0.024063156416822516, "acc_norm": 0.8686868686868687, "acc_norm_stderr": 0.024063156416822516 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.02150024957603346, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.02150024957603346 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.735897435897436, "acc_stderr": 0.022352193737453264, "acc_norm": 0.735897435897436, "acc_norm_stderr": 0.022352193737453264 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.43333333333333335, "acc_stderr": 0.030213340289237927, "acc_norm": 0.43333333333333335, "acc_norm_stderr": 0.030213340289237927 }, "harness|hendrycksTest-high_school_microeconomics|5": {
