open-llm-leaderboard-old/details_Qwen__Qwen1.5-0.5B
收藏数据集概述
数据集名称
Evaluation run of Qwen/Qwen1.5-0.5B
数据集描述
该数据集是在模型 Qwen/Qwen1.5-0.5B 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割找到，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。
最新结果
以下是 最新结果 的摘要：
python { "all": { "acc": 0.39069662187305154, "acc_stderr": 0.0341843478273196, "acc_norm": 0.39384390529564994, "acc_norm_stderr": 0.03494423149674395, "mc1": 0.2386780905752754, "mc1_stderr": 0.014922629695456421, "mc2": 0.3829926844374736, "mc2_stderr": 0.014100403601959433 }, "harness|arc:challenge|25": { "acc": 0.2832764505119454, "acc_stderr": 0.013167478735134575, "acc_norm": 0.3148464163822526, "acc_norm_stderr": 0.013572657703084948 }, "harness|hellaswag|10": { "acc": 0.38259310894244175, "acc_stderr": 0.004850268986903351, "acc_norm": 0.4905397331208923, "acc_norm_stderr": 0.004988888194063273 }, "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": 0.362962962962963, "acc_stderr": 0.04153948404742398, "acc_norm": 0.362962962962963, "acc_norm_stderr": 0.04153948404742398 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4144736842105263, "acc_stderr": 0.04008973785779205, "acc_norm": 0.4144736842105263, "acc_norm_stderr": 0.04008973785779205 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.36981132075471695, "acc_stderr": 0.029711421880107926, "acc_norm": 0.36981132075471695, "acc_norm_stderr": 0.029711421880107926 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.375, "acc_stderr": 0.04048439222695598, "acc_norm": 0.375, "acc_norm_stderr": 0.04048439222695598 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3468208092485549, "acc_stderr": 0.036291466701596636, "acc_norm": 0.3468208092485549, "acc_norm_stderr": 0.036291466701596636 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171453, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171453 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3574468085106383, "acc_stderr": 0.03132941789476425, "acc_norm": 0.3574468085106383, "acc_norm_stderr": 0.03132941789476425 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.04227054451232199, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.04227054451232199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.42758620689655175, "acc_stderr": 0.041227371113703316, "acc_norm": 0.42758620689655175, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.28835978835978837, "acc_stderr": 0.0233306540545359, "acc_norm": 0.28835978835978837, "acc_norm_stderr": 0.0233306540545359 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.29365079365079366, "acc_stderr": 0.04073524322147126, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.04073524322147126 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4096774193548387, "acc_stderr": 0.02797605491534736, "acc_norm": 0.4096774193548387, "acc_norm_stderr": 0.02797605491534736 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0317852971064275, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0317852971064275 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4727272727272727, "acc_stderr": 0.03898531605579419, "acc_norm": 0.4727272727272727, "acc_norm_stderr": 0.03898531605579419 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.45454545454545453, "acc_stderr": 0.03547601494006937, "acc_norm": 0.45454545454545453, "acc_norm_stderr": 0.03547601494006937 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.46632124352331605, "acc_stderr": 0.036002440698671784, "acc_norm": 0.46632124352331605, "acc_norm_stderr": 0.036002440698671784 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.358974358974359, "acc_stderr": 0.024321738484602354, "acc_norm": 0.358974358974359, "acc_norm_stderr": 0.024321738484602354 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.02773896963217609, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.02773896963217609 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3697478991596639, "acc_stderr": 0.031357095996135904
