open-llm-leaderboard-old/details_BFauber__opt125m_10e5_lr2e-6
收藏数据集概述
数据集描述
该数据集是在评估模型 BFauber/opt125m_10e5_lr2e-6 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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" 分割始终指向最新结果。
- 额外的配置 "results" 存储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_BFauber__opt125m_10e5_lr2e-6", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-23T19:20:56.626640 运行的最新结果：
python { "all": { "acc": 0.2641892087262916, "acc_stderr": 0.03085510021617982, "acc_norm": 0.26543393876937765, "acc_norm_stderr": 0.03165431816632097, "mc1": 0.23011015911872704, "mc1_stderr": 0.014734557959807763, "mc2": 0.4286260263191467, "mc2_stderr": 0.014902273171640702 }, "harness|arc:challenge|25": { "acc": 0.20563139931740615, "acc_stderr": 0.011810745260742578, "acc_norm": 0.2295221843003413, "acc_norm_stderr": 0.012288926760890804 }, "harness|hellaswag|10": { "acc": 0.2907787293367855, "acc_stderr": 0.004531935391507023, "acc_norm": 0.3114917347142004, "acc_norm_stderr": 0.004621568125102044 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.22962962962962963, "acc_stderr": 0.03633384414073461, "acc_norm": 0.22962962962962963, "acc_norm_stderr": 0.03633384414073461 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.2631578947368421, "acc_stderr": 0.03583496176361062, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.03583496176361062 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2981132075471698, "acc_stderr": 0.028152837942493857, "acc_norm": 0.2981132075471698, "acc_norm_stderr": 0.028152837942493857 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2847222222222222, "acc_stderr": 0.03773809990686935, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.03773809990686935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3236994219653179, "acc_stderr": 0.0356760379963917, "acc_norm": 0.3236994219653179, "acc_norm_stderr": 0.0356760379963917 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105655, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105655 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.22127659574468084, "acc_stderr": 0.02713634960242406, "acc_norm": 0.22127659574468084, "acc_norm_stderr": 0.02713634960242406 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748142, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748142 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.034559302019248124, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.034559302019248124 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2619047619047619, "acc_stderr": 0.02264421261552522, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.02264421261552522 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.25396825396825395, "acc_stderr": 0.038932596106046755, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.038932596106046755 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904277, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.03161856335358609, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.03161856335358609 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.35353535353535354, "acc_stderr": 0.03406086723547153, "acc_norm": 0.35353535353535354, "acc_norm_stderr": 0.03406086723547153 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.36787564766839376, "acc_stderr": 0.03480175668466036, "acc_norm": 0.36787564766839376, "acc_norm_stderr": 0.03480175668466036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3641025641025641, "acc_stderr": 0.02439667298509477, "acc_norm": 0.3641025641025641, "acc_norm_stderr": 0.02439667298509477 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057873833706,
