open-llm-leaderboard-old/details_grayhacker91__gemma-7b-open-platypus-commercial
收藏数据集概述
该数据集是在模型grayhacker91/gemma-7b-open-platypus-commercial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，每个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。
- 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_grayhacker91__gemma-7b-open-platypus-commercial", "harness_winogrande_5", split="train")
最新结果
以下是最新结果来自2024-03-07T11:17:44.139094：
python { "all": { "acc": 0.589653948612351, "acc_stderr": 0.033003448848161414, "acc_norm": 0.5939310007920258, "acc_norm_stderr": 0.03367613885880847, "mc1": 0.3671970624235006, "mc1_stderr": 0.01687480500145318, "mc2": 0.5353748688901258, "mc2_stderr": 0.015087933955827179 }, "harness|arc:challenge|25": { "acc": 0.5656996587030717, "acc_stderr": 0.014484703048857359, "acc_norm": 0.6279863481228669, "acc_norm_stderr": 0.014124597881844461 }, "harness|hellaswag|10": { "acc": 0.6123282214698267, "acc_stderr": 0.004862232790041568, "acc_norm": 0.8164708225453097, "acc_norm_stderr": 0.0038630862999845896 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5111111111111111, "acc_stderr": 0.04318275491977976, "acc_norm": 0.5111111111111111, "acc_norm_stderr": 0.04318275491977976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5789473684210527, "acc_stderr": 0.04017901275981749, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.04017901275981749 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5849056603773585, "acc_stderr": 0.030325945789286105, "acc_norm": 0.5849056603773585, "acc_norm_stderr": 0.030325945789286105 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7152777777777778, "acc_stderr": 0.037738099906869334, "acc_norm": 0.7152777777777778, "acc_norm_stderr": 0.037738099906869334 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.049888765156985884, "acc_norm": 0.44, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.04793724854411019, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5722543352601156, "acc_stderr": 0.03772446857518026, "acc_norm": 0.5722543352601156, "acc_norm_stderr": 0.03772446857518026 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077615, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077615 }, "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": 0.502127659574468, "acc_stderr": 0.03268572658667492, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.39473684210526316, "acc_stderr": 0.045981880578165414, "acc_norm": 0.39473684210526316, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.47586206896551725, "acc_stderr": 0.0416180850350153, "acc_norm": 0.47586206896551725, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41798941798941797, "acc_stderr": 0.025402555503260912, "acc_norm": 0.41798941798941797, "acc_norm_stderr": 0.025402555503260912 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7129032258064516, "acc_stderr": 0.025736542745594528, "acc_norm": 0.7129032258064516, "acc_norm_stderr": 0.025736542745594528 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43349753694581283, "acc_stderr": 0.034867317274198714, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.034867317274198714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.04793724854411018, "acc_norm": 0.65, "acc_norm_stderr": 0.04793724854411018 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7393939393939394, "acc_stderr": 0.034277431758165236, "acc_norm": 0.7393939393939394, "acc_norm_stderr": 0.034277431758165236 }, "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": 0.8549222797927462, "acc_stderr": 0.025416343096306433, "acc_norm": 0.8549222797927462, "acc_norm_stderr": 0.025416343096306433 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5615384615384615, "acc_stderr": 0.025158266016868578, "acc_norm": 0.5615384615384615, "acc_norm_stderr": 0.025158266016868578 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948496, "acc_norm": 0.333
