open-llm-leaderboard-old/details_SicariusSicariiStuff__Tinybra_13B
收藏数据集概述
数据集简介
该数据集是在对模型 SicariusSicariiStuff/Tinybra_13B 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 创建来源：从1次运行中创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 训练分割："train" 分割始终指向最新的结果。
- 结果配置："results" 配置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_SicariusSicariiStuff__Tinybra_13B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-10T16:09:08.574464 运行 的最新结果：
python { "all": { "acc": 0.5418757648022121, "acc_stderr": 0.0340842399843829, "acc_norm": 0.5484756586160711, "acc_norm_stderr": 0.034833096638910925, "mc1": 0.3329253365973072, "mc1_stderr": 0.016497402382012052, "mc2": 0.49143267175287075, "mc2_stderr": 0.015300501325826228 }, "harness|arc:challenge|25": { "acc": 0.5324232081911263, "acc_stderr": 0.014580637569995421, "acc_norm": 0.5571672354948806, "acc_norm_stderr": 0.014515573873348904 }, "harness|hellaswag|10": { "acc": 0.609838677554272, "acc_stderr": 0.004867893927258144, "acc_norm": 0.8098984266082454, "acc_norm_stderr": 0.003915792315457794 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5986842105263158, "acc_stderr": 0.039889037033362836, "acc_norm": 0.5986842105263158, "acc_norm_stderr": 0.039889037033362836 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5924528301886792, "acc_stderr": 0.030242233800854494, "acc_norm": 0.5924528301886792, "acc_norm_stderr": 0.030242233800854494 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5277777777777778, "acc_stderr": 0.04174752578923185, "acc_norm": 0.5277777777777778, "acc_norm_stderr": 0.04174752578923185 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5086705202312138, "acc_stderr": 0.038118909889404105, "acc_norm": 0.5086705202312138, "acc_norm_stderr": 0.038118909889404105 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3235294117647059, "acc_stderr": 0.046550104113196156, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.046550104113196156 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.425531914893617, "acc_stderr": 0.03232146916224468, "acc_norm": 0.425531914893617, "acc_norm_stderr": 0.03232146916224468 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3157894736842105, "acc_stderr": 0.043727482902780064, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.043727482902780064 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3306878306878307, "acc_stderr": 0.024229965298425082, "acc_norm": 0.3306878306878307, "acc_norm_stderr": 0.024229965298425082 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.04190596438871136, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.04190596438871136 }, "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": 0.635483870967742, "acc_stderr": 0.027379871229943255, "acc_norm": 0.635483870967742, "acc_norm_stderr": 0.027379871229943255 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.035025446508458714, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.035025446508458714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6121212121212121, "acc_stderr": 0.038049136539710114, "acc_norm": 0.6121212121212121, "acc_norm_stderr": 0.038049136539710114 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7121212121212122, "acc_stderr": 0.03225883512300993, "acc_norm": 0.7121212121212122, "acc_norm_stderr": 0.03225883512300993 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7772020725388601, "acc_stderr": 0.03003114797764154, "acc_norm": 0.7772020725388601, "acc_norm_stderr": 0.03003114797764154 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5256410256410257, "acc_stderr": 0.025317649726448656, "acc_norm": 0.5256410256410257, "acc_norm_stderr": 0.025317649726448656 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.02822644674968352, "acc_norm": 0.3
