open-llm-leaderboard-old/details_HIT-SCIR__Chinese-Mixtral-8x7B
收藏数据集概述
数据集简介
数据集名为 "Evaluation run of HIT-SCIR/Chinese-Mixtral-8x7B"，是在评估模型 HIT-SCIR/Chinese-Mixtral-8x7B 在 Open LLM Leaderboard 上的自动创建的。
数据集组成
- 该数据集包含 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。
- 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_HIT-SCIR__Chinese-Mixtral-8x7B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 2024-02-09T23:17:17.937361 运行：
python { "all": { "acc": 0.7057638872269479, "acc_stderr": 0.030354776034335715, "acc_norm": 0.7107881469116898, "acc_norm_stderr": 0.030943456958256423, "mc1": 0.3108935128518972, "mc1_stderr": 0.016203316673559696, "mc2": 0.45859152966658717, "mc2_stderr": 0.014076354765836803 }, "harness|arc:challenge|25": { "acc": 0.6126279863481229, "acc_stderr": 0.014235872487909865, "acc_norm": 0.6356655290102389, "acc_norm_stderr": 0.01406326027988242 }, "harness|hellaswag|10": { "acc": 0.6600278828918542, "acc_stderr": 0.004727312448892832, "acc_norm": 0.859788886675961, "acc_norm_stderr": 0.0034649633793799434 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6962962962962963, "acc_stderr": 0.039725528847851375, "acc_norm": 0.6962962962962963, "acc_norm_stderr": 0.039725528847851375 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8157894736842105, "acc_stderr": 0.0315469804508223, "acc_norm": 0.8157894736842105, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.68, "acc_stderr": 0.046882617226215034, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7735849056603774, "acc_stderr": 0.025757559893106734, "acc_norm": 0.7735849056603774, "acc_norm_stderr": 0.025757559893106734 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8472222222222222, "acc_stderr": 0.030085743248565656, "acc_norm": 0.8472222222222222, "acc_norm_stderr": 0.030085743248565656 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "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": 0.4019607843137255, "acc_stderr": 0.04878608714466996, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.04878608714466996 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653695, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653695 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6638297872340425, "acc_stderr": 0.030881618520676942, "acc_norm": 0.6638297872340425, "acc_norm_stderr": 0.030881618520676942 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6140350877192983, "acc_stderr": 0.04579639422070435, "acc_norm": 0.6140350877192983, "acc_norm_stderr": 0.04579639422070435 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6827586206896552, "acc_stderr": 0.03878352372138622, "acc_norm": 0.6827586206896552, "acc_norm_stderr": 0.03878352372138622 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47619047619047616, "acc_stderr": 0.025722097064388525, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.025722097064388525 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8419354838709677, "acc_stderr": 0.020752831511875278, "acc_norm": 0.8419354838709677, "acc_norm_stderr": 0.020752831511875278 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6305418719211823, "acc_stderr": 0.03395970381998574, "acc_norm": 0.6305418719211823, "acc_norm_stderr": 0.03395970381998574 }, "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": 0.793939393939394, "acc_stderr": 0.0315841532404771, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.0315841532404771 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8636363636363636, "acc_stderr": 0.024450155973189835, "acc_norm": 0.8636363636363636, "acc_norm_stderr": 0.024450155973189835 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.017426974154240524, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.017426974154240524 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6846153846153846, "acc_stderr": 0.02355964698318994, "acc_norm": 0.6846153846153846, "acc_norm_stderr": 0.02355964698318994 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37037037037037035, "acc_stderr": 0.02944316932303154, "acc_norm": 0.37037037037037035,
