open-llm-leaderboard-old/details_ContextualAI__archangel_sft-kto_llama13b
收藏数据集概述
该数据集是在评估模型 ContextualAI/archangel_sft-kto_llama13b 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片，分片名称使用运行的时间戳。
- "train" 分片始终指向最新的结果。
- 额外的 "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。
最新结果
以下是 2023-12-09T20:01:05.918025 运行 的最新结果：
python { "all": { "acc": 0.4808497396801513, "acc_stderr": 0.0342816178342491, "acc_norm": 0.48534799426464065, "acc_norm_stderr": 0.03504863417527385, "mc1": 0.26193390452876375, "mc1_stderr": 0.015392118805015023, "mc2": 0.39418229629364515, "mc2_stderr": 0.013748123967336172 }, "harness|arc:challenge|25": { "acc": 0.5264505119453925, "acc_stderr": 0.01459093135812017, "acc_norm": 0.5614334470989761, "acc_norm_stderr": 0.014500682618212864 }, "harness|hellaswag|10": { "acc": 0.6093407687711612, "acc_stderr": 0.004869010152280754, "acc_norm": 0.8080063732324239, "acc_norm_stderr": 0.003930631369978262 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4666666666666667, "acc_stderr": 0.043097329010363554, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.04060127035236395, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.04060127035236395 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4641509433962264, "acc_stderr": 0.030693675018458003, "acc_norm": 0.4641509433962264, "acc_norm_stderr": 0.030693675018458003 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4861111111111111, "acc_stderr": 0.04179596617581, "acc_norm": 0.4861111111111111, "acc_norm_stderr": 0.04179596617581 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.41040462427745666, "acc_stderr": 0.037507570448955356, "acc_norm": 0.41040462427745666, "acc_norm_stderr": 0.037507570448955356 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179963, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179963 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39574468085106385, "acc_stderr": 0.03196758697835361, "acc_norm": 0.39574468085106385, "acc_norm_stderr": 0.03196758697835361 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.43448275862068964, "acc_stderr": 0.041307408795554966, "acc_norm": 0.43448275862068964, "acc_norm_stderr": 0.041307408795554966 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2619047619047619, "acc_stderr": 0.02264421261552521, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.02264421261552521 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3333333333333333, "acc_stderr": 0.042163702135578345, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.042163702135578345 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5225806451612903, "acc_stderr": 0.028414985019707868, "acc_norm": 0.5225806451612903, "acc_norm_stderr": 0.028414985019707868 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.0316185633535861, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.0316185633535861 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.5454545454545454, "acc_stderr": 0.03547601494006937, "acc_norm": 0.5454545454545454, "acc_norm_stderr": 0.03547601494006937 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6632124352331606, "acc_stderr": 0.03410780251836183, "acc_norm": 0.6632124352331606, "acc_norm_stderr": 0.03410780251836183 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4666666666666667, "acc_stderr": 0.025294608023986472, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.025294608023986472 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.026719240783712173, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.026719240783712173 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc
