open-llm-leaderboard-old/details_pankajmathur__orca_mini_v3_70b
收藏数据集概述
数据集摘要
该数据集是在对模型 pankajmathur/orca_mini_v3_70b 进行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 61 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_pankajmathur__orca_mini_v3_70b", "harness_truthfulqa_mc_0", split="train")
最新结果
这些是最新的结果，来自 2023-10-09T02:12:05.216705 的运行： python { "all": { "acc": 0.7010508529623596, "acc_stderr": 0.0309286120388273, "acc_norm": 0.7049679984523141, "acc_norm_stderr": 0.030896356315399304, "mc1": 0.42962056303549573, "mc1_stderr": 0.017329234580409098, "mc2": 0.6126968953087459, "mc2_stderr": 0.015087648780065216 }, "harness|arc:challenge|25": { "acc": 0.6646757679180887, "acc_stderr": 0.013796182947785562, "acc_norm": 0.712457337883959, "acc_norm_stderr": 0.013226719056266129 }, "harness|hellaswag|10": { "acc": 0.6951802429794861, "acc_stderr": 0.00459390260197934, "acc_norm": 0.8785102569209321, "acc_norm_stderr": 0.0032602788112468337 }, "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": 0.6296296296296297, "acc_stderr": 0.04171654161354543, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.04171654161354543 }, "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": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7396226415094339, "acc_stderr": 0.027008766090708052, "acc_norm": 0.7396226415094339, "acc_norm_stderr": 0.027008766090708052 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8125, "acc_stderr": 0.032639560491693344, "acc_norm": 0.8125, "acc_norm_stderr": 0.032639560491693344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.036146654241808254, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.036146654241808254 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "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": 0.6936170212765957, "acc_stderr": 0.03013590647851756, "acc_norm": 0.6936170212765957, "acc_norm_stderr": 0.03013590647851756 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6344827586206897, "acc_stderr": 0.040131241954243856, "acc_norm": 0.6344827586206897, "acc_norm_stderr": 0.040131241954243856 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.48148148148148145, "acc_stderr": 0.02573364199183898, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.02573364199183898 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04444444444444449, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8161290322580645, "acc_stderr": 0.02203721734026783, "acc_norm": 0.8161290322580645, "acc_norm_stderr": 0.02203721734026783 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5665024630541872, "acc_stderr": 0.034867317274198714, "acc_norm": 0.5665024630541872, "acc_norm_stderr": 0.034867317274198714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.02845038880528436, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.02845038880528436 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8737373737373737, "acc_stderr": 0.023664359402880232, "acc_norm": 0.8737373737373737, "acc_norm_stderr": 0.023664359402880232 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9326424870466321, "acc_stderr": 0.0180883938390789, "acc_norm": 0.9326424870466321, "acc_norm_stderr": 0.0180883938390789 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7025641025641025, "acc_stderr": 0.023177408131465942, "acc_norm": 0.7025641025641025, "acc_norm_stderr": 0.023177408131465942 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114986, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.028037929969114986 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7478991596638656, "acc_stderr": 0.
