open-llm-leaderboard-old/details_jingyeom__SOLAR_KO_1.3_deup
收藏数据集概述
该数据集是在对模型 jingyeom/SOLAR_KO_1.3_deup 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 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_jingyeom__SOLAR_KO_1.3_deup", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要：
python { "all": { "acc": 0.5568308436610663, "acc_stderr": 0.03382759863491837, "acc_norm": 0.562882955720715, "acc_norm_stderr": 0.03456146092708182, "mc1": 0.3182374541003672, "mc1_stderr": 0.016305988648920623, "mc2": 0.4754562707057089, "mc2_stderr": 0.01501819768286651 }, "harness|arc:challenge|25": { "acc": 0.5238907849829352, "acc_stderr": 0.014594701798071654, "acc_norm": 0.5597269624573379, "acc_norm_stderr": 0.014506769524804234 }, "harness|hellaswag|10": { "acc": 0.5974905397331209, "acc_stderr": 0.004894012555642646, "acc_norm": 0.7997410874327823, "acc_norm_stderr": 0.003993761698847879 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4962962962962963, "acc_stderr": 0.04319223625811331, "acc_norm": 0.4962962962962963, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5723684210526315, "acc_stderr": 0.04026097083296564, "acc_norm": 0.5723684210526315, "acc_norm_stderr": 0.04026097083296564 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "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": 0.6666666666666666, "acc_stderr": 0.039420826399272135, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.039420826399272135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5606936416184971, "acc_stderr": 0.03784271932887468, "acc_norm": 0.5606936416184971, "acc_norm_stderr": 0.03784271932887468 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808778, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808778 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.04688261722621504, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5319148936170213, "acc_stderr": 0.03261936918467382, "acc_norm": 0.5319148936170213, "acc_norm_stderr": 0.03261936918467382 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.37719298245614036, "acc_stderr": 0.04559522141958216, "acc_norm": 0.37719298245614036, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.36243386243386244, "acc_stderr": 0.02475747390275206, "acc_norm": 0.36243386243386244, "acc_norm_stderr": 0.02475747390275206 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.043902592653775614, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.043902592653775614 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.632258064516129, "acc_stderr": 0.02743086657997347, "acc_norm": 0.632258064516129, "acc_norm_stderr": 0.02743086657997347 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.03413963805906235, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.03413963805906235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6727272727272727, "acc_stderr": 0.036639749943912434, "acc_norm": 0.6727272727272727, "acc_norm_stderr": 0.036639749943912434 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7070707070707071, "acc_stderr": 0.03242497958178816, "acc_norm": 0.7070707070707071, "acc_norm_stderr": 0.03242497958178816 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7772020725388601, "acc_stderr": 0.030031147977641538, "acc_norm": 0.7772020725388601, "acc_norm_stderr": 0.030031147977641538 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5051282051282051, "acc_stderr": 0.025349672906838653, "acc_norm": 0.5051282051282051, "acc_norm_stderr": 0.025349672906838653 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.028820884666253252, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.028820884666253252 }, "harness|hendrycksTest-high_school_microeconomics|5": {
