open-llm-leaderboard-old/details_LeroyDyer__Mixtral_ThoughtsProcess_1
收藏数据集概述
该数据集是在对模型 LeroyDyer/Mixtral_ThoughtsProcess_1 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。
- 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。
最新结果
以下是 2024-03-22T00:07:18.196733 运行的最新结果：
python { "all": { "acc": 0.6196981873098155, "acc_stderr": 0.03305059771688219, "acc_norm": 0.623627298072695, "acc_norm_stderr": 0.03371284612436172, "mc1": 0.5165238678090576, "mc1_stderr": 0.017493940190057723, "mc2": 0.6734400618205734, "mc2_stderr": 0.015274440350493154 }, "harness|arc:challenge|25": { "acc": 0.6015358361774744, "acc_stderr": 0.014306946052735567, "acc_norm": 0.6527303754266212, "acc_norm_stderr": 0.013913034529620455 }, "harness|hellaswag|10": { "acc": 0.6727743477394941, "acc_stderr": 0.004682414968323627, "acc_norm": 0.8569010157339175, "acc_norm_stderr": 0.003494581076398543 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6513157894736842, "acc_stderr": 0.0387813988879761, "acc_norm": 0.6513157894736842, "acc_norm_stderr": 0.0387813988879761 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322666, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322666 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "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": 0.5953757225433526, "acc_stderr": 0.03742461193887248, "acc_norm": 0.5953757225433526, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.548936170212766, "acc_stderr": 0.032529096196131965, "acc_norm": 0.548936170212766, "acc_norm_stderr": 0.032529096196131965 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.046854730419077895, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.046854730419077895 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.593103448275862, "acc_stderr": 0.04093793981266236, "acc_norm": 0.593103448275862, "acc_norm_stderr": 0.04093793981266236 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4126984126984127, "acc_stderr": 0.02535574126305527, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.02535574126305527 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3968253968253968, "acc_stderr": 0.043758884927270605, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.043758884927270605 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6612903225806451, "acc_stderr": 0.02692344605930284, "acc_norm": 0.6612903225806451, "acc_norm_stderr": 0.02692344605930284 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.03317505930009182, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.03317505930009182 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7626262626262627, "acc_stderr": 0.030313710538198896, "acc_norm": 0.7626262626262627, "acc_norm_stderr": 0.030313710538198896 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8601036269430051, "acc_stderr": 0.025033870583015178, "acc_norm": 0.8601036269430051, "acc_norm_stderr": 0.025033870583015178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5717948717948718, "acc_stderr": 0.02508830145469483, "acc_norm": 0.5717948717948718, "acc_norm_stderr": 0.02508830145469483 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.028317533496066485, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.028317533496066485 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.680672268907563, "acc
