open-llm-leaderboard-old/details_damerajee__Gaja-v2.00-dpo
收藏数据集概述
该数据集是在对模型damerajee/Gaja-v2.00-dpo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2024-03-05T17:37:53.198082运行的最新结果：
python { "all": { "acc": 0.40989996507866366, "acc_stderr": 0.03417962031118376, "acc_norm": 0.4157031727799528, "acc_norm_stderr": 0.03509007681440263, "mc1": 0.2717258261933905, "mc1_stderr": 0.015572840452875833, "mc2": 0.4129256818841227, "mc2_stderr": 0.014654469964710336 }, "harness|arc:challenge|25": { "acc": 0.4684300341296928, "acc_stderr": 0.01458223646086698, "acc_norm": 0.5170648464163823, "acc_norm_stderr": 0.014602878388536597 }, "harness|hellaswag|10": { "acc": 0.566620195180243, "acc_stderr": 0.004945291270072425, "acc_norm": 0.7587134037044413, "acc_norm_stderr": 0.004269893011588913 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4074074074074074, "acc_stderr": 0.042446332383532286, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.042446332383532286 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.40789473684210525, "acc_stderr": 0.03999309712777471, "acc_norm": 0.40789473684210525, "acc_norm_stderr": 0.03999309712777471 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4075471698113208, "acc_stderr": 0.030242233800854498, "acc_norm": 0.4075471698113208, "acc_norm_stderr": 0.030242233800854498 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04076663253918567, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04076663253918567 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.31213872832369943, "acc_stderr": 0.035331333893236574, "acc_norm": 0.31213872832369943, "acc_norm_stderr": 0.035331333893236574 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617747, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617747 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3191489361702128, "acc_stderr": 0.030472973363380045, "acc_norm": 0.3191489361702128, "acc_norm_stderr": 0.030472973363380045 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21052631578947367, "acc_stderr": 0.038351539543994194, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.038351539543994194 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.45517241379310347, "acc_stderr": 0.04149886942192117, "acc_norm": 0.45517241379310347, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.02241804289111394, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.02241804289111394 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.25396825396825395, "acc_stderr": 0.038932596106046734, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.038932596106046734 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4483870967741935, "acc_stderr": 0.028292056830112735, "acc_norm": 0.4483870967741935, "acc_norm_stderr": 0.028292056830112735 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.24630541871921183, "acc_stderr": 0.03031509928561773, "acc_norm": 0.24630541871921183, "acc_norm_stderr": 0.03031509928561773 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5575757575757576, "acc_stderr": 0.03878372113711274, "acc_norm": 0.5575757575757576, "acc_norm_stderr": 0.03878372113711274 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.41414141414141414, "acc_stderr": 0.03509438348879629, "acc_norm": 0.41414141414141414, "acc_norm_stderr": 0.03509438348879629 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5440414507772021, "acc_stderr": 0.035944137112724386, "acc_norm": 0.5440414507772021, "acc_norm_stderr": 0.035944137112724386 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.37948717948717947, "acc_stderr": 0.024603626924097413, "acc_norm": 0.37948717948717947, "acc_norm_stderr": 0.024603626924097413 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340496, "acc_norm": 0.2851851851851852, "acc_norm_stderr": 0.027528599210340496 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.373949579831
