open-llm-leaderboard-old/details_chargoddard__mistral-11b-slimorca
收藏数据集概述
数据集简介
该数据集是在模型chargoddard/mistral-11b-slimorca在Open LLM Leaderboard上的评估运行期间自动创建的。
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。
- 数据集由1次运行创建,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_chargoddard__mistral-11b-slimorca", "harness_winogrande_5", split="train")
最新结果
这些是最新结果(来自2024-01-08T07:32:00.985160的运行): python { "all": { "acc": 0.6367892367382408, "acc_stderr": 0.032420458743968754, "acc_norm": 0.6401126581266797, "acc_norm_stderr": 0.03306588858456459, "mc1": 0.38310893512851896, "mc1_stderr": 0.017018461679389855, "mc2": 0.5466386336115909, "mc2_stderr": 0.015507674046261742 }, "harness|arc:challenge|25": { "acc": 0.6075085324232082, "acc_stderr": 0.01426963463567073, "acc_norm": 0.6424914675767918, "acc_norm_stderr": 0.014005494275916573 }, "harness|hellaswag|10": { "acc": 0.6468830910177256, "acc_stderr": 0.004769618829196511, "acc_norm": 0.8380800637323242, "acc_norm_stderr": 0.0036762448867232586 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411021, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411021 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_01_08T07_32_00.985160
- path: [**/details_harness|arc:challenge|25_2024-01-08T07-32-00.985160.parquet]
- split: latest
- path: [**/details_harness|arc:challenge|25_2024-01-08T07-32-00.985160.parquet]
- split: 2024_01_08T07_32_00.985160
-
config_name: harness_gsm8k_5
- split: 2024_01_08T07_32_00.985160
- path: [**/details_harness|gsm8k|5_2024-01-08T07-32-00.985160.parquet]
- split: latest
- path: [**/details_harness|gsm8k|5_2024-01-08T07-32-00.985160.parquet]
- split: 2024_01_08T07_32_00.985160
-
config_name: harness_hellaswag_10
- split: 2024_01_08T07_32_00.985160
- path: [**/details_harness|hellaswag|10_2024-01-08T07-32-00.985160.parquet]
- split: latest
- path: [**/details_harness|hellaswag|10_2024-01-08T07-32-00.985160.parquet]
- split: 2024_01_08T07_32_00.985160
-
config_name: harness_hendrycksTest_5
- split: 2024_01_08T07_32_00.985160
- path: [ **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-anatomy|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-astronomy|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-business_ethics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-college_biology|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-college_chemistry|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-college_computer_science|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-college_mathematics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-college_medicine|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-college_physics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-computer_security|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-econometrics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-formal_logic|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-global_facts|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_biology|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_geography|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_physics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-human_aging|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-human_sexuality|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-international_law|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-jurisprudence|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-machine_learning|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-management|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-marketing|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-medical_genetics|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-miscellaneous|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-moral_disputes|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-nutrition|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-philosophy|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-prehistory|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-professional_accounting|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-professional_law|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-professional_medicine|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-professional_psychology|5_2024-01-08T07-32-00.985160.parquet, **/details_harness|hendrycksTest-public_relations|5_2024-01-08
- split: 2024_01_08T07_32_00.985160



