open-llm-leaderboard-old/details_kwchoi__DPO_mistral_7b_ultra_0129_1k
收藏数据集概述
数据集摘要
该数据集是在评估模型 kwchoi/DPO_mistral_7b_ultra_0129_1k 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行创建,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。
额外配置
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_kwchoi__DPO_mistral_7b_ultra_0129_1k", "harness_winogrande_5", split="train")
最新结果
这些是最新结果的示例: python { "all": { "acc": 0.6099611898518866, "acc_stderr": 0.033230906844496894, "acc_norm": 0.6150815540917772, "acc_norm_stderr": 0.03391141680931445, "mc1": 0.5287637698898409, "mc1_stderr": 0.017474513848525518, "mc2": 0.6834430823847926, "mc2_stderr": 0.015682529110673984 }, "harness|arc:challenge|25": { "acc": 0.6049488054607508, "acc_stderr": 0.01428589829293817, "acc_norm": 0.6416382252559727, "acc_norm_stderr": 0.014012883334859857 }, "harness|hellaswag|10": { "acc": 0.6885082652857997, "acc_stderr": 0.004621568125102045, "acc_norm": 0.8554072893845848, "acc_norm_stderr": 0.003509709647791843 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_01_29T02_08_21.931644
- path: **/details_harness|arc:challenge|25_2024-01-29T02-08-21.931644.parquet
- split: 2024_01_29T02_14_53.024485
- path: **/details_harness|arc:challenge|25_2024-01-29T02-14-53.024485.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-01-29T02-14-53.024485.parquet
- split: 2024_01_29T02_08_21.931644
-
config_name: harness_gsm8k_5
- split: 2024_01_29T02_08_21.931644
- path: **/details_harness|gsm8k|5_2024-01-29T02-08-21.931644.parquet
- split: 2024_01_29T02_14_53.024485
- path: **/details_harness|gsm8k|5_2024-01-29T02-14-53.024485.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-01-29T02-14-53.024485.parquet
- split: 2024_01_29T02_08_21.931644
-
config_name: harness_hellaswag_10
- split: 2024_01_29T02_08_21.931644
- path: **/details_harness|hellaswag|10_2024-01-29T02-08-21.931644.parquet
- split: 2024_01_29T02_14_53.024485
- path: **/details_harness|hellaswag|10_2024-01-29T02-14-53.024485.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-01-29T02-14-53.024485.parquet
- split: 2024_01_29T02_08_21.931644
-
config_name: harness_hendrycksTest_5
- split: 2024_01_29T02_08_21.931644
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-formal_logic|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-global_facts|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_biology|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_geography|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_physics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-human_sexuality|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-international_law|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-jurisprudence|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-machine_learning|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-management|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-marketing|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-medical_genetics|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-miscellaneous|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-moral_disputes|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-29T02-08-21.931644.parquet
- path: **/details_harness|hendrycksTest-nutrition|5_2024-01-29T02-
- split: 2024_01_29T02_08_21.931644



