open-llm-leaderboard-old/details_Epiculous__Crunchy-onion
收藏数据集概述
数据集简介
该数据集是在模型 Epiculous/Crunchy-onion 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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
- 配置数量:63
- 数据来源:1 次运行
- 数据分割:每个配置包含特定运行的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置:"results" 配置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_Epiculous__Crunchy-onion", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-23T07:42:32.669813 运行 的最新结果:
python { "all": { "acc": 0.6967211080887986, "acc_stderr": 0.030785488462122614, "acc_norm": 0.7024337864338088, "acc_norm_stderr": 0.031360406648538196, "mc1": 0.4810281517747858, "mc1_stderr": 0.017490896405762346, "mc2": 0.6387747489748049, "mc2_stderr": 0.01598416710685737 }, "harness|arc:challenge|25": { "acc": 0.6390784982935154, "acc_stderr": 0.014034761386175456, "acc_norm": 0.6715017064846417, "acc_norm_stderr": 0.013724978465537304 }, "harness|hellaswag|10": { "acc": 0.6981676956781517, "acc_stderr": 0.0045811472479632, "acc_norm": 0.8618801035650269, "acc_norm_stderr": 0.003443206472757467 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_01_23T07_42_32.669813
- path: **/details_harness|arc:challenge|25_2024-01-23T07-42-32.669813.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-01-23T07-42-32.669813.parquet
- split: 2024_01_23T07_42_32.669813
-
config_name: harness_gsm8k_5
- split: 2024_01_23T07_42_32.669813
- path: **/details_harness|gsm8k|5_2024-01-23T07-42-32.669813.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-01-23T07-42-32.669813.parquet
- split: 2024_01_23T07_42_32.669813
-
config_name: harness_hellaswag_10
- split: 2024_01_23T07_42_32.669813
- path: **/details_harness|hellaswag|10_2024-01-23T07-42-32.669813.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-01-23T07-42-32.669813.parquet
- split: 2024_01_23T07_42_32.669813
-
config_name: harness_hendrycksTest_5
- split: 2024_01_23T07_42_32.669813
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-23T07-42-32.669813.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024
- path:
- split: 2024_01_23T07_42_32.669813



