open-llm-leaderboard/details_RWKV__rwkv-4-7b-pile
收藏数据集概述
数据集名称
- Evaluation run of RWKV/rwkv-4-7b-pile
数据集组成
- 该数据集包含64个配置,每个配置对应一个评估任务。
- 数据集由2次运行结果组成,每次运行结果作为特定分片存储在每个配置中,分片名称使用运行的时间戳。
- "train"分片始终指向最新的结果。
- 一个额外的配置"results"存储所有运行结果的聚合数据,用于计算和显示在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_RWKV__rwkv-4-7b-pile", "harness_winogrande_5", split="train")
最新结果
- 最新结果来自2023-10-16T04:13:51.306808的运行,包含以下指标: python { "all": { "em": 0.003145973154362416, "em_stderr": 0.0005734993648436389, "f1": 0.04605390100671147, "f1_stderr": 0.0012821309890559797, "acc": 0.31555081370989124, "acc_stderr": 0.008003106736372202 }, "harness|drop|3": { "em": 0.003145973154362416, "em_stderr": 0.0005734993648436389, "f1": 0.04605390100671147, "f1_stderr": 0.0012821309890559797 }, "harness|gsm8k|5": { "acc": 0.0075815011372251705, "acc_stderr": 0.0023892815120772127 }, "harness|winogrande|5": { "acc": 0.6235201262825573, "acc_stderr": 0.01361693196066719 } }
配置详情
-
harness_arc_challenge_25
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|arc:challenge|25_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|arc:challenge|25_2023-09-03T08:57:35.818807.parquet
-
harness_drop_3
- 分片:2023_10_16T04_13_51.306808
- 路径:
**/details_harness|drop|3_2023-10-16T04-13-51.306808.parquet - 分片:latest
- 路径:
**/details_harness|drop|3_2023-10-16T04-13-51.306808.parquet
-
harness_gsm8k_5
- 分片:2023_10_16T04_13_51.306808
- 路径:
**/details_harness|gsm8k|5_2023-10-16T04-13-51.306808.parquet - 分片:latest
- 路径:
**/details_harness|gsm8k|5_2023-10-16T04-13-51.306808.parquet
-
harness_hellaswag_10
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hellaswag|10_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hellaswag|10_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_5
- 分片:2023_09_03T08_57_35.818807
- 路径:多个文件路径,如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-03T08:57:35.818807.parquet等 - 分片:latest
- 路径:多个文件路径,如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-03T08:57:35.818807.parquet等
-
harness_hendrycksTest_abstract_algebra_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_anatomy_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_astronomy_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_business_ethics_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_college_biology_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_college_chemistry_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_college_computer_science_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_college_mathematics_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_college_medicine_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_college_physics_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_computer_security_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_econometrics_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 分片:2023_09_03T08_57_35.818807
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-03T08:57:35.818807.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-03T08:57:35.818807.parquet
-
harness_hendrycksTest_elementary_mathematics_5
- 分片:2023_09_03T08_57_35.818807
- 路径:`**/details_harness|hendrycksTest-elementary_mathematics|



