open-llm-leaderboard-old/details_EleutherAI__pythia-2.7b
收藏数据集概述
数据集名称
- Evaluation run of EleutherAI/pythia-2.7b
数据集来源
- 该数据集是在模型 EleutherAI/pythia-2.7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 该数据集包含 64 个配置,每个配置对应一个评估任务。
- 数据集从 2 次运行中创建,每个运行可以在每个配置中作为一个特定的分片找到,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,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_EleutherAI__pythia-2.7b", "harness_winogrande_5", split="train")
最新结果
- 以下是 2023-10-13T09:56:45.840530 运行 的最新结果: python { "all": { "em": 0.0010486577181208054, "em_stderr": 0.0003314581465219123, "f1": 0.045142617449664524, "f1_stderr": 0.0011715787583837264, "acc": 0.315883214963382, "acc_stderr": 0.008228218962784018 }, "harness|drop|3": { "em": 0.0010486577181208054, "em_stderr": 0.0003314581465219123, "f1": 0.045142617449664524, "f1_stderr": 0.0011715787583837264 }, "harness|gsm8k|5": { "acc": 0.01061410159211524, "acc_stderr": 0.002822713322387704 }, "harness|winogrande|5": { "acc": 0.6211523283346487, "acc_stderr": 0.013633724603180334 } }
配置详情
-
harness_arc_challenge_25
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|arc:challenge|25_2023-07-19T16:50:21.612353.parquet
-
harness_drop_3
- 分片:2023_10_13T09_56_45.840530, latest
- 路径:
**/details_harness|drop|3_2023-10-13T09-56-45.840530.parquet
-
harness_gsm8k_5
- 分片:2023_10_13T09_56_45.840530, latest
- 路径:
**/details_harness|gsm8k|5_2023-10-13T09-56-45.840530.parquet
-
harness_hellaswag_10
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hellaswag|10_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:多个路径,例如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_abstract_algebra_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_anatomy_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_astronomy_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_business_ethics_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_college_biology_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_college_chemistry_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_college_computer_science_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_college_mathematics_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_college_medicine_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_college_physics_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_computer_security_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_econometrics_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T16:50:21.612353.parquet
-
harness_hendrycksTest_elementary_mathematics_5
- 分片:2023_07_19T16_50_21.612353, latest
- 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T16:50:21.612353.parquet
以上是数据集的详细概述,包括数据集名称、来源、结构、加载示例、最新结果以及各个配置的详细信息。



