open-llm-leaderboard/details_WizardLM__WizardLM-30B-V1.0
收藏Hugging Face2023-12-03 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard/details_WizardLM__WizardLM-30B-V1.0
下载链接
链接失效反馈官方服务：
资源简介：
---
pretty_name: Evaluation run of WizardLM/WizardLM-30B-V1.0
dataset_summary: "Dataset automatically created during the evaluation run of model\
\ [WizardLM/WizardLM-30B-V1.0](https://huggingface.co/WizardLM/WizardLM-30B-V1.0)\
\ on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\
\nThe dataset is composed of 3 configuration, each one coresponding to one of the\
\ evaluated task.\n\nThe dataset has been created from 8 run(s). Each run can be\
\ found as a specific split in each configuration, the split being named using the\
\ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\
\nAn additional configuration \"results\" store all the aggregated results of the\
\ run (and is used to compute and display the aggregated metrics on the [Open LLM\
\ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\
\nTo load the details from a run, you can for instance do the following:\n```python\n\
from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_WizardLM__WizardLM-30B-V1.0\"\
,\n\t\"harness_gsm8k_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese\
\ are the [latest results from run 2023-12-03T06:39:48.508245](https://huggingface.co/datasets/open-llm-leaderboard/details_WizardLM__WizardLM-30B-V1.0/blob/main/results_2023-12-03T06-39-48.508245.json)(note\
\ that their might be results for other tasks in the repos if successive evals didn't\
\ cover the same tasks. You find each in the results and the \"latest\" split for\
\ each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.0,\n \"\
acc_stderr\": 0.0\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.0,\n \
\ \"acc_stderr\": 0.0\n }\n}\n```"
repo_url: https://huggingface.co/WizardLM/WizardLM-30B-V1.0
leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
point_of_contact: clementine@hf.co
configs:
- config_name: harness_drop_3
data_files:
- split: 2023_10_21T14_56_55.024771
path:
- '**/details_harness|drop|3_2023-10-21T14-56-55.024771.parquet'
- split: 2023_10_21T17_46_17.809151
path:
- '**/details_harness|drop|3_2023-10-21T17-46-17.809151.parquet'
- split: latest
path:
- '**/details_harness|drop|3_2023-10-21T17-46-17.809151.parquet'
- config_name: harness_gsm8k_5
data_files:
- split: 2023_10_21T14_56_55.024771
path:
- '**/details_harness|gsm8k|5_2023-10-21T14-56-55.024771.parquet'
- split: 2023_10_21T17_46_17.809151
path:
- '**/details_harness|gsm8k|5_2023-10-21T17-46-17.809151.parquet'
- split: 2023_12_03T04_35_31.048043
path:
- '**/details_harness|gsm8k|5_2023-12-03T04-35-31.048043.parquet'
- split: 2023_12_03T04_36_04.759843
path:
- '**/details_harness|gsm8k|5_2023-12-03T04-36-04.759843.parquet'
- split: 2023_12_03T04_42_48.050570
path:
- '**/details_harness|gsm8k|5_2023-12-03T04-42-48.050570.parquet'
- split: 2023_12_03T04_43_48.387414
path:
- '**/details_harness|gsm8k|5_2023-12-03T04-43-48.387414.parquet'
- split: 2023_12_03T06_38_27.690404
path:
- '**/details_harness|gsm8k|5_2023-12-03T06-38-27.690404.parquet'
- split: 2023_12_03T06_39_48.508245
path:
- '**/details_harness|gsm8k|5_2023-12-03T06-39-48.508245.parquet'
- split: latest
path:
- '**/details_harness|gsm8k|5_2023-12-03T06-39-48.508245.parquet'
- config_name: harness_winogrande_5
data_files:
- split: 2023_10_21T14_56_55.024771
path:
- '**/details_harness|winogrande|5_2023-10-21T14-56-55.024771.parquet'
- split: 2023_10_21T17_46_17.809151
path:
- '**/details_harness|winogrande|5_2023-10-21T17-46-17.809151.parquet'
- split: latest
path:
- '**/details_harness|winogrande|5_2023-10-21T17-46-17.809151.parquet'
- config_name: results
data_files:
- split: 2023_10_21T14_56_55.024771
path:
- results_2023-10-21T14-56-55.024771.parquet
- split: 2023_10_21T17_46_17.809151
path:
- results_2023-10-21T17-46-17.809151.parquet
- split: 2023_12_03T04_35_31.048043
path:
- results_2023-12-03T04-35-31.048043.parquet
- split: 2023_12_03T04_36_04.759843
path:
- results_2023-12-03T04-36-04.759843.parquet
- split: 2023_12_03T04_42_48.050570
path:
- results_2023-12-03T04-42-48.050570.parquet
- split: 2023_12_03T04_43_48.387414
path:
- results_2023-12-03T04-43-48.387414.parquet
- split: 2023_12_03T06_38_27.690404
path:
- results_2023-12-03T06-38-27.690404.parquet
- split: 2023_12_03T06_39_48.508245
path:
- results_2023-12-03T06-39-48.508245.parquet
- split: latest
path:
- results_2023-12-03T06-39-48.508245.parquet
---
# Dataset Card for Evaluation run of WizardLM/WizardLM-30B-V1.0
## Dataset Description
- **Homepage:**
- **Repository:** https://huggingface.co/WizardLM/WizardLM-30B-V1.0
- **Paper:**
- **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
- **Point of Contact:** clementine@hf.co
### Dataset Summary
Dataset automatically created during the evaluation run of model [WizardLM/WizardLM-30B-V1.0](https://huggingface.co/WizardLM/WizardLM-30B-V1.0) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 3 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 8 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_WizardLM__WizardLM-30B-V1.0",
"harness_gsm8k_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-12-03T06:39:48.508245](https://huggingface.co/datasets/open-llm-leaderboard/details_WizardLM__WizardLM-30B-V1.0/blob/main/results_2023-12-03T06-39-48.508245.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.0,
"acc_stderr": 0.0
},
"harness|gsm8k|5": {
"acc": 0.0,
"acc_stderr": 0.0
}
}
```
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
[More Information Needed]
提供机构：
open-llm-leaderboard
原始信息汇总
数据集卡片：WizardLM/WizardLM-30B-V1.0 评估运行
数据集描述
数据集摘要
该数据集是在模型 WizardLM/WizardLM-30B-V1.0 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集由 3 个配置组成，每个配置对应一个评估任务。
数据集从 8 次运行中创建。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。
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）。
要加载某个运行的详细信息，可以执行以下操作： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_WizardLM__WizardLM-30B-V1.0", "harness_gsm8k_5", split="train")
最新结果
这些是最新结果来自 2023-12-03T06:39:48.508245 运行（注意，如果有其他任务的结果，可以在结果和每个评估的 "latest" 分割中找到）：
python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }
数据集结构
配置
-
harness_drop_3
- 分割：2023_10_21T14_56_55.024771
- 路径：
**/details_harness|drop|3_2023-10-21T14-56-55.024771.parquet
- 路径：
- 分割：2023_10_21T17_46_17.809151
- 路径：
**/details_harness|drop|3_2023-10-21T17-46-17.809151.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|drop|3_2023-10-21T17-46-17.809151.parquet
- 路径：
- 分割：2023_10_21T14_56_55.024771
-
harness_gsm8k_5
- 分割：2023_10_21T14_56_55.024771
- 路径：
**/details_harness|gsm8k|5_2023-10-21T14-56-55.024771.parquet
- 路径：
- 分割：2023_10_21T17_46_17.809151
- 路径：
**/details_harness|gsm8k|5_2023-10-21T17-46-17.809151.parquet
- 路径：
- 分割：2023_12_03T04_35_31.048043
- 路径：
**/details_harness|gsm8k|5_2023-12-03T04-35-31.048043.parquet
- 路径：
- 分割：2023_12_03T04_36_04.759843
- 路径：
**/details_harness|gsm8k|5_2023-12-03T04-36-04.759843.parquet
- 路径：
- 分割：2023_12_03T04_42_48.050570
- 路径：
**/details_harness|gsm8k|5_2023-12-03T04-42-48.050570.parquet
- 路径：
- 分割：2023_12_03T04_43_48.387414
- 路径：
**/details_harness|gsm8k|5_2023-12-03T04-43-48.387414.parquet
- 路径：
- 分割：2023_12_03T06_38_27.690404
- 路径：
**/details_harness|gsm8k|5_2023-12-03T06-38-27.690404.parquet
- 路径：
- 分割：2023_12_03T06_39_48.508245
- 路径：
**/details_harness|gsm8k|5_2023-12-03T06-39-48.508245.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|gsm8k|5_2023-12-03T06-39-48.508245.parquet
- 路径：
- 分割：2023_10_21T14_56_55.024771
-
harness_winogrande_5
- 分割：2023_10_21T14_56_55.024771
- 路径：
**/details_harness|winogrande|5_2023-10-21T14-56-55.024771.parquet
- 路径：
- 分割：2023_10_21T17_46_17.809151
- 路径：
**/details_harness|winogrande|5_2023-10-21T17-46-17.809151.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|winogrande|5_2023-10-21T17-46-17.809151.parquet
- 路径：
- 分割：2023_10_21T14_56_55.024771
-
results
- 分割：2023_10_21T14_56_55.024771
- 路径：
results_2023-10-21T14-56-55.024771.parquet
- 路径：
- 分割：2023_10_21T17_46_17.809151
- 路径：
results_2023-10-21T17-46-17.809151.parquet
- 路径：
- 分割：2023_12_03T04_35_31.048043
- 路径：
results_2023-12-03T04-35-31.048043.parquet
- 路径：
- 分割：2023_12_03T04_36_04.759843
- 路径：
results_2023-12-03T04-36-04.759843.parquet
- 路径：
- 分割：2023_12_03T04_42_48.050570
- 路径：
results_2023-12-03T04-42-48.050570.parquet
- 路径：
- 分割：2023_12_03T04_43_48.387414
- 路径：
results_2023-12-03T04-43-48.387414.parquet
- 路径：
- 分割：2023_12_03T06_38_27.690404
- 路径：
results_2023-12-03T06-38-27.690404.parquet
- 路径：
- 分割：2023_12_03T06_39_48.508245
- 路径：
results_2023-12-03T06-39-48.508245.parquet
- 路径：
- 分割：latest
- 路径：
results_2023-12-03T06-39-48.508245.parquet
- 路径：
- 分割：2023_10_21T14_56_55.024771
