open-llm-leaderboard-old/details_MayaPH__opt-flan-iml-6.7b
收藏Hugging Face2023-10-13 更新2024-06-22 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_MayaPH__opt-flan-iml-6.7b
下载链接
链接失效反馈官方服务：
资源简介：
---
pretty_name: Evaluation run of MayaPH/opt-flan-iml-6.7b
dataset_summary: "Dataset automatically created during the evaluation run of model\
\ [MayaPH/opt-flan-iml-6.7b](https://huggingface.co/MayaPH/opt-flan-iml-6.7b) 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 1 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 agregated 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_MayaPH__opt-flan-iml-6.7b\"\
,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\
These are the [latest results from run 2023-10-13T03:06:32.697788](https://huggingface.co/datasets/open-llm-leaderboard/details_MayaPH__opt-flan-iml-6.7b/blob/main/results_2023-10-13T03-06-32.697788.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 \"em\": 0.07518875838926174,\n\
\ \"em_stderr\": 0.002700490526265294,\n \"f1\": 0.10838401845637569,\n\
\ \"f1_stderr\": 0.0028760995167941457,\n \"acc\": 0.3212312549329124,\n\
\ \"acc_stderr\": 0.006735003721960345\n },\n \"harness|drop|3\": {\n\
\ \"em\": 0.07518875838926174,\n \"em_stderr\": 0.002700490526265294,\n\
\ \"f1\": 0.10838401845637569,\n \"f1_stderr\": 0.0028760995167941457\n\
\ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.0,\n \"acc_stderr\"\
: 0.0\n },\n \"harness|winogrande|5\": {\n \"acc\": 0.6424625098658248,\n\
\ \"acc_stderr\": 0.01347000744392069\n }\n}\n```"
repo_url: https://huggingface.co/MayaPH/opt-flan-iml-6.7b
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_13T03_06_32.697788
path:
- '**/details_harness|drop|3_2023-10-13T03-06-32.697788.parquet'
- split: latest
path:
- '**/details_harness|drop|3_2023-10-13T03-06-32.697788.parquet'
- config_name: harness_gsm8k_5
data_files:
- split: 2023_10_13T03_06_32.697788
path:
- '**/details_harness|gsm8k|5_2023-10-13T03-06-32.697788.parquet'
- split: latest
path:
- '**/details_harness|gsm8k|5_2023-10-13T03-06-32.697788.parquet'
- config_name: harness_winogrande_5
data_files:
- split: 2023_10_13T03_06_32.697788
path:
- '**/details_harness|winogrande|5_2023-10-13T03-06-32.697788.parquet'
- split: latest
path:
- '**/details_harness|winogrande|5_2023-10-13T03-06-32.697788.parquet'
- config_name: results
data_files:
- split: 2023_10_13T03_06_32.697788
path:
- results_2023-10-13T03-06-32.697788.parquet
- split: latest
path:
- results_2023-10-13T03-06-32.697788.parquet
---
# Dataset Card for Evaluation run of MayaPH/opt-flan-iml-6.7b
## Dataset Description
- **Homepage:**
- **Repository:** https://huggingface.co/MayaPH/opt-flan-iml-6.7b
- **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 [MayaPH/opt-flan-iml-6.7b](https://huggingface.co/MayaPH/opt-flan-iml-6.7b) 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 1 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 agregated 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_MayaPH__opt-flan-iml-6.7b",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-10-13T03:06:32.697788](https://huggingface.co/datasets/open-llm-leaderboard/details_MayaPH__opt-flan-iml-6.7b/blob/main/results_2023-10-13T03-06-32.697788.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": {
"em": 0.07518875838926174,
"em_stderr": 0.002700490526265294,
"f1": 0.10838401845637569,
"f1_stderr": 0.0028760995167941457,
"acc": 0.3212312549329124,
"acc_stderr": 0.006735003721960345
},
"harness|drop|3": {
"em": 0.07518875838926174,
"em_stderr": 0.002700490526265294,
"f1": 0.10838401845637569,
"f1_stderr": 0.0028760995167941457
},
"harness|gsm8k|5": {
"acc": 0.0,
"acc_stderr": 0.0
},
"harness|winogrande|5": {
"acc": 0.6424625098658248,
"acc_stderr": 0.01347000744392069
}
}
```
### 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]
# MayaPH/opt-flan-iml-6.7b 模型评估运行数据集卡片
## 数据集元数据
- **数据集名称：** Evaluation run of MayaPH/opt-flan-iml-6.7b
- **数据集摘要：** 本数据集是在[Open LLM Leaderboard（开放大语言模型排行榜）](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上对[MayaPH/opt-flan-iml-6.7b](https://huggingface.co/MayaPH/opt-flan-iml-6.7b)模型进行评估运行时自动生成的。本数据集包含3个配置项，每个配置项对应一个被评估的任务。本数据集仅由1次评估运行生成，每个配置项下均设有对应此次运行的特定拆分（split），拆分名称以运行的时间戳命名，其中`train`拆分始终指向最新的评估结果。额外增设的`results`配置项存储了此次运行的所有聚合评估结果，并用于在Open LLM Leaderboard上计算并展示聚合指标。若要加载某次运行的详细数据，可参考如下示例代码：
python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_MayaPH__opt-flan-iml-6.7b",
"harness_winogrande_5",
split="train")
- **代码仓库：** https://huggingface.co/MayaPH/opt-flan-iml-6.7b
- **排行榜链接：** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
- **联系方式：** clementine@hf.co
- **配置项列表：**
1. 配置名称：`harness|drop|3`，数据文件包含两个拆分：`2023_10_13T03_06_32.697788`与`latest`，对应路径均为`**/details_harness|drop|3_2023-10-13T03-06-32.697788.parquet`
2. 配置名称：`harness|gsm8k|5`，数据文件包含两个拆分：`2023_10_13T03_06_32.697788`与`latest`，对应路径均为`**/details_harness|gsm8k|5_2023-10-13T03-06-32.697788.parquet`
3. 配置名称：`harness|winogrande|5`，数据文件包含两个拆分：`2023_10_13T03_06_32.697788`与`latest`，对应路径均为`**/details_harness|winogrande|5_2023-10-13T03-06-32.697788.parquet`
4. 配置名称：`results`，数据文件包含两个拆分：`2023_10_13T03_06_32.697788`与`latest`，对应路径均为`results_2023-10-13T03-06-32.697788.parquet`
## 最新评估结果
以下为[2023-10-13T03:06:32.697788 运行的最新评估结果](https://huggingface.co/datasets/open-llm-leaderboard/details_MayaPH__opt-flan-iml-6.7b/blob/main/results_2023-10-13T03-06-32.697788.json)（注：若后续多次评估未覆盖全部任务，则仓库中可能存在其他任务的评估结果。您可在各次运行的结果文件以及对应评估的`latest`拆分中找到所有结果。其中，`em`为精确匹配（Exact Match），`em_stderr`为精确匹配标准误差，`f1`为F1分数（F1-score），`f1_stderr`为F1分数标准误差，`acc`为准确率（Accuracy），`acc_stderr`为准确率标准误差）：
python
{
"all": {
"em": 0.07518875838926174,
"em_stderr": 0.002700490526265294,
"f1": 0.10838401845637569,
"f1_stderr": 0.0028760995167941457,
"acc": 0.3212312549329124,
"acc_stderr": 0.006735003721960345
},
"harness|drop|3": {
"em": 0.07518875838926174,
"em_stderr": 0.002700490526265294,
"f1": 0.10838401845637569,
"f1_stderr": 0.0028760995167941457
},
"harness|gsm8k|5": {
"acc": 0.0,
"acc_stderr": 0.0
},
"harness|winogrande|5": {
"acc": 0.6424625098658248,
"acc_stderr": 0.01347000744392069
}
}
### 支持的任务与排行榜
[需要更多信息]
### 语言
[需要更多信息]
## 数据集结构
### 数据实例
[需要更多信息]
### 数据字段
[需要更多信息]
### 数据拆分
[需要更多信息]
## 数据集创建
### 筛选依据
[需要更多信息]
### 源数据
#### 初始数据收集与归一化
[需要更多信息]
#### 源语言生产者是谁？
[需要更多信息]
### 标注
#### 标注流程
[需要更多信息]
#### 标注人员是谁？
[需要更多信息]
### 个人与敏感信息
[需要更多信息]
## 数据使用注意事项
### 数据集的社会影响
[需要更多信息]
### 偏差讨论
[需要更多信息]
### 其他已知局限性
[需要更多信息]
## 附加信息
### 数据集维护者
[需要更多信息]
### 许可信息
[需要更多信息]
### 引用信息
[需要更多信息]
### 贡献
[需要更多信息]
提供机构：
open-llm-leaderboard-old
原始信息汇总
数据集卡片 for Evaluation run of MayaPH/opt-flan-iml-6.7b
数据集描述
数据集概述
该数据集是在模型 MayaPH/opt-flan-iml-6.7b 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。
数据集是从1次运行中创建的。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 timestamp。"train" 分割始终指向最新的结果。
一个额外的配置 "results" 存储了运行的所有聚合结果（用于在 Open LLM Leaderboard 上计算和显示聚合指标）。
要加载运行的详细信息，可以执行以下操作： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_MayaPH__opt-flan-iml-6.7b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-13T03:06:32.697788 运行的最新结果：
python { "all": { "em": 0.07518875838926174, "em_stderr": 0.002700490526265294, "f1": 0.10838401845637569, "f1_stderr": 0.0028760995167941457, "acc": 0.3212312549329124, "acc_stderr": 0.006735003721960345 }, "harness|drop|3": { "em": 0.07518875838926174, "em_stderr": 0.002700490526265294, "f1": 0.10838401845637569, "f1_stderr": 0.0028760995167941457 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.6424625098658248, "acc_stderr": 0.01347000744392069 } }
数据集结构
配置
-
harness_drop_3
- 分割: 2023_10_13T03_06_32.697788
- 路径: **/details_harness|drop|3_2023-10-13T03-06-32.697788.parquet
- 分割: latest
- 路径: **/details_harness|drop|3_2023-10-13T03-06-32.697788.parquet
- 分割: 2023_10_13T03_06_32.697788
-
harness_gsm8k_5
- 分割: 2023_10_13T03_06_32.697788
- 路径: **/details_harness|gsm8k|5_2023-10-13T03-06-32.697788.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2023-10-13T03-06-32.697788.parquet
- 分割: 2023_10_13T03_06_32.697788
-
harness_winogrande_5
- 分割: 2023_10_13T03_06_32.697788
- 路径: **/details_harness|winogrande|5_2023-10-13T03-06-32.697788.parquet
- 分割: latest
- 路径: **/details_harness|winogrande|5_2023-10-13T03-06-32.697788.parquet
- 分割: 2023_10_13T03_06_32.697788
-
results
- 分割: 2023_10_13T03_06_32.697788
- 路径: results_2023-10-13T03-06-32.697788.parquet
- 分割: latest
- 路径: results_2023-10-13T03-06-32.697788.parquet
- 分割: 2023_10_13T03_06_32.697788
