Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: CastError
Message: Couldn't cast
example_index: int64
question_id: int64
db_id: string
difficulty: string
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
to
{'messages': List({'role': Value('string'), 'content': Value('string')})}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1816, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 613, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 343, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2369, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2297, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
example_index: int64
question_id: int64
db_id: string
difficulty: string
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
to
{'messages': List({'role': Value('string'), 'content': Value('string')})}
because column names don't match
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1369, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 948, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1683, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1869, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
messages list |
|---|
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
[
{
"role": "system",
"content": "You are a senior Text-to-SQL engineer. Solve the user task using only the supplied complete SQLite schema, column meanings, and evidence.\n\nYour response must contain exactly three XML-like blocks in this order, with no Markdown fences, commentary, or text outside the blocks... |
End of preview.
结构化 Text-to-SQL 蒸馏 SFT（本地通用导出）
这是本项目完整的结构化 Text-to-SQL SFT 导出，共 6,246 条 messages 格式 JSONL 样本；其中正式 Qwen3-8B 实验实际使用的是本仓库中明确标注的 5,160 条训练 split。
文件与划分
qwen_sft_messages.jsonl：全量 SFT，6,246 条。splits/dbdev4_train_5160.jsonl：正式 Qwen3-8B LoRA 训练集，5,160 条。它是全量教师样本按数据库划分后的子集，对应训练机中的qwen_sft_messages_train_dbdev4.jsonl。splits/dbdev4_execution_dev_prompts_400.jsonl：训练期 database-disjoint execution-dev 的 400 条提示词，只含 system/user messages，不含 gold SQL。splits/dbdev4_split_manifest.json：划分参数、样本数和 SHA-256。
划分从同一个 6,246 条教师样本源构造，随机种子为 42：
| 用途 | 数据库与规则 | 条数 |
|---|---|---|
| 正式训练 | 排除下方所有保留/剔除数据库后的样本 | 5,160 |
| execution-dev | hockey、mondial_geo、movie_3、student_loan 各按 SHA-256("42:record_id") 排序选取前 100 条 |
400 |
| 未参与训练的同库余量 | 上述四库未被抽入 execution-dev 的其余样本 | 318 |
| 长上下文剔除 | works_cycles 全部样本 |
368 |
四个 execution-dev 数据库总计 718 条，因此训练集与 execution-dev 在数据库层面完全不重叠。已完成的 8B 训练命令使用全部 5,160 条训练样本并显式设置 split_dataset_ratio=0；400 条 execution-dev 是独立的运行级开发集，不是训练器内部的 validation-loss split。
- 不包含 BIRD SQLite 数据库、gold SQL 或任何原始数据库内容。
样本格式
每行是 Hugging Face / Qwen 兼容的 messages JSON 对象，包含系统提示、用户问题及目标助手回复。样本由工程中的教师样本构造和导出脚本产生，相关代码见 GitHub 仓库：https://github.com/craboy4/text-to-sql-struct-distillation。
来源与许可
本数据包含基于 BIRD 任务构造的派生内容。BIRD Mini-Dev 上游材料采用 CC BY-SA 4.0；本仓库以 CC BY-SA 4.0 发布。使用者须保留署名、引用上游 BIRD 工作，并以兼容条款发布派生成果。
引用
@inproceedings{li2024bird,
title={Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs},
author={Li, Jinyang and others},
year={2024}
}
- Downloads last month
- 39