Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed because of a cast error
Error code: DatasetGenerationCastError
Exception: DatasetGenerationCastError
Message: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 9 new columns ({'gold_sql', 'question_en', 'difficulty', 'tags', 'mysql_db_name', 'task_id', 'protected_literals', 'execution_validation', 'sql_tables'}) and 3 missing columns ({'id', 'meta', 'messages'}).
This happened while the json dataset builder was generating data using
hf://datasets/acomagu/dbbench-mysql-synth/tasks_train.jsonl (at revision 4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d), [/tmp/hf-datasets-cache/medium/datasets/36054225742639-config-parquet-and-info-acomagu-dbbench-mysql-syn-796e265a/hub/datasets--acomagu--dbbench-mysql-synth/snapshots/4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/messages_train.jsonl (origin=hf://datasets/acomagu/dbbench-mysql-synth@4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/messages_train.jsonl), /tmp/hf-datasets-cache/medium/datasets/36054225742639-config-parquet-and-info-acomagu-dbbench-mysql-syn-796e265a/hub/datasets--acomagu--dbbench-mysql-synth/snapshots/4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/tasks_train.jsonl (origin=hf://datasets/acomagu/dbbench-mysql-synth@4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/tasks_train.jsonl)]
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
writer.write_table(table)
File "/usr/local/lib/python3.12/site-packages/datasets/arrow_writer.py", line 675, in write_table
pa_table = table_cast(pa_table, self._schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2272, in table_cast
return cast_table_to_schema(table, schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2218, in cast_table_to_schema
raise CastError(
datasets.table.CastError: Couldn't cast
task_id: string
db_id: string
mysql_db_name: string
domain: string
question_en: string
gold_sql: string
difficulty: string
tags: list<item: string>
child 0, item: string
sql_tables: list<item: string>
child 0, item: string
protected_literals: list<item: string>
child 0, item: string
execution_validation: struct<ok: bool, columns: list<item: string>, rowcount: int64, final_answer: list<item: string>>
child 0, ok: bool
child 1, columns: list<item: string>
child 0, item: string
child 2, rowcount: int64
child 3, final_answer: list<item: string>
child 0, item: string
to
{'id': Value('string'), 'db_id': Value('string'), 'domain': Value('string'), 'messages': List({'role': Value('string'), 'content': Value('string')}), 'meta': {'difficulty': Value('string'), 'tags': List(Value('string')), 'sql_tables': List(Value('string')), 'gold_sql': Value('string'), 'final_answer': List(Value('string')), 'format': Value('string'), 'validated_on_mysql': Value('bool'), 'mysql_db_name': Value('string'), 'contains_error_recovery': Value('bool')}}
because column names don't match
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1347, in compute_config_parquet_and_info_response
parquet_operations = convert_to_parquet(builder)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 980, in convert_to_parquet
builder.download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 884, in download_and_prepare
self._download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 947, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1736, in _prepare_split
for job_id, done, content in self._prepare_split_single(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1889, in _prepare_split_single
raise DatasetGenerationCastError.from_cast_error(
datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 9 new columns ({'gold_sql', 'question_en', 'difficulty', 'tags', 'mysql_db_name', 'task_id', 'protected_literals', 'execution_validation', 'sql_tables'}) and 3 missing columns ({'id', 'meta', 'messages'}).
This happened while the json dataset builder was generating data using
hf://datasets/acomagu/dbbench-mysql-synth/tasks_train.jsonl (at revision 4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d), [/tmp/hf-datasets-cache/medium/datasets/36054225742639-config-parquet-and-info-acomagu-dbbench-mysql-syn-796e265a/hub/datasets--acomagu--dbbench-mysql-synth/snapshots/4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/messages_train.jsonl (origin=hf://datasets/acomagu/dbbench-mysql-synth@4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/messages_train.jsonl), /tmp/hf-datasets-cache/medium/datasets/36054225742639-config-parquet-and-info-acomagu-dbbench-mysql-syn-796e265a/hub/datasets--acomagu--dbbench-mysql-synth/snapshots/4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/tasks_train.jsonl (origin=hf://datasets/acomagu/dbbench-mysql-synth@4bee0f182e9ed2ddf42e7bf3e764cf15e80f9d8d/tasks_train.jsonl)]
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
id string | db_id string | domain string | messages list | meta dict |
|---|---|---|---|---|
ecommerce_0001_t0017 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "hard",
"tags": [
"having",
"join",
"group_by"
],
"sql_tables": [
"orders",
"customers"
],
"gold_sql": "SELECT c.`region`, COUNT(*) AS order_count FROM `orders` o JOIN `customers` c ON o.`customer_id` = c.`customer_id` GROUP BY c.`region` HAVING COUNT(*) > 30 ORDER BY ord... |
ecommerce_0001_t0002 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"single_table",
"equality"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `status` = 'pending';",
"final_answer": [
"62"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysql":... |
ecommerce_0001_t0007 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"distinct",
"single_table"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT DISTINCT `status` FROM `orders` ORDER BY `status` ASC;",
"final_answer": [
"cancelled",
"completed",
"pending",
"refunded"
],
"format": "dbbench_style_text_intera... |
ecommerce_0001_t0010 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"avg",
"filter"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT ROUND(AVG(`list_price`), 2) AS avg_list_price FROM `products` WHERE `category` = 'Books';",
"final_answer": [
"455.3"
],
"format": "dbbench_style_text_interaction",
"validated_on_my... |
ecommerce_0001_t0012 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0001_t0016 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"topk",
"join",
"aggregation"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT p.`name` AS product_name, ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id... |
ecommerce_0001_t0009 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"avg",
"filter"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT ROUND(AVG(`list_price`), 2) AS avg_list_price FROM `products` WHERE `category` = 'Food';",
"final_answer": [
"363.73"
],
"format": "dbbench_style_text_interaction",
"validated_on_my... |
ecommerce_0001_t0013 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0001_t0015 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0001_t0005 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"date_filter"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS completed_order_count FROM `orders` WHERE `status` = 'completed' AND YEAR(`order_date`) = 2025;",
"final_answer": [
"113"
],
"format": "dbbench_style_text_interaction... |
ecommerce_0001_t0006 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"group_by",
"order_by"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT `category`, COUNT(*) AS product_count FROM `products` GROUP BY `category` ORDER BY product_count DESC, `category` ASC;",
"final_answer": [
"Sports | 16",
"Books | 15",
"Hom... |
ecommerce_0001_t0014 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0001_t0003 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"single_table",
"equality"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `status` = 'cancelled';",
"final_answer": [
"28"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysql... |
ecommerce_0001_t0004 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"date_filter"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS completed_order_count FROM `orders` WHERE `status` = 'completed' AND YEAR(`order_date`) = 2024;",
"final_answer": [
"101"
],
"format": "dbbench_style_text_interaction... |
ecommerce_0001_t0019 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"date_range",
"count"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `order_date` >= '2025-01-01' AND `order_date` < '2025-02-01';",
"final_answer": [
"14"
],
"format": "dbbench_style_text_interaction",... |
ecommerce_0001_t0001 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"single_table",
"equality"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `status` = 'completed';",
"final_answer": [
"214"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysq... |
ecommerce_0001_t0008 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"avg",
"filter"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT ROUND(AVG(`list_price`), 2) AS avg_list_price FROM `products` WHERE `category` = 'Home';",
"final_answer": [
"372.77"
],
"format": "dbbench_style_text_interaction",
"validated_on_my... |
ecommerce_0001_t0011 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"group_by",
"count"
],
"sql_tables": [
"orders",
"customers"
],
"gold_sql": "SELECT c.`region`, COUNT(*) AS order_count FROM `orders` o JOIN `customers` c ON o.`customer_id` = c.`customer_id` GROUP BY c.`region` ORDER BY order_count DESC, c.`re... |
ecommerce_0001_t0018 | ecommerce_0001 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "hard",
"tags": [
"subquery",
"having",
"join"
],
"sql_tables": [
"products",
"order_items"
],
"gold_sql": "SELECT p.`name` FROM `products` p JOIN `order_items` oi ON p.`product_id` = oi.`product_id` GROUP BY p.`product_id`, p.`name` HAVING AVG(oi.`unit_price`) > (SELECT ... |
school_0002_t0009 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"count",
"join",
"filter"
],
"sql_tables": [
"enrollments",
"students"
],
"gold_sql": "SELECT COUNT(*) AS enrollment_count FROM `enrollments` e JOIN `students` s ON e.`student_id` = s.`student_id` WHERE s.`department` = 'Finance';",
"final_answer": [... |
school_0002_t0001 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"group_by",
"count"
],
"sql_tables": [
"students"
],
"gold_sql": "SELECT `department`, COUNT(*) AS student_count FROM `students` GROUP BY `department` ORDER BY student_count DESC, `department` ASC;",
"final_answer": [
"Support | 36",
"Engineering | 33"... |
school_0002_t0004 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"filter"
],
"sql_tables": [
"students"
],
"gold_sql": "SELECT COUNT(*) AS student_count FROM `students` WHERE `enrollment_year` = 2024;",
"final_answer": [
"28"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysql": true,
"my... |
school_0002_t0008 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"topk",
"avg",
"join"
],
"sql_tables": [
"students",
"enrollments"
],
"gold_sql": "SELECT s.`name` AS student_name, ROUND(AVG(e.`score`), 2) AS avg_score FROM `students` s JOIN `enrollments` e ON s.`student_id` = e.`student_id` GROUP BY s.`student_id`,... |
school_0002_t0010 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"count",
"join",
"filter"
],
"sql_tables": [
"enrollments",
"students"
],
"gold_sql": "SELECT COUNT(*) AS enrollment_count FROM `enrollments` e JOIN `students` s ON e.`student_id` = s.`student_id` WHERE s.`department` = 'HR';",
"final_answer": [
... |
school_0002_t0012 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "hard",
"tags": [
"subquery",
"having",
"join"
],
"sql_tables": [
"enrollments",
"courses"
],
"gold_sql": "SELECT c.`course_name` FROM `enrollments` e JOIN `courses` c ON e.`course_id` = c.`course_id` GROUP BY c.`course_id`, c.`course_name` HAVING AVG(e.`score`) > (SELECT... |
school_0002_t0003 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"filter"
],
"sql_tables": [
"students"
],
"gold_sql": "SELECT COUNT(*) AS student_count FROM `students` WHERE `enrollment_year` = 2023;",
"final_answer": [
"27"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysql": true,
"my... |
school_0002_t0011 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "hard",
"tags": [
"having",
"join",
"count"
],
"sql_tables": [
"courses",
"course_instructors"
],
"gold_sql": "SELECT c.`course_name`, COUNT(ci.`instructor_id`) AS instructor_count FROM `courses` c JOIN `course_instructors` ci ON c.`course_id` = ci.`course_id` GROUP BY c.... |
school_0002_t0005 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"avg",
"group_by"
],
"sql_tables": [
"enrollments",
"courses"
],
"gold_sql": "SELECT c.`course_name`, ROUND(AVG(e.`score`), 2) AS avg_score FROM `enrollments` e JOIN `courses` c ON e.`course_id` = c.`course_id` GROUP BY c.`course_id`, c.`course... |
school_0002_t0007 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"avg",
"term_filter"
],
"sql_tables": [
"enrollments",
"students"
],
"gold_sql": "SELECT s.`department`, ROUND(AVG(e.`score`), 2) AS avg_score FROM `enrollments` e JOIN `students` s ON e.`student_id` = s.`student_id` WHERE e.`term` = '2024-Spri... |
school_0002_t0002 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"filter"
],
"sql_tables": [
"students"
],
"gold_sql": "SELECT COUNT(*) AS student_count FROM `students` WHERE `enrollment_year` = 2022;",
"final_answer": [
"46"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysql": true,
"my... |
school_0002_t0006 | school_0002 | school | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"avg",
"term_filter"
],
"sql_tables": [
"enrollments",
"students"
],
"gold_sql": "SELECT s.`department`, ROUND(AVG(e.`score`), 2) AS avg_score FROM `enrollments` e JOIN `students` s ON e.`student_id` = s.`student_id` WHERE e.`term` = '2025-Spri... |
ecommerce_0004_t0018 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "hard",
"tags": [
"subquery",
"having",
"join"
],
"sql_tables": [
"products",
"order_items"
],
"gold_sql": "SELECT p.`name` FROM `products` p JOIN `order_items` oi ON p.`product_id` = oi.`product_id` GROUP BY p.`product_id`, p.`name` HAVING AVG(oi.`unit_price`) > (SELECT ... |
ecommerce_0004_t0007 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"distinct",
"single_table"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT DISTINCT `status` FROM `orders` ORDER BY `status` ASC;",
"final_answer": [
"cancelled",
"completed",
"pending",
"refunded"
],
"format": "dbbench_style_text_intera... |
ecommerce_0004_t0012 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0004_t0013 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0004_t0019 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"date_range",
"count"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `order_date` >= '2025-01-01' AND `order_date` < '2025-02-01';",
"final_answer": [
"16"
],
"format": "dbbench_style_text_interaction",... |
ecommerce_0004_t0015 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0004_t0011 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"group_by",
"count"
],
"sql_tables": [
"orders",
"customers"
],
"gold_sql": "SELECT c.`region`, COUNT(*) AS order_count FROM `orders` o JOIN `customers` c ON o.`customer_id` = c.`customer_id` GROUP BY c.`region` ORDER BY order_count DESC, c.`re... |
ecommerce_0004_t0005 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"date_filter"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS completed_order_count FROM `orders` WHERE `status` = 'completed' AND YEAR(`order_date`) = 2025;",
"final_answer": [
"103"
],
"format": "dbbench_style_text_interaction... |
ecommerce_0004_t0017 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "hard",
"tags": [
"having",
"join",
"group_by"
],
"sql_tables": [
"orders",
"customers"
],
"gold_sql": "SELECT c.`region`, COUNT(*) AS order_count FROM `orders` o JOIN `customers` c ON o.`customer_id` = c.`customer_id` GROUP BY c.`region` HAVING COUNT(*) > 30 ORDER BY ord... |
ecommerce_0004_t0010 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"avg",
"filter"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT ROUND(AVG(`list_price`), 2) AS avg_list_price FROM `products` WHERE `category` = 'Books';",
"final_answer": [
"447.81"
],
"format": "dbbench_style_text_interaction",
"validated_on_m... |
ecommerce_0004_t0016 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"topk",
"join",
"aggregation"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT p.`name` AS product_name, ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id... |
ecommerce_0004_t0001 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"single_table",
"equality"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `status` = 'completed';",
"final_answer": [
"197"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysq... |
ecommerce_0004_t0008 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"avg",
"filter"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT ROUND(AVG(`list_price`), 2) AS avg_list_price FROM `products` WHERE `category` = 'Home';",
"final_answer": [
"422.09"
],
"format": "dbbench_style_text_interaction",
"validated_on_my... |
ecommerce_0004_t0014 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"join",
"sum",
"date_filter"
],
"sql_tables": [
"orders",
"order_items",
"products"
],
"gold_sql": "SELECT ROUND(SUM(oi.`quantity` * oi.`unit_price`), 2) AS total_sales FROM `orders` o JOIN `order_items` oi ON o.`order_id` = oi.`order_id` JOIN `pro... |
ecommerce_0004_t0003 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"single_table",
"equality"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `status` = 'cancelled';",
"final_answer": [
"32"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysql... |
ecommerce_0004_t0009 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"avg",
"filter"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT ROUND(AVG(`list_price`), 2) AS avg_list_price FROM `products` WHERE `category` = 'Sports';",
"final_answer": [
"461.88"
],
"format": "dbbench_style_text_interaction",
"validated_on_... |
ecommerce_0004_t0004 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"date_filter"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS completed_order_count FROM `orders` WHERE `status` = 'completed' AND YEAR(`order_date`) = 2024;",
"final_answer": [
"94"
],
"format": "dbbench_style_text_interaction"... |
ecommerce_0004_t0002 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"count",
"single_table",
"equality"
],
"sql_tables": [
"orders"
],
"gold_sql": "SELECT COUNT(*) AS order_count FROM `orders` WHERE `status` = 'pending';",
"final_answer": [
"68"
],
"format": "dbbench_style_text_interaction",
"validated_on_mysql":... |
ecommerce_0004_t0006 | ecommerce_0004 | ecommerce | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"group_by",
"order_by"
],
"sql_tables": [
"products"
],
"gold_sql": "SELECT `category`, COUNT(*) AS product_count FROM `products` GROUP BY `category` ORDER BY product_count DESC, `category` ASC;",
"final_answer": [
"Books | 16",
"Sports | 16",
"Foo... |
diplomatic_0006_t0010 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"distinct",
"quoted_identifier"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT DISTINCT `Title` FROM `US Ambassadors and Envoy Extraordinary to Colombia` ORDER BY `Title` ASC;",
"final_answer": [
"Ambassador"... |
diplomatic_0006_t0009 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "medium",
"tags": [
"group_by",
"quoted_identifier"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Appointed by`, COUNT(*) AS cnt FROM `US Ambassadors and Envoy Extraordinary to Colombia` GROUP BY `Appointed by` ORDER BY cnt DESC, ... |
diplomatic_0006_t0006 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Representative` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Presentation of Credentials` = 'October 9, 2003'... |
diplomatic_0006_t0002 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality",
"single_table"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Presentation of Credentials` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Termination of ... |
diplomatic_0006_t0008 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Representative` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Presentation of Credentials` = 'February 4, 2009... |
diplomatic_0006_t0001 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality",
"single_table"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Presentation of Credentials` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Termination of ... |
diplomatic_0006_t0007 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Representative` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Presentation of Credentials` = 'November 26, 198... |
diplomatic_0006_t0004 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality",
"single_table"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Presentation of Credentials` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Termination of ... |
diplomatic_0006_t0005 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality",
"single_table"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Presentation of Credentials` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Termination of ... |
diplomatic_0006_t0003 | diplomatic_0006 | diplomatic | [
{
"role": "user",
"content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\n\nYou have to explain the problem and your solution to me and write down your thoughts.\nAfter thinking and explaining thoroughly, every round you can choose to operate... | {
"difficulty": "easy",
"tags": [
"quoted_identifier",
"text_equality",
"single_table"
],
"sql_tables": [
"US Ambassadors and Envoy Extraordinary to Colombia"
],
"gold_sql": "SELECT `Presentation of Credentials` FROM `US Ambassadors and Envoy Extraordinary to Colombia` WHERE `Termination of ... |
End of preview.
DBBench-Style MySQL Synthetic SFT Dataset (English)
This directory contains a DBBench-style (MySQL / English) synthetic dataset for SFT. It is designed for:
- SFT training in a DBBench-like interaction format
- Auditing data quality (SQL / answers / difficulty / distribution)
- Reproducing and debugging queries on MySQL
- Future DAgger / hard example mining
This dataset is synthetic and not the official DBBench data. It is meant to teach DBBench-style skills (SQL generation, result reading, format adherence, and recovery behavior).
Directory Structure
catalog/manifest.jsondata.jsonlmessages_val.jsonlmysql_seed/tasks_all.jsonltasks_train.jsonltask_summary.csvtasks_val.jsonl
What to Use for What
For SFT training (main inputs)
data.jsonl(train)messages_val.jsonl(validation)
For audit / analysis (structured metadata)
tasks_train.jsonltasks_val.jsonltasks_all.jsonltask_summary.csv
For reproduction / debugging (reloadable into MySQL)
mysql_seed/
For schema inspection / quality checks
catalog/
For generation conditions / reproducibility
manifest.json
1. data.jsonl / messages_val.jsonl
Role
These are the primary SFT inputs. Each line is a JSON object with a messages array.
Key characteristics
- DBBench-style conversation format
- English questions / reasoning / final answers
Action: Operation(SQL execution)- User-side messages include raw MySQL-like responses
Action: Answer/Final Answer: [...]- Some samples include real error → fix → re-run trajectories
Notes
Some notebooks will ignore messages_val.jsonl and do their own split. In that case, a common workflow is:
- Upload
data.jsonlto HF - Let the notebook split with
SFT_VAL_RATIO
2. tasks_train.jsonl / tasks_val.jsonl / tasks_all.jsonl
Role
Structured metadata for auditing and analysis. Easier to work with than messages_*.
Typical fields include:
task_id,db_id,domainquestion_en,gold_sqldifficulty,tags,sql_tablesexecution_validation.final_answer
Common uses
- SQL validity checks
- Difficulty / domain distribution
- Hard example mining (e.g.,
subquery,having,quoted_identifier) - Quick evaluation after SFT
3. task_summary.csv
A human-readable summary for quick inspection in Excel / Sheets / pandas:
- domain balance
- difficulty balance
- error recovery ratio
- rowcount distribution
- surface-level duplication checks
4. catalog/
Schema metadata per db_id (table/column info and row counts), useful for:
- Understanding schemas
- Auditing column types
- Prompt design and future data generation
5. mysql_seed/
MySQL re-import SQL (DDL + INSERT) for each db_id:
- Reproduce specific tasks
- Debug model SQL with real execution
- Rebuild datasets for DAgger
Example:
mysql -u root -p dbbench_syn_ecommerce_0001 < mysql_seed/ecommerce_0001.sql
6. manifest.json
Generation conditions for reproducibility and auditing:
- generation time
- dialect
n_dbs_generated,n_tasks_total- train/val sizes
- domains
- error recovery ratio
- db_id splits
Minimal Share Set
If you only need SFT training:
data.jsonlmessages_val.jsonlmanifest.json
If you also want audit:
- plus
tasks_train.jsonl,tasks_val.jsonl,task_summary.csv
If you need full reproduction:
- plus
catalog/andmysql_seed/
Quick sanity checks
wc -l data.jsonl messages_val.jsonl
head -n 2 data.jsonl
wc -l tasks_all.jsonl tasks_train.jsonl tasks_val.jsonl
head -n 2 tasks_train.jsonl
head -n 20 task_summary.csv
Notes and Limitations
- Synthetic dataset; not official DBBench data.
- Train/val split is done by
db_idto reduce leakage across databases. messages_val.jsonlmay be unused if your training pipeline re-splits train data.
If you find gaps (e.g., too few hard cases, null/empty results, edge cases), consider regenerating with adjusted parameters.
- Downloads last month
- 24