Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
6
52
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\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 o...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\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 o...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\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 o...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\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 o...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question.\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 o...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
[ { "role": "user", "content": "I will ask you a question, then you should help me operate a MySQL database with SQL to answer the question. You have to explain the problem and your solution to me and write down your thoughts. After thinking and explaining thoroughly, every round you can choose to operate or ...
[ { "role": "system", "content": "Interact with a household to solve a task. Imagine you are an intelligent agent in a household environment and your target is to perform actions to complete the task goal. At the beginning of your interactions, you will be given the detailed description of the current environ...
End of preview. Expand in Data Studio

Deepthinking ALFWorld & DBBench Spider v2

AgentBench 評価の 2 タスク(ALFWorld / DBBench)を統合した マルチタスク SFT 訓練データセット。 フォーマット検査・フィルタリング済みの 7,779 件を、サイズ比率に基づく等間隔インターリーブで結合。


Dataset Summary

Metric Value
Total rows 7,779
ALFWorld 4,884 (62.8%)
DBBench 2,895 (37.2%)
Avg messages per item 18.3
Columns messages
Interleave method 比率ベース等間隔マージ

Source Datasets

Source Rows Description
mark-22/Deepthinking-sft_alfworld_final1 4,884 ALFWorld タスク。GPT-OSS-120B で最初の THOUGHT に状況分析・常識推論・ステップ分解を挿入したデータ拡張版
mark-22/dbbench_spider_v4_mergeddata_final1 2,897 → 2,895 DBBench タスク。Spider 生成データ (1,697) + u-10bei クレンジング済みデータ (1,200) の統合。フォーマット検査で 2 件除外

Merge Pipeline

mark-22/Deepthinking-sft_alfworld_final1 (4,884)
  ↓ フォーマット検査: THOUGHT + ACTION パターン必須
  ↓ 除外: 0 件
  ↓ シャッフル (seed=42)
  ↓
  ├─────────────────────────────────────────────┐
  │  等間隔インターリーブ (サイズ比率ベース)      │
  ├─────────────────────────────────────────────┘
  ↓
mark-22/dbbench_spider_v4_mergeddata_final1 (2,897)
  ↓ フォーマット検査: Action: Operation/Answer 必須
  ↓ 除外: 2 件(フォーマット違反)
  ↓ シャッフル (seed=42)
  ↓
  → 7,779 件(ALF:DB ≈ 63:37)

Formatting Filters

ALFWorld

  • 全 assistant メッセージに THOUGHT:ACTION: の両方が含まれること
  • THOUGHT:ACTION: より前に出現すること

DBBench

  • "Ok." 等の承認応答はスキップ
  • それ以外の assistant メッセージに Action: Operation または Action: Answer が含まれること
  • 少なくとも 1 回は Action が実行されていること

Interleave Strategy

単純な連結ではなく、比率ベースの等間隔マージを採用:

  • 各データセットを独立シャッフル後、正規化位置 (i + 0.5) / N を付与
  • 全アイテムを正規化位置でソートし、ALFWorld と DBBench が均等に混ざるよう配置
  • 訓練時にタスクが偏らず、安定した学習を実現
結果のインターリーブパターン(先頭10件):
  [0] ALF  [1] DB  [2] ALF  [3] ALF  [4] DB
  [5] ALF  [6] DB  [7] ALF  [8] ALF  [9] DB

Conversation Structures

ALFWorld items

[system]    Interact with a household to solve a task...
[user]      You arrive in a room. You can see...
[assistant] THOUGHT: {AI-generated analysis} + {original thought}
            ACTION: {action command}
[user]      Environment response
...

DBBench items

[user]      I will ask you a question, then you should help me operate a MySQL database...
[assistant] Ok.
[user]      Question text
[assistant] Thought + Action: Operation ```sql ... ```
[user]      MySQL raw output
...
[assistant] ... Action: Answer  Final Answer: ["..."]

Usage

from datasets import load_dataset

ds = load_dataset("mark-22/Deepthinking-alfworld_and_dbbench_spider_v2", split="train")

for item in ds:
    messages = item["messages"]
    # Detect task type by first message role:
    #   system -> ALFWorld
    #   user   -> DBBench
    task_type = "alfworld" if messages[0]["role"] == "system" else "dbbench"

Merge Code

結合スクリプト全文(クリックで展開)
import os, re
from datasets import load_dataset, Dataset, Features, Value
from huggingface_hub import login

ds_alf = load_dataset("mark-22/Deepthinking-sft_alfworld_final1", split="train")
ds_db  = load_dataset("mark-22/dbbench_spider_v4_mergeddata_final1", split="train")

# Unify columns to "messages" only
ds_alf = ds_alf.select_columns(["messages"])
ds_db  = ds_db.select_columns(["messages"])

unified_features = Features({
    "messages": [{"role": Value("string"), "content": Value("string")}]
})

def fix_message_order(example):
    return {"messages": [
        {"role": msg["role"], "content": msg["content"]}
        for msg in example["messages"]
    ]}

ds_alf = ds_alf.map(fix_message_order, features=unified_features)
ds_db  = ds_db.map(fix_message_order, features=unified_features)

# Format validation
def is_valid_alfworld(example):
    for msg in example["messages"]:
        if msg["role"] == "assistant":
            content = msg["content"]
            t = re.search(r"THOUGHT\s*:", content, re.IGNORECASE)
            a = re.search(r"ACTION\s*:", content, re.IGNORECASE)
            if not t or not a or t.start() > a.start():
                return False
    return True

def is_valid_dbbench(example):
    has_action = False
    for msg in example["messages"]:
        if msg["role"] == "assistant":
            content = msg["content"].strip()
            if content.lower() in ["ok", "ok.", "understood", "understood.", "yes", "yes."]:
                continue
            if not re.search(r"Action:\s*(Operation|Answer)", content, re.IGNORECASE):
                return False
            has_action = True
    return has_action

ds_alf = ds_alf.filter(is_valid_alfworld)
ds_db  = ds_db.filter(is_valid_dbbench)

# Independent shuffle + ratio-based interleave
ds_alf = ds_alf.shuffle(seed=42)
ds_db  = ds_db.shuffle(seed=42)

alf_items = [((i + 0.5) / len(ds_alf), item) for i, item in enumerate(ds_alf)]
db_items  = [((i + 0.5) / len(ds_db),  item) for i, item in enumerate(ds_db)]
combined  = sorted(alf_items + db_items, key=lambda x: x[0])
merged_ds = Dataset.from_list(
    [item for _, item in combined], features=unified_features
)

merged_ds.push_to_hub("mark-22/Deepthinking-alfworld_and_dbbench_spider_v2")

License

Apache 2.0

Downloads last month
39

Models trained or fine-tuned on mark-22/Deepthinking-alfworld_and_dbbench_spider_v2