# ジョブの作成方法

## モデルの選択

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/09/Create-New-Jobs-Select-Model.png" alt=""><figcaption></figcaption></figure>

**モデルハブ**からモデルを選択する方法は2通りあります：

* **モデルカタログ：**&#x44;eepSeek、Gemma、Llama、Qwenなど、様々なプロバイダーからのモデルソ  \
  ースを保管するリポジトリ。
* **プライベートモデル**：ユーザー所有モデルおよび微調整済みモデルのリポジトリ。これらのモ  \
  デルには**必要なファイルがすべてアップロード済みである**必要があります。互換性と準備完了を  \
  示す**特定のタグ**を含める必要があります。

{% hint style="info" %}
注記：テストジョブで使用するには、モデルは以下の条件を満たす必要があります：

* **モデルタイプ：**
  * LLM: テキスト入力のみ対応
  * VLM: テキストと画像の両方の入力に対応
* **モデルサイズ** > 0
* 学習段階: 必ずインストラクション調整済みであるこ  と
  {% endhint %}

例:

| モデル名                                                  | モデル バージョ ン  | モデル ファミ リー | モデルタイプ                                      | モデルサイズ                                     | 学習 ステージ                                                   |
| ----------------------------------------------------- | ----------- | ---------- | ------------------------------------------- | ------------------------------------------ | --------------------------------------------------------- |
| ft\_Llama-3.1-8B\_20250508124054\_samples-15d5e2f6fe7 | 15d5e2f6fe7 | Llama      | <p>LLM<br><br><strong>(→ 利用可能)</strong></p> | <p>8B<br><br><strong>(→ 利用可能)</strong></p> | <p>Instruction-tuned<br><br><strong>(→ 利用可能)</strong></p> |

## テストスイートの選択

モデルをテストする適切なテストスイートを選択してください。

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/09/Create-New-Job-Select-Test-Suite.png" alt=""><figcaption></figcaption></figure>

以下のテストスイートを提供します：

| テストスイート                                                                     | 目的                                                                                                                                                     | 最適対象                               |
| --------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------- |
| 標準                                                                          | 独自のデータセットを使用したモ&#xD;デル評価。                                                                                                                              | 内部ベンチマーク、特定分野のタ&#xD;スク（例：金融、医療...） |
| Nejumi Leaderboard 3                                                        | 特に日本語タスク向けのLLMをベン&#xD;チマーク。参照: [Nejumi Leaderboard 3](https://wandb.ai/wandb-japan/llm-leaderboard3/reports/Nejumi-LLM-Leaderboard3--Vmlldzo4NDkwODEy) | 日本語タスクにおけるLLMの比較&#xD;。             |
| LM 評価ハーネス                                                                   | 多くの標準的なNLPベンチマーク&#xD;で言語モデルを評価するための&#xD;汎用フレームワーク。参照: [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness)                     | 英語中心のLLMを評価し、研究文&#xD;献との比較可能性を確保   |
| VLM 評価キッ                                                                    | <p>マルチモデルタスクにおけ                                                                                                                                        |                                    |
| <br>るVLMs（視覚言語モデル                                                           |                                                                                                                                                        |                                    |
| ）の評価。                                                                       |                                                                                                                                                        |                                    |
| 参照: <a href="https://github.com/open-compass/VLMEvalKit">VLMEvalKit</a></p> | マルチモーダルモデルのテスト                                                                                                                                         |                                    |

{% tabs %}
{% tab title="標準" %}

## データ形式の選択

**テストスイート = 標準**を選択する場合にのみデータ形式を選択してください

| サポートされているデータ形式  | サポートされているファイル形式                                             | サポートされているファイルサイズ |
| --------------- | ----------------------------------------------------------- | ---------------- |
| Alpaca          | <p>- CSV<br>- JSON<br>- JSONLINES<br>- ZIP<br>- PARQUET</p> | 制限100MB          |
| ShareGPT        | <p>- JSON<br>- JSONLINES<br>- ZIP<br>- PARQUET</p>          | 制限 100MB         |
| ShareGPT\_Image | <p>- ZIP<br>- PARQUET</p>                                   | 制限100MB          |

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/09/Data-format.png" alt=""><figcaption></figcaption></figure>

現在テスト用にサポートしているデータ形式は以下の通りです：

#### a/ Alpaca <a href="#contentify_0" id="contentify_0"></a>

**Alpaca**、教師あり微調整タスク向けに、入力と出力のペアを用いた指示順守形式でモデルを微調整するために、非常にシンプルな構造を採用しています。基本構造は以下の通りです：

* **Instruction**:モデルが実行すべき特定のタスクや要求を含む文字列。
* **Input**: モデルがタスクを実行するために処理する必要がある情報を含む文字列。
* **Output**: 指示と入力を処理して生成される、モデルが返すべき結果を表す文字列。

**詳細な構造:**

```json
[
   {
      “instruction”: “string”,
      “input”: “string”,
      “output” “string”
  }
]
```

**例:**

```json
[
    {
        "instruction": "In this task, you are given Wikipedia articles on a range of topics as passages and a question from the passage. We ask you to answer the question by classifying the answer as 0 (False) or 1 (True)\n\nNow complete the following instance -\nInput: Passage: Missouri River -- Tonnage of goods shipped by barges on the Missouri River has seen a serious decline from the 1960s to the present. In the 1960s, the USACE predicted an increase to 12 million short tons (11 Mt) per year by 2000, but instead the opposite has happened. The amount of goods plunged from 3.3 million short tons (3.0 Mt) in 1977 to just 1.3 million short tons (1.2 Mt) in 2000. One of the largest drops has been in agricultural products, especially wheat. Part of the reason is that irrigated land along the Missouri has only been developed to a fraction of its potential. In 2006, barges on the Missouri hauled only 200,000 short tons (180,000 t) of products which is equal to the amount of daily freight traffic on the Mississippi.\nQuestion: is there barge traffic on the missouri river\nOutput:",
        "input": "",
        "output": "1"
    },
    {
        "instruction": "CARAÏBES Communauté des Caraïbes (CARICOM) Aperçu Les 15 membres de la Communauté des Caraïbes (CARICOM) sont Antigua et Barbuda, les Bahamas, la Barbade, le Belize, la République dominicaine, la Grenade, la Guyane, Haïti, la Jamaïque, Saint-Kitts-et-Nevis, Sainte-Lucie, Saint Vincent et les Grenadines, le Suriname, Trinité-et-Tobago, ainsi que Montserrat (sous la dépendance du Royaume-Uni).\n\nWhich language is this?",
        "input": "",
        "output": "French"
    }
]
```

**サンプル:** <https://github.com/fpt-corp/ai-studio-samples/tree/main/sample-datasets/alpaca>

**サポートされているファイル形式:** .csv, .json, .jsonlines, .zip, .parquet

#### b/ ShareGPT <a href="#contentify_1" id="contentify_1"></a>

ShareGPTは、ユーザーとAIアシスタント間の複数ターンにわたる会話（やり取りのあるチャット\
）を表現するために設計されています。これは、複数ターンにわたる文脈のある会話を処理する必\
要がある対話システムやチャットボットのモデルをトレーニングまたは微調整する際に一般的に使\
用されます。

Each data sample consists of a `conversations` array, where each turn in the chat includes:

* **from**: 発言者 — 通常`"human"` または`"system"`.
* **value**: その話者からの実際のメッセージテキスト。

**詳細な構造:**

```json
[
   {
      “conversations”: [
         {
            “from”: “string”,
            “value”: “string”
         }
      ]
   }
]
```

**例:**

```json
[
    {
        "conversations": [
            {
                "from": "system",
                "value": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."
            },
            {
                "from": "human",
                "value": "Select the latest conversation state of the provided conversation history. Response only with the conversation state index.\n\n# Context\n- Hôm nay: Thứ tư, 19/02\n- Họ tên khách hàng: LÊ HOÀNG LOAN\n- Sản phẩm vay: Điện thoại Samsung\n- Số tiền cần thanh toán kỳ này: 1515000\n- Ngày đến hạn thanh toán kỳ này: 16/02\n- Số ngày đã trễ hạn thanh toán: 3\n- Hạn thanh toán cuối: 21/02\n\n# Conversation history\nTổng đài viên: Dạ có phải Anh LOAN đang nghe máy không ạ?\nNgười nhận cuộc gọi: có gì không em\n\n# Conversation states\n1) Xác nhận danh tính của mình là khách hàng - Ví dụ: \"ừ ai đấy\", \"phải chị\", \"đúng rồi ai gọi thế\", \"ờ vâng\", \"dạ vâng\", \"Anh LOAN đây\", \"sao thế\", \"mình nghe ạ\", \"có chuyện gì\", \"nói đi\"\n2) Hỏi danh tính của tổng đài viên - Ví dụ: \"ai đấy\", \"bạn tên gì\", \"bạn là ai\", \"công ty gì\", \"lừa đảo à\"\n3) Xác nhận là người thân (như ông, bà, bố, mẹ, cô, dì, chú, bác, anh, chị, em, vợ, con) của khách hàng hoặc có quen biết khách hàng - Ví dụ: \"anh là anh nó\", \"mình là chị của LOAN\", \"bác là mẹ nó nghe máy hộ nó đây\", \"cô là dì nó\", \"em là người nhà của Anh LOAN\", \"bạn ấy ra ngoài rồi mình là bạn của bạn ấy\", \"à Anh làm cùng cơ quan với nó\", \"mình là bạn nó\", \"quen biết qua thôi\"\n4) Thông báo không quen biết khách hàng hoặc thông báo nhầm số / nhầm người hoặc thông báo khách hàng đi vắng / chỉ nghe máy hộ và không cung cấp thông tin về mối quan hệ với khách hàng - Ví dụ: \"có quen biết gì đâu\", \"mình không biết bạn đấy\", \"ủa số này của tôi mà có biết đấy là ai đâu\", \"tôi nghe hộ bạn ấy ra ngoài rồi\", \"không nhầm rồi em ơi\", \"LOAN nào nhỉ\", \"LOAN á không phải rồi\", \"ai cơ\"\n5) Đồng ý thanh toán chung chung hoặc thông báo thời điểm hoặc số tiền sẽ thanh toán - Ví dụ: \"à ờ\", \"đúng rồi\", \"biết rồi nhé\", \"lát nữa nhé\", \"tý nữa giả nhé\", \"mai Anh đóng\", \"để tôi sắp xếp\", \"để hỏi nhờ người nhà xem sao\", \"giờ chưa có nhưng mai sẽ trả\", \"ngày kia trả được không nhỉ\"\n6) Đặt câu hỏi hoặc thắc mắc về khoản nợ, số hotline, phương thức thanh toán, ngày tháng - Ví dụ: \"tôi vay sản phẩm nào ấy nhỉ\", \"Anh cần trả bao nhiêu tiền ấy nhỉ\", \"Anh chưa biết cấch thanh toán như thế nào ấy\", \"hợp đồng của tôi còn bao nhiêu kỳ nữa\", \"ơ hạn thanh toán là ngày mùng sáu hàng tháng mà nhỉ\", \"sao lại nhiều tiền thế nhỉ\", \"sao tháng này cần đóng nhiều tiền hơn tháng trước\", \"lãi suất quá hạn là bao nhiêu hả em\", \"Anh đóng luôn mấy kỳ còn lại được không\", \"hôm nay ngày mấy nhỉ\", \"số điện thoại phản ánh là số mấy\", \"không biết đóng ở cửa hàng nào\"\n7) Báo bận hoặc đang không tiện nghe máy hoặc hẹn gọi lại sau - Ví dụ: \"Anh đang bận nhé\", \"tôi đang đi làm bạn ơi\", \"giờ không tiện lắm gọi lại sau đi\", \"tôi đang ngoài đường gọi lại sau nhé\"\n8) Phàn nàn hoặc khiếu nại do bị gọi nhiều - Ví dụ: \"bên em gọi nhiều thế\", \"sao một ngày gọi chục cuộc thế hả em\", \"đừng có gọi nữa mệt lắm rồi\"\n9) Không nghe rõ hoặc yêu cầu nhắc lại thông tin - Ví dụ: \"alo em nói gì thế\", \"Anh chưa nghe được em ơi\", \"ừ cái gì ấy nhỉ\", \"bạn nói lại giúp mình với\", \"ồn quá mình không nghe được ấy\", \"không nói gì à\"\n10) Thông báo khách hàng đã qua đời - Ví dụ: \"bạn ấy bị tại nạn mới mất rồi\", \"nó qua đời rồi em ạ\", \"Anh LOAN chết rồi bạn ơi\"\n11) Muốn gặp tổng đài viên - Ví dụ: \"cho tôi nói chuyện với tổng đài bên bạn nào\", \"Anh muốn gặp tổng đài viên\", \"chuyển máy cho tổng đài xử lý được không\"\n12) Trả lời sai trọng tâm của câu hỏi trước đó hoặc cung cấp thông tin chưa rõ ràng hoặc cần xác nhận lại thông tin hoặc đặt yêu cầu ngoài phạm vi hỗ trợ\n\n# Answer:"
            }
        ]
    }
]
[
    {
        "conversations": [
            {
                "from": "human",
                "value": "Summarize the main ideas of Jeff Walker's Product Launch Formula into bullet points as it pertains to a growth marketing agency implementing these strategies and tactics for their clients..."
            },
            {
                "from": "gpt",
                "value": "Here are the main ideas of Jeff Walker's Product Launch Formula that can be applied by a growth marketing agency for their clients:\n\n1. Identify the target audience and their needs: Understand the ideal customer for the product or service, and create a messaging that resonates with them.\n2. Pre-launch: Build anticipation and excitement for the launch by creating buzz, gathering testimonials and case studies, and using social media to create awareness.\n3. Launch: Use a well-crafted launch sequence to maximize sales and conversions. This can include offering bonuses, creating scarcity, and using a deadline to create urgency.\n4. Post-launch: Follow up with customers, gather feedback, and continue to provide value to keep them engaged and loyal.\n5. Create a product suite: Once the initial product is successful, expand the offering by creating additional products or services that address other needs of the same audience.\n6. Continual optimization: Continually monitor and optimize the launch process and product suite to improve results.\n7. Build a community: Use the launch process to build a community of customers who are passionate about the product and can help spread the word.\n8. Use automation: Use technology and automation to streamline the launch process and improve efficiency."
            }
        ]
    }
]
```

**サンプル:** <https://github.com/fpt-corp/ai-studio-samples/tree/main/sample-datasets/sharegpt>

**サポートされているファイル形式:** .json, .jsonlines, .zip, .parquet

#### c/ ShareGPT\_Image <a href="#contentify_2" id="contentify_2"></a>

**ShareGPT\_Image** は、ShareGPT マルチターンチャット形式の拡張機能です。マルチモーダル学習、すなわち会話においてテキストと画像の両方を扱うモデルの学習に特化して設計されています。

これは、画像と自然言語を同時に処理する必要がある視覚言語モデル（VLMs）の微調整に使用されます。

構造は以下の通りです：

* 下の会話**ターン一覧** `"message"` (ShareGPTと同様).
* A field called `"image"` or `"image_path"` that points to the image used in the conversation (using format png, jpg, jpeg)

**注意:**

* 画像を表示させる必要があるチャットコンテンツには、必ず **`image`** トークンを含める必要があります。
* **複数の画像**がある場合：
  * 画像パス&#x306F;**`images`** 配列内で定義する必要があります。
  * チャットフロー内の画像の位置は、 **`image`**&#x30C8;ークンで示されます
  * チャット内の **`image`** トークンの数は、 **`images`** 配列内のアイテム数と一致する必要があります。
  * 画像は出現順にマッピングされ、各 `image` トークンは `images` 配列の対応する画像に置き換えられます。

**詳細な構造:**

```json
[
   {
      “message”: [
         {
            “role”: “string”, “content”: “<image>string”
         }
      ],
      “images”: [
         “images/0.jpg”
      ]
   }
]
```

**例:**

```json
[
    {
        "messages": [
            {
                "role": "user",
                "content": "<image>How many baseball players are visible in the image?"
            },
            {
                "role": "assistant",
                "content": "There are three baseball players visible in the image."
            }
        ],
        "images": [
            "images/0.jpg"
        ]
    },
    {
        "messages": [
            {
                "role": "user",
                "content": "What is the man wearing in the image?<image>"
            },
            {
                "role": "assistant",
                "content": "The man in the image is wearing chaps, a cowboy hat, and is dressed like a cowboy."
            }
        ],
        "images": [
            "images/1.jpg"
        ]
    },
    {
        "messages": [
            {
                "role": "user",
                "content": "<image>Explain the visual content of the image in great detail."
            },
            {
                "role": "assistant",
                "content": "The image presents a view of a hotel room, showing both the bathroom and bedroom areas. In the bathroom, there is a white sink under a mirror, accompanied by several bottles placed on the counter, and two cups nearby. \n\nLooking through a doorway into the bedroom area, a large bed can be seen dominating the space. A chair is also visible within the room, situated near the foot of the bed. The hair drier is located in the foreground, implying that it likely belongs to the bathroom area as well. The arrangement of the objects and the furniture suggests a comfortable and well-equipped hotel room."
            }
        ],
        "images": [
            "images/2.jpg"
        ]
    }
]
```

**サンプル**: <https://github.com/fpt-corp/ai-studio-samples/tree/main/sample-datasets/sharegpt-image>

**サポートされているファイル形式：**.zip, .parquet

## Select Test Data

<figure><img src="/files/n1bBNoZRZWztzFyr3Ygs" alt=""><figcaption></figcaption></figure>

You have two ways to transfer the **Test data**:

* Connect to Data Hub
  1. Click **Data Hub**
  2. Select a connection or dataset from the Data Hub. **Notice:** Ensure the dataset is compatible with the selected format.
  3. (Optional) Click **Open Data Hub** to preview or manage datasets.
  4. (Optional) Click **Reload icon** to update connection and dataset list.
  5. Follow the detailed guide Data Hub

| Supported data format | Supported file format                                       | Supported file size |
| --------------------- | ----------------------------------------------------------- | ------------------- |
| Alpaca                | <p>- CSV<br>- JSON<br>- JSONLINES<br>- ZIP<br>- PARQUET</p> | Limit 100MB         |
| ShareGPT              | <p>- JSON<br>- JSONLINES<br>- ZIP<br>- PARQUET</p>          | Limit 100MB         |
| ShareGPT\_Image       | <p>- ZIP<br>- PARQUET</p>                                   | Limit 100MB         |

**Notice:** Ensure the file matches the selected data format

* Upload a file
  1. Default value Upload file
  2. Choose a local file from your computer.
  3. (Optional) Click **Download sample** to see an example of the expected format.

## Test Criteria

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/09/Test-criteria.png" alt=""><figcaption></figcaption></figure>

1. Click **Add & update** button
2. The **Tasks** window appears. Select the task type:
   * Text similarity: Measures similarity metrics between model outputs and reference texts.
3. Click **Next** to open the list of available metrics
4. Select one or more metrics
5. Click **Update** to apply changes

The following metrics of **Text similarity** are available:

| Test criteria / Metric | How it tests                                                                                                                        | Best for                                          |
| ---------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------- |
| BLEU                   | Measures how precisely a model’s output matches reference text using n-gram overlap.                                                | Evaluating translation and short text similarity. |
| Fuzzy Match            | Measures how closely the model’s output resembles the reference text, allowing for minor differences in wording or order.           | Checking approximate correctness.                 |
| ROUGE-1                | Measures unigram (single word) overlap between model output and reference text.                                                     | Short summarization and text generation tasks.    |
| ROUGE-2                | Measures bigram (two-word sequence) overlap between model output and reference text.                                                | Evaluating contextual accuracy.                   |
| ROUGE-L                | Measures the longest common subsequence (LCS) between model output and reference text to capture fluency and word order similarity. | Longer text evaluation where structure matters.   |
| ROUGE-LSUM             | Measures LCS-based similarity across multiple sentences, suitable for evaluating longer summaries.                                  | Summarization tasks.                              |
| {% endtab %}           |                                                                                                                                     |                                                   |

{% tab title="その他" %}

## タスク

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/09/Tasks.png" alt=""><figcaption></figcaption></figure>

選択したテストスイートに応じて、以下のタスクを提供します：

| テストスイート              | タスク         | 説明                             |
| -------------------- | ----------- | ------------------------------ |
| Nejumi Leaderboard 3 | Jaster      | モデルの日本語理解・処理能力を測定する。           |
|                      | JBBQ        | 日本語の質問応答におけるLLMの社会的バイアスを測定する。  |
|                      | JtruthfulQA | 日本語の質問に対する模範解答の真実性を測定する。       |
| LM評価ハーネス             | ARC         | 小学校レベルの質問で科学的推論を測定する。          |
|                      | GSM8K       | 数学の文章題における多段階推論を測定する。          |
|                      | HellaSwag   | 文脈に応じた常識的推論を測定する。              |
|                      | HumanEval   | Pythonコード生成能力を測定する。            |
|                      | IFEval      | 指示に従う能力と有害な入力の拒否を測定する。         |
|                      | LAMBADA     | 長距離の文脈理解を測定する。                 |
|                      | MMLU        | 57の学術・専門分野における推論能力を測定する。       |
|                      | OpenBookQA  | 科学的な品質保証を事実と常識を用いて測定する。        |
|                      | PIQA        | 物理的な常識的推論を測定する。                |
|                      | SciQ        | 小学校・中学校レベル向け理科の多肢選択式問題の質を測定する。 |
|                      | TruthfulQA  | オープンドメイン質問応答における真実性の測定         |
|                      | Winogrande  | 代名詞の曖昧性解消タスクにおける意味理解を測定する。     |
| VLM評価キット             | ChartQA     | 図表に基づくデータ解釈および質問応答能力を測定する。     |
|                      | DocVQA      | 文書画像における質問応答性能を測定する。           |
|                      | InfoVQA     | 画像に埋め込まれた情報に基づいて質問応答を測定する。     |
|                      | MTVQA       | 多言語の視覚的テキスト質問応答性能を測定する。        |
|                      | OCRBench    | 様々なデータセットにおける光学式文字認識の精度を測定する。  |
| {% endtab %}         |             |                                |
| {% endtabs %}        |             |                                |

## パラメータの設定

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/09/Parameters.png" alt=""><figcaption></figcaption></figure>

パラメータを使用すると、テスト中のモデルの動作を調整できます。以下に各パラメータとその目的を説明します：

| 名称              | 説明                                                                                                                                    | 型        | サポートされる値      |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------------- |
| ログサンプル          | <p>モデルの出力とモデル                                                                                                                         |          |               |
| <br>に入力されたテキスト  |                                                                                                                                       |          |               |
| <br>が保存されます</p> | bool                                                                                                                                  | 真 / 偽    |               |
| 最大トークン数         | 生成するトークンの最大数                                                                                                                          | 整数       | (0, +∞)       |
| 少数のショット数        | <p>コンテキストに配置す                                                                                                                         |          |               |
| <br>る少数のショット例の  |                                                                                                                                       |          |               |
| <br>数。整数で指定する必  |                                                                                                                                       |          |               |
| <br>要があります。</p> | 整数                                                                                                                                    | \[0, +∞) |               |
| 温度              | サンプリングの温度                                                                                                                             | 浮動小数点数   | \[0, +∞)      |
| 繰り返しペナルティ       | <p>プロンプトと生成され たテキストに現れるか どうかに基づいて新し いトークンにペナルティ を課す浮動小数点数。</p><ul><li>値が 1 より大きい場合 新しいトークンを 奨励する。</li><li>値 < 1繰り返 しを奨励する 。</li></ul> | 浮動小数点数   | (0, 5)        |
| シード             | <p>再現性のための乱数                                                                                                                          |          |               |
| <br>シード</p>     | 整数                                                                                                                                    | \[0, +∞) |               |
| 上位K             | 考慮する上位トークンの&#xD;累積確率を制御する整数&#xD;。すべてのトークンを考&#xD;慮するには-1を設定しま&#xD;す。                                                                   | 整数       | -1 or (0, +∞) |
| 上位P             | 考慮対象となる上位トー&#xD;クンの累積確率を制御&#xD;する浮動小数点数。すべ&#xD;てのトークンを考慮する&#xD;には1に設定します。                                                             | 浮動小数点数   | (0, 1]        |

## 完了

<figure><img src="/files/RFh2yBnAEMTWONJBhJ25" alt=""><figcaption></figcaption></figure>

最後に、以下の条件を満たす一意のジョブ名（例: testj\_20250919145022）を入力する必要があります:

* 文字または数字で始まる
* アルファベット（a-z, A-Z）、数字（0-9）、アンダースコア「\_」、ハイフン「-」のみ使用
* 最大100文字
* 重複しない名前

最大200文字のオプションのメモ付きジョブ記述を行い、パイプラインが**成功**または**失敗した**際にメール通知（<noreply@fptcloud.com>）を受け取ります。


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-docs.fptcloud.com/ai-factory-guideline-jp/fpt-ai-studio/sbisu/moderutesuto-tesutojobu/chtoriaru/jobuno.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
