---
title: "Create training"
slug: "clovastudio-posttask"
tags: ["CLOVA Studio"]
updated: 2026-10-08T04:23:39Z
published: 2026-10-08T04:23:39Z
canonical: "api.ncloud-docs.com/clovastudio-posttask"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://api.ncloud-docs.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Create training

Available in Classic and VPC

Create a training. After the training you created is complete, you can call [Chat Completions API](/docs/en/clovastudio-chatcompletions) or [Chat Completions V3 API](/docs/en/clovastudio-chatcompletionsv3) to generate interactive sentences to see the answers CLOVA Studio generated.

## Request

This section describes the request format. The method and URI are as follows:

| Method | URI |
| --- | --- |
| POST | /tuning/v2/tasks |

### Request headers

For information about the request headers common to all CLOVA Studio APIs, see [CLOVA Studio request headers](/docs/en/ai-naver-clovastudio-summary#%EC%9A%94%EC%B2%AD%ED%97%A4%EB%8D%94).

### Request body

You can include the following data in the body of your request:

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `name` | String | Optional | Training name - Auto-generate with training creation date if not entered. |
| `model` | String | Required | Model name to use for tuning |
| `tuningType` | String | Optional | Tuning method - `PEFT` (default) |
| `trainEpochs` | String | Optional | Number of epochs trained on the model - 1 ≤ `trainEpochs` ≤ 20 (default: 8) |
| `learningRate` | String | Optional | Training rate (level or degree to which model parameters are relearned when tuning) - 1 ≤ `learningRate` ≤ 1.0E-6 (default: 1.0E-4) |
| `validationSplitRatio` | Double | Optional | Dataset ratio for validation - 0.0-0.1 (default: 0.0) |
| `loraR` | Integer | Optional | Number of dimensions for the low-dimensional matrix used during PEFT training - 2-8 (default: 8) |
| `loraAlpha` | Integer | Optional | Scale factor to apply when applying PEFT training results - 2-512 (default: 64) |
| `trainingDatasetFilePath` | String | Conditional | Path to the dataset file to be used for training (path within the bucket, excluding the bucket name) - Required if uploaded to the Object Storage service. |
| `trainingDatasetBucket` | String | Conditional | Name of the bucket where the dataset file to be used for training was uploaded - Required if `trainingDatasetFilePath` is entered. |
| `trainingDatasetAccessKey` | String | Conditional | Access key for accessing the dataset file used for training - Required if `trainingDatasetFilePath` is entered. |
| `trainingDatasetSecretKey` | String | Conditional | Secret key for accessing the training dataset file - Required if `trainingDatasetFilePath` is entered. |

### Request example

The request example is as follows:

```
curl --location --request POST 'https://clovastudio.stream.ntruss.com/tuning/v2/tasks' \
--header 'Authorization: Bearer {API Key}' \
--header 'Content-Type: multipart/form-data' \
--header 'X-NCP-CLOVASTUDIO-REQUEST-ID: {Request ID}' 
--data '{
  "name": "generation_task",
  "model": "HCX-003",
  "tuningType": "PEFT",
  "trainEpochs": 8,
  "learningRate": 1e-5f,
  "trainingDatasetFilePath": "root_path/sub_path/file_name",
  "trainingDatasetBucket": "bucket_name",
  "trainingDatasetAccessKey": "access_key",
  "trainingDatasetSecretKey": "secret_key",
   "validationSplitRatio": 0,
   "loraR": 8,
   "loraAlpha": 64
}'
```

## Response

This section describes the response format.

### Response headers

The following describes the response headers.

| Headers | Required | Description |
| --- | --- | --- |
| Content-Type | - | Response data format - `application/json` |

### Response body

The response body includes the following data:

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `status` | Object | - | See [Response status](/docs/en/ai-naver-clovastudio-summary#%EC%9D%91%EB%8B%B5). |
| `result` | Object | - | Response result |
| `result.id` | String | - | Training ID |
| `result.name` | String | - | Training name |
| `result.model` | String | - | Tuning model name |
| `result.taskType` | String | - | Job type - GENERATION: generation (default) - CLASSIFICATION: classification |
| `result.trainEpochs` | Integer | - | Number of epochs trained on the model |
| `result.learningRate` | Double | - | Training rate (level or degree to which model parameters are retrained when tuning) |
| `result.status` | String | - | Training progress - `WAIT` \| `RUNNING` \| `FAILED` \| `SUCCEEDED` - `WAIT`: Training pending - `RUNNING`: Training in progress - `FAILED`: Training stopped - `SUCCEEDED`: Training completed |
| `result.statusInfo` | Array | - | Training progress details: [statusInfo](/docs/en/clovastudio-posttask#statusInfo) |
| `result.createdClientType` | String | - | Type of client requesting training - `API` \| `WEB` - `API`: API client - `WEB`: Web client |
| `result.createdDate` | String | - | Training creation date - ISO 8601 format |
| `result.updatedDate` | String | - | Training modification date - ISO 8601 format |

#### `statusInfo`

The following describes `statusInfo`.

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `label` | Array | - | - When the training type is `CLASSIFICATION`: User data labels are displayed. - When the training type is `GENERATION`: `null` |
| `dataRows` | Integer | - | Number of data |
| `numOfTokens` | Integer | - | Number of data tokens |
| `currStep` | Integer | - | Number of current training steps |
| `totalTrainSteps` | Integer | - | Number of total training steps |
| `currEpoch` | Integer | - | Current epoch |
| `totalTrainEpochs` | Integer | - | All training epochs |
| `estimatedTime` | Integer | - | Estimated run time - Derived by multiplying the average time of 1 epoch by the total number of training epochs |
| `trainLoss` | Double | - | Training loss |
| `sendWeightSuccess` | Boolean | - | Whether to save training results - `false` \| `true` - `false`: Don't save - `true`: Save |
| `failureReason` | String | - | [Reason for training failure (`FAILED`)](/docs/en/clovastudio-posttask#failureReasonmessage) |
| `message` | String | - | [Detailed message for training failure (`FAILED`) reason](/docs/en/clovastudio-posttask#failureReasonmessage) |
| `endDatetime` | String | - | Training end date - ISO 8601 format |

#### `failureReason`, `message`

The following describes training failure reasons (`failureReason`) and the detailed message (`message`) for each training failure reason.

| Training failure reason | Message details | Description |
| --- | --- | --- |
| `file.extension` | `Unavailable file extension. Please check the file extension again.` | The data file extension does not match the requested `tuningType`. |
| `file.size` | `Exceeded the disk usage limit. Please check if the file size is {limit} or less.` | The expected file size for the training request is exceeded. |
| `file.encoding` | `Unsupported charset` | Non-UTF8-sig encoding |
| `file.format` | `Invalid json format. {reason}` | Unable to decode the dataset file (.json/.jsonl) |
| `file.format` | `Invalid dataset: required field empty. {column}` | The dataset file does not have the required columns. |
| `file.format` | `Invalid dataset: unexpected column. {column}` | The dataset file has unexpected columns. |
| `file.format` | `Invalid dataset: duplicate columns. {column}` | The dataset file is not case sensitive and contains duplicate columns. |
| `file.format` | `Invalid dataset: column order` | The column order in the dataset file deviates from System_Prompt, C_ID, T_ID, Text, and Completion. |
| `file.format` | `Invalid dataset: {column}` | The C_ID (or T_ID) in the dataset file does not satisfy the pattern of starting at 0 and incrementing by 1, or the value is empty. |
| `file.error` | - | File read error upon training |
| `file.noexist` | - | If the dataset file does not exist |
| `File not found` | - | If the file can't be found in Object Storage |
| `resource.timeout` | - | Response timeout due to GPU acquisition failure; retry required |
| `clops.error` | - | CLOps error while training |
| `train.unknown` | - | Non-file related error while training |

### Response example

The response example is as follows:

#### Succeeded

The following is a sample response upon a successful call.

```
{
    "status": {
        "code": "20000",
        "message": "OK"
    },
"result": {
    "id": "czf9fbky",
    "name": "230821-130704",
    "model": "HCX-003",
    "trainEpochs": 8,
    "learningRate": 1.0E-4,
    "status": "WAIT",
    "statusInfo": {
        "label": null,
        "dataRows": null,
        "numOfTokens": null,
        "currStep": null,
        "totalTrainSteps": null,
        "currEpoch": null,
        "totalTrainEpochs": null,
        "estimatedTime": null,
        "trainLoss": null,
        "sendWeightSuccess": null,
        "failureReason": null,
        "message":null,
        "endDatetime": null
        },
        "createdClientType": "API",
        "createdDate": "2023-08-21T13:07:06+0900",
        "updatedDate": "2023-08-21T13:07:06+0900"
    }
}
```

#### Failure

The following is a sample response upon a failed call.

- [Common client error troubleshooting (4xx)](/docs/en/clovastudio-troubleshoot-c4xx)
- [Common server error troubleshooting (5xx)](/docs/en/clovastudio-troubleshoot-c5xx)