Manage tasks

Available in Classic and VPC

Task management describes how to create and manage tasks in the Tuning menu and how to check the training status. It also introduces how to use Inference Test to evaluate the performance and accuracy of trained tasks and how to create a test app.

Create a new task

You can test a part of a pre-trained model by retraining it to your dataset by creating a new task. To create a tuning task, you need a dataset proper for the upload conditions, and the more the number of cases of data, the more improved the performance of the tuning completion. For more information on dataset, see Prepare dataset.

The following describes how to create a new task.

1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.

2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.

3. Click the Tuning menu.

4. Click the [Create] button for the type of task you want to create.

   • Tuning provides a total of 7 task types and an API for direct training.

   • When you select a task type, you can see the description and usage examples of the task type in the form of a card.

   • When you select an API, you can call the API directly for training.

   Note

   To train more about how to use the API, see the API guide.
   While model training creation and retrieval can be accessed according to the API specifications provided on the Service page, in order to generate result values from the trained model using the Chat Completion API and Completion API, create a test app as before.

5. When you see the pop-up window, click the [Create] button on selecting the model engine.

   • You cannot change the model engine later.
   • For more information on the model engine, see Engine.

6. Enter a task name.

7. Please upload datasets after clicking on the file upload area and checking the personal information and harmful information guide.

   • For .csv files, you can download the dataset format file by clicking Download format.
   • If you upload the dataset successfully, you can see the dataset file name and size in the file upload area.
   • Even if you upload the dataset successfully, when improvements are recommended for optimal performance, you can view the caveats by clicking Check cautions.
   • If you fail to upload the dataset, you can see the file name and reason for failure in the file upload area. You can check specific errors on clicking View details.

8. Click the [Next] button.

9. Check the expected token usage and click the [Train] button when the Token calculation pop-up window appears.

10. Check the contents of the pop-up window while training is waiting, and then click the [OK] button.

    • You can check training status in the User name > My task > [Tuning] tab.

Check training status

The following describes how to check the training status.

1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
3. Click on the user name at the top right corner of CLOVA Studio, and then select the My task menu.
4. Click the [Tuning] tab.
   
   • Create new task: click to go to the [New task] tab
   • / : click to change the sorting method
   • Training pending: waiting for training, you can click to see a pop-up window of waiting for training
   • Training in progress: training is in progress, you can click to check the estimated time required
   • Training completed: training is complete, you can click to check and test task information
   • Suspend training: training is suspended

Check the information of training-completed tasks

Click a training-completed task to view its information.

• Creation date and time: date and time of creation of a new task
• Training completion date: date and time of completion of training
• Workflow ID: an ID for identifying a task in training
• Problem Type: task type
• Model Engine: type of trained language model
• Dataset: dataset file name used for training
• Train Loss: a figure that shows how proper the model is to the dataset. The lower the figure is, the less the error from the correct answer
• Tokens Used: number of tokens actually used

Suspend training

The following describes how to suspend training.

1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
3. Click on the user name at the top right corner of CLOVA Studio, and then select the My task menu.
4. Click the [Tuning] tab.
5. Please click on the task to suspend training.
6. Click the [Suspend] button.
7. Check the contents of the pop-up window of suspending training, and then click the [Suspend] button.
   • If you suspend the pending training, you will lose all previously uploaded dataset files.
   • If you suspend training in progress, you will lose previously uploaded dataset files and tasks, and the token that was notified when creating the task will be used.

Utilize training-completed tasks

You can perform an inference test to test performance and accuracy before creating a test app for a training-completed task. After completing the test, you can create a test app, and you can also share your work via a share URL.

Inference Test

The following describes how to test with the Inference Test function.

1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
3. Click on the user name at the top right corner of CLOVA Studio, and then select the My task menu.
4. Click the [Tuning] tab.
5. Click the task to test.
   • You can only test tasks that are in the training-completed status.
6. After entering a value in the Input area, click the [Run] button.
   
   • You can enter up to 2000 characters including spaces.
   • The result values generated by training are displayed in the Output area.
   • Please verify performance and accuracy through sufficient testing.
   • If you trained with an HCX model, go to the Playground to test it.
     

Create test app

The following describes how to create the test app.

1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
3. Select [User name] in the upper right corner and click [My task] > Tuning.
4. Click the task you want to create a test app for.
5. Click the [Create test app] button.
6. Enter a test app name, and then click the [Create] button.
   • You can create a test app, and see a test app pop-up window.
     
     • You can check the API information of the test app, and you can set whether to use an AI Filter. (For more information on APIs, see CLOVA Studio API guide)
     • As for the code type, curl and python are provided.
     • You can click [Copy] to copy the API information to the clipboard.
     • You can click [Reissue] to reissue API Gateway key.
     • You can check AI Filter guide when clicking View guide.