Skip to content

DeepAR InternalServerError: We encountered an internal error. Please try again #1758

Closed

Description

@chaitanyasathi

Here is the error I am getting

Error for Transform job forecasting-deepar-2020-07-28-12-59-06--2020-07-28-12-59-07-635: Failed. Reason: InternalServerError: We encountered an internal error. Please try again.

My DeepAR Batch Transformer jobs are working fine for small subset of the data. But however for larger set of data, I am getting above error. This has really been a show stopper not sure how to proceed further. I also tried with different combination of instance count, instance type and it is still failing.

Here is the transformer code I am using

deepar_transformer = estimator.transformer(instance_count = 4,
                                  instance_type = 'ml.m4.4xlarge',strategy='MultiRecord', output_path=batch_output , max_payload=100)
                                  
deepar_transformer.transform(data=data_channels["test"]) 

deepar_transformer.wait()

Activity

  1. laurenyu commented on Jul 28, 2020

    @laurenyu
    Contributor

    I've passed this along to the team that owns DeepAR to see if they have any insight (reference: P38158491). Thanks for using SageMaker!

  2. chaitanyasathi commented on Jul 31, 2020

    @chaitanyasathi
    Author

    @laurenyu Any updates on the following issue?

  3. locked and limited conversation to collaborators on May 20, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions