Skip to content

[FEA]: Evaluation overwrites the files in the output directory #325

Open
@AnuradhaKaruppiah

Description

@AnuradhaKaruppiah

Is this a new feature, an improvement, or a change to existing functionality?

New Feature

How would you describe the priority of this feature request

High

Please provide a clear description of problem this feature solves

The current eval mechanism overwrites the output contents of eval.general.output.dir across multiple runs (this should work for local and remote storage where the contents are s3 uploaded) -

eval:
  general:
    output:
      dir: ./.tmp/aiq/examples/simple/
      cleanup: false

Provide an option to store outputs by unique job-ids to avoid the need to change the output-dir across runs

Describe your ideal solution

eval:
  general:
    output:
      dir: ./.tmp/aiq/examples/simple/
      append_job_id_to_output_dir: true
      cleanup: false

Additional context

No response

Code of Conduct

  • I agree to follow this project's Code of Conduct
  • I have searched the open feature requests and have found no duplicates for this feature request

Metadata

Metadata

Assignees

Labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions