Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

​ Problem with remote evaluation worker #4424

Open
JannikSchneider12 opened this issue Oct 21, 2024 · 2 comments
Open

​ Problem with remote evaluation worker #4424

JannikSchneider12 opened this issue Oct 21, 2024 · 2 comments

Comments

@JannikSchneider12
Copy link

Hello everyone,

I am trying to set up a remote evaluation challenge and facing issues. When I submit a file in the web interface, the fetching as well as the evaluation script are working but at the end, I am getting this error:

Error: 400 Client Error: Bad Request for url: https://eval.ai/api/jobs/challenge/2389/update_submission/

I also printed out the data that is passed to the update_submission_data function:

{‘challenge_phase’: 4723, ‘submission’: 477497, ‘stdout’: ‘’, ‘stderr’: ‘’, ‘submission_status’: ‘FINISHED’, ‘result’: [{‘train_split’: {‘final_train_loss’: 0.00010908210573358123, ‘final_val_loss’: 0.0009243950532566357, ‘Metric3’: 123, ‘Total’: 123}}, {‘test_split’: {‘final_train_loss’: 0.00010908210573358123, ‘final_val_loss’: 0.0009243950532566357, ‘Metric3’: 123, ‘Total’: 123}}], ‘metadata’: ‘’}

Can someone help me whats wrong?

Thanks for your time and help

@PredictiveManish
Copy link

Does anyone working on this? If not interested to work on this issue. Please assign it to me.

@JannikSchneider12
Copy link
Author

Just to give an update. So I changed the structure of my results dictionary and now it runs without errors. However while the result files for the submissions are now present, the leaderboard remains empty, so I am not sure whether something with my format is still wrong. One result file in the web interface looks e.g. like this:

[{'final_train_loss': 6.025793465431145e-05, 'final_val_loss': 0.00013760417953432937, 'Metric3': 123, 'Total': 123}]

And this is my leaderboard setting in the config:

leaderboard:

  • id: 1
    schema:
    {
    "labels": ["final_train_loss","final_val_loss","Metric3","Total"],
    "default_order_by": "final_val_loss",
    "metadata": {
    "final_val_loss": {
    "sort_ascending": True,
    "description": "The last validation loss from training the linear probing layer",
    }
    }
    }

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants