Spaces:

autoevaluate

/

model-evaluator

like 172

Running

Same error for a summarization run

Thanks for reporting this issue @pszemraj ! I've just deployed a fix - can you please try again?

Closing this issue for now - feel free to reopen if the error returns :)

Thanks for all the help thus far! hopefully it's related, and it's correct to put this here, but getting a similar but slightly different error now. I can submit jobs for other datasets and models but get a somewhat similar HTTP error when trying to eval on kmfoda/booksum

• original error from trying to eval pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13 on kmfoda/booksum
• am able to eval pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13 on other datasets
• am not able to get other models to work on kmfoda/booksum

error

HTTPError: 400 Client Error: Bad Request for url: https://api-staging.autotrain.huggingface.co/projects/create
Traceback:
File "/home/user/.local/lib/python3.8/site-packages/streamlit/scriptrunner/script_runner.py", line 554, in _run_script
    exec(code, module.__dict__)
File "/home/user/app/app.py", line 550, in <module>
    project_json_resp = http_post(
File "/home/user/app/utils.py", line 45, in http_post
    response.raise_for_status()
File "/home/user/.local/lib/python3.8/site-packages/requests/models.py", line 1021, in raise_for_status
    raise HTTPError(http_error_msg, response=self)

screenshot

I am also facing the same issue as pszemraj.
I get the exact same error message when trying to evaluate the model KamilAin/bart-base-booksum on the dataset kmfoda/booksum.
Has there been progress on finding a fix?

@lewtun tagging you in case it doesn't pop up :)

Lil update - I was able to submit jobs now; I will report back if they are complete. If you don't hear anything in a few days, please feel free to ping me!

BookSum evals are coming through and making it to model repo PRs - closing this!