Spaces:

autoevaluate

/

model-evaluator

like 172

Running

I pushed my test split to a new dataset ejschwartz/oo-method-test-bylibrary-test and I was able to submit an evaluation job for that. So I guess this is some incompatibility with my dataset and autotrain.

The ejschwartz/oo-method-test-split dataset is weird. It downloads my original dataset and does the splitting dynamically. So maybe it's just timing out.

Hmm, it's been over an hour and still no results yet.

Still no results. I think it is safe to say the autoeval is not going to complete 😁

@julien-c you probably know who to ping...

@lewtun @abhishek just in case