@tomaarsen pointed out that the logging of step/epoch of the triplet evaluator in the model card might be broken, pointing this model card as an example.
I did not have time to check yet, but I believe this is because evaluators have been refactored in ST when adding the NanoBEIR evaluator, we should propagate these changes to fix ig.
@tomaarsen pointed out that the logging of step/epoch of the triplet evaluator in the model card might be broken, pointing this model card as an example.
I did not have time to check yet, but I believe this is because evaluators have been refactored in ST when adding the NanoBEIR evaluator, we should propagate these changes to fix ig.