Closed engindeniz closed 1 year ago
Hi,
Thanks for the great work and publicly available code.
Could you please share the few-shot training parameters (batch size, learning rate, etc.)? I could not reproduce the results.
Thanks in advance.
Hi, Thanks for your interest! For the few-shot setting, I ran the same hyperparameter swipes as for the fully-supervised setting (see Section 4.1 and Appendix Section C.2).
Hi,
Thanks for the great work and publicly available code.
Could you please share the few-shot training parameters (batch size, learning rate, etc.)? I could not reproduce the results.
Thanks in advance.