heather

The warning pointing to this issue appears even when using RMS normalization (`-nt rms`). If I understand the explanation above correctly, there is no minimum length requirement for RMS normalization;...

hi, I'm having this same issue, also with a Conv1D layer originally from a PyTorch model. @KietHoang2212 if this fix works for you, any chance you could write a PR?...

for anyone else who sees similar behavior: this happens when you're not using the validation set in `LRFinder()`. if you include the validation set, it'll be wiggly.