I tried to work with ULMFiT with a highly imbalance dataset. After fine tuning the language model and in training the classifier; I tried to change the sampler of the training dataloader from
SortishSampler to a weighted sampler and keep the validation dataloader with the default
SortSampler . My question is simple. When I tried to
predict the validation dataset without a sampler it gives a difference results (accuracy) from the one computed after each epochs.
Is there a reason for that ?