regex_ratio:0.7epoch=100: train_ppl.item()=1.042122721672058 train_epoch_loss.item()=0.0412597730755806 eval_ppl.item()=1.030087947845459 eval_epoch_loss.item()=0.029644226655364037

#9
by jeffrey82221 - opened
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment