|
verb_1, value_1, loss.item(), loss_total / ((total_steps) % (eval_frequency*len(train_loader) + 1)), (time.time() - time_all))) |
It seems like that it should be
loss_total / ((total_steps - 1) % (eval_frequency*len(train_loader)) + 1)
rather than
loss_total / ((total_steps) % (eval_frequency*len(train_loader) + 1))
if I understand correctly.
reducingbias/PosteriorBias/baseline_crf_prob.py
Line 695 in ca3376e
It seems like that it should be
loss_total / ((total_steps - 1) % (eval_frequency*len(train_loader)) + 1)rather than
loss_total / ((total_steps) % (eval_frequency*len(train_loader) + 1))if I understand correctly.