def evaluate_epoch(self, iterator, criterion):
epoch_loss = 0
epoch_acc = 0
self.eval()
with torch.no_grad():
for batch in iterator:
predictions = self.forward(batch.text, batch.num)
loss = criterion(predictions, batch.label)
acc = categorical_accuracy(predictions, batch.label)
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator)
def train_epoch(self, iterator, optimizer, criterion):
epoch_loss = 0
epoch_acc = 0
self.train()
for batch in iterator:
optimizer.zero_grad()
predictions = self.forward(batch.text, batch.num)
loss = criterion(predictions, batch.label)
acc = categorical_accuracy(predictions, batch.label)
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator)