def val_epoc(tst,model,criterion):
model.eval
loss = 0
acc = 0
for text, offsets, clss in tst:
text, offsets, clss = text.long().to(device), offsets.to(device), clss.to(device)
with torch.no_grad():
output = model(text, offsets)
loss = criterion(output, clss)
loss += loss.item()
acc += (output.argmax(1) == clss).sum().item()
return loss , acc
def val_epoc(tst,model,criterion):
model.eval()
loss = 0
acc = 0
for text_ap, offsets_ap, text_cid,offsets_cid, clss in tst:
text_ap, text_cid=text_ap.long().to(device),text_cid.long().to(device)
offsets_ap, offsets_cid, clss = offsets_ap.to(device),offsets_cid.to(device), clss.to(device)
with torch.no_grad():
output = model(text_ap, offsets_ap,text_cid, offsets_cid)
loss = criterion(output, clss)
loss += loss.item()
acc += (output.argmax(1) == clss).sum().item()
return loss , acc
def train_epoc(trn,model,criterion,optimizer,scheduler):
# Train the model
model.train()
train_loss = 0
train_acc = 0
for text_ap, offsets_ap, text_cid,offsets_cid, clss in tqdm(trn):
optimizer.zero_grad()
text_ap, text_cid=text_ap.long().to(device),text_cid.long().to(device)
offsets_ap, offsets_cid, clss = offsets_ap.to(device),offsets_cid.to(device), clss.to(device)
output = model(text_ap, offsets_ap,text_cid, offsets_cid)
loss = criterion(output, clss)
train_loss += loss.item()
loss.backward()
optimizer.step()
train_acc += (output.argmax(1) == clss).sum().item()
# Adjust the learning rate
scheduler.step()
return train_loss , train_acc