def training(args, train_loader, valid_loader, model, device, split):
"""Training Procedure"""
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
criterion = torch.nn.BCELoss()
metric = Recall()
total_iter = 0
best_valid_f1 = 0
for epoch in range(args.epochs):
train_trange = tqdm(enumerate(train_loader),
total=len(train_loader),
desc='training')
train_loss = 0
for i, batch in train_trange:
answer = batch['label'].to(device)
prob = run_iter(batch, model, device, training=True)
loss = criterion(prob, answer)
train_loss += loss.item()
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_iter += 1
metric.update(prob, answer)
train_trange.set_postfix(loss=train_loss / (i + 1),
**{metric.name: metric.print_score()})
if total_iter % args.eval_steps == 0:
valid_f1 = validation(valid_loader, model, device)
if valid_f1 > best_valid_f1:
best_valid_f1 = valid_f1
torch.save(
model,
os.path.join(
args.model_dir,
'fine_tuned_roberta_{}.pkl'.format(split)))
def validation(dataloader, model, device):
metric = Recall()
criterion = torch.nn.BCELoss()
valid_trange = tqdm(enumerate(dataloader),
total=len(dataloader),
desc='validation')
model.eval()
valid_loss = 0
for i, batch in valid_trange:
prob = run_iter(batch, model, device, training=False)
answer = batch['label'].to(device)
loss = criterion(prob, answer)
valid_loss += loss.item()
metric.update(prob, answer)
valid_trange.set_postfix(loss=valid_loss / (i + 1),
**{metric.name: metric.print_score()})
return metric.get_f1()