in aiops/Pathformer_ICLR2024/exp/exp_main.py [0:0]
def train(self, setting):
train_data, train_loader = self._get_data(flag='train')
vali_data, vali_loader = self._get_data(flag='val')
test_data, test_loader = self._get_data(flag='test')
path = os.path.join(self.args.checkpoints, setting)
if not os.path.exists(path):
os.makedirs(path)
total_num = sum(p.numel() for p in self.model.parameters())
time_now = time.time()
train_steps = len(train_loader)
early_stopping = EarlyStopping(patience=self.args.patience, verbose=True)
model_optim = self._select_optimizer()
criterion = self._select_criterion()
if self.args.use_amp:
scaler = torch.cuda.amp.GradScaler()
scheduler = lr_scheduler.OneCycleLR(optimizer=model_optim,
steps_per_epoch=train_steps,
pct_start=self.args.pct_start,
epochs=self.args.train_epochs,
max_lr=self.args.learning_rate)
for epoch in range(self.args.train_epochs):
iter_count = 0
train_loss = []
self.model.train()
epoch_time = time.time()
for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(train_loader):
iter_count += 1
model_optim.zero_grad()
batch_x = batch_x.float().to(self.device)
batch_y = batch_y.float().to(self.device)
batch_x_mark = batch_x_mark.float().to(self.device)
batch_y_mark = batch_y_mark.float().to(self.device)
# encoder - decoder
if self.args.use_amp:
with torch.cuda.amp.autocast():
if self.args.model=='PathFormer':
outputs, balance_loss = self.model(batch_x)
else:
outputs = self.model(batch_x)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, -self.args.pred_len:, f_dim:]
batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
loss = criterion(outputs, batch_y)
train_loss.append(loss.item())
else:
if self.args.model == 'PathFormer':
outputs, balance_loss = self.model(batch_x)
else:
outputs = self.model(batch_x)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, -self.args.pred_len:, f_dim:]
batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
loss = criterion(outputs, batch_y)
if self.args.model=="PathFormer":
loss = loss + balance_loss
train_loss.append(loss.item())
if (i + 1) % 100 == 0:
print("\titers: {0}, epoch: {1} | loss: {2:.7f}".format(i + 1, epoch + 1, loss.item()))
speed = (time.time() - time_now) / iter_count
left_time = speed * ((self.args.train_epochs - epoch) * train_steps - i)
print('\tspeed: {:.4f}s/iter; left time: {:.4f}s'.format(speed, left_time))
iter_count = 0
time_now = time.time()
if self.args.use_amp:
scaler.scale(loss).backward()
scaler.step(model_optim)
scaler.update()
else:
loss.backward()
model_optim.step()
if self.args.lradj == 'TST':
adjust_learning_rate(model_optim, scheduler, epoch + 1, self.args, printout=False)
scheduler.step()
print("Epoch: {} cost time: {}".format(epoch + 1, time.time() - epoch_time))
train_loss = np.average(train_loss)
vali_loss = self.vali(vali_data, vali_loader, criterion)
test_loss = self.vali(test_data, test_loader, criterion)
print("Epoch: {0}, Steps: {1} | Train Loss: {2:.7f} Vali Loss: {3:.7f} Test Loss: {4:.7f}".format(
epoch + 1, train_steps, train_loss, vali_loss, test_loss))
early_stopping(vali_loss, self.model, path)
if early_stopping.early_stop:
print("Early stopping")
break
if self.args.lradj != 'TST':
adjust_learning_rate(model_optim, scheduler, epoch + 1, self.args)
else:
print('Updating learning rate to {}'.format(scheduler.get_last_lr()[0]))
best_model_path = path + '/' + 'checkpoint.pth'
self.model.load_state_dict(torch.load(best_model_path))
return self.model