print("training...")
    for epoch in range(0, self.config["epoch"]):

        # setting lr
        if epoch <= self.config["warmup_epoch"]:
            lr = 0.005
        else:
            lr = 0.005 * (0.995 ** ((epoch - 1) // 2))
        self.config["lr"] = lr

        self.variable_dict["epoch"] = epoch
        self.run_hook(self.epoch_begin_hook)
        self.variable_dict["avg_mentor"] = AvgMeter()  # operate and update average
        self.model.train()
        # max_step = len(self.trainloader)
        # print("This is the max_step", max_step)
        for step, data in enumerate(tqdm(self.trainloader)):
            # tqdm.write("Step: {}".format(step))
            self.variable_dict["step"] = step + 1
            self.variable_dict["iteration"] += 1
            self.run_hook(self.iteration_begin_hook)  # record prune_iteration
            data = self._sample_to_device(data, self.variable_dict["base_device"])
            c_sample_number = self._get_sample_number(data)  # get the num_sample
            predict = self.config["predict_function"](self.model, data)
            self.variable_dict["loss"] = self.config["calculate_loss_function"](
                predict, data
            )
            self.on_loss_backward()
            self.variable_dict["loss"].backward()
            self.after_loss_backward()
            # add the gradient of penalty with decay to the gradient of precision parameter for the compactor
            self.optimizer.step()  # update parameter
            self.optimizer.zero_grad()  # zero out gradient
        evaluate_result = self.config["evaluate_function"](predict, data)
        evaluate_result["loss"] = self.variable_dict["loss"].item()  # get high accuracy loss
        self.variable_dict["avg_mentor"].update(
            evaluate_result, c_sample_number
        )  # update average
        # del evaluate_result, predict
        # if self.variable_dict["iteration"] % self.config["log_interval"] == 0:
        self.write_log(
            self.variable_dict["epoch"],
            self.variable_dict["iteration"],
            self.variable_dict["avg_mentor"].get(),
            self.config["lr"],
        )
        self.write_tensorboard(
            "train_log",
            self.variable_dict["iteration"],
            self.variable_dict["avg_mentor"].get(),
        )
        self.run_hook(self.iteration_end_hook)  # model prune, optimizer prune, compute flops
        del self.variable_dict["loss"]
        self.scheduler.step()  # adjust lr

        # evaluation/testing step
        print("evaluating...")
        self.variable_dict["test_avg_mentor"] = AvgMeter()
        self.model.eval()
        # for step, data in enumerate(self.testloader):
        #     self.variable_dict["step"] = step + 1
        #     data = self._sample_to_device(data, self.variable_dict["base_device"])
        #     c_sample_number = self._get_sample_number(data)
        #     predict = self.config["predict_function"](self.model, data)
        evaluate_result = self.config["evaluate_function"](predict, data)
        evaluate_result["loss"] = self.config["calculate_loss_function_test"](
            predict, data
        ).item()
        self.variable_dict["test_avg_mentor"].update(
            evaluate_result, c_sample_number
        )  # update precision result and num_sample
        if self.variable_dict["step"] % self.config["log_interval"] == 0:  # (useless at present) decide log_out_period, log_interval=20
            self.write_log(
                self.variable_dict["epoch"],
                self.variable_dict["step"],
                self.variable_dict["test_avg_mentor"].get(),
            )
        # del evaluate_result, predict
        self.write_log(
            self.variable_dict["epoch"],
            "final",
            self.variable_dict["test_avg_mentor"].get(),
            self.config["lr"],
        )
        self.write_tensorboard(
            "test_log",
            self.variable_dict["epoch"],
            self.variable_dict["test_avg_mentor"].get(),
        )