diff --git a/train_ms.py b/train_ms.py
index 6bab64d..34115dc 100644
--- a/train_ms.py
+++ b/train_ms.py
@@ -8,7 +8,6 @@ from torch import nn, optim
 from torch.nn import functional as F
 from torch.utils.data import DataLoader
 from torch.utils.tensorboard import SummaryWriter
-#import wandb
 import torch.multiprocessing as mp
 import torch.distributed as dist
 from torch.nn.parallel import DistributedDataParallel as DDP
@@ -255,7 +254,7 @@ def train_and_evaluate(rank, epoch, hps, nets, optims, schedulers, scaler, loade
                 loss_disc, losses_disc_r, losses_disc_g = discriminator_loss(y_d_hat_r, y_d_hat_g)
                 loss_disc_all = loss_disc
             if net_dur_disc is not None:
-                y_dur_hat_r, y_dur_hat_g = net_dur_disc(hidden_x.detach(), x_mask.detach(), logw_.detach(), logw.detach())
+                y_dur_hat_r, y_dur_hat_g = net_dur_disc(hidden_x.detach(), x_mask.detach(), logw.detach(), logw_.detach())
                 with autocast(enabled=False):
                  # TODO: I think need to mean using the mask, but for now, just mean all
                     loss_dur_disc, losses_dur_disc_r, losses_dur_disc_g = discriminator_loss(y_dur_hat_r, y_dur_hat_g)
@@ -276,7 +275,7 @@ def train_and_evaluate(rank, epoch, hps, nets, optims, schedulers, scaler, loade
             # Generator
             y_d_hat_r, y_d_hat_g, fmap_r, fmap_g = net_d(y, y_hat)
             if net_dur_disc is not None:
-                y_dur_hat_r, y_dur_hat_g = net_dur_disc(hidden_x, x_mask, logw_, logw)
+                y_dur_hat_r, y_dur_hat_g = net_dur_disc(hidden_x, x_mask, logw, logw_)
             with autocast(enabled=False):
                 loss_dur = torch.sum(l_length.float())
                 loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel