diff --git a/loss.py b/loss.py
index 0021caf94bb9fb8eb90572c0c6f9ad012937c2d5..0d82d027da425b2aa14925d2e43befca37fe35b6 100644
--- a/loss.py
+++ b/loss.py
@@ -37,7 +37,7 @@ def masked_spectral_angle(y_true, y_pred):
     true_masked = F.normalize(true_masked, p=2, dim=1)
     # print(pred_masked.sum(dim=1))
     # print((pred_masked * true_masked).sum(dim=1).shape)
-    return 1 -2 * torch.acos((pred_masked * true_masked).sum(dim=1)).mean() / np.pi
+    return 1 -2 * torch.acos((pred_masked * true_masked).sum(dim=1).mean()) / np.pi
 
 
 def masked_pearson_correlation_distance(y_true, y_pred, reduce='mean'):
diff --git a/main_custom.py b/main_custom.py
index 7048332c805a7e88a84b13704abe9d8b52e78b17..ff87467c0aba7a9f854810fb31f62114f8e55ecc 100644
--- a/main_custom.py
+++ b/main_custom.py
@@ -24,6 +24,7 @@ def train(model, data_train, epoch, optimizer, criterion_rt, criterion_intensity
     for param in model.parameters():
         param.requires_grad = True
     if forward == 'both':
+        i=0
         for seq, charge, rt, intensity in data_train:
             rt, intensity = rt.float(), intensity.float()
             if torch.cuda.is_available():
@@ -41,6 +42,7 @@ def train(model, data_train, epoch, optimizer, criterion_rt, criterion_intensity
             optimizer.zero_grad()
             loss.backward()
             optimizer.step()
+            print(i,'/',len(data_train))
 
         if wandb is not None:
             wdb.log({"train rt loss": losses_rt / len(data_train), "train int loss": losses_int / len(data_train),