diff --git a/src/main.py b/src/main.py
index 18e420c..7ecc702 100644
--- a/src/main.py
+++ b/src/main.py
@@ -135,8 +135,8 @@ def main(opt):
         yte_ = cls.predict(Xte)
         print('end-to-end-finetuning network prediction')
         acc, macrof1, microf1 = evaluation(yte, yte_)
-        foo.write(
-            f'end-to-end-finetuning network prediction: acc={acc:.3f} macrof1={macrof1:.3f} microf1={microf1:.3f}\n')
+        foo.write(f'end-to-end-finetuning network prediction: '
+                  f'acc={acc:.3f} macrof1={macrof1:.3f} microf1={microf1:.3f}\n')
 
         print('training end-to-end without self-supervision init')
         cls, phi = instantiate_model(A, index, pad_index, device)
@@ -150,6 +150,8 @@ def main(opt):
         yte_ = cls.predict(Xte)
         print('end-to-end (w/o self-supervised initialization) network prediction')
         acc, macrof1, microf1 = evaluation(yte, yte_)
+        foo.write(f'end-to-end (w/o self-supervised initialization) '
+                  f'network prediction: acc={acc:.3f} macrof1={macrof1:.3f} microf1={microf1:.3f}\n')
 
         svm_experiment(Xtr_svm, ytr, Xte_svm, yte, foo, 'svm-kernel')
 
diff --git a/src/model/classifiers.py b/src/model/classifiers.py
index 3fce2f1..435a772 100644
--- a/src/model/classifiers.py
+++ b/src/model/classifiers.py
@@ -133,7 +133,7 @@ class AuthorshipAttributionClassifier(nn.Module):
         early_stop = EarlyStop(patience, lower_is_better=True)
 
         criterion = SupConLoss1View().to(self.device)
-        optim = torch.optim.Adam(self.parameters(), lr=lr)
+        optim = torch.optim.Adam(self.parameters(), lr=lr)  # take only phi's parameters
 
         tr_data = IndexedDataset(X, y, self.pad_length, self.pad_index, self.device)
         val_data = IndexedDataset(Xval, yval, self.pad_length, self.pad_index, self.device)