Update Sentiment_analysis_with_bert.py

Sentiment_analysis_with_bert.py

@@ -303,48 +303,46 @@ def eval_model(model, data_loader, loss_fn, device, n_examples):
 
   return correct_predictions.double() / n_examples, np.mean(losses)
 
-# Commented out IPython magic to ensure Python compatibility.
-# %%time
-# 
-# history = defaultdict(list)
-# best_accuracy = 0
-# 
-# for epoch in range(EPOCHS):
-# 
-#   print(f'Epoch {epoch + 1}/{EPOCHS}')
-#   print('-' * 10)
-# 
-#   train_acc, train_loss = train_epoch(
-#     model,
-#     train_data_loader,
-#     loss_fn,
-#     optimizer,
-#     device,
-#     scheduler,
-#     len(df_train)
-#   )
-# 
-#   print(f'Train loss {train_loss} accuracy {train_acc}')
-# 
-#   val_acc, val_loss = eval_model(
-#     model,
-#     val_data_loader,
-#     loss_fn,
-#     device,
-#     len(df_val)
-#   )
-# 
-#   print(f'Val   loss {val_loss} accuracy {val_acc}')
-#   print()
-# 
-#   history['train_acc'].append(train_acc)
-#   history['train_loss'].append(train_loss)
-#   history['val_acc'].append(val_acc)
-#   history['val_loss'].append(val_loss)
-# 
-#   if val_acc > best_accuracy:
-#     torch.save(model.state_dict(), 'best_model_state.bin')
-#     best_accuracy = val_acc
+%%time 
+history = defaultdict(list)
+best_accuracy = 0
+ 
+for epoch in range(EPOCHS):
+ 
+  print(f'Epoch {epoch + 1}/{EPOCHS}')
+  print('-' * 10)
+
+  train_acc, train_loss = train_epoch(
+    model,
+    train_data_loader,
+    loss_fn,
+    optimizer,
+    device,
+    scheduler,
+    len(df_train)
+  )
+ 
+  print(f'Train loss {train_loss} accuracy {train_acc}')
+ 
+  val_acc, val_loss = eval_model(
+    model,
+    val_data_loader,
+    loss_fn,
+    device,
+    len(df_val)
+  )
+ 
+  print(f'Val   loss {val_loss} accuracy {val_acc}')
+  print()
+ 
+  history['train_acc'].append(train_acc)
+  history['train_loss'].append(train_loss)
+  history['val_acc'].append(val_acc)
+  history['val_loss'].append(val_loss)
+
+  if val_acc > best_accuracy:
+    torch.save(model.state_dict(), 'best_model_state.bin')
+    best_accuracy = val_acc
 
 print(history['train_acc'])