AttributeError: 'numpy.float64' object has no attribute 'cpu'

Question

I am trying to run BERT and train a model using pytorch. I am not sure why I am getting this error after finishing the first Epoch. I am using this code link

history = defaultdict(list)
best_accuracy = 0

for epoch in range(EPOCHS):
    
    # Show details 
    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}")
    
    # Get model performance (accuracy and loss)
    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.cpu())
    history['train_loss'].append(train_loss.cpu())
    history['val_acc'].append(val_acc.cpu())
    history['val_loss'].append(val_loss.cpu())
    
    # If we beat prev performance
    if val_acc > best_accuracy:
        torch.save(model.state_dict(), 'best_model_state.bin')
        best_accuracy = val_acc

Here is the output and the error message Image

It is a first time for me to work with pytorch. Any ideas how to fix the error>

Answer 1

I checked kaggle link and I see that there is no cpu() reference as you have posted in your code. It should simply be:

history['train_acc'].append(train_acc)
history['train_loss'].append(train_loss)
history['val_acc'].append(val_acc)
history['val_loss'].append(val_loss)