I’m having an issue: cannot unpack non-iterable float object

nlp
1 
train_loss = 0
for bi, d in tqdm(enumerate(data_loader)):
    ids = d['ids']
    mask = d['mask']
    token_type_ids = d['token_type_ids']
    target = d['target']
# putting them into the device

    ids = ids.to(device, dtype=torch.long)
    mask = mask.to(device, dtype=torch.long)
    token_type_ids = token_type_ids.to(device, dtype=torch.long)
    target = target.to(device, dtype=torch.long)
        
    optimizer.zero_grad()
    outputs = model(
        ids = ids,
        mask = mask,
        token_type_ids = token_type_ids
    )
    
    loss = loss_fn(outputs, target)
    loss.backward()
    optimizer.step()
    scheduler.step()
    train_loss += loss.item()
train_loss = train_loss / len(data_loader)

print(f'Train loss: {train_loss:.3f}')

def eval_fx(data_loader, model, device):
model.eval()
valid_loss = 0

#final_target = []
#final_outputs = []
with torch.no_grad():
    for bi, d in tqdm(enumerate(data_loader)):
        ids = d['ids']
        mask = d['mask']
        token_type_ids = d['token_type_ids']
        target = d['target']
    # putting them into the device

        ids = ids.to(device, dtype=torch.long)
        mask = mask.to(device, dtype=torch.long)
        token_type_ids = token_type_ids.to(device, dtype=torch.long)
        target = target.to(device, dtype=torch.long)
            
        outputs = model(
            ids = ids,
            mask = mask,
            token_type_ids = token_type_ids
        )
        loss = loss_fn(outputs, target)

        valid_loss += loss.item()
    valid_loss = valid_loss / len(data_loader)

print(f'valid loss: {valid_loss:.3f}')

def accuracy_metrics(self, outputs, target):
outputs = torch.argmax(outputs).cpu().detach().numpy() # Due to the linear layer in our feedforward function
target = target.cpu().detach().numpy()
return {‘Accuracy’: metrics.accuracy_score(outputs, target)}

from tqdm import tqdm
best_accuracy = 0
for epoch in range(config.epochs):
train_fx(train_data_loader, model, optimizer,scheduler, device)
outputs, target = eval_fx(valid_data_loader, model, device)
accuracy = accuracy_metrics(outputs, target)
print(f’Accuracy score ----- {accuracy}')
if accuracy > best_accuracy:
torch.save(model.state_dict(), config.model_path)
best_accuracy = accuracy_metrics

I’ve checked the shape of my outputs and target for both training and validation loops and it gave me this…….
Training:
Outputs - torch.size([4, 3])
Target - torch.size([4])

Validation:
Outputs - torch.size([1, 3])
Target - torch.size([1])

So I don’t know why it’s showing me errors in my validation loop.

2

You may have to mention the specific line number in which there is an error, so that, it will be easy to get help here.

On a quick look, eval_fx does not seem to return any values. But the below line seem to expect some return values.

P.S. you can use ``` to format the code neatly.

3

outputs, target = eval_fx(valid_data_loader, model, device)
This is where the problem lies

Even when I returned valid_loss in the code itself, it said cannot unpack float object.

4

I am not sure if I understand your question correctly.
From your code, I understand that eval_fx is supposed to return two values (outputs, target).

5

Yes, but it’s getting just a single float value.

6

Then maybe you could change the code to receive a “single float value”?

loss = eval_fx(valid_data_loader, model, device)

I think it’s a general python related error and not related to Pytorch.

7

I know the problem is from my code and it’s coming from the eval function. But I don’t know how to tweak it.

8

Double post from here with follow up.