Click here to Skip to main content
15,905,148 members
Please Sign up or sign in to vote.
0.00/5 (No votes)
See more: , +
I faced an error, when i call this function train_bert :
train_bert(net, criterion, opti, lr, lr_scheduler, train_loader, val_loader, epochs, iters_to_accumulate)

The error is: AttributeError: 'tuple' object has no attribute 'to'

The implementation of the train function is as follows:

def train_bert(net, criterion, opti, lr, lr_scheduler, train_loader, val_loader, epochs, iters_to_accumulate): 
best_loss = np.Inf 
best_ep = 1 
nb_iterations = len(train_loader) 
print_every = nb_iterations // 5  # print the training loss 5 times per epoch 
iters = [] 
train_losses = [] 
val_losses = [] 
scaler = GradScaler() 
for ep in range(epochs): 
    running_loss = 0.0 
    for it, (seq, attn_masks, token_type_ids, labels) in enumerate(tqdm(train_loader)): 
        # Converting to cuda tensors 
        seq, attn_masks, token_type_ids, labels = \ 
        # Enables autocasting for the forward pass (model + loss) 
        with autocast(): 
            # Obtaining the logits from the model 
            logits = net(seq, attn_masks, token_type_ids) 
            # Computing loss 
            loss = criterion(logits.squeeze(-1), labels.float()) 
            loss = loss / iters_to_accumulate  # Normalize the loss because it is averaged 
        # Backpropagating the gradients 
        # Scales loss.  Calls backward() on scaled loss to create scaled gradients. 
        if (it + 1) % iters_to_accumulate == 0: 
            # Optimization step 
            # scaler.step() first unscales the gradients of the optimizer's assigned params. 
            # If these gradients do not contain infs or NaNs, opti.step() is then called, 
            # otherwise, opti.step() is skipped. 
            # Updates the scale for next iteration. 
            # Adjust the learning rate based on the number of iterations. 
            # Clear gradients 
        running_loss += loss.item() 
        if (it + 1) % print_every == 0:  # Print training loss information 
            print("Iteration {}/{} of epoch {} complete. Loss : {} " 
                  .format(it+1, nb_iterations, ep+1, running_loss / print_every)) 
            running_loss = 0.0 
    val_loss = evaluate_loss(net, device, criterion, val_loader)  # Compute validation loss 
    print("Epoch {} complete! Validation Loss : {}".format(ep+1, val_loss)) 
    if val_loss < best_loss: 
        print("Best validation loss improved from {} to {}".format(best_loss, val_loss)) 
        net_copy = copy.deepcopy(net)  # save a copy of the model 
        best_loss = val_loss 
        best_ep = ep + 1 

path_to_model='models/{}_lr_{}_val_loss_{}_ep_{}.pt'.format(bert_model, lr, round(best_loss, 5), best_ep), path_to_model) 
print("The model has been saved in {}".format(path_to_model)) 
del loss 

Please help me i struggle with this problem for weeks:(

What I have tried:

I tried lots of solutions, one of them is to encode the labels but didn't work.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900