Resnet segmentation model with zero loss

I am working on a pytorch resnet model for image segmentation and while I am getting fairly high accuracy values, both my training and validation losses are zeroes. The shapes of all inputs seem right but when I view my tensors they are all zeroes (or very small values). My training inputs are images and binary masks (two classes). I have been stuck on this for a while so any help would be very appreciated!

I have attached the model training part of my code below, thank you in advance!

for epoch in range(num_epochs):
#zero out epoch based performance variables
print(‘Epoch {}/{}’.format(epoch, num_epochs - 1))
print(’-’ * 10)
all_acc = {key: 0 for key in phases}
all_loss = {key: torch.zeros(0).to(device) for key in phases}
cmatrix = {key: np.zeros((2,2)) for key in phases}

for phase in phases: #iterate through both training and validation states

    if phase == 'train':
        model.train()  # Set model to training mode
    else: #when in eval mode, we don't want parameters to be updated
        model.eval()   # Set model to evaluate mode
    running_loss = 0.0
    running_corrects = 0
    for ii , (X, y, y_weight) in enumerate(dataLoader[phase]): #for each of the batches
        optim.zero_grad()
        X = X.to(device)  # [Nbatch, 3, H, W]
        y_weight = y_weight.type('torch.FloatTensor').to(device)
        y = y.type('torch.LongTensor').to(device)  # [Nbatch, H, W] with class indices (0, 1)
        with torch.set_grad_enabled(phase == 'train'): #dynamically set gradient computation, in case of validation, this isn't needed
                                                        #disabling is good practice and improves inference time

            prediction = model_ft(X)  # [N, Nclass]
            y = y[:, 0,0]
            loss = criterion(prediction, y)
            _, preds = torch.max(X, 1)
            preds = preds[:,0,0]
            if phase=="train": #in case we're in train mode, need to do back propogation
                
                loss.mean().backward()
                optim.step()
            
            #all_loss[phase]=torch.cat((all_loss[phase],loss.detach().view(1,-1)))

            
    #all_acc[phase]=(cmatrix[phase]/cmatrix[phase].sum()).trace()
    #all_loss[phase] = all_loss[phase].cpu().numpy().mean()
        running_loss += loss.data[0]
        running_corrects += torch.sum(preds == y)
    epoch_loss = running_loss / len(dataLoader[phase].dataset)
    epoch_acc = running_corrects.double() / len(dataLoader[phase].dataset)

    print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))

    # deep copy the model
    if phase == 'val' and epoch_acc > best_acc:
       best_acc = epoch_acc
       best_model_wts = copy.deepcopy(model.state_dict())
    if phase == 'val':
       val_acc_history.append(epoch_acc)

print()

time_elapsed = time.time() - since
print(‘Training complete in {:.0f}m {:.0f}s’.format(time_elapsed // 60, time_elapsed % 60))
print(‘Best val Acc: {:4f}’.format(best_acc))

model.load_state_dict(best_model_wts)

Could you post an example of the model output and the corresponding target which gives a high accuracy and a zero loss?