ValueError: too many values to unpack (expected 2)

[sadanyh]

Environment info

transformers version: 3.0.2

• Platform: Linux-4.19.112+-x86_64-with-Ubuntu-18.04-bionic
• Python version: 3.6.9
• PyTorch version (GPU?): 1.7.0+cu101 (True)
• Tensorflow version (GPU?): 2.4.1 (True)
• Using GPU in script?: True
• Using distributed or parallel set-up in script?: No

Who can help

albert, bert, xlm: @LysandreJik trainer: @sgugger

Information

Model I am using (XLMRobertaForSequenceClassification):

The problem arises when using:

• [ *] the official example scripts: (give details below)
• [ ] my own modified scripts: (give details below)

The tasks I am working on is:

• [ ] an official GLUE/SQUaD task: (give the name)
• [* ] my own task or dataset: (give details below)

To reproduce

This training code is based on the run_glue.py script here:

https://github.com/huggingface/transformers/blob/5bfcd0485ece086ebcbed2d008813037968a9e58/examples/run_glue.py#L128

for epoch_i in range(0, epochs):

# ========================================
#               Training
# ========================================

# Perform one full pass over the training set.

print("")
print('======== Epoch {:} / {:} ========'.format(epoch_i + 1, epochs))
print('Training...')

# Measure how long the training epoch takes.
t0 = time.time()

# Reset the total loss for this epoch.
total_train_loss = 0

# Put the model into training mode. Don't be mislead--the call to 
# `train` just changes the *mode*, it doesn't *perform* the training.
# `dropout` and `batchnorm` layers behave differently during training
# vs. test (source: https://stackoverflow.com/questions/51433378/what-does-model-train-do-in-pytorch)
model.train()

# For each batch of training data...
for step, batch in enumerate(train_dataloader):

    # Progress update every 40 batches.
    if step % 40 == 0 and not step == 0:
        # Calculate elapsed time in minutes.
        elapsed = format_time(time.time() - t0)

        # Report progress.
        print('  Batch {:>5,}  of  {:>5,}.    Elapsed: {:}.'.format(step, len(train_dataloader), elapsed))

    # Unpack this training batch from our dataloader. 
    #
    # As we unpack the batch, we'll also copy each tensor to the GPU using the 
    # `to` method.
    #
    # `batch` contains three pytorch tensors:
    #   [0]: input ids 
    #   [1]: attention masks
    #   [2]: labels 
    b_input_ids = batch[0].to(device)
    b_input_mask = batch[1].to(device)
    b_labels = batch[2].to(device)

    # Always clear any previously calculated gradients before performing a
    # backward pass. PyTorch doesn't do this automatically because 
    # accumulating the gradients is "convenient while training RNNs". 
    # (source: https://stackoverflow.com/questions/48001598/why-do-we-need-to-call-zero-grad-in-pytorch)
    model.zero_grad()        

    # Perform a forward pass (evaluate the model on this training batch).
    # The documentation for this `model` function is here: 
    # https://huggingface.co/transformers/v2.2.0/model_doc/bert.html#transformers.BertForSequenceClassification
    # It returns different numbers of parameters depending on what arguments
    # arge given and what flags are set. For our useage here, it returns
    # the loss (because we provided labels) and the "logits"--the model
    # outputs prior to activation.
    loss, logits = model(b_input_ids, 
                         token_type_ids=None, 
                         attention_mask=b_input_mask, 
                         labels=b_labels)

    # Accumulate the training loss over all of the batches so that we can
    # calculate the average loss at the end. `loss` is a Tensor containing a
    # single value; the `.item()` function just returns the Python value 
    # from the tensor.
    total_train_loss += loss.item()

    # Perform a backward pass to calculate the gradients.
    loss.backward()

    # Clip the norm of the gradients to 1.0.
    # This is to help prevent the "exploding gradients" problem.
    torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)

    # Update parameters and take a step using the computed gradient.
    # The optimizer dictates the "update rule"--how the parameters are
    # modified based on their gradients, the learning rate, etc.
    optimizer.step()

    # Update the learning rate.
    scheduler.step()

# Calculate the average loss over all of the batches.
avg_train_loss = total_train_loss / len(train_dataloader)            

# Measure how long this epoch took.
training_time = format_time(time.time() - t0)

print("")
print("  Average training loss: {0:.2f}".format(avg_train_loss))
print("  Training epcoh took: {:}".format(training_time))

# ========================================
#               Validation
# ========================================
# After the completion of each training epoch, measure our performance on
# our validation set.

print("")
print("Running Validation...")

t0 = time.time()

# Put the model in evaluation mode--the dropout layers behave differently
# during evaluation.
model.eval()

# Tracking variables 
total_eval_accuracy = 0
total_eval_loss = 0
nb_eval_steps = 0

# Evaluate data for one epoch
for batch in validation_dataloader:

    # Unpack this training batch from our dataloader. 
    #
    # As we unpack the batch, we'll also copy each tensor to the GPU using 
    # the `to` method.
    #
    # `batch` contains three pytorch tensors:
    #   [0]: input ids 
    #   [1]: attention masks
    #   [2]: labels 
    b_input_ids = batch[0].to(device)
    b_input_mask = batch[1].to(device)
    b_labels = batch[2].to(device)

    # Tell pytorch not to bother with constructing the compute graph during
    # the forward pass, since this is only needed for backprop (training).
    with torch.no_grad():        

        # Forward pass, calculate logit predictions.
        # token_type_ids is the same as the "segment ids", which 
        # differentiates sentence 1 and 2 in 2-sentence tasks.
        # The documentation for this `model` function is here: 
        # https://huggingface.co/transformers/v2.2.0/model_doc/bert.html#transformers.BertForSequenceClassification
        # Get the "logits" output by the model. The "logits" are the output
        # values prior to applying an activation function like the softmax.
        (loss, logits) = model(b_input_ids, 
                               token_type_ids=None, 
                               attention_mask=b_input_mask,
                               labels=b_labels)

    # Accumulate the validation loss.
    total_eval_loss += loss.item()

    # Move logits and labels to CPU
    logits = logits.detach().cpu().numpy()
    label_ids = b_labels.to('cpu').numpy()

    # Calculate the accuracy for this batch of test sentences, and
    # accumulate it over all batches.
    total_eval_accuracy += flat_accuracy(logits, label_ids)

# Report the final accuracy for this validation run.
avg_val_accuracy = total_eval_accuracy / len(validation_dataloader)
print("  Accuracy: {0:.2f}".format(avg_val_accuracy))

# Calculate the average loss over all of the batches.
avg_val_loss = total_eval_loss / len(validation_dataloader)

# Measure how long the validation run took.
validation_time = format_time(time.time() - t0)

print("  Validation Loss: {0:.2f}".format(avg_val_loss))
print("  Validation took: {:}".format(validation_time))

# Record all statistics from this epoch.
training_stats.append(
    {
        'epoch': epoch_i + 1,
        'Training Loss': avg_train_loss,
        'Valid. Loss': avg_val_loss,
        'Valid. Accur.': avg_val_accuracy,
        'Training Time': training_time,
        'Validation Time': validation_time
    }
)

print("") print("Training complete!")

print("Total training took {:} (h:mm:ss)".format(format_time(time.time()-total_t0)))

Expected behavior

THE ERROR: ======== Epoch 1 / 4 ======== Training...

ValueError Traceback (most recent call last)

in () 85 token_type_ids=None, 86 attention_mask=b_input_mask, ---> 87 labels=b_labels) 88 89 # Accumulate the training loss over all of the batches so that we can ValueError: too many values to unpack (expected 2) I am working an a four-label classification task (on an Arabic dataset). I have run this code before but it is not working now. I get this error: ValueError: too many values to unpack (expected 2). I have not changed any of the steps or the preprocessing but it raises up this error this time. The tensor for each label instance is [0,1,2,3]. The error points to the labels parameter. Could you please suggest solutions?

[cronoik]

Please post the full error stacktrace. Which version of the script are you using?

[sadanyh]

Hi thank you for your reply. I did post the trace back for the error.

Looking forward to your reply

Hadeel

On 21 Feb 2021, at 10:01 am, cronoik notifications@github.com wrote:

 Please post the full error stacktrace. Which version of the script are you using?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[sgugger]

Please use the forums to debug custom code with help from the community and only when you have isolated a part that is a bug in the library use a GitHub issue. In this particular case, you should include the full stack trace, as pointed out before (it's not in your message, just the last frame) and the code that created your model: the error seems to point out that it only returns one value when you need two (since you write loss, logits = model(...)). You should debug that by looking at the model return on one batch.

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.