Getting ValueError

Hey there,
I am trying to use BERT for the multilabel classification task. But I got this unexpected error below.

I set the batch_size to 32 in train and validation data loader
Here is the code below.
train_loss_set = []
epochs = 4
for _ in trange(epochs, desc=“Epoch”):
model.train()
tr_loss = 0
nb_tr_examples, nb_tr_steps = 0, 0
for step, batch in enumerate(train_dataloader):
batch = tuple(t.to(device) for t in batch)
b_input_ids, b_input_mask, b_labels = batch
optimizer.zero_grad()
loss = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask, labels=b_labels)
train_loss_set.append(loss.item())
loss.backward()
optimizer.step()
tr_loss += loss.item()
nb_tr_examples += b_input_ids.size(0)
nb_tr_steps += 1
print(“Train loss: {}”.format(tr_loss/nb_tr_steps))
model.eval()
eval_loss, eval_accuracy = 0, 0
nb_eval_steps, nb_eval_examples = 0, 0

for batch in validation_dataloader:
batch = tuple(t.to(device) for t in batch)
b_input_ids, b_input_mask, b_labels = batch
with torch.no_grad():
logits = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask)
logits = logits.detach().cpu().numpy()
label_ids = b_labels.to(‘cpu’).numpy()
tmp_eval_accuracy = flat_accuracy(logits, label_ids)
eval_accuracy += tmp_eval_accuracy
nb_eval_steps += 1
print(“Validation Accuracy: {}”.format(eval_accuracy/nb_eval_steps))

Hi,

You can use triple backticks to format your code nicely:

```
# Your code
```

For your specific question, it looks like the label Tensor you give your loss has a first dimension of size 192. While it should be the same as the input 32.
You might want to add some prints to make sure it has the right size.