Expected input batch_size (1) to match target batch_size (11)

I know this seems to be a common problem but I wasn't able to find a solution. I'm running a multi-label classification model and having issues with tensor sizing.

My full code looks like this:

from transformers import DistilBertTokenizerFast, DistilBertForSequenceClassification
import torch

# Instantiating tokenizer and model
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-cased')
model = DistilBertForSequenceClassification.from_pretrained('distilbert-base-cased')

# Instantiating quantized model
quantized_model = torch.quantization.quantize_dynamic(model, {torch.nn.Linear}, dtype=torch.qint8)

# Forming data tensors
input_ids = torch.tensor(tokenizer.encode(x_train[0], add_special_tokens=True)).unsqueeze(0)
labels = torch.tensor(Y[0]).unsqueeze(0)

# Train model
outputs = quantized_model(input_ids, labels=labels)
loss, logits = outputs[:2]

Which yields the error:

ValueError: Expected input batch_size (1) to match target batch_size (11)

Input_ids looks like:

tensor([[  101,   789,   160,  1766,  1616,  1110,   170,  1205,  7727,  1113,
           170,  2463,  1128,  1336,  1309,  1138,   112,   119, 11882, 11545,
           119,   108, 15710,   108,  3645,   108,  3994,   102]])

with shape:

torch.Size([1, 28])

and labels looks like:

tensor([[0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1]])

with shape:

torch.Size([1, 11])

The size of input_ids will vary as the strings to be encoded vary in size.

I also noticed that when feeding in 5 values of Y to produce 5 labels, it yields the error:

ValueError: Expected input batch_size (1) to match target batch_size (55).

with labels shape:

torch.Size([1, 5, 11])

(Note that I didn't feed 5 input_ids, which is presumably why input size remains constant)

I've tried a few different approaches to getting these to work, but I'm currently at a loss. I'd really appreciate some guidance. Thanks!