Transformers replacing loss function

This page shows how to use a custom trainer

from torch import nn
from transformers import Trainer


class CustomTrainer(Trainer):
    def compute_loss(self, model, inputs, return_outputs=False):
        labels = inputs.get("labels")
        # forward pass
        outputs = model(**inputs)
        logits = outputs.get("logits")
        # compute custom loss (suppose one has 3 labels with different weights)
        loss_fct = nn.CrossEntropyLoss(weight=torch.tensor([1.0, 2.0, 3.0]))
        loss = loss_fct(logits.view(-1, self.model.config.num_labels), labels.view(-1))
        return (loss, outputs) if return_outputs else loss

My questions -

  1. if logits = outputs.get("logits") returns logits then why outputs are always in range 0 to 1? Am I missing something?
  2. I have class imbalance problem and I would like to use bce with logits loss? That loss requires input to be logits (values before converting to probability) . what should I do to use that loss?