How to use the PyTorch Transformer with multi-dimensional sequence-to-seqence?

I'm trying to go seq2seq with a Transformer model. My input and output are the same shape (torch.Size([499, 128]) where 499 is the sequence length and 128 is the number of features.

My input looks like:

My output looks like:

My training loop is:

    for batch in tqdm(dataset):
        optimizer.zero_grad()
        x, y = batch

        x = x.to(DEVICE)
        y = y.to(DEVICE)

        pred = model(x, torch.zeros(x.size()).to(DEVICE))

        loss = loss_fn(pred, y)
        loss.backward()
        optimizer.step()

My model is:

import math
from typing import final
import torch
import torch.nn as nn

class Reconstructor(nn.Module):
    def __init__(self, input_dim, output_dim, dim_embedding, num_layers=4, nhead=8, dim_feedforward=2048, dropout=0.5):
        super(Reconstructor, self).__init__()

        self.model_type = 'Transformer'
        self.src_mask = None
        self.pos_encoder = PositionalEncoding(d_model=dim_embedding, dropout=dropout)
        self.transformer = nn.Transformer(d_model=dim_embedding, nhead=nhead, dim_feedforward=dim_feedforward, num_encoder_layers=num_layers, num_decoder_layers=num_layers)
        self.decoder = nn.Linear(dim_embedding, output_dim)
        self.decoder_act_fn = nn.PReLU()

        self.init_weights()

    def init_weights(self):
        initrange = 0.1
        nn.init.zeros_(self.decoder.weight)
        nn.init.uniform_(self.decoder.weight, -initrange, initrange)

    def forward(self, src, tgt):

        pe_src = self.pos_encoder(src.permute(1, 0, 2))  # (seq, batch, features)
        transformer_output = self.transformer_encoder(pe_src)
        decoder_output = self.decoder(transformer_output.permute(1, 0, 2)).squeeze(2)
        decoder_output = self.decoder_act_fn(decoder_output)
        return decoder_output

My output has a shape of torch.Size([32, 499, 128]) where 32 is batch, 499 is my sequence length and 128 is the number of features. But the output has the same values:

tensor([[[0.0014, 0.0016, 0.0017,  ..., 0.0018, 0.0021, 0.0017],
         [0.0014, 0.0016, 0.0017,  ..., 0.0018, 0.0021, 0.0017],
         [0.0014, 0.0016, 0.0017,  ..., 0.0018, 0.0021, 0.0017],
         ...,
         [0.0014, 0.0016, 0.0017,  ..., 0.0018, 0.0021, 0.0017],
         [0.0014, 0.0016, 0.0017,  ..., 0.0018, 0.0021, 0.0017],
         [0.0014, 0.0016, 0.0017,  ..., 0.0018, 0.0021, 0.0017]]],
       grad_fn=<PreluBackward>)

What am I doing wrong? Thank you so much for any help.

from How to use the PyTorch Transformer with multi-dimensional sequence-to-seqence?