Using Subsequent Mask for Transformer Decoder Leads to NaN values

1

Hi.

I’m trying to implement an autoregressive transformer model similar to the paper “attention is all you need”. From what I’ve understood, in order to replicate the architecture fully, I need to give the transformer decoder 3 masks.

1 - Target subsequent mask: this is for casaulity.
2 - Target padding indexes: just to look at non-padded indices.
3 - Encoder padding indices: just to look at non-padded inputs from the encoder.

The snippet is here:

y = self.decoder(y, x,
                         tgt_mask=tgt_causal_mask,
                         tgt_key_padding_mask=tgt_padding_mask,
                         memory_key_padding_mask=src_padding_mask)

With masks being generated like this:


    def generate_no_peek_mask(self, sz):
        mask = (torch.triu(torch.ones(sz, sz)) == 1).transpose(0, 1)
        mask = mask.float().masked_fill(mask == 0, float("-inf")).masked_fill(mask == 1, float(0.0))
        mask = mask.to(self.device)
        return mask

    def generate_padding_mask(self, seq, pad_idx):
        return (seq != pad_idx).to(self.device)

The problem is that using these masks leads to issues with the Softmax function because of NaN values. Without these masks, the model does not generate any NaN value.