src/evaluator.py [473:489]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            encoded = encoder("fwd", x=x1_, lengths=len1_, causal=False)
            decoded = decoder(
                "fwd",
                x=x2,
                lengths=len2,
                causal=True,
                src_enc=encoded.transpose(0, 1),
                src_len=len1_,
            )
            word_scores, loss = decoder(
                "predict", tensor=decoded, pred_mask=pred_mask, y=y, get_scores=True
            )

            # correct outputs per sequence / valid top-1 predictions
            t = torch.zeros_like(pred_mask, device=y.device)
            t[pred_mask] += word_scores.max(1)[1] == y
            valid = (t.sum(0) == len2 - 1).cpu().long()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/evaluator.py [609:625]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            encoded = encoder("fwd", x=x1_, lengths=len1_, causal=False)
            decoded = decoder(
                "fwd",
                x=x2,
                lengths=len2,
                causal=True,
                src_enc=encoded.transpose(0, 1),
                src_len=len1_,
            )
            word_scores, loss = decoder(
                "predict", tensor=decoded, pred_mask=pred_mask, y=y, get_scores=True
            )

            # correct outputs per sequence / valid top-1 predictions
            t = torch.zeros_like(pred_mask, device=y.device)
            t[pred_mask] += word_scores.max(1)[1] == y
            valid = (t.sum(0) == len2 - 1).cpu().long()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -