def aggregate_logging_outputs()

in custom/candidate_penalty_ce_loss.py [0:0]

• 20 lines of code
• 11 McCabe index (conditional complexity)

    def aggregate_logging_outputs(logging_outputs):
        """Aggregate logging outputs from data parallel training."""
        loss_sum = sum(log.get('loss', 0) for log in logging_outputs)
        custom_loss_sum = sum(log.get('custom_loss', 0) for log in logging_outputs)
        ntokens = sum(log.get('ntokens', 0) for log in logging_outputs)
        nsentences = sum(log.get('nsentences', 0) for log in logging_outputs)
        sample_size = sum(log.get('sample_size', 0) for log in logging_outputs)

        agg_output = {
            'loss': loss_sum / sample_size / math.log(2) if sample_size > 0 else 0.,
            'custom_loss': custom_loss_sum / sample_size / math.log(2) if sample_size > 0 else 0.,
            'ntokens': ntokens,
            'nsentences': nsentences,
            'sample_size': sample_size,
        }

        from fairseq.custom.metrics import TrainingMetrics
        custom_output = TrainingMetrics.aggregate_and_normalize(logging_outputs)
        for k, v in custom_output.items():
            agg_output[k] = v

        if sample_size != ntokens:
            agg_output['nll_loss'] = loss_sum / ntokens / math.log(2) if ntokens > 0 else 0.
        return agg_output