def target, mask): нин batch_size, seq_len, num_classes network_output.shape flat_output network_output.view(-1, num_classes) flat_target target.view(batch_size seq_len) flat_mask mask.view(batch_size

def target, mask):
нин
batch_size, seq_len, num_classes network_output.shape
flat_output network_output.view(-1, num_classes)
flat_target target.view(batch_size seq_len)
flat_mask mask.view(batch_size seq_len)
per_token_loss F.cross_entropy(flat_output, flat_target, reduce=False)
return th.sum(per_token_loss flat_mask) th.sum(flat_mask)