tensorflow/models · error · ValueError

Unexpected negative label_id: %s

Error message

Unexpected negative label_id: %s

What it means

Error "Unexpected negative label_id: %s" thrown in tensorflow/models.

Source

Thrown at official/nlp/data/tagging_data_lib.py:228

  def get_labels(self):
    return [
        "ADJ", "ADP", "ADV", "AUX", "CCONJ", "DET", "INTJ", "NOUN", "NUM",
        "PART", "PRON", "PROPN", "PUNCT", "SCONJ", "SYM", "VERB", "X"
    ]

  @staticmethod
  def get_processor_name():
    return "udpos"


def _tokenize_example(example, max_length, tokenizer, text_preprocessing=None):
  """Tokenizes words and breaks long example into short ones."""
  # Needs additional [CLS] and [SEP] tokens.
  max_length = max_length - 2
  new_examples = []
  new_example = InputExample(sentence_id=example.sentence_id, sub_sentence_id=0)
  if any([x < 0 for x in example.label_ids]):
    raise ValueError("Unexpected negative label_id: %s" % example.label_ids)

  for i, word in enumerate(example.words):
    if text_preprocessing:
      word = text_preprocessing(word)
    subwords = tokenizer.tokenize(word)
    if (not subwords or len(subwords) > max_length) and word:
      subwords = [_UNK_TOKEN]

    if len(subwords) + len(new_example.words) > max_length:
      # Start a new example.
      new_examples.append(new_example)
      last_sub_sentence_id = new_example.sub_sentence_id
      new_example = InputExample(
          sentence_id=example.sentence_id,
          sub_sentence_id=last_sub_sentence_id + 1)

    for j, subword in enumerate(subwords):
      # Use the real label for the first subword, and pad label for

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/data/tagging_data_lib.py:228 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24). Data as JSON: /api/errors/aab93d87d4017074. Report an issue: GitHub.