tensorflow/models · error · ValueError

Task %s not supported.

Error message

Task %s not supported.

What it means

Error "Task %s not supported." thrown in tensorflow/models.

Source

Thrown at official/nlp/finetuning/glue/run_glue.py:129

        metric_type='matthews_corrcoef')
  elif FLAGS.task_name in ('MNLI', 'QNLI', 'RTE', 'SST-2',
                           'WNLI'):
    override_task_cfg_fn = functools.partial(
        binary_helper.override_sentence_prediction_task_config,
        num_classes=input_meta_data['num_labels'])
  elif FLAGS.task_name in ('QQP', 'MRPC'):
    override_task_cfg_fn = functools.partial(
        binary_helper.override_sentence_prediction_task_config,
        metric_type='f1',
        num_classes=input_meta_data['num_labels'])
  elif FLAGS.task_name in ('STS-B',):
    override_task_cfg_fn = functools.partial(
        binary_helper.override_sentence_prediction_task_config,
        num_classes=1,
        metric_type='pearson_spearman_corr',
        label_type='float')
  else:
    raise ValueError('Task %s not supported.' % FLAGS.task_name)

  binary_helper.override_trainer_cfg(
      exp_config.trainer,
      learning_rate=FLAGS.learning_rate,
      num_epoch=FLAGS.num_epoch,
      global_batch_size=FLAGS.global_batch_size,
      warmup_ratio=FLAGS.warmup_ratio,
      training_data_size=input_meta_data['train_data_size'],
      eval_data_size=input_meta_data['eval_data_size'],
      num_eval_per_epoch=FLAGS.num_eval_per_epoch,
      best_checkpoint_export_subdir=BEST_CHECKPOINT_EXPORT_SUBDIR,
      best_checkpoint_eval_metric=EVAL_METRIC_MAP[FLAGS.task_name],
      best_checkpoint_metric_comp='higher')

  override_task_cfg_fn(
      exp_config.task,
      model_config_file=FLAGS.model_config_file,
      init_checkpoint=FLAGS.init_checkpoint,

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/finetuning/glue/run_glue.py:129 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/6a3855479ade6b11. Report an issue: GitHub.