tensorflow/models · error · ValueError

distill_ground_truth_ratio has to be within [0, 1].

Error message

distill_ground_truth_ratio has to be within [0, 1].

What it means

Error "distill_ground_truth_ratio has to be within [0, 1]." thrown in tensorflow/models.

Source

Thrown at official/projects/mobilebert/distillation.py:164

    transfer_teacher_layers = layer_wise_config.transfer_teacher_layers
    num_teacher_layers = (
        self._task_config.teacher_model.encoder.mobilebert.num_blocks)
    num_student_layers = (
        self._task_config.student_model.encoder.mobilebert.num_blocks)
    if transfer_teacher_layers and len(
        transfer_teacher_layers) != num_student_layers:
      raise ValueError('The number of `transfer_teacher_layers` %s does not '
                       'match the number of student layers. %d' %
                       (transfer_teacher_layers, num_student_layers))
    if not transfer_teacher_layers and (num_teacher_layers !=
                                        num_student_layers):
      raise ValueError('`transfer_teacher_layers` is not specified, and the '
                       'number of teacher layers does not match '
                       'the number of student layers.')

    ratio = progressive.pretrain_distill_config.distill_ground_truth_ratio
    if ratio < 0 or ratio > 1:
      raise ValueError('distill_ground_truth_ratio has to be within [0, 1].')

    # A non-trainable layer for feature normalization for transfer loss
    self._layer_norm = tf_keras.layers.LayerNormalization(
        axis=-1,
        beta_initializer='zeros',
        gamma_initializer='ones',
        trainable=False)

    # Build the teacher and student pretrainer model.
    self._teacher_pretrainer = self._build_pretrainer(
        self._task_config.teacher_model, name='teacher')
    self._student_pretrainer = self._build_pretrainer(
        self._task_config.student_model, name='student')

    base_task.Task.__init__(
        self, params=task_config, logging_dir=logging_dir)
    policies.ProgressivePolicy.__init__(self)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/mobilebert/distillation.py:164 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/2346221dd8009a9d. Report an issue: GitHub.