tensorflow/models · error · ValueError
Unknown distillation mode: {self.mode}.
Error message
Unknown distillation mode: {self.mode}. What it means
Error "Unknown distillation mode: {self.mode}." thrown in tensorflow/models.
Source
Thrown at official/projects/edgetpu/nlp/mobilebert_edgetpu_trainer.py:229
student_attention_score=student_attention_score,
teacher_output_feature=teacher_output_feature,
teacher_attention_score=teacher_attention_score))
elif self.mode == DistillationMode.END2END:
# Build a model that outputs teacher's and student's MLM/NSP outputs.
inputs = self.student_model.inputs
student_pretrainer_outputs = self.student_model(inputs)
teacher_pretrainer_outputs = self.teacher_model(inputs)
model = tf_keras.Model(
inputs=inputs,
outputs=dict(
student_pretrainer_outputs=student_pretrainer_outputs,
teacher_pretrainer_outputs=teacher_pretrainer_outputs,
))
# Checkpoint the student encoder which is the goal of distillation.
model.checkpoint_items = self.student_model.checkpoint_items
return model
else:
raise ValueError(f'Unknown distillation mode: {self.mode}.')
def build_optimizer(self, config):
"""Creates optimier for the fused model."""
optimizer_config = self.optimizer_config.replace(
learning_rate={
'polynomial': {
'decay_steps': config.decay_steps,
'initial_learning_rate': config.initial_learning_rate,
'end_learning_rate': config.end_learning_rate,
}
},
warmup={
'type': 'linear',
'linear': {
'warmup_steps': config.warmup_steps,
}
})
logging.info('The optimizer config is: %s', optimizer_config.as_dict())View on GitHub (pinned to e006f5f0d5)
When it happens
Trigger: Thrown at official/projects/edgetpu/nlp/mobilebert_edgetpu_trainer.py:229 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/05db731b2ead121d.
Report an issue: GitHub.