tf.keras.callbacks.TerminateOnNaN

View source on GitHub

Callback that terminates training when a NaN loss is encountered.

Inherits From: Callback

tf.keras.callbacks.TerminateOnNaN(
    raise_error: bool = False
)

This callback monitors the loss value during training and terminates training when a NaN or Inf loss is detected. By default, training is stopped gracefully by setting model.stop_training = True, which triggers all callback cleanup methods including on_train_end().

Alternatively, you can use raise_error=True to immediately raise a RuntimeError when NaN/Inf is detected. This raise_error termination prevents on_train_end() from being called on other callbacks, which is useful for preserving backup states or preventing unintended cleanup when training fails.

Args
`raise_error`	Boolean, default False. If False, uses graceful stop via `model.stop_training = True`. If True, immediately raises RuntimeError on NaN/Inf loss, bypassing callback cleanup methods.

Example:

# Graceful termination (default)
callback = keras.callbacks.TerminateOnNaN()
model.fit(x, y, callbacks=[callback])

# raise_error termination (strict failure)
callback = keras.callbacks.TerminateOnNaN(raise_error=True)
model.fit(x, y, callbacks=[callback])

Attributes

model

Methods

`on_batch_begin`

on_batch_begin(
    batch, logs=None
)

A backwards compatibility alias for on_train_batch_begin.

`on_batch_end`

on_batch_end(
    batch, logs=None
)

Check for NaN/Inf loss at the end of each batch.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict, contains the return value of `model.train_step()`.

Raises
`RuntimeError`	If loss is NaN/Inf and raise_error=True.

`on_epoch_begin`

on_epoch_begin(
    epoch, logs=None
)

Called at the start of an epoch.

Subclasses should override for any actions to run. This function should only be called during TRAIN mode.

Args
`epoch`	Integer, index of epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_epoch_end`

on_epoch_end(
    epoch, logs=None
)

Called at the end of an epoch.

Subclasses should override for any actions to run. This function should only be called during TRAIN mode.

Args
`epoch`	Integer, index of epoch.
`logs`	Dict, metric results for this training epoch, and for the validation epoch if validation is performed. Validation result keys are prefixed with `val_`. For training epoch, the values of the `Model`'s metrics are returned. Example: `{'loss': 0.2, 'accuracy': 0.7}`.

`on_predict_batch_begin`

on_predict_batch_begin(
    batch, logs=None
)

Called at the beginning of a batch in predict methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_predict_batch_end`

on_predict_batch_end(
    batch, logs=None
)

Called at the end of a batch in predict methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Aggregated metric results up until this batch.

`on_predict_begin`

on_predict_begin(
    logs=None
)

Called at the beginning of prediction.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_predict_end`

on_predict_end(
    logs=None
)

Called at the end of prediction.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_test_batch_begin`

on_test_batch_begin(
    batch, logs=None
)

Called at the beginning of a batch in evaluate methods.

Also called at the beginning of a validation batch in the fit methods, if validation data is provided.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_test_batch_end`

on_test_batch_end(
    batch, logs=None
)

Called at the end of a batch in evaluate methods.

Also called at the end of a validation batch in the fit methods, if validation data is provided.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Aggregated metric results up until this batch.

`on_test_begin`

on_test_begin(
    logs=None
)

Called at the beginning of evaluation or validation.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_test_end`

on_test_end(
    logs=None
)

Called at the end of evaluation or validation.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently the output of the last call to `on_test_batch_end()` is passed to this argument for this method but that may change in the future.

`on_train_batch_begin`

on_train_batch_begin(
    batch, logs=None
)

Called at the beginning of a training batch in fit methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_train_batch_end`

on_train_batch_end(
    batch, logs=None
)

Called at the end of a training batch in fit methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Aggregated metric results up until this batch.

`on_train_begin`

on_train_begin(
    logs=None
)

Called at the beginning of training.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_train_end`

on_train_end(
    logs=None
)

Called at the end of training.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently the output of the last call to `on_epoch_end()` is passed to this argument for this method but that may change in the future.

`set_model`

set_model(
    model
)

`set_params`

set_params(
    params
)

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2026-11-04 UTC.