callbacks = [
    EarlyStopping(monitor='val_loss', patience=2, verbose=0),
    ModelCheckpoint(kfold_weights_path, monitor='val_loss', save_best_only=True, verbose=0),
]
model.fit(X_train.astype('float32'), Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
      shuffle=True, verbose=1, validation_data=(X_valid, Y_valid),
      callbacks=callbacks)​

if val_loss < THR:
    break​

I found the answer. I looked into Keras sources and find out code for EarlyStopping. I made my own callback, based on it:

class EarlyStoppingByLossVal(Callback):
    def __init__(self, monitor='val_loss', value=0.00001, verbose=0):
        super(Callback, self).__init__()
        self.monitor = monitor
        self.value = value
        self.verbose = verbose

    def on_epoch_end(self, epoch, logs={}):
        current = logs.get(self.monitor)
        if current is None:
            warnings.warn("Early stopping requires %s available!" % self.monitor, RuntimeWarning)

        if current < self.value:
            if self.verbose > 0:
                print("Epoch %05d: early stopping THR" % epoch)
            self.model.stop_training = True

And usage:

callbacks = [
    EarlyStoppingByLossVal(monitor='val_loss', value=0.00001, verbose=1),
    # EarlyStopping(monitor='val_loss', patience=2, verbose=0),
    ModelCheckpoint(kfold_weights_path, monitor='val_loss', save_best_only=True, verbose=0),
]
model.fit(X_train.astype('float32'), Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
      shuffle=True, verbose=1, validation_data=(X_valid, Y_valid),
      callbacks=callbacks)

I solved the same problem using custom callback.

In the following custom callback code assign THR with the value at which you want to stop training and add the callback to your model.

from keras.callbacks import Callback

class stopAtLossValue(Callback):

        def on_batch_end(self, batch, logs={}):
            THR = 0.03 #Assign THR with the value at which you want to stop training.
            if logs.get('loss') <= THR:
                 self.model.stop_training = True

The keras.callbacks.EarlyStopping callback does have a min_delta argument. From Keras documentation:

min_delta: minimum change in the monitored quantity to qualify as an improvement, i.e. an absolute change of less than min_delta, will count as no improvement.

Keras is an open-source neural network library written in Python. There are many classes in Keras. Keras supports the early stopping of training via a callback called EarlyStopping. You can use

tf.keras.callbacks.EarlyStopping

For example:

#python implementation

callbacks = [ EarlyStoppingByLossVal(monitor='val_loss', value=0.00001, verbose=1)

ModelCheckpoint(kfold_weights_path, monitor='val_loss', save_best_only=True, verbose=0), ] model.fit(X_train.astype('float32'),

Y_train, batch_size=batch_size, nb_epoch=nb_epoch, shuffle=True, verbose=1, validation_data=(X_valid, Y_valid), callbacks=callbacks)

It stops training when a monitored quantity(threshold value) has stopped improving. This callback allows you to specify the performance measure to monitor the trigger, and once triggered, it will stop the training process. The EarlyStopping callback is configured when instantiated via arguments.