pythonlessons · September 4, 2023 15:04
diff --git a/transformers_training_11.py b/transformers_training_11.py
 optimizer = tf.keras.optimizers.Adam(learning_rate=configs.init_lr, beta_1=0.9, beta_2=0.98, epsilon=1e-9)

 # Compile the model
 transformer.compile(
    loss=MaskedLoss(),
    optimizer=optimizer,
    metrics=[MaskedAccuracy()],
    run_eagerly=False
    )
	optimizer = tf.keras.optimizers.Adam(learning_rate=configs.init_lr, beta_1=0.9, beta_2=0.98, epsilon=1e-9)

	# Compile the model
	transformer.compile(
	loss=MaskedLoss(),
	optimizer=optimizer,
	metrics=[MaskedAccuracy()],
	run_eagerly=False
	)