# Load the pre-trained BERT model
model = TFAutoModelForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

import tensorflow as tf
from tensorflow.keras.optimizers import Adam

# Instantiate the optimizer
optimizer = tf.keras.optimizers.Adam(learning_rate = 0.001)

# Compile the model
model.compile(
    loss=model.compute_loss,
    optimizer=optimizer,
    metrics=['accuracy']
)

model.fit(train_dataset, validation_data=val_dataset, epochs=3)

I am creating an entity extraction model in PyTorch using bert-base-uncased but when I try to run the model I get this error:

ValueError                                Traceback (most recent call last)
Cell In[13], line 11
      8 optimizer = tf.keras.optimizers.Adam(learning_rate = 0.001)
     10 # Compile the model
---> 11 model.compile(
     12     loss='sparse_categorical_crossentropy',
     13     optimizer=Adam,
     14     metrics=['accuracy']
     15 )
     20 # Train the model
     21 model.fit(train_dataset, validation_data=val_dataset, epochs=3)

File c:UsersASUSanaconda3Libsite-packagestransformersmodeling_tf_utils.py:1563, in TFPreTrainedModel.compile(self, optimizer, loss, metrics, loss_weights, weighted_metrics, run_eagerly, steps_per_execution, **kwargs)
   1561 # This argument got renamed, we need to support both versions
   1562 if "steps_per_execution" in parent_args:
-> 1563     super().compile(
   1564         optimizer=optimizer,
   1565         loss=loss,
   1566         metrics=metrics,
   1567         loss_weights=loss_weights,
   1568         weighted_metrics=weighted_metrics,
   1569         run_eagerly=run_eagerly,
   1570         steps_per_execution=steps_per_execution,
   1571         **kwargs,
...
--> 335     raise ValueError(
    336         f"Could not interpret optimizer identifier: {identifier}"
    337     )

ValueError: Could not interpret optimizer identifier: <class 'keras.src.optimizers.adam.Adam'>

I have the latest version for transformers(4.40.1) and keras (2.16.0).

I also referred to this thread but am still getting the same error.
“Could not interpret optimizer identifier” error in Keras