I am trying to use Adam anizer in Google Colab. I have the following code:

import tensorflow as tf
import numpy as np
from transformers import BertTokenizer, TFBertForSequenceClassification
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.losses import SparseCategoricalCrossentropy

I compile my model using the code below:

modelpile(
    optimizer=tf.keras.optimizers.Adam(learning_rate=2e-5),
    loss=SparseCategoricalCrossentropy(from_logits=True),
    metrics=["accuracy"]
)

But I get:

ValueError                                Traceback (most recent call last)
<ipython-input-38-0183d53e319d> in <cell line: 0>()
----> 1 modelpile(
      2     optimizer=tf.keras.optimizers.Adam(learning_rate=2e-5),
      3     loss=SparseCategoricalCrossentropy(from_logits=True),
      4     metrics=["accuracy"]
      5 )

2 frames
/usr/local/lib/python3.11/dist-packages/tf_keras/src/optimizers/__init__.py in get(identifier, **kwargs)
    333         )
    334     else:
--> 335         raise ValueError(
    336             f"Could not interpret optimizer identifier: {identifier}"
    337         )

ValueError: Could not interpret optimizer identifier: <keras.src.optimizers.adam.Adam object at 0x7cef33ad4050>

What am I missing?