Okay here is a standalone code that should be close enough? (if I missed anything let me know)

` import tempfile
from datetime import datetime
from pathlib import Path

import tensorflow as tf
import tensorflow_datasets as tfds
from clearml import Task

task = Task.init(project_name="debug", task_name="test")
(ds_train, ds_test), ds_info = tfds.load(
'mnist',
split=['train', 'test'],
shuffle_files=True,
as_supervised=True,
with_info=True,
)

def normalize_img(image, label):
"""Normalizes images: uint8 -> float32."""
return tf.cast(image, tf.float32) / 255., label

ds_train = ds_train.map(
normalize_img, num_parallel_calls=tf.data.AUTOTUNE)

ds_train = ds_train.cache()
ds_train = ds_train.shuffle(ds_info.splits['train'].num_examples)
ds_train = ds_train.batch(128)
ds_train = ds_train.prefetch(tf.data.AUTOTUNE)
ds_test = ds_test.map(
normalize_img, num_parallel_calls=tf.data.AUTOTUNE)
ds_test = ds_test.batch(128)
ds_test = ds_test.cache()
ds_test = ds_test.prefetch(tf.data.AUTOTUNE)
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(10)
])
model.compile(
optimizer=tf.keras.optimizers.Adam(0.001),
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=[tf.keras.metrics.SparseCategoricalAccuracy()],
)

log_dir = Path(tempfile.gettempdir()) / datetime.now().strftime("%Y%m%d-%H%M%S")
file_writer = tf.summary.create_file_writer(str(log_dir / "metrics"))
file_writer.set_as_default()

cb = tf.keras.callbacks.TensorBoard(log_dir=log_dir, update_freq='epoch')
model.fit(
ds_train,
epochs=6,
validation_data=ds_test,
callbacks=[cb]
) `