Задача о построение сети на фото. Ошибка в GPU-тренажёре: ваш код работает, но не выполняет поставленное задание либо делает что-либо сверх задания

import pandas as pd
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications.resnet import ResNet50
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.layers import GlobalAveragePooling2D, Flatten, Dense

def load_train(path):
    labels = pd.read_csv('/datasets/faces/labels.csv')
    train_datagen = ImageDataGenerator(
        rescale=1./255,
        validation_split=0.25
    )
    train_gen_flow = train_datagen.flow_from_dataframe(
        dataframe=labels,
        directory='/datasets/faces/final_files',
        x_col='file_name',
        y_col='real_age',
        target_size=(224, 224),
        batch_size=32,
        class_mode='raw',
        subset='training',
        seed=12345)

    return train_gen_flow

def load_test(path):
    labels = pd.read_csv('/datasets/faces/labels.csv')
    test_datagen = ImageDataGenerator(rescale=1./255)
                            
    test_gen_flow = test_datagen.flow_from_dataframe(
        dataframe=labels,
        directory= '/datasets/faces/final_files',
        x_col='file_name',
        y_col='real_age',
        target_size=(224, 224),
        batch_size=32,
        class_mode='raw',
        subset='validation',
        seed=12345)

    return test_gen_flow

def create_model(input_shape):
    optimizer = Adam(learning_rate = 0.0005)
    backbone = ResNet50(
        input_shape=(224, 224, 3),
        weights='imagenet',
        include_top=False
    )

    model = Sequential()
    model.add(backbone)
    model.add(GlobalAveragePooling2D())
    model.add(Dense(1, activation='relu'))
    model.compile(optimizer=optimizer, loss= 'mean_absolute_error', metrics=['mae'])

    return model

def train_model(model, train_data, test_data, batch_size=None, epochs=10, steps_per_epoch=None, validation_steps=None):
    train_gen_flow=train_data
    test_gen_flow=test_data
    if steps_per_epoch is None:
        steps_per_epoch = len(train_data)
        validation_steps = len(test_data)

    model.fit(
        train_data,
        epochs=epochs,
        steps_per_epoch=steps_per_epoch,
        validation_data=test_data,
        validation_steps=validation_steps,
        verbose=2)
    return model