keras_bert.py

from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
import tensorflow as tf

model_name = 'bert-base-cased'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = TFAutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)

texts = ["I'm a positive example!", "I'm a negative example!"]
labels = [1, 0]

# Pad the tokenizer outputs to the same length for all samples
processed_text = tokenizer(texts, padding='longest', return_tensors='tf')  
labels = tf.convert_to_tensor(labels)

opt = tf.keras.optimizers.Adam(5e-5)  # Transformers like lower learning rates
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)  # Model outputs raw logits
model.compile(optimizer=opt, loss=loss)

model.fit(dict(processed_text), labels, epochs=3)