trainer.py

# Import Hugging Face libraries and datasets
from transformers import Trainer, TrainingArguments, BertForSequenceClassification, BertTokenizer
from datasets import load_dataset

# Load dataset
dataset = load_dataset("imdb")

# Preprocess data: Tokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

def tokenize_function(examples):
    return tokenizer(examples['text'], padding='max_length', truncation=True)

# Apply tokenization
tokenized_datasets = dataset.map(tokenize_function, batched=True)

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

# Training Arguments
training_args = TrainingArguments(
    output_dir='/results',               # Save path in the Space environment
    evaluation_strategy="epoch",         # Eval after each epoch
    learning_rate=2e-5,                  # Learning rate
    per_device_train_batch_size=8,       # Training batch size
    per_device_eval_batch_size=8,        # Eval batch size
    num_train_epochs=3,                  # Number of epochs
    weight_decay=0.01                    # Weight decay for regularization
)

# Trainer setup
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["test"]
)

# Train the model (this will run in the cloud, no need for local machine)
trainer.train()