train.py

from transformers import Trainer, TrainingArguments, AutoModelForSequenceClassification, AutoTokenizer
from datasets import load_dataset
import numpy as np
import evaluate

# Load dataset
dataset = load_dataset("imdb")
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")

# Tokenization function
def tokenize_function(example):
    return tokenizer(example["text"], padding="max_length", truncation=True)

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

# Load model
model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased", num_labels=2)

# Load accuracy metric
accuracy = evaluate.load("accuracy")

# Compute metrics function
def compute_metrics(eval_pred):
    logits, labels = eval_pred
    predictions = np.argmax(logits, axis=-1)
    return accuracy.compute(predictions=predictions, references=labels)

# Define training arguments
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    learning_rate=2e-5,
    per_device_train_batch_size=8,
    per_device_eval_batch_size=8,
    num_train_epochs=1,
    weight_decay=0.01,
)

# Initialize Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_datasets["train"].shuffle(seed=42).select(range(2000)),
    eval_dataset=tokenized_datasets["test"].shuffle(seed=42).select(range(1000)),
    compute_metrics=compute_metrics,
)

# Train model
trainer.train()