from datasets import load_dataset
from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
from transformers import AutoTokenizer
import torch

# Load the dataset
dataset = load_dataset("louiecerv/sentiment_analysis")

# Load tokenizer
model_checkpoint = "distilbert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

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

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

# Prepare dataset for training
train_dataset = tokenized_datasets["train"]

# Load model
model = AutoModelForSequenceClassification.from_pretrained(model_checkpoint, num_labels=2)

# Training arguments
training_args = TrainingArguments(
    output_dir="./results",
    eval_strategy="no",
    per_device_train_batch_size=8,
    per_device_eval_batch_size=8,
    num_train_epochs=3,
    save_strategy="epoch",
    push_to_hub=True,
    hub_model_id="louiecerv/sentiment_analysis_model"
)

# Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset
)

# Train and save model
trainer.train()
trainer.push_to_hub()