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

# Load dataset from Hugging Face
dataset = load_dataset("Soundaryasos/Verdictclassifications")

# Load tokenizer and model
model_name = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_name)

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

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

# Load model for binary classification (Guilty/Not Guilty)
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)

# Training arguments
training_args = TrainingArguments(
    output_dir="criminal_case_model",
    evaluation_strategy="epoch",
    save_strategy="epoch",
    per_device_train_batch_size=8,
    per_device_eval_batch_size=8,
    num_train_epochs=3,
    weight_decay=0.01,
    push_to_hub=True,  # Push model to Hugging Face
    logging_dir="./logs",
)

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

# Train the model
trainer.train()

trainer.push_to_hub("Soundaryasos/criminal_case_model")