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

# Load dataset
dataset = load_dataset("csv", data_files={"train": "train_data.csv", "test": "test_data.csv"})

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased", num_labels=6)

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

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

# Training arguments
training_args = TrainingArguments(
    output_dir="./results",
    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,
    hub_model_id="PSivaMallikarjun/herbivorous-food-model"
)

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

# Train model
trainer.train()

# Save model
trainer.save_model("herbivorous_food_model")
print("Model training complete and saved!")

# Push to Hugging Face Hub
trainer.push_to_hub()