train.py

import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader

from chatbot.preprocessing import load_training_data
from chatbot.model import ChatModel

import numpy as np
import json
import random

# Load data
X_train, y_train, all_words, tags = load_training_data('data/intents.json')

# Hyperparameters
batch_size = 8
hidden_size = 8
input_size = len(X_train[0])
output_size = len(tags)
learning_rate = 0.001
num_epochs = 1000

# Custom Dataset
class ChatDataset(Dataset):
    def __init__(self):
        self.n_samples = len(X_train)
        self.x_data = X_train
        self.y_data = y_train

    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]

    def __len__(self):
        return self.n_samples

dataset = ChatDataset()
train_loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True)

# Model, loss, optimizer
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = ChatModel(input_size, hidden_size, output_size).to(device)

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Training loop
for epoch in range(num_epochs):
    for (words, labels) in train_loader:
        words = words.to(device)
        labels = labels.to(dtype=torch.long).to(device)

        outputs = model(words)
        loss = criterion(outputs, labels)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    if (epoch+1) % 100 == 0:
        print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')

print(f'Final loss: {loss.item():.4f}')

# Save model
model_data = {
    "model_state": model.state_dict(),
    "input_size": input_size,
    "hidden_size": hidden_size,
    "output_size": output_size,
    "all_words": all_words,
    "tags": tags
}

FILE = "chatbot_model.pth"
torch.save(model_data, FILE)

print(f'Model trained and saved to {FILE}')