train_aviator_model.py

import torch
import torch.nn as nn
import torch.optim as optim
from aviator_predictor import AviatorLSTM
import numpy as np

def train_model():
    # Hyperparameters
    input_size = 1
    hidden_size = 64
    num_layers = 2
    output_size = 1
    learning_rate = 0.001
    num_epochs = 10

    model = AviatorLSTM(input_size, hidden_size, num_layers, output_size)
    criterion = nn.BCELoss()
    optimizer = optim.Adam(model.parameters(), lr=learning_rate)

    # Dummy training loop for demonstration
    print("Starting training...")
    for epoch in range(num_epochs):
        # Simulated batch
        inputs = torch.randn(32, 10, 1)
        targets = torch.randint(0, 2, (32, 1)).float()
        
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()
        
        if (epoch+1) % 2 == 0:
            print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')

    torch.save(model.state_dict(), 'aviator_model.pth')
    print("Model saved to aviator_model.pth")

if __name__ == '__main__':
    train_model()