import torch
import torch.nn as nn

# Explicitly detect and assign the cluster's GPU device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Target runtime device assigned: {device}")

if device.type == 'cuda':
    print(f"Active GPU Hardware: {torch.cuda.get_device_name(0)}")
else:
    print("WARNING: CUDA is not active. The script is falling back to CPU compute paths.")

# Define a minimal linear transformation model
model = nn.Sequential(
    nn.Linear(10, 50),
    nn.ReLU(),
    nn.Linear(50, 2)
).to(device)

print("Neural network layer architecture moved onto device memory.")

# Generate arbitrary mock tensor parameters directly on the device
inputs = torch.randn(32, 10).to(device)
print(f"Input batch tensor shape: {inputs.shape}")

# Execute forward processing pass
outputs = model(inputs)
print(f"Forward computation completed. Output matrix shape: {outputs.shape}")

# Simple validation calculation assertion
loss = outputs.sum()
print(f"Verification tracking metric: {loss.item():.4f}")
print("PyTorch model diagnostics ran successfully!")