const { torch } = require("js-pytorch");

// Instantiate Tensors:
let x = torch.randn([8, 4, 5]);
let w = torch.randn([8, 5, 4], (requires_grad = true));
let b = torch.tensor([0.2, 0.5, 0.1, 0.0], (requires_grad = true));

// Make calculations:
let out = torch.matmul(x, w);
out = torch.add(out, b);

// Compute gradients on whole graph:
out.backward();

// Get gradients from specific Tensors:
console.log(w.grad);
console.log(b.grad);

const { torch } = require("js-pytorch");
const nn = torch.nn;
const optim = torch.optim;

// Define training hyperparameters:
const vocab_size = 52;
const hidden_size = 32;
const n_timesteps = 16;
const n_heads = 4;
const dropout_p = 0;
const batch_size = 8;

// Create Transformer decoder Module:
class Transformer extends nn.Module {
  constructor(vocab_size, hidden_size, n_timesteps, n_heads, dropout_p) {
    super();
    // Instantiate Transformer's Layers:
    this.embed = new nn.Embedding(vocab_size, hidden_size);
    this.pos_embed = new nn.PositionalEmbedding(n_timesteps, hidden_size);
    this.b1 = new nn.Block(hidden_size, hidden_size, n_heads, n_timesteps,dropout_p);
    this.b2 = new nn.Block(hidden_size, hidden_size, n_heads, n_timesteps,dropout_p);
    this.ln = new nn.LayerNorm(hidden_size);
    this.linear = new nn.Linear(hidden_size, vocab_size);
  }

  forward(x) {
    let z;
    z = torch.add(this.embed.forward(x), this.pos_embed.forward(x));
    z = this.b1.forward(z);
    z = this.b2.forward(z);
    z = this.ln.forward(z);
    z = this.linear.forward(z);
    return z;
  }
}

// Instantiate your custom nn.Module:
const model = new Transformer(vocab_size, hidden_size, n_timesteps, n_heads, dropout_p);

// Define loss function and optimizer:
const loss_func = new nn.CrossEntropyLoss();
const optimizer = new optim.Adam(model.parameters(), (lr = 5e-3), (reg = 0));

// Instantiate sample input and output:
let x = torch.randint(0, vocab_size, [batch_size, n_timesteps, 1]);
let y = torch.randint(0, vocab_size, [batch_size, n_timesteps]);
let loss;

// Training Loop:
for (let i = 0; i < 40; i++) {
  // Forward pass through the Transformer:
  let z = model.forward(x);

  // Get loss:
  loss = loss_func.forward(z, y);

  // Backpropagate the loss using torch.tensor's backward() method:
  loss.backward();

  // Update the weights:
  optimizer.step();

  // Reset the gradients to zero after each training step:
  optimizer.zero_grad();

  // Print loss at every iteration:
  console.log(`Iter ${i} - Loss ${loss.data[0].toFixed(4)}`)
}