Build A Large Language Model - From Scratch Pdf

if __name__ == '__main__': main()

# Train the model def train(model, device, loader, optimizer, criterion): model.train() total_loss = 0 for batch in loader: input_seq = batch['input'].to(device) output_seq = batch['output'].to(device) optimizer.zero_grad() output = model(input_seq) loss = criterion(output, output_seq) loss.backward() optimizer.step() total_loss += loss.item() return total_loss / len(loader) build a large language model from scratch pdf

def __getitem__(self, idx): text = self.text_data[idx] input_seq = [] output_seq = [] for i in range(len(text) - 1): input_seq.append(self.vocab[text[i]]) output_seq.append(self.vocab[text[i + 1]]) return { 'input': torch.tensor(input_seq), 'output': torch.tensor(output_seq) } if __name__ == '__main__': main() # Train the

# Evaluate the model def evaluate(model, device, loader, criterion): model.eval() total_loss = 0 with torch.no_grad(): for batch in loader: input_seq = batch['input'].to(device) output_seq = batch['output'].to(device) output = model(input_seq) loss = criterion(output, output_seq) total_loss += loss.item() return total_loss / len(loader) vocab) loader = DataLoader(dataset

# Create dataset and data loader dataset = LanguageModelDataset(text_data, vocab) loader = DataLoader(dataset, batch_size=batch_size, shuffle=True)

# Set device device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')