 |
|
# Set device device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Define a dataset class for our language model class LanguageModelDataset(Dataset): def __init__(self, text_data, vocab): self.text_data = text_data self.vocab = vocab build a large language model from scratch pdf
# Train and evaluate model for epoch in range(epochs): loss = train(model, device, loader, optimizer, criterion) print(f'Epoch {epoch+1}, Loss: {loss:.4f}') eval_loss = evaluate(model, device, loader, criterion) print(f'Epoch {epoch+1}, Eval Loss: {eval_loss:.4f}') # Set device device = torch
def __len__(self): return len(self.text_data) criterion) print(f'Epoch {epoch+1}
if __name__ == '__main__': main()