# 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)
import torch import torch.nn as nn import torch.optim as optim from torch.utils.data import Dataset, DataLoader build a large language model from scratch pdf
# Set device device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # Evaluate the model def evaluate(model, device, loader,
# Create model, optimizer, and criterion model = LanguageModel(vocab_size, embedding_dim, hidden_dim, output_dim).to(device) optimizer = optim.Adam(model.parameters(), lr=0.001) criterion = nn.CrossEntropyLoss() # Evaluate the model def evaluate(model