torch.manual_seed(123)

model = GPTModel(GPT_CONFIG_124M)
model.to(device)

optimizer = torch.optim.AdamW(model.parameters(),lr=3e-4,
    weight_decay=0.1)

num_epochs = 10

train_losses, val_losses, track_tokens_seen = train_model_simple(model,train_loader,val_loader,optimizer,
    device,num_epochs=num_epochs,eval_freq=5,eval_iter=5,
    start_context="Every effort moves you",      tokenizer=tokenizer)

        __
        __