# create a Pytorch optimizer optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate) for iter in range(max_iters): if iter % eval_iters == 0: losses = estimate_loss() print(f"step: {iter}, loss {losses}") # sample a batch of data xb, yb = get_batch("train") #evaluate the loss logits, loss = model.forward(xb, yb) optimizer.zero_grad(set_to_none=True) loss.backward() optimizer.step() print(loss.item()) RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper_CUDA__index_select) I tried adding model = model.to(device) and adding .cuda() after inputs, but none of them worked. I'm struggling to get it fixed. Continue reading...
