Update gpt.py

gpt.py

@@ -18,7 +18,6 @@ dropout = 0.2
 
 torch.manual_seed(1337)
 
-# wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
 with open('input.txt', 'r', encoding='utf-8') as f:
     text = f.read()
 
@@ -196,30 +195,4 @@ class GPTLanguageModel(nn.Module):
         return idx
 
 model = GPTLanguageModel()
-m = model.to(device)
-# print the number of parameters in the model
-print(sum(p.numel() for p in m.parameters())/1e6, 'M parameters')
-
-# create a PyTorch optimizer
-optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)
-
-for iter in range(max_iters):
-
-    # every once in a while evaluate the loss on train and val sets
-    if iter % eval_interval == 0 or iter == max_iters - 1:
-        losses = estimate_loss()
-        print(f"step {iter}: train loss {losses['train']:.4f}, val loss {losses['val']:.4f}")
-
-    # sample a batch of data
-    xb, yb = get_batch('train')
-
-    # evaluate the loss
-    logits, loss = model(xb, yb)
-    optimizer.zero_grad(set_to_none=True)
-    loss.backward()
-    optimizer.step()
-
-# generate from the model
-context = torch.zeros((1, 1), dtype=torch.long, device=device)
-print(decode(m.generate(context, max_new_tokens=500)[0].tolist()))
-#open('more.txt', 'w').write(decode(m.generate(context, max_new_tokens=10000)[0].tolist()))
+model = model.to(device)