Update model.py

mingpt/model.py

@@ -281,6 +281,9 @@ class GPT(nn.Module):
                 elif pn.endswith('weight') and isinstance(m, blacklist_weight_modules):
                     # weights of blacklist modules will NOT be weight decayed
                     no_decay.add(fpn)
+                else: # NOTE: jh added
+                    if pn.endswith('weight'):
+                        decay.add(fpn)
 
         # validate that we considered every parameter
         param_dict = {pn: p for pn, p in self.named_parameters()}