small tweaks, make default WD be 0.1 as is often cited, and remove spurious init of LayerNorm, which is already initialized at 1,0

model.py

@@ -173,10 +173,6 @@ class GPT(nn.Module):
                 torch.nn.init.zeros_(module.bias)
         elif isinstance(module, nn.Embedding):
             torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
-        elif isinstance(module, (LayerNorm, nn.LayerNorm)):
-            torch.nn.init.ones_(module.weight)
-            if module.bias is not None:
-                torch.nn.init.zeros_(module.bias)
 
     def forward(self, idx, targets=None):
         device = idx.device

train.py

@@ -57,7 +57,7 @@ bias = False # do we use bias inside LayerNorm and Linear layers?
 # adamw optimizer
 learning_rate = 6e-4 # max learning rate
 max_iters = 600000 # total number of training iterations
-weight_decay = 1e-2
+weight_decay = 1e-1
 beta1 = 0.9
 beta2 = 0.95
 grad_clip = 1.0 # clip gradients at this value, or disable if == 0.0