[NFC] polish colossalai/nn/optimizer/lamb.py code style (#1275)

colossalai/nn/optimizer/lamb.py

@@ -29,20 +29,16 @@ class Lamb(Optimizer):
         https://arxiv.org/abs/1904.00962
     """
 
-    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-6,
+    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-6, weight_decay=0, adam=False):
-                 weight_decay=0, adam=False):
         if not 0.0 <= lr:
             raise ValueError("Invalid learning rate: {}".format(lr))
         if not 0.0 <= eps:
             raise ValueError("Invalid epsilon value: {}".format(eps))
         if not 0.0 <= betas[0] < 1.0:
-            raise ValueError(
+            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
-                "Invalid beta parameter at index 0: {}".format(betas[0]))
         if not 0.0 <= betas[1] < 1.0:
-            raise ValueError(
+            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
-                "Invalid beta parameter at index 1: {}".format(betas[1]))
+        defaults = dict(lr=lr, betas=betas, eps=eps, weight_decay=weight_decay)
-        defaults = dict(lr=lr, betas=betas, eps=eps,
-                        weight_decay=weight_decay)
         self.adam = adam
         super(Lamb, self).__init__(params, defaults)
 
@@ -63,8 +59,7 @@ class Lamb(Optimizer):
                     continue
                 grad = p.grad.data
                 if grad.is_sparse:
-                    raise RuntimeError(
+                    raise RuntimeError('Lamb does not support sparse gradients, consider SparseAdam instad.')
-                        'Lamb does not support sparse gradients, consider SparseAdam instad.')
 
                 state = self.state[p]