Fix UserWarning: This overload of add_ is deprecated in pytorch==1.5.0

src/transformers/optimization.py

@@ -152,7 +152,7 @@ class AdamW(Optimizer):
 
                 # Decay the first and second moment running average coefficient
                 # In-place operations to update the averages at the same time
-                exp_avg.mul_(beta1).add_(1.0 - beta1, grad)
+                exp_avg.mul_(beta1).add_(grad, alpha=1.0 - beta1)
                 exp_avg_sq.mul_(beta2).addcmul_(1.0 - beta2, grad, grad)
                 denom = exp_avg_sq.sqrt().add_(group["eps"])
 
@@ -173,6 +173,6 @@ class AdamW(Optimizer):
                 # of the weights to the loss with plain (non-momentum) SGD.
                 # Add weight decay at the end (fixed version)
                 if group["weight_decay"] > 0.0:
-                    p.data.add_(-group["lr"] * group["weight_decay"], p.data)
+                    p.data.add_(p.data, alpha=-group["lr"] * group["weight_decay"])
 
         return loss