Fix addcmul_

src/transformers/optimization.py

@@ -153,7 +153,7 @@ 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_(grad, alpha=1.0 - beta1)
-                exp_avg_sq.mul_(beta2).addcmul_(grad, grad, 1.0 - beta2)
+                exp_avg_sq.mul_(beta2).addcmul_(grad, grad, value=1.0 - beta2)
                 denom = exp_avg_sq.sqrt().add_(group["eps"])
 
                 step_size = group["lr"]