Adaptive gradient methods, notably Adam, have become indispensable for optimizing neural networks, particularly in conjunction with Transformers. In this paper, we present a novel optimization anomaly called the Slingshot Effect, which manifests during extremely late stages of training. We identify a distinctive characteristic of this phenomenon through cyclic phase transitions between stable and unstable training regimes, as evidenced by the cyclic behavior of the norm of the last layer’s weights. Although the Slingshot Effect can be easily reproduced in more general settings, it does not… Adaptive gradient methods, notably Adam, have become indispensable for optimizing neural networks, particularly in conjunction with Transformers. In this paper, we present a novel optimization anomaly called the Slingshot Effect, which manifests during extremely late stages of training. We identify a distinctive characteristic of this phenomenon through cyclic phase transitions between stable and unstable training regimes, as evidenced by the cyclic behavior of the norm of the last layer’s weights. Although the Slingshot Effect can be easily reproduced in more general settings, it does not… Read More