Fantastic Pretraining Optimizers and Where to Find Them
机构 * Stanford University(斯坦福大学)
Comments 108 pages, 8 figures, reproducible runs available at https://wandb.ai/marin-community/optimizer-scaling
作者
Natural Language Processing
机构 * Stanford University(斯坦福大学)
Comments 108 pages, 8 figures, reproducible runs available at https://wandb.ai/marin-community/optimizer-scaling