Common use of Training; Details Clause in Contracts

Training; Details. ‌ 1. Mask training and IMP basically use the same hyper-parameters (adopting from [55]) as full XXXX. An exception is longer training, because we find that good subnetworks at high sparsity levels require more training to be found. Unless otherwise specified, we select the best checkpoints based on the ID dev performance, without using OOD information. All the reported results are averaged over 4 runs. We defer training details about each dataset, and each training and pruning setup, to Appendix B.3.

Training; Details. ‌ 1. Mask training and IMP basically use the same hyper-parameters (adopting from [5542]) as full XXXX. An exception is longer training, because we find that good subnetworks at high sparsity levels require more training to be found. Unless otherwise specified, we select the best checkpoints based on the ID dev performance, without using OOD information. All the reported results are averaged over 4 runs. We defer training details about each dataset, and each training and pruning setup, to Appendix B.3.