epoch: 405 LearningRate: base_lr: 0.01 schedulers: - !PiecewiseDecay gamma: 0.1 milestones: - 243 - 324 - !LinearWarmup start_factor: 0. steps: 4000 OptimizerBuilder: clip_grad_by_norm: 35. optimizer: momentum: 0.9 type: Momentum regularizer: factor: 0.0005 type: L2
