epoch: 240 LearningRate: base_lr: 0.001 schedulers: - !PiecewiseDecay gamma: 0.1 milestones: - 160 - 200 - !LinearWarmup start_factor: 0.3333333333333333 steps: 500 OptimizerBuilder: optimizer: momentum: 0.9 type: Momentum regularizer: factor: 0.0005 type: L2
