epoch: 12 LearningRate: base_lr: 0.015 schedulers: - !PiecewiseDecay gamma: 0.1 milestones: [8, 11] - !LinearWarmup start_factor: 0.2 steps: 500 OptimizerBuilder: optimizer: momentum: 0.9 type: Momentum regularizer: factor: 0.0004 type: L2
