epoch: 240 LearningRate: base_lr: 0.015 schedulers: - !PiecewiseDecay gamma: 0.1 milestones: [160, 220] - !LinearWarmup start_factor: 0.2 steps: 1000 OptimizerBuilder: clip_grad_by_norm: 35 optimizer: momentum: 0.9 type: Momentum regularizer: factor: 0.0004 type: L2
