Distillation:
  distill_lambda: 1.0
  distill_loss: l2_loss
  distill_node_pair:
  - teacher_tmp_9
  - tmp_9
  - teacher_tmp_12
  - tmp_12
  - teacher_tmp_15
  - tmp_15
  - teacher_tmp_18
  - tmp_18
  - teacher_tmp_21
  - tmp_21
  - teacher_tmp_24
  - tmp_24
  - teacher_tmp_27
  - tmp_27
  - teacher_tmp_30
  - tmp_30
  - teacher_tmp_33
  - tmp_33
  - teacher_tmp_36
  - tmp_36
  - teacher_tmp_39
  - tmp_39
  - teacher_tmp_42
  - tmp_42
  - teacher_linear_147.tmp_1
  - linear_147.tmp_1
  merge_feed: true
  teacher_model_dir: ../auto-compression_origin/static_bert_models
  teacher_model_filename: bert.pdmodel
  teacher_params_filename: bert.pdiparams
Quantization:
  activation_bits: 8
  is_full_quantize: false
  not_quant_pattern:
  - skip_quant
  quantize_op_types:
  - conv2d
  - depthwise_conv2d
  - mul
  - matmul
  weight_bits: 8
TrainConfig:
  epochs: 3
  eval_iter: 1000
  learning_rate: 0.0001
  optimizer: SGD
  optim_args:
    weight_decay: 4.0e-05
  origin_metric: 0.93