init_train.yaml

model_args:
  hidden_sizes: [100, 100, 100]
  output_scale: 100
  use_resnet: true
  actv_fn: mygelu
data_args: 
  batch_size: 16
  group_batch: 1
  e_name: l_e_delta
preprocess_args:
  preshift: true
  prescale: false
  prefit_ridge: 1e1
  prefit_trainable: false
train_args: 
  ckpt_file: model.pth
  decay_rate: 0.96
  decay_steps: 500
  display_epoch: 100
  n_epoch: 50000
  start_lr: 0.0001
train_paths:
  - data_train/* 
test_paths:
  - data_test/*