# @package _group_

common:
  fp16: true
  log_format: json
  log_interval: 200
  seed: 1337
  tensorboard_logdir: tblog

checkpoint:
  save_dir: ???
  save_interval: 4
  keep_last_epochs: 4
  save_interval_updates: 20000
  keep_interval_updates: -1
  keep_interval_updates_pattern: 50000
  # no_epoch_checkpoints: true

distributed_training:
  ddp_backend: no_c10d
  distributed_backend: 'nccl'
  distributed_world_size: 8
  nprocs_per_node: 8
  find_unused_parameters: true

task:
  _name: denoising
  data: ???
  mask: 0.15

dataset:
  num_workers: 6
  max_tokens: 1400000
  skip_invalid_size_inputs_valid_test: true
  validate_interval: ${checkpoint.save_interval}
  validate_interval_updates: ${checkpoint.save_interval_updates}
  required_batch_size_multiple: 1

criterion:
  _name: sc2t
  pred_masked_weight: 1.0
  pred_nomask_weight: 0.0
  loss_weights: [10,]
  label_smoothing: 0.1
  text_weight: 0.1

optimization:
  max_update: 400000
  lr: [0.0005]
  clip_norm: 10.0

optimizer:
  _name: adam
  adam_betas: (0.9,0.98)
  adam_eps: 1e-06
  weight_decay: 0.01

lr_scheduler:
  _name: polynomial_decay
  warmup_updates: 32000

model:
  _name: stbert
  label_rate: ???
  skip_masked: false
  skip_nomask: false
  mask_prob: 0.80
  extractor_mode: default
  conv_feature_layers: '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2'
  final_dim: 256
  encoder_layers: 6
  encoder_attention_heads: 8
  decoder_layerdrop: 0.05
  dropout_input: 0.1
  dropout_features: 0.1
  dropout: 0.1
  attention_dropout: 0.1
  feature_grad_mult: 0.1
  untie_final_proj: true
  activation_dropout: 0.0
  use_rel_pos_enc: true
  add_code_encoder: true
  add_adaptor: false
  text_transformer:
    activation_fn: ${model.activation_fn}
    dropout: ${model.dropout}
    attention_dropout: ${model.attention_dropout}
    activation_dropout: ${model.activation_dropout}
    adaptive_input: ${model.adaptive_input}
    max_source_positions: 3000
    checkpoint_activations: ${model.checkpoint_activations}
    no_scale_embedding: false
    layernorm_embedding: false
    quant_noise:
      pq: ${model.quant_noise_pq}
    encoder:
      embed_dim: 768
      ffn_embed_dim: 3072
      layers: 6
      attention_heads: 8
      normalize_before: false
      learned_pos: true
      layerdrop: ${model.encoder_layerdrop}
     

hydra:
  job:
    config:
      override_dirname:
        kv_sep: '-'
        item_sep: '__'
        exclude_keys:
          - run
          - task.data
          - task.label_dir
  run:
    dir: ???
  sweep:
    dir: ???
    subdir: ${hydra.job.config_name}__${hydra.job.override_dirname}