accumulate_grad_batches: 1
audio_sample_rate: 44100
binarization_args:
  num_workers: 0
  shuffle: true
binarizer_cls: preprocessing.MIDIExtractionBinarizer
binary_data_dir: data/some_ds_fixmel_spk3_aug8/binary
clip_grad_norm: 1
dataloader_prefetch_factor: 2
ddp_backend: nccl
ds_workers: 4
finetune_ckpt_path: null
finetune_enabled: false
finetune_ignored_params: []
finetune_strict_shapes: true
fmax: 8000
fmin: 40
freezing_enabled: false
frozen_params: []
hop_size: 512
log_interval: 100
lr_scheduler_args:
  min_lr: 1.0e-05
  scheduler_cls: lr_scheduler.scheduler.WarmupLR
  warmup_steps: 5000
max_batch_frames: 80000
max_batch_size: 8
max_updates: 10000000
max_val_batch_frames: 10000
max_val_batch_size: 1
midi_extractor_args:
  attention_drop: 0.1
  attention_heads: 8
  attention_heads_dim: 64
  conv_drop: 0.1
  dim: 512
  ffn_latent_drop: 0.1
  ffn_out_drop: 0.1
  kernel_size: 31
  lay: 8
  use_lay_skip: true
midi_max: 128
midi_min: 0
midi_num_bins: 256
midi_prob_deviation: 0.5
midi_shift_proportion: 0.0
midi_shift_range:
- -6
- 6
model_cls: modules.model.Gmidi_conform.midi_conforms
num_ckpt_keep: 5
num_sanity_val_steps: 1
num_valid_plots: 300
optimizer_args:
  beta1: 0.9
  beta2: 0.98
  lr: 0.0001
  optimizer_cls: torch.optim.AdamW
  weight_decay: 0
pe: rmvpe
pe_ckpt: pretrained/rmvpe/model.pt
permanent_ckpt_interval: 40000
permanent_ckpt_start: 200000
pl_trainer_accelerator: auto
pl_trainer_devices: auto
pl_trainer_num_nodes: 1
pl_trainer_precision: 32-true
pl_trainer_strategy: auto
raw_data_dir: []
rest_threshold: 0.1
sampler_frame_count_grid: 6
seed: 114514
sort_by_len: true
task_cls: training.MIDIExtractionTask
test_prefixes: null
train_set_name: train
units_dim: 80
units_encoder: mel
units_encoder_ckpt: pretrained/contentvec/checkpoint_best_legacy_500.pt
use_buond_loss: true
use_midi_loss: true
val_check_interval: 4000
valid_set_name: valid
win_size: 2048