| # @package __global__ | |
| # This is the training loop solver | |
| # for the base MusicGen model (text-to-music) | |
| # on monophonic audio sampled at 32 kHz | |
| defaults: | |
| - musicgen/default | |
| - /model: lm/musicgen_lm | |
| - override /dset: audio/default | |
| - _self_ | |
| autocast: true | |
| autocast_dtype: float16 | |
| # EnCodec large trained on mono-channel music audio sampled at 32khz | |
| # with a total stride of 640 leading to 50 frames/s. | |
| # rvq.n_q=4, rvq.bins=2048, no quantization dropout | |
| # (transformer_lm card and n_q must be compatible) | |
| compression_model_checkpoint: //pretrained/facebook/encodec_32khz | |
| channels: 1 | |
| sample_rate: 32000 | |
| deadlock: | |
| use: true # deadlock detection | |
| dataset: | |
| batch_size: 192 # 32 GPUs | |
| sample_on_weight: false # Uniform sampling all the way | |
| sample_on_duration: false # Uniform sampling all the way | |
| generate: | |
| lm: | |
| use_sampling: true | |
| top_k: 250 | |
| top_p: 0.0 | |
| optim: | |
| epochs: 500 | |
| optimizer: dadam | |
| lr: 1 | |
| ema: | |
| use: true | |
| updates: 10 | |
| device: cuda | |
| logging: | |
| log_tensorboard: true | |
| schedule: | |
| lr_scheduler: cosine | |
| cosine: | |
| warmup: 4000 | |
| lr_min_ratio: 0.0 | |
| cycle_length: 1.0 | |