config: conf/train_lm_rnn_unit1024_nlayers3_dropout0.2.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/lm_train_lm_rnn_unit1024_nlayers3_dropout0.2_word ngpu: 1 seed: 0 num_workers: 1 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: 2 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 35485 dist_launcher: null multiprocessing_distributed: true unused_parameters: false sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 40 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - loss - min keep_nbest_models: 1 nbest_averaging_interval: 0 grad_clip: 5.0 grad_clip_type: 2.0 grad_noise: false accum_grad: 1 no_forward_run: false resume: true train_dtype: float32 use_amp: true log_interval: null use_matplotlib: true use_tensorboard: true create_graph_in_tensorboard: false use_wandb: false wandb_project: null wandb_id: null wandb_entity: null wandb_name: null wandb_model_log_interval: -1 detect_anomaly: false pretrain_path: null init_param: [] ignore_init_mismatch: false freeze_param: [] num_iters_per_epoch: null batch_size: 20 valid_batch_size: null batch_bins: 10000000 valid_batch_bins: null train_shape_file: - exp/lm_stats_word/train/text_shape.word valid_shape_file: - exp/lm_stats_word/valid/text_shape.word batch_type: numel valid_batch_type: null fold_length: - 150 sort_in_batch: descending sort_batch: descending multiple_iterator: false chunk_length: 500 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 train_data_path_and_name_and_type: - - dump/raw/lm_train.txt - text - text valid_data_path_and_name_and_type: - - nunit_50_rep/lm_valid_50_rep.txt - text - text allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adam optim_conf: lr: 0.002 scheduler: reducelronplateau scheduler_conf: mode: min factor: 0.5 patience: 2 token_list: - - - '7' - '35' - '44' - '49' - '20' - '47' - '0' - '3' - '46' - '45' - '31' - '11' - '28' - '4' - '37' - '43' - '26' - '36' - '18' - '32' - '5' - '14' - '33' - '16' - '9' - '8' - '17' - '30' - '24' - '48' - '21' - '34' - '6' - '29' - '38' - '23' - '39' - '10' - '27' - '19' - '40' - '42' - '25' - '41' - '12' - '15' - '1' - '2' - '13' - '22' - init: null model_conf: ignore_id: 0 use_preprocessor: true token_type: word bpemodel: null non_linguistic_symbols: null cleaner: null g2p: null lm: seq_rnn lm_conf: unit: 1024 nlayers: 3 dropout_rate: 0.2 required: - output_dir - token_list version: '202207' distributed: true