config: conf/train_lm.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/lm_train_lm_en_bpe30 ngpu: 1 seed: 0 num_workers: 1 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: null dist_rank: null local_rank: 0 dist_master_addr: null dist_master_port: null dist_launcher: null multiprocessing_distributed: false 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: false log_interval: null use_matplotlib: true use_tensorboard: true 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: 256 valid_batch_size: null batch_bins: 1000000 valid_batch_bins: null train_shape_file: - exp/lm_stats_en_bpe30/train/text_shape.bpe valid_shape_file: - exp/lm_stats_en_bpe30/valid/text_shape.bpe batch_type: folded 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: - - dump/raw/train_dev/text - 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: 0.1 scheduler: null scheduler_conf: {} token_list: - - - ▁ - T - E - O - R - Y - A - H - U - S - I - F - B - L - P - D - G - M - C - V - X - J - K - Z - W - N - Q - init: null model_conf: ignore_id: 0 use_preprocessor: true token_type: bpe bpemodel: data/en_token_list/bpe_unigram30/bpe.model non_linguistic_symbols: null cleaner: null g2p: null lm: seq_rnn lm_conf: unit: 650 nlayers: 2 required: - output_dir - token_list version: 0.10.6a1 distributed: false