accum_grad: 1 allow_variable_data_keys: false batch_bins: 1000000 batch_size: 20 batch_type: folded best_model_criterion: - - train - loss - min - - valid - loss - min - - train - acc - max - - valid - acc - max bpemodel: data/token_list/bpe_unigram30/bpe.model chunk_length: 500 chunk_shift_ratio: 0.5 cleaner: null collect_stats: false config: null cudnn_benchmark: false cudnn_deterministic: true cudnn_enabled: true dist_backend: nccl dist_init_method: env:// dist_launcher: null dist_master_addr: null dist_master_port: null dist_rank: null dist_world_size: null distributed: false dry_run: false early_stopping_criterion: - valid - loss - min fold_length: - 150 g2p: null grad_clip: 5.0 grad_noise: false init: null iterator_type: sequence keep_nbest_models: 10 lm: seq_rnn lm_conf: {} local_rank: 0 log_interval: null log_level: INFO max_cache_size: 0.0 max_epoch: 40 model_conf: ignore_id: 0 multiple_iterator: false multiprocessing_distributed: false ngpu: 1 no_forward_run: false non_linguistic_symbols: null num_att_plot: 3 num_cache_chunks: 1024 num_iters_per_epoch: null num_workers: 1 optim: adadelta optim_conf: {} output_dir: exp/lm_train_bpe patience: null pretrain_key: [] pretrain_path: [] print_config: false required: - output_dir - token_list resume: true scheduler: null scheduler_conf: {} seed: 0 sort_batch: descending sort_in_batch: descending token_list: - - - T - "\u2581" - I - H - G - O - AR - "\u2581T" - NE - E - EN - Y - "\u2581E" - "\u2581S" - EVEN - F - M - C - R - D - N - W - ENT - L - token_type: bpe train_data_path_and_name_and_type: - - dump/raw/srctexts - text - text train_dtype: float32 train_shape_file: - exp/lm_stats/train/text_shape.bpe use_preprocessor: true val_scheduler_criterion: - valid - loss valid_batch_bins: null valid_batch_size: null valid_batch_type: null valid_data_path_and_name_and_type: - - dump/raw/train_dev/text - text - text valid_max_cache_size: null valid_shape_file: - exp/lm_stats/valid/text_shape.bpe write_collected_feats: false