| config: null |
| print_config: false |
| log_level: INFO |
| drop_last_iter: false |
| dry_run: false |
| iterator_type: sequence |
| valid_iterator_type: null |
| output_dir: exp/lm_ch_lm |
| 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 |
| use_tf32: false |
| 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: |
| - - train |
| - loss |
| - min |
| - - valid |
| - loss |
| - min |
| - - train |
| - acc |
| - max |
| - - valid |
| - acc |
| - max |
| keep_nbest_models: |
| - 10 |
| 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 |
| 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 |
| use_adapter: false |
| adapter: lora |
| save_strategy: all |
| adapter_conf: {} |
| 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: 1000000 |
| valid_batch_bins: null |
| train_shape_file: |
| - exp/lm_stats_en_char/train/text_shape.char |
| valid_shape_file: |
| - exp/lm_stats_en_char/valid/text_shape.char |
| batch_type: folded |
| valid_batch_type: null |
| fold_length: |
| - 150 |
| sort_in_batch: descending |
| shuffle_within_batch: false |
| sort_batch: descending |
| multiple_iterator: false |
| chunk_length: 500 |
| chunk_shift_ratio: 0.5 |
| num_cache_chunks: 1024 |
| chunk_excluded_key_prefixes: [] |
| chunk_default_fs: null |
| chunk_max_abs_length: null |
| chunk_discard_short_samples: true |
| train_data_path_and_name_and_type: |
| - - dump/raw_copy/lm_train.txt |
| - text |
| - text |
| valid_data_path_and_name_and_type: |
| - - dump/raw_copy/org/valid/text |
| - text |
| - text |
| multi_task_dataset: false |
| allow_variable_data_keys: false |
| max_cache_size: 0.0 |
| max_cache_fd: 32 |
| allow_multi_rates: false |
| valid_max_cache_size: null |
| exclude_weight_decay: false |
| exclude_weight_decay_conf: {} |
| optim: adadelta |
| optim_conf: {} |
| scheduler: null |
| scheduler_conf: {} |
| token_list: |
| - <blank> |
| - <unk> |
| - <space> |
| - ा |
| - े |
| - र |
| - क |
| - न |
| - स |
| - ् |
| - म |
| - ि |
| - ल |
| - ह |
| - त |
| - ी |
| - य |
| - ज |
| - ब |
| - प |
| - व |
| - ो |
| - ग |
| - ं |
| - द |
| - थ |
| - ु |
| - ट |
| - अ |
| - उ |
| - ू |
| - ख |
| - च |
| - भ |
| - ए |
| - इ |
| - आ |
| - ध |
| - ड |
| - छ |
| - श |
| - फ |
| - ड़ |
| - ई |
| - ै |
| - ढ़ |
| - घ |
| - ँ |
| - ठ |
| - ष |
| - ौ |
| - ण |
| - . |
| - ृ |
| - ॉ |
| - ओ |
| - ञ |
| - झ |
| - ऊ |
| - ऑ |
| - ॅ |
| - ऐ |
| - ढ |
| - औ |
| - '?' |
| - ऋ |
| - ः |
| - ॐ |
| - ङ |
| - ऍ |
| - <sos/eos> |
| init: null |
| use_preprocessor: true |
| token_type: char |
| bpemodel: null |
| non_linguistic_symbols: null |
| cleaner: null |
| g2p: null |
| lm: seq_rnn |
| lm_conf: {} |
| model: lm |
| model_conf: {} |
| required: |
| - output_dir |
| - token_list |
| version: '202402' |
| distributed: false |
|
|
