| { | |
| "framework": "tensorflow", | |
| "task": "translation", | |
| "pipeline": { | |
| "type": "csanmt-translation" | |
| }, | |
| "model": { | |
| "type": "csanmt-translation", | |
| "hidden_size": 1024, | |
| "filter_size": 4096, | |
| "num_heads": 16, | |
| "num_encoder_layers": 24, | |
| "num_decoder_layers": 6, | |
| "attention_dropout": 0.0, | |
| "residual_dropout": 0.0, | |
| "relu_dropout": 0.0, | |
| "layer_preproc": "layer_norm", | |
| "layer_postproc": "none", | |
| "shared_embedding_and_softmax_weights": true, | |
| "shared_source_target_embedding": true, | |
| "initializer_scale": 0.1, | |
| "position_info_type": "absolute", | |
| "max_relative_dis": 16, | |
| "num_semantic_encoder_layers": 4, | |
| "src_vocab_size": 50000, | |
| "trg_vocab_size": 50000, | |
| "seed": 1234, | |
| "beam_size": 4, | |
| "lp_rate": 0.6, | |
| "max_decoded_trg_len": 100 | |
| }, | |
| "dataset": { | |
| "train_src": "train.zh", | |
| "train_trg": "train.en", | |
| "src_vocab": { | |
| "file": "src_vocab.txt" | |
| }, | |
| "trg_vocab": { | |
| "file": "trg_vocab.txt" | |
| } | |
| }, | |
| "preprocessor": { | |
| "src_lang": "zh", | |
| "tgt_lang": "en", | |
| "src_bpe": { | |
| "file": "bpe.zh" | |
| } | |
| }, | |
| "train": { | |
| "num_gpus": 0, | |
| "warmup_steps": 4000, | |
| "update_cycle": 1, | |
| "keep_checkpoint_max": 1, | |
| "confidence": 0.9, | |
| "optimizer": "adam", | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.98, | |
| "adam_epsilon": 1e-9, | |
| "gradient_clip_norm": 0.0, | |
| "learning_rate_decay": "linear_warmup_rsqrt_decay", | |
| "initializer": "uniform_unit_scaling", | |
| "initializer_scale": 0.1, | |
| "learning_rate": 1.0, | |
| "train_batch_size_words": 1024, | |
| "scale_l1": 0.0, | |
| "scale_l2": 0.0, | |
| "train_max_len": 100, | |
| "num_of_epochs": 2, | |
| "save_checkpoints_steps": 1000, | |
| "num_of_samples": 4, | |
| "eta": 0.6 | |
| }, | |
| "evaluation": { | |
| "beam_size": 4, | |
| "lp_rate": 0.6, | |
| "max_decoded_trg_len": 100 | |
| } | |
| } | |