SequenceLabelingTask.ConfigΒΆ

Component: SequenceLabelingTask

class SequenceLabelingTask.Config[source]

Bases: NewTask.Config

All Attributes (including base classes)

Default JSON

{
    "data": {
        "Data": {
            "source": {
                "TSVDataSource": {
                    "column_mapping": {},
                    "train_filename": null,
                    "test_filename": null,
                    "eval_filename": null,
                    "field_names": null,
                    "delimiter": "\t",
                    "quoted": false,
                    "drop_incomplete_rows": false
                }
            },
            "batcher": {
                "PoolingBatcher": {
                    "train_batch_size": 16,
                    "eval_batch_size": 16,
                    "test_batch_size": 16,
                    "pool_num_batches": 1000,
                    "num_shuffled_pools": 1
                }
            },
            "sort_key": null,
            "in_memory": true
        }
    },
    "trainer": {
        "TaskTrainer": {
            "epochs": 10,
            "early_stop_after": 0,
            "max_clip_norm": null,
            "report_train_metrics": true,
            "target_time_limit_seconds": null,
            "do_eval": true,
            "load_best_model_after_train": true,
            "num_samples_to_log_progress": 1000,
            "num_accumulated_batches": 1,
            "num_batches_per_epoch": null,
            "optimizer": {
                "Adam": {
                    "lr": 0.001,
                    "weight_decay": 1e-05,
                    "eps": 1e-08
                }
            },
            "scheduler": null,
            "sparsifier": null,
            "fp16_args": {
                "FP16OptimizerFairseq": {
                    "init_loss_scale": 128,
                    "scale_window": null,
                    "scale_tolerance": 0.0,
                    "threshold_loss_scale": null,
                    "min_loss_scale": 0.0001
                }
            },
            "privacy_engine": null,
            "use_tensorboard": false
        }
    },
    "use_elastic": null,
    "model": {
        "inputs": {
            "src_seq_tokens": {
                "is_input": true,
                "column": "text",
                "tokenizer": {
                    "Tokenizer": {
                        "split_regex": "\\s+",
                        "lowercase": true,
                        "use_byte_offsets": false
                    }
                },
                "add_bos_token": false,
                "add_eos_token": false,
                "use_eos_token_for_bos": false,
                "max_seq_len": null,
                "vocab": {
                    "build_from_data": true,
                    "size_from_data": 0,
                    "min_counts": 0,
                    "vocab_files": []
                },
                "vocab_file_delimiter": " "
            },
            "trg_seq_tokens": {
                "is_input": true,
                "column": "text",
                "tokenizer": {
                    "Tokenizer": {
                        "split_regex": "\\s+",
                        "lowercase": true,
                        "use_byte_offsets": false
                    }
                },
                "add_bos_token": false,
                "add_eos_token": false,
                "use_eos_token_for_bos": false,
                "max_seq_len": null,
                "vocab": {
                    "build_from_data": true,
                    "size_from_data": 0,
                    "min_counts": 0,
                    "vocab_files": []
                },
                "vocab_file_delimiter": " "
            },
            "dict_feat": null,
            "contextual_token_embedding": null
        },
        "encoder_decoder": {
            "encoder": {
                "embed_dim": 512,
                "hidden_dim": 512,
                "num_layers": 1,
                "dropout_in": 0.1,
                "dropout_out": 0.1,
                "bidirectional": false
            },
            "decoder": {
                "encoder_hidden_dim": 512,
                "embed_dim": 512,
                "hidden_dim": 512,
                "out_embed_dim": 512,
                "cell_type": "lstm",
                "num_layers": 1,
                "dropout_in": 0.1,
                "dropout_out": 0.1,
                "attention_type": "dot",
                "attention_heads": 8,
                "first_layer_attention": false,
                "averaging_encoder": false
            }
        },
        "source_embedding": {
            "load_path": null,
            "save_path": null,
            "freeze": false,
            "shared_module_key": null,
            "embed_dim": 100,
            "embedding_init_strategy": "random",
            "embedding_init_range": null,
            "embeddding_init_std": 0.02,
            "export_input_names": [
                "tokens_vals"
            ],
            "pretrained_embeddings_path": "",
            "vocab_file": "",
            "vocab_size": 0,
            "vocab_from_train_data": true,
            "vocab_from_all_data": false,
            "vocab_from_pretrained_embeddings": false,
            "lowercase_tokens": true,
            "min_freq": 1,
            "mlp_layer_dims": [],
            "padding_idx": null,
            "cpu_only": false,
            "skip_header": true,
            "delimiter": " "
        },
        "target_embedding": {
            "load_path": null,
            "save_path": null,
            "freeze": false,
            "shared_module_key": null,
            "embed_dim": 100,
            "embedding_init_strategy": "random",
            "embedding_init_range": null,
            "embeddding_init_std": 0.02,
            "export_input_names": [
                "tokens_vals"
            ],
            "pretrained_embeddings_path": "",
            "vocab_file": "",
            "vocab_size": 0,
            "vocab_from_train_data": true,
            "vocab_from_all_data": false,
            "vocab_from_pretrained_embeddings": false,
            "lowercase_tokens": true,
            "min_freq": 1,
            "mlp_layer_dims": [],
            "padding_idx": null,
            "cpu_only": false,
            "skip_header": true,
            "delimiter": " "
        },
        "dict_embedding": null,
        "contextual_token_embedding": null,
        "output_layer": {
            "loss": {
                "CrossEntropyLoss": {}
            }
        },
        "sequence_generator": {
            "beam_size": 2,
            "targetlen_cap": 100,
            "targetlen_a": 0,
            "targetlen_b": 2,
            "targetlen_c": 2,
            "quantize": true,
            "length_penalty": 0.25,
            "nbest": 2,
            "stop_at_eos": true,
            "record_attention": false
        }
    },
    "metric_reporter": {
        "output_path": "/tmp/test_out.txt",
        "pep_format": false,
        "student_column_names": [],
        "log_gradient": false,
        "accept_flat_intents_slots": false
    }
}