PairwiseRegressionTask.Config

Component: PairwiseRegressionTask

class PairwiseRegressionTask.Config

Bases: PairwiseClassificationTask.Config

All Attributes (including base classes)

data: Data.Config = Data.Config()

trainer: TaskTrainer.Config = TaskTrainer.Config()

use_elastic: Optional[bool] = None

model: BasePairwiseModel.Config = BertPairwiseRegressionModel.Config()

metric_reporter: RegressionMetricReporter.Config = RegressionMetricReporter.Config()

trace_both_encoders: bool = True

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": {
        "BertPairwiseRegressionModel": {
            "inputs": {
                "tokens1": {
                    "BERTTensorizer": {
                        "is_input": true,
                        "columns": [
                            "text1"
                        ],
                        "tokenizer": {
                            "WordPieceTokenizer": {
                                "basic_tokenizer": {
                                    "split_regex": "\\s+",
                                    "lowercase": true,
                                    "use_byte_offsets": false
                                },
                                "wordpiece_vocab_path": "manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/vocab.txt"
                            }
                        },
                        "base_tokenizer": null,
                        "vocab_file": "manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/vocab.txt",
                        "max_seq_len": 128
                    }
                },
                "tokens2": {
                    "BERTTensorizer": {
                        "is_input": true,
                        "columns": [
                            "text2"
                        ],
                        "tokenizer": {
                            "WordPieceTokenizer": {
                                "basic_tokenizer": {
                                    "split_regex": "\\s+",
                                    "lowercase": true,
                                    "use_byte_offsets": false
                                },
                                "wordpiece_vocab_path": "manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/vocab.txt"
                            }
                        },
                        "base_tokenizer": null,
                        "vocab_file": "manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/vocab.txt",
                        "max_seq_len": 128
                    }
                },
                "labels": {
                    "is_input": false,
                    "column": "label",
                    "rescale_range": null
                },
                "num_tokens": {
                    "is_input": false,
                    "names": [
                        "tokens1",
                        "tokens2"
                    ],
                    "indexes": [
                        2,
                        2
                    ]
                }
            },
            "decoder": null,
            "output_layer": {
                "load_path": null,
                "save_path": null,
                "freeze": false,
                "shared_module_key": null,
                "loss": {
                    "MSELoss": {}
                }
            },
            "encode_relations": false,
            "encoder": {
                "HuggingFaceBertSentenceEncoder": {
                    "load_path": null,
                    "save_path": null,
                    "freeze": false,
                    "shared_module_key": null,
                    "output_dropout": 0.4,
                    "embedding_dim": 768,
                    "pooling": "cls_token",
                    "export": false,
                    "projection_dim": 0,
                    "normalize_output_rep": false,
                    "bert_cpt_dir": "manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/",
                    "load_weights": true
                }
            },
            "shared_encoder": true
        }
    },
    "metric_reporter": {
        "output_path": "/tmp/test_out.txt",
        "pep_format": false,
        "student_column_names": [],
        "log_gradient": false
    },
    "trace_both_encoders": true
}