finetune_args.py

# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from typing import Optional
from dataclasses import dataclass, field


@dataclass
class DataArguments:
    """
    Arguments pertaining to what data we are going to input our model for training and eval.
    """

    task_name: Optional[str] = field(
        default="ner", metadata={"help": "The name of the task (ner, pos...)."})
    dataset_name: Optional[str] = field(
        default=None,
        metadata={
            "help": "The name of the dataset to use (via the datasets library)."
        })
    dataset_config_name: Optional[str] = field(
        default=None,
        metadata={
            "help":
            "The configuration name of the dataset to use (via the datasets library)."
        })
    overwrite_cache: bool = field(
        default=False,
        metadata={"help": "Overwrite the cached training and evaluation sets"})
    preprocessing_num_workers: Optional[int] = field(
        default=None,
        metadata={
            "help": "The number of processes to use for the preprocessing."
        },
    )
    max_seq_length: int = field(
        default=512,
        metadata={
            "help":
            "The maximum total input sequence length after tokenization. Sequences longer "
            "than this will be truncated, sequences shorter will be padded."
        },
    )
    doc_stride: int = field(
        default=128,
        metadata={
            "help":
            "When splitting up a long document into chunks, how much stride to take between chunks."
        },
    )
    target_size: int = field(
        default=1024,
        metadata={"help": "The maximum 2d pos size"},
    )
    pad_to_max_length: bool = field(
        default=True,
        metadata={
            "help":
            "Whether to pad all samples to model maximum sentence length. "
            "If False, will pad the samples dynamically when batching to the maximum length in the batch. More "
            "efficient on GPU but very bad for TPU."
        },
    )
    max_train_samples: Optional[int] = field(
        default=None,
        metadata={
            "help":
            "For debugging purposes or quicker training, truncate the number of training examples to this "
            "value if set."
        },
    )
    max_val_samples: Optional[int] = field(
        default=None,
        metadata={
            "help":
            "For debugging purposes or quicker training, truncate the number of validation examples to this "
            "value if set."
        },
    )
    max_test_samples: Optional[int] = field(
        default=None,
        metadata={
            "help":
            "For debugging purposes or quicker training, truncate the number of test examples to this "
            "value if set."
        },
    )
    label_all_tokens: bool = field(
        default=False,
        metadata={
            "help":
            "Whether to put the label for one word on all tokens of generated by that word or just on the "
            "one (in which case the other tokens will have a padding index)."
        },
    )
    return_entity_level_metrics: bool = field(
        default=False,
        metadata={
            "help":
            "Whether to return all the entity levels during evaluation or just the overall ones."
        },
    )
    train_log_file: Optional[str] = field(
        default=None,
        metadata={"help": "train log file"},
    )
    train_nshard: Optional[int] = field(
        default=1,
        metadata={
            "help": "For big dataset, DocVQA/CORD when using ner3 pattern"
        },
    )
    use_segment_box: bool = field(
        default=False,
        metadata={"help": "Whether use segment box"},
    )
    task_type: str = field(
        default="ner",
        metadata={"help": "The task type"},
    )
    pattern: Optional[str] = field(
        default="ner1",
        metadata={
            "help": "The way to process input, choose from ner1, ner2, ner3"
        },
    )
    rst_converter: Optional[str] = field(
        default=None,
        metadata={"help": "The way to convert the predict result"},
    )
    lang: Optional[str] = field(
        default="en",
        metadata={"help": "Languge type of the dataset"},
    )


@dataclass
class ModelArguments:
    """
    Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
    """

    model_name_or_path: str = field(
        metadata={
            "help":
            "Path to pretrained model or model identifier from huggingface.co/models"
        })
    config_name: Optional[str] = field(
        default=None,
        metadata={
            "help":
            "Pretrained config name or path if not the same as model_name"
        })
    tokenizer_name: Optional[str] = field(
        default=None,
        metadata={
            "help":
            "Pretrained tokenizer name or path if not the same as model_name"
        })
    cache_dir: Optional[str] = field(
        default=None,
        metadata={
            "help":
            "Where do you want to store the pretrained models downloaded from huggingface.co"
        },
    )