#!/usr/bin/env python
# coding: utf-8
# In[7]:
from dataclasses import dataclass, field
from datetime import datetime
from typing import List, Optional
from transformers.file_utils import ExplicitEnum
task_to_keys = {
"mimic3-50": ("mimic3-50"),
"mimic3-full": ("mimic3-full"),
}
class TransformerLayerUpdateStrategy(ExplicitEnum):
NO = "no"
LAST = "last"
ALL = "all"
class DocumentPoolingStrategy(ExplicitEnum):
FLAT = "flat"
MAX = "max"
MEAN = "mean"
@dataclass
class DataTrainingArguments:
"""
Arguments pertaining to what data we are going to input our model for training and eval.
Using `HfArgumentParser` we can turn this class
into argparse arguments to be able to specify them on
the command line.
"""
task_name: Optional[str] = field(
default=None,
metadata={"help": "The name of the task to train on: " + ", ".join(task_to_keys.keys())},
)
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)."}
)
max_seq_length: int = field(
default=128,
metadata={
"help": "The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded."
},
)
overwrite_cache: bool = field(
default=False, metadata={"help": "Overwrite the cached preprocessed datasets or not."}
)
pad_to_max_length: bool = field(
default=True,
metadata={
"help": "Whether to pad all samples to `max_seq_length`. "
"If False, will pad the samples dynamically when batching to the maximum length in the batch."
},
)
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_eval_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
"value if set."
},
)
max_predict_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of prediction examples to this "
"value if set."
},
)
train_file: Optional[str] = field(
default=None, metadata={"help": "A csv or a json file containing the training data."}
)
validation_file: Optional[str] = field(
default=None, metadata={"help": "A csv or a json file containing the validation data."}
)
test_file: Optional[str] = field(default=None, metadata={"help": "A csv or a json file containing the test data."})
# customized data arguments
label_dictionary_file: Optional[str] = field(
default=None, metadata={"help": "The name of the test data file."}
)
code_max_seq_length: int = field(
default=128,
metadata={
"help": "The maximum total input sequence length after tokenization for code long titles"
},
)
code_batch_size: int = field(
default=8,
metadata={
"help": "The batch size for generating code representation"
},
)
ignore_keys_for_eval: Optional[List[str]] = field(
default=None, metadata={"help": "The list of keys to be ignored during evaluation process."}
)
use_cached_datasets: bool = field(
default=True,
metadata={"help": "if use cached datasets to save preprocessing time. The cached datasets were preprocessed "
"and saved into data folder."})
data_segmented: bool = field(
default=False,
metadata={"help": "if dataset is segmented or not"})
lazy_loading: bool = field(
default=False,
metadata={"help": "if dataset is larger than 500MB, please use lazy_loading"})
def __post_init__(self):
if self.task_name is not None:
self.task_name = self.task_name.lower()
if self.task_name not in task_to_keys.keys():
raise ValueError("Unknown task, you should pick one in " + ",".join(task_to_keys.keys()))
elif self.dataset_name is not None:
pass
elif self.train_file is None or self.validation_file is None:
raise ValueError("Need a training/validation file")
elif self.label_dictionary_file is None:
raise ValueError("label dictionary must be provided")
else:
train_extension = self.train_file.split(".")[-1]
assert train_extension in ["csv", "json"], "`train_file` should be a csv or a json file."
validation_extension = self.validation_file.split(".")[-1]
assert (
validation_extension == train_extension
), "`validation_file` should have the same extension (csv or json) as `train_file`."
@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"},
)
use_fast_tokenizer: bool = field(
default=True,
metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
)
model_revision: str = field(
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
use_auth_token: bool = field(
default=False,
metadata={
"help": "Will use the token generated when running `transformers-cli login` (necessary to use this script "
"with private models)."
},
)
# Customized model arguments
d_model: int = field(default=768, metadata={"help": "hidden size of model. should be the same as base transformer "
"model"})
dropout: float = field(default=0.1, metadata={"help": "Dropout of transformer layer"})
dropout_att: float = field(default=0.1, metadata={"help": "Dropout of label-wise attention layer"})
num_chunks_per_document: int = field(default=0.1, metadata={"help": "Num of chunks per document"})
transformer_layer_update_strategy: TransformerLayerUpdateStrategy = field(
default="all",
metadata={"help": "Update which transformer layers when training"})
use_code_representation: bool = field(
default=True,
metadata={"help": "if use code representation as the "
"initial parameters of code vectors in attention layer"})
multi_head_attention: bool = field(
default=True,
metadata={"help": "if use multi head attention for different chunks"})
chunk_attention: bool = field(
default=True,
metadata={"help": "if use chunk attention for each label"})
multi_head_chunk_attention: bool = field(
default=True,
metadata={"help": "if use multi head chunk attention for each label"})
num_hidden_layers: int = field(
default=2, metadata={"help": "NUm of hidden layers in longformer"}
)
linear_init_mean: float = field(default=0.0, metadata={"help": "mean value for initializing linear layer weights"})
linear_init_std: float = field(default=0.03, metadata={"help": "standard deviation value for initializing linear "
"layer weights"})
document_pooling_strategy: DocumentPoolingStrategy = field(
default="flat",
metadata={"help": "how to pool document representation after label-wise attention layer for each label"})