run_tc module

Fine-tuning the library models for named entity recognition on CoNLL-2003 (Bert or Roberta).

class run_tc.DataTrainingArguments(dataset_name: Optional[str] = None, dataset_config_name: Optional[str] = None, train_file: Optional[str] = None, validation_file: Optional[str] = None, test_file: Optional[str] = None, text_column_name: Optional[str] = None, label_column_name: Optional[str] = None, max_seq_length: int = 512, pad_to_max_length: bool = False, overwrite_cache: bool = False, preprocessing_num_workers: Optional[int] = None, task_name: str = 'ner', early_stop: bool = False)

Bases: object

Arguments pertaining to what data we are going to input our model for training and eval.

dataset_config_name: Optional[str] = None

dataset_name: Optional[str] = None

early_stop: bool = False

label_column_name: Optional[str] = None

max_seq_length: int = 512

overwrite_cache: bool = False

pad_to_max_length: bool = False

preprocessing_num_workers: Optional[int] = None

task_name: str = 'ner'

test_file: Optional[str] = None

text_column_name: Optional[str] = None

train_file: Optional[str] = None

validation_file: Optional[str] = None

class run_tc.ModelArguments(model_name_or_path: str, config_name: Optional[str] = None, tokenizer_name: Optional[str] = None, use_fast: bool = False, cache_dir: Optional[str] = None, log_dir: Optional[str] = None, use_auth_token: bool = False)

Bases: object

Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.

cache_dir: Optional[str] = None

config_name: Optional[str] = None

log_dir: Optional[str] = None

model_name_or_path: str

tokenizer_name: Optional[str] = None

use_auth_token: bool = False

use_fast: bool = False

run_tc.main(args)