relogic/entity-to-text-train.py [31:112]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  MODEL_WITH_LM_HEAD_MAPPING,
  AutoTokenizer,
    HfArgumentParser,
    PreTrainedTokenizer,
    set_seed,
)
from relogic.pretrainkit.models.sql_to_text import SQL2TextModel
from relogic.pretrainkit.trainer import Trainer
from relogic.pretrainkit.datasets.text_generation.entity_to_text import Entity2QueryDataset, DataCollatorForEntity2Query
from relogic.pretrainkit.scorers.text_generation import TextGenerationScorer
from relogic.pretrainkit.training_args import TrainingArguments

logger = logging.getLogger(__name__)


MODEL_CONFIG_CLASSES = list(MODEL_WITH_LM_HEAD_MAPPING.keys())
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)


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

    model_name_or_path: Optional[str] = field(
        default=None,
        metadata={
            "help": "The model checkpoint for weights initialization. Leave None if you want to train a model from scratch."
        },
    )
    model_type: Optional[str] = field(
        default=None,
        metadata={"help": "If training from scratch, pass a model type from the list: " + ", ".join(MODEL_TYPES)},
    )
    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 s3"}
    )


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

    train_data_file: Optional[str] = field(
        default=None, metadata={"help": "The input training data file (a text file)."}
    )
    eval_data_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
    )
    line_by_line: bool = field(
        default=False,
        metadata={"help": "Whether distinct lines of text in the dataset are to be handled as distinct sequences."},
    )

    mlm: bool = field(
        default=False, metadata={"help": "Train with masked-language modeling loss instead of language modeling."}
    )
    mlm_probability: float = field(
        default=0.15, metadata={"help": "Ratio of tokens to mask for masked language modeling loss"}
    )

    block_size: int = field(
        default=-1,
        metadata={
            "help": "Optional input sequence length after tokenization."
            "The training dataset will be truncated in block of this size for training."
            "Default to the model max input length for single sentence inputs (take into account special tokens)."
        },
    )
    overwrite_cache: bool = field(
        default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



relogic/sql-to-text-train.py [31:112]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  MODEL_WITH_LM_HEAD_MAPPING,
  AutoTokenizer,
    HfArgumentParser,
    PreTrainedTokenizer,
    set_seed,
)
from relogic.pretrainkit.models.sql_to_text import SQL2TextModel
from relogic.pretrainkit.trainer import Trainer
from pretrainkit.datasets.text_generation.sql_to_text import SQL2QueryDataset, DataCollatorForSQL2Query
from relogic.pretrainkit.scorers.text_generation import TextGenerationScorer
from relogic.pretrainkit.training_args import TrainingArguments

logger = logging.getLogger(__name__)


MODEL_CONFIG_CLASSES = list(MODEL_WITH_LM_HEAD_MAPPING.keys())
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)


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

    model_name_or_path: Optional[str] = field(
        default=None,
        metadata={
            "help": "The model checkpoint for weights initialization. Leave None if you want to train a model from scratch."
        },
    )
    model_type: Optional[str] = field(
        default=None,
        metadata={"help": "If training from scratch, pass a model type from the list: " + ", ".join(MODEL_TYPES)},
    )
    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 s3"}
    )


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

    train_data_file: Optional[str] = field(
        default=None, metadata={"help": "The input training data file (a text file)."}
    )
    eval_data_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
    )
    line_by_line: bool = field(
        default=False,
        metadata={"help": "Whether distinct lines of text in the dataset are to be handled as distinct sequences."},
    )

    mlm: bool = field(
        default=False, metadata={"help": "Train with masked-language modeling loss instead of language modeling."}
    )
    mlm_probability: float = field(
        default=0.15, metadata={"help": "Ratio of tokens to mask for masked language modeling loss"}
    )

    block_size: int = field(
        default=-1,
        metadata={
            "help": "Optional input sequence length after tokenization."
            "The training dataset will be truncated in block of this size for training."
            "Default to the model max input length for single sentence inputs (take into account special tokens)."
        },
    )
    overwrite_cache: bool = field(
        default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -