rag-end2end-retriever/lightning_base.py [11:134]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    AdamW,
    AutoConfig,
    AutoModel,
    AutoModelForPreTraining,
    AutoModelForQuestionAnswering,
    AutoModelForSeq2SeqLM,
    AutoModelForSequenceClassification,
    AutoModelForTokenClassification,
    AutoModelWithLMHead,
    AutoTokenizer,
    PretrainedConfig,
    PreTrainedTokenizer,
)
from transformers.optimization import (
    Adafactor,
    get_cosine_schedule_with_warmup,
    get_cosine_with_hard_restarts_schedule_with_warmup,
    get_linear_schedule_with_warmup,
    get_polynomial_decay_schedule_with_warmup,
)
from transformers.utils.versions import require_version


logger = logging.getLogger(__name__)

require_version("pytorch_lightning>=1.0.4")

MODEL_MODES = {
    "base": AutoModel,
    "sequence-classification": AutoModelForSequenceClassification,
    "question-answering": AutoModelForQuestionAnswering,
    "pretraining": AutoModelForPreTraining,
    "token-classification": AutoModelForTokenClassification,
    "language-modeling": AutoModelWithLMHead,
    "summarization": AutoModelForSeq2SeqLM,
    "translation": AutoModelForSeq2SeqLM,
}


# update this and the import above to support new schedulers from transformers.optimization
arg_to_scheduler = {
    "linear": get_linear_schedule_with_warmup,
    "cosine": get_cosine_schedule_with_warmup,
    "cosine_w_restarts": get_cosine_with_hard_restarts_schedule_with_warmup,
    "polynomial": get_polynomial_decay_schedule_with_warmup,
    # '': get_constant_schedule,             # not supported for now
    # '': get_constant_schedule_with_warmup, # not supported for now
}
arg_to_scheduler_choices = sorted(arg_to_scheduler.keys())
arg_to_scheduler_metavar = "{" + ", ".join(arg_to_scheduler_choices) + "}"


class BaseTransformer(pl.LightningModule):
    def __init__(
        self,
        hparams: argparse.Namespace,
        num_labels=None,
        mode="base",
        config=None,
        tokenizer=None,
        model=None,
        **config_kwargs,
    ):
        """Initialize a model, tokenizer and config."""
        super().__init__()
        # TODO: move to self.save_hyperparameters()
        # self.save_hyperparameters()
        # can also expand arguments into trainer signature for easier reading

        self.save_hyperparameters(hparams)
        self.step_count = 0
        self.output_dir = Path(self.hparams.output_dir)
        cache_dir = self.hparams.cache_dir if self.hparams.cache_dir else None
        if config is None:
            self.config = AutoConfig.from_pretrained(
                self.hparams.config_name if self.hparams.config_name else self.hparams.model_name_or_path,
                **({"num_labels": num_labels} if num_labels is not None else {}),
                cache_dir=cache_dir,
                **config_kwargs,
            )
        else:
            self.config: PretrainedConfig = config

        extra_model_params = ("encoder_layerdrop", "decoder_layerdrop", "dropout", "attention_dropout")
        for p in extra_model_params:
            if getattr(self.hparams, p, None):
                assert hasattr(self.config, p), f"model config doesn't have a `{p}` attribute"
                setattr(self.config, p, getattr(self.hparams, p))

        if tokenizer is None:
            self.tokenizer = AutoTokenizer.from_pretrained(
                self.hparams.tokenizer_name if self.hparams.tokenizer_name else self.hparams.model_name_or_path,
                cache_dir=cache_dir,
            )
        else:
            self.tokenizer: PreTrainedTokenizer = tokenizer
        self.model_type = MODEL_MODES[mode]
        if model is None:
            self.model = self.model_type.from_pretrained(
                self.hparams.model_name_or_path,
                from_tf=bool(".ckpt" in self.hparams.model_name_or_path),
                config=self.config,
                cache_dir=cache_dir,
            )
        else:
            self.model = model

    def load_hf_checkpoint(self, *args, **kwargs):
        self.model = self.model_type.from_pretrained(*args, **kwargs)

    def get_lr_scheduler(self):
        get_schedule_func = arg_to_scheduler[self.hparams.lr_scheduler]
        scheduler = get_schedule_func(
            self.opt, num_warmup_steps=self.hparams.warmup_steps, num_training_steps=self.total_steps()
        )
        scheduler = {"scheduler": scheduler, "interval": "step", "frequency": 1}
        return scheduler

    def configure_optimizers(self):
        """Prepare optimizer and schedule (linear warmup and decay)"""
        model = self.model
        no_decay = ["bias", "LayerNorm.weight"]
        optimizer_grouped_parameters = [
            {
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



rag/lightning_base.py [11:134]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    AdamW,
    AutoConfig,
    AutoModel,
    AutoModelForPreTraining,
    AutoModelForQuestionAnswering,
    AutoModelForSeq2SeqLM,
    AutoModelForSequenceClassification,
    AutoModelForTokenClassification,
    AutoModelWithLMHead,
    AutoTokenizer,
    PretrainedConfig,
    PreTrainedTokenizer,
)
from transformers.optimization import (
    Adafactor,
    get_cosine_schedule_with_warmup,
    get_cosine_with_hard_restarts_schedule_with_warmup,
    get_linear_schedule_with_warmup,
    get_polynomial_decay_schedule_with_warmup,
)
from transformers.utils.versions import require_version


logger = logging.getLogger(__name__)

require_version("pytorch_lightning>=1.0.4")

MODEL_MODES = {
    "base": AutoModel,
    "sequence-classification": AutoModelForSequenceClassification,
    "question-answering": AutoModelForQuestionAnswering,
    "pretraining": AutoModelForPreTraining,
    "token-classification": AutoModelForTokenClassification,
    "language-modeling": AutoModelWithLMHead,
    "summarization": AutoModelForSeq2SeqLM,
    "translation": AutoModelForSeq2SeqLM,
}


# update this and the import above to support new schedulers from transformers.optimization
arg_to_scheduler = {
    "linear": get_linear_schedule_with_warmup,
    "cosine": get_cosine_schedule_with_warmup,
    "cosine_w_restarts": get_cosine_with_hard_restarts_schedule_with_warmup,
    "polynomial": get_polynomial_decay_schedule_with_warmup,
    # '': get_constant_schedule,             # not supported for now
    # '': get_constant_schedule_with_warmup, # not supported for now
}
arg_to_scheduler_choices = sorted(arg_to_scheduler.keys())
arg_to_scheduler_metavar = "{" + ", ".join(arg_to_scheduler_choices) + "}"


class BaseTransformer(pl.LightningModule):
    def __init__(
        self,
        hparams: argparse.Namespace,
        num_labels=None,
        mode="base",
        config=None,
        tokenizer=None,
        model=None,
        **config_kwargs,
    ):
        """Initialize a model, tokenizer and config."""
        super().__init__()
        # TODO: move to self.save_hyperparameters()
        # self.save_hyperparameters()
        # can also expand arguments into trainer signature for easier reading

        self.save_hyperparameters(hparams)
        self.step_count = 0
        self.output_dir = Path(self.hparams.output_dir)
        cache_dir = self.hparams.cache_dir if self.hparams.cache_dir else None
        if config is None:
            self.config = AutoConfig.from_pretrained(
                self.hparams.config_name if self.hparams.config_name else self.hparams.model_name_or_path,
                **({"num_labels": num_labels} if num_labels is not None else {}),
                cache_dir=cache_dir,
                **config_kwargs,
            )
        else:
            self.config: PretrainedConfig = config

        extra_model_params = ("encoder_layerdrop", "decoder_layerdrop", "dropout", "attention_dropout")
        for p in extra_model_params:
            if getattr(self.hparams, p, None):
                assert hasattr(self.config, p), f"model config doesn't have a `{p}` attribute"
                setattr(self.config, p, getattr(self.hparams, p))

        if tokenizer is None:
            self.tokenizer = AutoTokenizer.from_pretrained(
                self.hparams.tokenizer_name if self.hparams.tokenizer_name else self.hparams.model_name_or_path,
                cache_dir=cache_dir,
            )
        else:
            self.tokenizer: PreTrainedTokenizer = tokenizer
        self.model_type = MODEL_MODES[mode]
        if model is None:
            self.model = self.model_type.from_pretrained(
                self.hparams.model_name_or_path,
                from_tf=bool(".ckpt" in self.hparams.model_name_or_path),
                config=self.config,
                cache_dir=cache_dir,
            )
        else:
            self.model = model

    def load_hf_checkpoint(self, *args, **kwargs):
        self.model = self.model_type.from_pretrained(*args, **kwargs)

    def get_lr_scheduler(self):
        get_schedule_func = arg_to_scheduler[self.hparams.lr_scheduler]
        scheduler = get_schedule_func(
            self.opt, num_warmup_steps=self.hparams.warmup_steps, num_training_steps=self.total_steps()
        )
        scheduler = {"scheduler": scheduler, "interval": "step", "frequency": 1}
        return scheduler

    def configure_optimizers(self):
        """Prepare optimizer and schedule (linear warmup and decay)"""
        model = self.model
        no_decay = ["bias", "LayerNorm.weight"]
        optimizer_grouped_parameters = [
            {
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -