workflow.py

# Inspired by: https://github.com/huggingface/transformers/blob/v4.29.2/examples/pytorch/language-modeling/run_clm.py

import math
from typing import TYPE_CHECKING, Optional, List
from transformers import DataCollatorForLanguageModeling, Trainer

from llmtuner.dsets import get_dataset, preprocess_dataset, split_dataset
from llmtuner.extras.ploting import plot_loss
from llmtuner.tuner.core import load_model_and_tokenizer

if TYPE_CHECKING:
    from transformers import Seq2SeqTrainingArguments, TrainerCallback
    from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments


def run_pt(
    model_args: "ModelArguments",
    data_args: "DataArguments",
    training_args: "Seq2SeqTrainingArguments",
    finetuning_args: "FinetuningArguments",
    callbacks: Optional[List["TrainerCallback"]] = None
):
    dataset = get_dataset(model_args, data_args)
    model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, stage="pt")
    dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="pt")
    data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)

    # Initialize our Trainer
    trainer = Trainer(
        model=model,
        args=training_args,
        tokenizer=tokenizer,
        data_collator=data_collator,
        callbacks=callbacks,
        **split_dataset(dataset, data_args, training_args)
    )

    # Training
    if training_args.do_train:
        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
        trainer.log_metrics("train", train_result.metrics)
        trainer.save_metrics("train", train_result.metrics)
        trainer.save_state()
        trainer.save_model()
        if trainer.is_world_process_zero() and model_args.plot_loss:
            plot_loss(training_args.output_dir, keys=["loss", "eval_loss"])

    # Evaluation
    if training_args.do_eval:
        metrics = trainer.evaluate(metric_key_prefix="eval")
        try:
            perplexity = math.exp(metrics["eval_loss"])
        except OverflowError:
            perplexity = float("inf")

        metrics["perplexity"] = perplexity
        trainer.log_metrics("eval", metrics)
        trainer.save_metrics("eval", metrics)