Spaces:
Running
Running
| # Copyright 2024 HuggingFace Inc. and the LlamaFactory team. | |
| # | |
| # This code is inspired by the HuggingFace's transformers library. | |
| # https://github.com/huggingface/transformers/blob/v4.40.0/examples/pytorch/language-modeling/run_clm.py | |
| # | |
| # Licensed under the Apache License, Version 2.0 (the "License"); | |
| # you may not use this file except in compliance with the License. | |
| # You may obtain a copy of the License at | |
| # | |
| # http://www.apache.org/licenses/LICENSE-2.0 | |
| # | |
| # Unless required by applicable law or agreed to in writing, software | |
| # distributed under the License is distributed on an "AS IS" BASIS, | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| # See the License for the specific language governing permissions and | |
| # limitations under the License. | |
| import math | |
| from typing import TYPE_CHECKING, List, Optional | |
| from transformers import DataCollatorForLanguageModeling | |
| from ...data import get_dataset, split_dataset | |
| from ...extras.ploting import plot_loss | |
| from ...model import load_model, load_tokenizer | |
| from ..trainer_utils import create_modelcard_and_push | |
| from .trainer import CustomTrainer | |
| if TYPE_CHECKING: | |
| from transformers import Seq2SeqTrainingArguments, TrainerCallback | |
| from ...hparams import DataArguments, FinetuningArguments, ModelArguments | |
| def run_pt( | |
| model_args: "ModelArguments", | |
| data_args: "DataArguments", | |
| training_args: "Seq2SeqTrainingArguments", | |
| finetuning_args: "FinetuningArguments", | |
| callbacks: Optional[List["TrainerCallback"]] = None, | |
| ): | |
| tokenizer_module = load_tokenizer(model_args) | |
| tokenizer = tokenizer_module["tokenizer"] | |
| dataset = get_dataset(model_args, data_args, training_args, stage="pt", **tokenizer_module) | |
| model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train) | |
| data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False) | |
| # Initialize our Trainer | |
| trainer = CustomTrainer( | |
| model=model, | |
| args=training_args, | |
| finetuning_args=finetuning_args, | |
| data_collator=data_collator, | |
| callbacks=callbacks, | |
| **tokenizer_module, | |
| **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.save_model() | |
| trainer.log_metrics("train", train_result.metrics) | |
| trainer.save_metrics("train", train_result.metrics) | |
| trainer.save_state() | |
| if trainer.is_world_process_zero() and finetuning_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) | |
| # Create model card | |
| create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args) | |