mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-10-14 23:58:11 +08:00
74 lines
2.7 KiB
Python
74 lines
2.7 KiB
Python
# Inspired by: https://github.com/huggingface/transformers/blob/v4.29.2/examples/pytorch/language-modeling/run_clm.py
|
|
|
|
import math
|
|
from typing import Optional, List
|
|
from transformers import Seq2SeqTrainingArguments, DataCollatorForSeq2Seq, TrainerCallback
|
|
|
|
from llmtuner.dsets import get_dataset, preprocess_dataset
|
|
from llmtuner.extras.callbacks import LogCallback
|
|
from llmtuner.extras.constants import IGNORE_INDEX
|
|
from llmtuner.extras.ploting import plot_loss
|
|
from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments
|
|
from llmtuner.tuner.core import load_model_and_tokenizer
|
|
from llmtuner.tuner.core.trainer import PeftTrainer
|
|
|
|
|
|
def run_pt(
|
|
model_args: ModelArguments,
|
|
data_args: DataArguments,
|
|
training_args: Seq2SeqTrainingArguments,
|
|
finetuning_args: FinetuningArguments,
|
|
callbacks: Optional[List[TrainerCallback]] = [LogCallback()]
|
|
):
|
|
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 = DataCollatorForSeq2Seq(
|
|
tokenizer=tokenizer,
|
|
label_pad_token_id=IGNORE_INDEX if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
|
|
)
|
|
|
|
# Split the dataset
|
|
if training_args.do_train:
|
|
if data_args.dev_ratio > 1e-6:
|
|
dataset = dataset.train_test_split(test_size=data_args.dev_ratio)
|
|
trainer_kwargs = {"train_dataset": dataset["train"], "eval_dataset": dataset["test"]}
|
|
else:
|
|
trainer_kwargs = {"train_dataset": dataset}
|
|
else: # do_eval or do_predict
|
|
trainer_kwargs = {"eval_dataset": dataset}
|
|
|
|
# Initialize our Trainer
|
|
trainer = PeftTrainer(
|
|
finetuning_args=finetuning_args,
|
|
model=model,
|
|
args=training_args,
|
|
tokenizer=tokenizer,
|
|
data_collator=data_collator,
|
|
callbacks=callbacks,
|
|
**trainer_kwargs
|
|
)
|
|
|
|
# Training
|
|
if training_args.do_train:
|
|
train_result = trainer.train()
|
|
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)
|