mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-10-16 00:28:10 +08:00
66 lines
2.5 KiB
Python
66 lines
2.5 KiB
Python
# Inspired by: https://github.com/huggingface/transformers/blob/v4.34.1/examples/pytorch/language-modeling/run_clm.py
|
|
|
|
import math
|
|
from typing import TYPE_CHECKING, Optional, List
|
|
from transformers import DataCollatorForLanguageModeling, Trainer
|
|
|
|
from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
|
|
from llmtuner.extras.ploting import plot_loss
|
|
from llmtuner.model import generate_model_card, 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.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
|
|
if training_args.do_train:
|
|
if training_args.push_to_hub:
|
|
trainer.push_to_hub(**generate_model_card(model_args, data_args, finetuning_args))
|
|
else:
|
|
trainer.create_model_card(**generate_model_card(model_args, data_args, finetuning_args))
|