File size: 2,518 Bytes
abbcb88 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
# coding=utf-8
# Implements parameter-efficient training of reward models.
# This code is inspired by:
# https://github.com/lvwerra/trl/blob/main/examples/summarization/scripts/reward_summarization.py
# https://github.com/CarperAI/trlx/blob/main/examples/summarize_rlhf/reward_model/train_reward_model_gptj.py
from utils import (
PairwiseDataCollatorWithPadding,
PairwisePeftTrainer,
LogCallback,
load_pretrained,
prepare_args,
prepare_data,
preprocess_data,
compute_accuracy,
plot_loss
)
def main():
# Prepare pretrained model and dataset
model_args, data_args, training_args, finetuning_args = prepare_args(stage="rm")
dataset = prepare_data(model_args, data_args)
model, tokenizer = load_pretrained(model_args, finetuning_args, training_args.do_train, stage="rm")
dataset = preprocess_data(dataset, tokenizer, data_args, training_args, stage="rm")
data_collator = PairwiseDataCollatorWithPadding(tokenizer)
training_args.remove_unused_columns = False # important for pairwise dataset
# 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 = PairwisePeftTrainer(
finetuning_args=finetuning_args,
model=model,
args=training_args,
tokenizer=tokenizer,
data_collator=data_collator,
callbacks=[LogCallback()],
compute_metrics=compute_accuracy,
**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")
trainer.log_metrics("eval", metrics)
trainer.save_metrics("eval", metrics)
def _mp_fn(index):
# For xla_spawn (TPUs)
main()
if __name__ == "__main__":
main()
|