Spaces:
Running
Running
File size: 3,325 Bytes
2852136 |
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 78 79 80 81 |
# Copyright 2024 HuggingFace Inc. and the LlamaFactory team.
#
# This code is inspired by the HuggingFace's TRL library.
# https://github.com/huggingface/trl/blob/v0.8.0/examples/scripts/ppo.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.
from typing import TYPE_CHECKING, List, Optional
from transformers import DataCollatorWithPadding
from ...data import get_dataset
from ...extras.callbacks import FixValueHeadModelCallback
from ...extras.misc import fix_valuehead_checkpoint
from ...extras.ploting import plot_loss
from ...model import load_model, load_tokenizer
from ..trainer_utils import create_ref_model, create_reward_model
from .trainer import CustomPPOTrainer
if TYPE_CHECKING:
from transformers import Seq2SeqTrainingArguments, TrainerCallback
from ...hparams import DataArguments, FinetuningArguments, GeneratingArguments, ModelArguments
def run_ppo(
model_args: "ModelArguments",
data_args: "DataArguments",
training_args: "Seq2SeqTrainingArguments",
finetuning_args: "FinetuningArguments",
generating_args: "GeneratingArguments",
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="ppo", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training
data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
# Create reference model and reward model
ref_model = create_ref_model(model_args, finetuning_args, add_valuehead=True)
reward_model = create_reward_model(model, model_args, finetuning_args)
# Initialize our Trainer
ppo_trainer = CustomPPOTrainer(
model_args=model_args,
training_args=training_args,
finetuning_args=finetuning_args,
generating_args=generating_args,
callbacks=callbacks + [FixValueHeadModelCallback()],
model=model,
reward_model=reward_model,
ref_model=ref_model,
dataset=dataset,
data_collator=data_collator,
**tokenizer_module,
)
# Training
if training_args.do_train:
ppo_trainer.ppo_train(resume_from_checkpoint=training_args.resume_from_checkpoint)
ppo_trainer.save_model()
if training_args.should_save:
fix_valuehead_checkpoint(model, training_args.output_dir, training_args.save_safetensors)
ppo_trainer.save_state() # must be called after save_model to have a folder
if ppo_trainer.is_world_process_zero() and finetuning_args.plot_loss:
plot_loss(training_args.output_dir, keys=["loss", "reward"])
|