ColossalAI/applications/Chat/coati/experience_buffer/base.py

44 lines
1.0 KiB
Python
Raw Normal View History

2023-03-28 12:25:36 +00:00
from abc import ABC, abstractmethod
from typing import Any
from coati.experience_maker.base import Experience
[chat] fix bugs and add unit tests (#4213) * style: rename replay buffer Experience replay is typically for off policy algorithms. Use this name in PPO maybe misleading. * fix: fix wrong zero2 default arg * test: update experience tests * style: rename zero_pad fn * fix: defer init in CycledDataLoader * test: add benchmark test * style: rename internal fn of generation * style: rename internal fn of lora * fix: remove unused loss fn * fix: remove unused utils fn * refactor: remove generate_with_actor fn * fix: fix type annotation * test: add models tests * fix: skip llama due to long execution time * style: modify dataset * style: apply formatter * perf: update reward dataset * fix: fix wrong IGNORE_INDEX in sft dataset * fix: remove DataCollatorForSupervisedDataset * test: add dataset tests * style: apply formatter * style: rename test_ci to test_train * feat: add llama in inference * test: add inference tests * test: change test scripts directory * fix: update ci * fix: fix typo * fix: skip llama due to oom * fix: fix file mod * style: apply formatter * refactor: remove duplicated llama_gptq * style: apply formatter * to: update rm test * feat: add tokenizer arg * feat: add download model script * test: update train tests * fix: modify gemini load and save pretrained * test: update checkpoint io test * to: modify nproc_per_node * fix: do not remove existing dir * fix: modify save path * test: add random choice * fix: fix sft path * fix: enlarge nproc_per_node to avoid oom * fix: add num_retry * fix: make lora config of rm and critic consistent * fix: add warning about lora weights * fix: skip some gpt2 tests * fix: remove grad ckpt in rm and critic due to errors * refactor: directly use Actor in train_sft * test: add more arguments * fix: disable grad ckpt when using lora * fix: fix save_pretrained and related tests * test: enable zero2 tests * revert: remove useless fn * style: polish code * test: modify test args
2023-08-02 02:17:36 +00:00
class ExperienceBuffer(ABC):
"""Experience buffer base class. It stores experience.
2023-03-28 12:25:36 +00:00
Args:
sample_batch_size (int): Batch size when sampling.
limit (int, optional): Limit of number of experience samples. A number <= 0 means unlimited. Defaults to 0.
"""
def __init__(self, sample_batch_size: int, limit: int = 0) -> None:
super().__init__()
self.sample_batch_size = sample_batch_size
# limit <= 0 means unlimited
self.limit = limit
@abstractmethod
def append(self, experience: Experience) -> None:
pass
@abstractmethod
def clear(self) -> None:
pass
@abstractmethod
def sample(self) -> Experience:
pass
@abstractmethod
def __len__(self) -> int:
pass
@abstractmethod
def __getitem__(self, idx: int) -> Any:
pass
@abstractmethod
def collate_fn(self, batch: Any) -> Experience:
pass