Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Determine FSDP/deepspeed settings on device select. #883

Merged
merged 3 commits into from
Nov 29, 2023
Merged

Determine FSDP/deepspeed settings on device select. #883

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5d56f1a
Determine FSDP/deepspeed settings on device select.
Nov 21, 2023
32ecd09
rename and move env setup call
winglian Nov 25, 2023
d6ff17c
chore: lint
winglian Nov 25, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions src/axolotl/cli/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
from axolotl.utils.distributed import is_main_process
from axolotl.utils.models import load_tokenizer
from axolotl.utils.tokenization import check_dataset_labels
from axolotl.utils.trainer import prepare_optim_env
from axolotl.utils.wandb_ import setup_wandb_env_vars

project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
Expand Down Expand Up @@ -296,6 +297,8 @@ def load_cfg(config: Path = Path("examples/"), **kwargs):

validate_config(cfg)

prepare_optim_env(cfg)

normalize_config(cfg)

setup_wandb_env_vars(cfg)
Expand Down
4 changes: 3 additions & 1 deletion src/axolotl/utils/trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,12 +267,14 @@ def setup_fsdp_envs(cfg):
] = cfg.fsdp_config.fsdp_transformer_layer_cls_to_wrap


def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_steps):
def prepare_optim_env(cfg):
if cfg.fsdp:
setup_fsdp_envs(cfg)
elif cfg.deepspeed:
os.environ["ACCELERATE_USE_DEEPSPEED"] = "true"


def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_steps):
trainer_builder = HFCausalTrainerBuilder(cfg, model, tokenizer)
trainer_builder.train_dataset = train_dataset
trainer_builder.eval_dataset = eval_dataset
Expand Down