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

Adding ppo training #1235

Draft
wants to merge 7 commits into
base: main
Choose a base branch
from
Draft

Adding ppo training #1235

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
9e39c54
initial commit
Goekdeniz-Guelmez Jan 31, 2025
3ad6405
Merge branch 'ml-explore:main' into adding-ppo-training
Goekdeniz-Guelmez Jan 31, 2025
595125a
updates
Goekdeniz-Guelmez Jan 31, 2025
aa7a11c
updates
Goekdeniz-Guelmez Jan 31, 2025
94debd5
Merge branch 'ml-explore:main' into adding-ppo-training
Goekdeniz-Guelmez Feb 3, 2025
9ece9ae
Merge branch 'ml-explore:main' into adding-ppo-training
Goekdeniz-Guelmez Feb 4, 2025
a7e4146
update create_dataset
Goekdeniz-Guelmez Feb 4, 2025
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
36 changes: 32 additions & 4 deletions llms/mlx_lm/tuner/datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,8 +102,35 @@ def create_dataset(
"https://github.com/ml-explore/mlx-examples/blob/main/llms/mlx_lm/LORA.md#data."
)

def create_dataset(
args,
data,
tokenizer: PreTrainedTokenizer,
prompt_feature: Optional[str] = None,
completion_feature: Optional[str] = None,
):
prompt_feature = prompt_feature or "prompt"
completion_feature = completion_feature or "completion"
sample = data[0]

if args.training_mode == "normal":
if "messages" in sample:
return ChatDataset(data, tokenizer)
elif prompt_feature in sample and completion_feature in sample:
return CompletionsDataset(data, tokenizer, prompt_feature, completion_feature)
elif "text" in sample:
return Dataset(data, tokenizer)
else:
raise ValueError(
"Unsupported data format, check the supported formats here:\n"
"https://github.com/ml-explore/mlx-examples/blob/main/llms/mlx_lm/LORA.md#data."
)
else:
return ""


def load_local_dataset(
args,
data_path: Path,
tokenizer: PreTrainedTokenizer,
prompt_feature: Optional[str] = None,
Expand All @@ -114,14 +141,15 @@ def load_subset(path):
return []
with open(path, "r") as fid:
data = [json.loads(l) for l in fid]
return create_dataset(data, tokenizer, prompt_feature, completion_feature)
return create_dataset(args, data, tokenizer, prompt_feature, completion_feature)

names = ("train", "valid", "test")
train, valid, test = [load_subset(data_path / f"{n}.jsonl") for n in names]
return train, valid, test


def load_hf_dataset(
args,
data_id: str,
tokenizer: PreTrainedTokenizer,
prompt_feature: Optional[str] = None,
Expand All @@ -137,7 +165,7 @@ def load_hf_dataset(
train, valid, test = [
(
create_dataset(
dataset[n], tokenizer, prompt_feature, completion_feature
args, dataset[n], tokenizer, prompt_feature, completion_feature
)
if n in dataset.keys()
else []
Expand Down Expand Up @@ -202,12 +230,12 @@ def load_dataset(args, tokenizer: PreTrainedTokenizer):
completion_feature = getattr(args, "completion_feature", None)
if data_path.exists():
train, valid, test = load_local_dataset(
data_path, tokenizer, prompt_feature, completion_feature
args, data_path, tokenizer, prompt_feature, completion_feature
)
else:
print(f"Loading Hugging Face dataset {args.data}.")
train, valid, test = load_hf_dataset(
args.data, tokenizer, prompt_feature, completion_feature
args, args.data, tokenizer, prompt_feature, completion_feature
)

if args.train and len(train) == 0:
Expand Down
Loading