ColossalAI/applications/ColossalChat/tests/verify_chat_data.py
YeAnbang df5e9c53cf
[ColossalChat] Update RLHF V2 (#5286)
* Add dpo. Fix sft, ppo, lora. Refactor all

* fix and tested ppo

* 2 nd round refactor

* add ci tests

* fix ci

* fix ci

* fix readme, style

* fix readme style

* fix style, fix benchmark

* reproduce benchmark result, remove useless files

* rename to ColossalChat

* use new image

* fix ci workflow

* fix ci

* use local model/tokenizer for ci tests

* fix ci

* fix ci

* fix ci

* fix ci timeout

* fix rm progress bar. fix ci timeout

* fix ci

* fix ci typo

* remove 3d plugin from ci temporary

* test environment

* cannot save optimizer

* support chat template

* fix readme

* fix path

* test ci locally

* restore build_or_pr

* fix ci data path

* fix benchmark

* fix ci, move ci tests to 3080, disable fast tokenizer

* move ci to 85

* support flash attention 2

* add all-in-one data preparation script. Fix colossal-llama2-chat chat template

* add hardware requirements

* move ci test data

* fix save_model, add unwrap

* fix missing bos

* fix missing bos; support grad accumulation with gemini

* fix ci

* fix ci

* fix ci

* fix llama2 chat template config

* debug sft

* debug sft

* fix colossalai version requirement

* fix ci

* add sanity check to prevent NaN loss

* fix requirements

* add dummy data generation script

* add dummy data generation script

* add dummy data generation script

* add dummy data generation script

* update readme

* update readme

* update readme and ignore

* fix logger bug

* support parallel_output

* modify data preparation logic

* fix tokenization

* update lr

* fix inference

* run pre-commit

---------

Co-authored-by: Tong Li <tong.li352711588@gmail.com>
2024-03-29 14:12:29 +08:00

65 lines
2.3 KiB
Python

import argparse
import json
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--data_source",
type=str,
required=True,
default=None,
help="The raw data file",
)
parser.add_argument(
"--to_verify_file",
type=str,
required=True,
default=None,
help="The file that contains the data to be verified",
)
parser.add_argument(
"--data_type",
type=str,
required=True,
default=None,
help="The data type",
)
args = parser.parse_args()
# Read data
data = []
with open(args.data_source, "r", encoding="utf8") as f:
for line in f.readlines():
data.append(json.loads(line))
to_verify_data = []
with open(args.to_verify_file, "r", encoding="utf8") as f:
for line in f.readlines():
to_verify_data.append(json.loads(line))
if args.data_type == "sft":
target_lable = [msg["content"].strip() for msg in data[0]["messages"] if msg["from"] == "assistant"]
target_negative_label = [msg["content"].strip() for msg in data[0]["messages"] if msg["from"] == "human"]
# Read to verify file
to_verify_lable = to_verify_data[0]["labels_decode"]
for label in target_lable:
assert any([label in s for s in to_verify_lable]), f"Label {label} not in target label {to_verify_lable}"
for label in target_negative_label:
assert all(
[label not in s for s in to_verify_lable]
), f"Negative label {label} in target label {to_verify_lable}"
elif args.data_type == "dpo":
chosen_lable = data[0]["chosen"][0]["content"].strip()
rejected_lable = data[0]["rejected"][0]["content"].strip()
# Read to verify file
to_verify_lable_chosen = to_verify_data[0]["chosen_label_decode"]
to_verify_lable_rejected = to_verify_data[0]["rejected_label_decode"]
assert any(
[chosen_lable in s for s in to_verify_lable_chosen]
), f"Chosen label {chosen_lable} not in target chosen label {to_verify_lable_chosen}"
assert any(
[rejected_lable in s for s in to_verify_lable_rejected]
), f"Rejected label {rejected_lable} not in target rejected label {to_verify_lable_chosen}"