Skip to content

Conversation

@lugimzzz
Copy link
Contributor

PR types

New features

PR changes

Others

Description

rm

@CLAassistant
Copy link

CLAassistant commented Sep 19, 2024

CLA assistant check
All committers have signed the CLA.

@lugimzzz lugimzzz changed the title ad flashmask rm add flashmask rm Sep 19, 2024
@codecov
Copy link

codecov bot commented Sep 19, 2024

Codecov Report

Attention: Patch coverage is 0% with 12 lines in your changes missing coverage. Please review.

Project coverage is 53.02%. Comparing base (ad14dc4) to head (ee302b6).
Report is 254 commits behind head on develop.

Files with missing lines Patch % Lines
paddlenlp/datasets/zero_padding_dataset.py 0.00% 8 Missing ⚠️
paddlenlp/transformers/llama/fusion_ops.py 0.00% 4 Missing ⚠️
Additional details and impacted files
@@ Coverage Diff @@ ## develop #9154 +/- ## =========================================== - Coverage 53.06% 53.02% -0.05%  =========================================== Files 656 656 Lines 106147 106162 +15 =========================================== - Hits 56324 56288 -36  - Misses 49823 49874 +51 

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

rejected_indexes = paddle.to_tensor(
[[response_index[0], response_index[2]] for response_index in response_indexs]
)
chosen_hidden_states = hidden_states.gather_nd(chosen_indexes)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sequence parallel 等都不支持吗

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

适配了

"""main"""
parser = PdArgumentParser((ModelArgument, DataArgument, TrainingArguments))
if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里要不支持下json和命令行,因为ce里面可能会增加命令行去覆盖json的配置,可参考这里:https://github.com/PaddlePaddle/PaddleNLP/blob/develop/llm/run_finetune.py#L77

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ok

logger.info("Start to create dataset")
trans_func = partial(preprocess_preference_data, tokenizer=tokenizer, data_args=data_args, model_args=model_args)
if data_args.lazy:
zero_padding_dataset = ZeroPaddingIterableDataset
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

如果设置Lazy,那么按epoch保存会报错吗?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lazy只支持step

@ZHUI ZHUI merged commit b2e4db2 into PaddlePaddle:develop Sep 27, 2024
@lugimzzz lugimzzz deleted the rm branch September 27, 2024 06:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

4 participants