yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-09-09 00:06:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
autogen/flaml/automl/nlp
History
Chi Wang a0b318b12e
create an automl option to remove unnecessary dependency for autogen and tune (#1007) 
* version update post release v1.2.2

* automl option

* import pandas

* remove automl.utils

* default

* test

* type hint and version update

* dependency update

* link to open in colab

* use packging.version to close #725

---------

Co-authored-by: Li Jiang <lijiang1@microsoft.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-05-24 23:55:04 +00:00
..
huggingface
create an automl option to remove unnecessary dependency for autogen and tune (#1007)
2023-05-24 23:55:04 +00:00
__init__.py
Refactor into automl subpackage (#809)
2022-12-06 15:46:08 -05:00
README.md
precommit: end-of-file-fixer (#929)
2023-02-28 16:27:14 +00:00
utils.py
set black with 120 line length (#975)
2023-04-10 19:50:40 +00:00

README.md

AutoML for NLP

This directory contains utility functions used by AutoNLP. Currently we support four NLP tasks: sequence classification, sequence regression, multiple choice and summarization.

Please refer to this link for examples.

Troubleshooting fine-tuning HPO for pre-trained language models

The frequent updates of transformers may lead to fluctuations in the results of tuning. To help users quickly troubleshoot the result of AutoNLP when a tuning failure occurs (e.g., failing to reproduce previous results), we have provided the following jupyter notebook:

Our findings on troubleshooting fine-tuning the Electra and RoBERTa model for the GLUE dataset can be seen in the following paper published in ACL 2021:

@inproceedings{liu2021hpo,
    title={An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models},
    author={Xueqing Liu and Chi Wang},
    year={2021},
    booktitle={ACL-IJCNLP},
}