Complete the code of prefix-tuning in low data setting

Last update: Jul 11, 2022

Related tags

Overview

Prefix Tuning

Note:

作者在论文中提到使用真实的word去初始化prefix的操作（Initializing the prefix with activations of real words，significantly improves generation）。我在使用作者提供的代码时遇到了一些问题，因此按照代码的思路添加了利用真实词汇进行初始化的内容。

可以采用以下的方式运行：

Train

cd seq2seq; 

python train_bart.py --mode xsum --preseqlen 200 --do_train yes --fp16 yes --bsz 16  --epoch 30  --gradient_accumulation_step 3 --learning_rate 0.00005  --mid_dim 800 --use_lowdata_token 'yes' --lowdata_token 'summarize'

其中use_lowdata_token表示是否采用real word初始化的方式；lowdata_token表示传入的real word.

Decode

cd seq2seq; 

python train_bart.py --mode xsum --do_train no --prefix_model_path {checkpoint_path} --preseqlen {same as training} --mid_dim {same as training} --use_lowdata_token 'yes' --lowdata_token 'summarize'

Files:

.
├── gpt2                          # Code for GPT2 style autoregressive LM
│   ├── train_e2e.py              # high-level scripts to train.
│   ├── train_control.py          # code that implements prefix-tuning.
│   ├── trainer_prefix.py         # trainer code for the training loop. 
│   ├── run_language_modeling.py  # training code (contains data loading, model loading, and calls trainer)
│   ├── gen.py                    # high-level scripts to decode. 
│   └── run_generation.py         # decoding code. 
│
├── seq2seq                       # Code for encoder-decoder architecture
│   ├── train_bart.py             # high-level scripts to train.
│   ├── prefixTuning.py           # code that implements prefix-tuning.
│   ├── finetune.py               # training code (contains data loading, model loading, and calls trainer)   
│   ├── lightning_base.py         # helper code
│   ├── utils.py                  # helper code
│   └── callbacks.py              # helper code
└── ...

To run the code for GPT2 style autoregressive LM, the code is in gpt2/. This corresponds to the table-to-text experiments in the paper.

To run the code for encoder-decoder architecture like BART, the code is in seq2seq. This corresponds to the summarization experiments in the paper.

The two primary scripts I used to run my codes are gpt2/train_e2e.py (for table-to-text) and seq2seq/train_bart.py(for summarization). they are set to default of good hyperparameters, and can be used to tune hyperparameter :)

Setup:

cd transformer; pip install -e .

Train via prefix-tuning:

cd gpt2;

python train_e2e.py --optim_prefix yes --preseqlen 5 --epoch 5 --learning_rate 0.00005 --mode webnlg --bsz 5 --seed 101

cd seq2seq; 

python train_bart.py --mode xsum --preseqlen 200 --do_train yes --fp16 yes --bsz 16  --epoch 30  --gradient_accumulation_step 3 --learning_rate 0.00005  --mid_dim 800

Other baseline approaches

cd gpt2;

python train_e2e.py --tuning_mode {finetune/adaptertune} --epoch 5 --learning_rate 0.00005 --mode webnlg --bsz 5 --seed 101

cd seq2seq;

python train_e2e.py --tuning_mode finetune --epoch 5 --learning_rate 0.00005 --mode webnlg --bsz 5 --seed 101

Decode:

cd gpt2;

python gen.py {data2text/webnlg/...} yes test {checkpoint_path} no

cd seq2seq; 

python train_bart.py --mode xsum --do_train no --prefix_model_path {checkpoint_path} --preseqlen {same as training} --mid_dim {same as training}

For details of the methods and results, please refer to our paper.

@misc{li2021prefixtuning,
      title={Prefix-Tuning: Optimizing Continuous Prompts for Generation}, 
      author={Xiang Lisa Li and Percy Liang},
      year={2021},
      eprint={2101.00190},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Complete the code of prefix-tuning in low data setting

Related tags

Overview

Prefix Tuning

Note:

Train

Decode

Files:

Setup:

Train via prefix-tuning:

Decode:

Owner

Andrew Zeng

Revisiting, benchmarking, and refining Heterogeneous Graph Neural Networks.

A hyperparameter optimization framework

Convert weight file.pth to weight file.blob

OpenVINO黑客松比赛项目

Seeing if I can put together an interactive version of 3b1b's Manim in Streamlit

DeconvNet : Learning Deconvolution Network for Semantic Segmentation

SpanNER: Named EntityRe-/Recognition as Span Prediction

Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning

Code for ICML 2021 paper: How could Neural Networks understand Programs?

Pytorch implementation of paper Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

Aerial Imagery dataset for fire detection: classification and segmentation (Unmanned Aerial Vehicle (UAV))

Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment"

Online Multi-Granularity Distillation for GAN Compression (ICCV2021)

A Home Assistant custom component for Lobe. Lobe is an AI tool that can classify images.

Model serving at scale

Incorporating Transformer and LSTM to Kalman Filter with EM algorithm

A curated list of awesome resources combining Transformers with Neural Architecture Search

My 1st place solution at Kaggle Hotel-ID 2021

Official Implementation of "Transformers Can Do Bayesian Inference"

Reinforcement Learning for the Blackjack