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}
}
72 Jan 01, 2023
25 Sep 21, 2022
20 Sep 19, 2022
83 Dec 31, 2022
1 Jan 21, 2022
1.2k Dec 21, 2022
460 Oct 13, 2022
47 Nov 17, 2022
15.3k Jan 05, 2023
2 Sep 22, 2022
1.1k Dec 30, 2022
2.3k Dec 17, 2022
254 Dec 16, 2022
1.2k Dec 29, 2022
405 Dec 17, 2022
24 Oct 23, 2022
35 Nov 20, 2022
190 Dec 27, 2022
[email protected]">
2 Apr 07, 2022
21 Nov 05, 2022