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

GPT, but made only out of gMLPs

The code of “Similarity Reasoning and Filtration for Image-Text Matching” [AAAI2021]

Large scale and asynchronous Hyperparameter Optimization at your fingertip.

IhoneyBakFileScan Modify - 批量网站备份文件扫描器，增加文件规则，优化内存占用

📚 A collection of Jupyter notebooks for learning and experimenting with OpenVINO 👓

Modified fork of Xuebin Qin's U-2-Net Repository. Used for demonstration purposes.

ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss (HDCWNet)

LightSeq is a high performance training and inference library for sequence processing and generation implemented in CUDA

Neural-net-from-scratch - A simple Neural Network from scratch in Python using the Pymathrix library

Road Crack Detection Using Deep Learning Methods

Prevent `CUDA error: out of memory` in just 1 line of code.

Playable Video Generation

ICLR2021 (Under Review)

N-Omniglot is a large neuromorphic few-shot learning dataset

Official PyTorch implementation for FastDPM, a fast sampling algorithm for diffusion probabilistic models

Streamlit tool to explore coco datasets

Code to accompany the paper "Finding Bipartite Components in Hypergraphs", which is published in NeurIPS'21.

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context Code in both PyTorch and TensorFlow

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

MIRACLE (Missing data Imputation Refinement And Causal LEarning)