The Codebase for Causal Distillation for Language Models.

Overview

Python 3.7 License CC BY-NC

Causal Distillation for Language Models

Zhengxuan Wu*,Atticus Geiger*, Josh Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, Noah D. Goodman

The is an implementation of our preprint Causal Distillation for Language Models. The standard approach to distillation trains a student model against two objectives: a task-specific objective (e.g., language modeling) and an imitation objective that encourages the hidden states of the student model to be similar to those of the larger teacher model. In this paper, we show that it is beneficial to augment distillation with a third objective that encourages the student to imitate the causal computation process of the teacher through interchange intervention training (IIT).

We fork our main codebase from the Huggingface Distillation Interface.

Release Notes

12/02/2021 Our paper on Interchange Intervention Training (IIT) is released! Read this more formal definition of the method.
12/06/2021 Released the causal distillation codebase with the preprint.
12/06/2021 Released evaluation results on distilled tiny-BERT (3 layers) with the Wiki-Text 103M dataset.
⬜️ Released evaluation results on causal-distilled tiny-BERT (3 layers) with the Wiki-Text 103M + BookCorpus dataset.
⬜️ Released evaluation results on causal-distilled BERT (6 layers) with the Wiki-Text 103M + BookCorpus dataset.
⬜️ Released more ablation studies.
⬜️ Released causal-distilled tiny-BERT (3 layers) model files.
⬜️ Released causal-distilled BERT (6 layers) model files.

If you experience any issues or have suggestions, please contact me either thourgh the issues page or at [email protected].

Benchmark Results

Here are the results on the dev sets of GLUE:

Model Average-score CoLA MNLI MRPC QNLI QQP RTE SST-2 STS-B WNLI
DistilBERT (3 layers) 67.81 22.8 71.6 78.2 82.1 84.3 55.4 86.5 56.7 24.2
CausalBERT (3 layers) 69.71 25.0 72.9 78.6 83.1 84.9 55.4 86.9 66.5 21.5

1 Average-score computed without WNLI.

Main Contents

Citation

If you use this repository, please cite the following two papers: paper for interchange intervention training, and paper for the our distillation method.

  @article{geiger-etal-2021-iit,
        title={Inducing Causal Structure for Interpretable Neural Networks}, 
        author={Geiger, Atticus and Wu, Zhengxuan and Lu, Hanson and Rozner, Josh and Kreiss, Elisa and Icard, Thomas and Goodman, Noah D. and Potts, Christopher},
        year={2021},
        eprint={2112.00826},
        archivePrefix={arXiv},
        primaryClass={cs.LG}
  }

  @article{wu-etal-2021-distill,
        title={Causal Distillation for Language Models}, 
        author={Wu, Zhengxuan and Geiger, Atticus and Rozner, Josh and Kreiss, Elisa and Lu, Hanson and Icard, Thomas and Potts, Christopher and Goodman, Noah D.},
        year={2021},
        eprint={2112.02505},
        archivePrefix={arXiv},
        primaryClass={cs.CL}
  }

Requirements

  • Python 3.6 or 3.7 are supported.
  • Pytorch Version: 1.9.0
  • Transfermers Version: 4.11.3
  • Datasets Version: Version: 1.8.0
  • We have performed experiments on Titan V GPU. We assume 12GB of GPU memory (more memory can expedite training).
  • Since we build our codebase off the Huggingface Distillation Interface, please review their doc for requirements.

Dataset

Following the Huggingface Distillation Interface, we need to pre-process the datasets before we do distillation. You can refer to their repo for details. We adapt their pre-processing scripts, and update with a few improvements. For example, we can now binarize datasets from the Dataset Hub from huggingface directly.

# preprocessing from disk
python script/binarized_data.py \
--file_path ../../bert-mid-tuning/data-files/wikitext-15M \
--split train \
--field_name text \
--max_parsing_example 1000 \
--tokenizer_type bert \
--tokenizer_name bert-base-uncased \
--dump_file ./data/binarized_text

# preprocessing from huggingface.
python scripts/binarized_data.py \
--dataset_name bookcorpus \
--split train \
--field_name text \
--tokenizer_type bert \
--tokenizer_name bert-base-uncased \
--dump_file bookcorpus-dataset/binarized_text \
--cache_dir ./distill_cache/

python scripts/binarized_data.py \
--dataset_name wikitext \
--split train \
--field_name text \
--tokenizer_type bert \
--tokenizer_name bert-base-uncased \
--dump_file wikitext-dataset/binarized_text \
--cache_dir ./distill_cache/

python scripts/binarized_data.py \
--dataset_name wikitext+bookcorpus \
--split train \
--field_name text \
--tokenizer_type bert \
--tokenizer_name bert-base-uncased \
--dump_file wikitext+bookcorpus-dataset/binarized_text \
--cache_dir ./distill_cache/

# helper scripts to combine two binarized data files
python scripts/data_combinator.py \
--file_path_left ./bookcorpus-dataset/binarized_text.train.bert-base-uncased.pickle \
--file_path_right ./wikitext-dataset/binarized_text.train.bert-base-uncased.pickle \
--split train \
--tokenizer_name bert-base-uncased \
--dump_file wikitext+bookcorpus-dataset/binarized_text

# multiprocessing preprocessor.
python scripts/binarized_data.py \
--dataset_name bookcorpus \
--split train \
--field_name text \
--tokenizer_type bert \
--tokenizer_name bert-base-uncased \
--dump_file bookcorpus-dataset/binarized_text \
--cache_dir ./distill_cache/ \
--fast_process \
--preprocessing_num_workers 48

After you get the datasets ready, you need to generate token counts as well.

python scripts/token_counts.py \
--data_file data/binarized_text.train.bert-base-uncased.pickle \
--token_counts_dump data/binarized_text.train.token_counts.bert-base-uncased.pickle \
--vocab_size 30522

Distillation

Before training, we recommand you to initialize your student model with weights extracted from the teacher model.

python scripts/extract_distilbert.py \
--model_type bert \
--model_name bert-base-uncased \
--dump_checkpoint ./distillation_checkpoints/bert-base-uncased_num_layer_3.pth \
--num_layers 3

Now, here is an example for you to distill with our causal distillation objective or without,

CUDA_VISIBLE_DEVICES=9,4 python causal_train.py \
--force \
--n_gpu 2 \
--is_wandb \
--log_interval 10 \
--student_type distilbert \
--student_config ./training_configs/distilbert-base-uncased-small.json \
--student_pretrained_weights ./distillation_checkpoints/bert-base-uncased_num_layer_3.pth \
--teacher_type bert \
--teacher_name bert-base-uncased \
--neuron_mapping ./training_configs/single_middle.nm \
--mlm --alpha_ce 0.25 --alpha_mlm 0.25 --alpha_cos 0.25 --alpha_clm 0.0 --alpha_causal 0.25 \
--freeze_pos_embs \
--dump_path ./results/ \
--data_file ./wikitext-15M/binarized_text.train.bert-base-uncased.pickle \
--token_counts ./wikitext-15M/binarized_text.train.token_counts.bert-base-uncased.pickle \
--seed 42 \
--gradient_accumulation_steps 50 \
--n_epoch 3 \
--batch_size 5

CUDA_VISIBLE_DEVICES=0,1,2,3 python causal_train.py \
--force \
--n_gpu 4 \
--is_wandb \
--log_interval 10 \
--student_type distilbert \
--student_config ./training_configs/distilbert-base-uncased-small.json \
--student_pretrained_weights ./distillation_checkpoints/bert-base-uncased_num_layer_3.pth \
--teacher_type bert \
--teacher_name bert-base-uncased \
--neuron_mapping ./training_configs/single_middle.nm \
--mlm --alpha_ce 0.33 --alpha_mlm 0.33 --alpha_cos 0.33 --alpha_clm 0.0 --alpha_causal 0.00 \
--freeze_pos_embs \
--dump_path ./results/ \
--data_file ./wikitext-15M/binarized_text.train.bert-base-uncased.pickle \
--token_counts ./wikitext-15M/binarized_text.train.token_counts.bert-base-uncased.pickle \
--seed 42 \
--gradient_accumulation_steps 124 \
--n_epoch 6 \
--batch_size 4

Note that you can simply turn our causal distillation objective on/off through setting the arguments.

Evaluation

After you get your distilled models, you need to fine-tune them and evaluate them with downstream tasks. We provide you all the scripts you need to run.

MLM Evaluation

CUDA_VISIBLE_DEVICES=5 python run_mlm.py \
--model_name_or_path ./results/s_distilbert_t_bert_data_wikitext-15M_seed_42_mlm_True_ce_0.25_mlm_0.25_cos_0.25_causal_0.25_nm_single_multilayer/ \
--dataset_dir ../../bert-mid-tuning/data-files/wikitext-15M/ \
--tokenizer_name bert-base-uncased \
--do_eval \
--output_dir /tmp/test-mlm \
--cache_dir ./distill_cache/

GLUE Evaluation

CUDA_VISIBLE_DEVICES=5,7,8,9 python run_glue.py \
--model_name_or_path ./results/s_distilbert_t_bert_data_wikitext-dataset_seed_42_mlm_True_ce_0.33_mlm_0.33_cos_0.33_causal_0.0_nm_single_middle/ \
--tokenizer_name bert-base-uncased \
--task_name sst2 \
--do_train \
--do_eval \
--max_seq_length 128 \
--per_device_train_batch_size 32 \
--learning_rate 2e-5 \
--num_train_epochs 3 \
--output_dir ./results/ \
--save_total_limit 1 \
--cache_dir ./distill_cache/

CoNLL Evaluation

CUDA_VISIBLE_DEVICES=2,3,7,8 python run_ner.py \
--model_name_or_path ./results/s_distilbert_t_bert_data_wikitext-dataset_seed_42_mlm_True_ce_0.33_mlm_0.33_cos_0.33_causal_0.0_nm_single_middle_crossway_False/ \
--tokenizer_name bert-base-uncased \
--dataset_name conll2003 \
--do_train \
--do_eval \
--output_dir ./ner_results/ \
--save_total_limit 1 \
--cache_dir ./distill_cache/

SQuAD Evaluation

CUDA_VISIBLE_DEVICES=2,3,7,8 python run_qa.py \
--model_name_or_path ./results/s_distilbert_t_bert_data_wikitext-dataset_seed_42_mlm_True_ce_0.33_mlm_0.33_cos_0.33_causal_0.0_nm_single_middle_crossway_False/ \
--tokenizer_name bert-base-uncased \
--dataset_name squad \
--do_train \
--do_eval \
--per_device_train_batch_size 12 \
--learning_rate 3e-5 \
--num_train_epochs 2 \
--max_seq_length 384 \
--doc_stride 128 \
--save_total_limit 1 \
--output_dir ./qa_results/
TVNet: Temporal Voting Network for Action Localization

TVNet: Temporal Voting Network for Action Localization This repo holds the codes of paper: "TVNet: Temporal Voting Network for Action Localization". P

hywang 5 Jul 26, 2022
This python-based package offers a way of creating a parametric OpenMC plasma source from plasma parameters.

openmc-plasma-source This python-based package offers a way of creating a parametric OpenMC plasma source from plasma parameters. The OpenMC sources a

Fusion Energy 10 Oct 18, 2022
C3DPO - Canonical 3D Pose Networks for Non-rigid Structure From Motion.

C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion By: David Novotny, Nikhila Ravi, Benjamin Graham, Natalia Neverova, Andrea Vedal

Meta Research 309 Dec 16, 2022
Python wrapper class for OpenVINO Model Server. User can submit inference request to OVMS with just a few lines of code

Python wrapper class for OpenVINO Model Server. User can submit inference request to OVMS with just a few lines of code.

Yasunori Shimura 7 Jul 27, 2022
Small little script to scrape, parse and check for active tor nodes. Can be used as proxies.

TorScrape TorScrape is a small but useful script made in python that scrapes a website for active tor nodes, parse the html and then save the nodes in

5 Dec 04, 2022
CS583: Deep Learning

CS583: Deep Learning

Shusen Wang 2.6k Dec 30, 2022
A collection of semantic image segmentation models implemented in TensorFlow

A collection of semantic image segmentation models implemented in TensorFlow. Contains data-loaders for the generic and medical benchmark datasets.

bobby 16 Dec 06, 2019
Repository for Driving Style Recognition algorithms for Autonomous Vehicles

Driving Style Recognition Using Interval Type-2 Fuzzy Inference System and Multiple Experts Decision Making Created by Iago Pachêco Gomes at USP - ICM

Iago Gomes 9 Nov 28, 2022
Independent and minimal implementations of some reinforcement learning algorithms using PyTorch (including PPO, A3C, A2C, ...).

PyTorch RL Minimal Implementations There are implementations of some reinforcement learning algorithms, whose characteristics are as follow: Less pack

Gemini Light 4 Dec 31, 2022
Source code for paper "Deep Diffusion Models for Robust Channel Estimation", TBA.

diffusion-channels Source code for paper "Deep Diffusion Models for Robust Channel Estimation". Generic flow: Use 'matlab/main.mat' to generate traini

The University of Texas Computational Sensing and Imaging Lab 15 Dec 22, 2022
Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning

SkFlow has been moved to Tensorflow. SkFlow has been moved to http://github.com/tensorflow/tensorflow into contrib folder specifically located here. T

3.2k Dec 29, 2022
A Python Library for Graph Outlier Detection (Anomaly Detection)

PyGOD is a Python library for graph outlier detection (anomaly detection). This exciting yet challenging field has many key applications, e.g., detect

PyGOD Team 757 Jan 04, 2023
This is the pytorch re-implementation of the IterNorm

IterNorm-pytorch Pytorch reimplementation of the IterNorm methods, which is described in the following paper: Iterative Normalization: Beyond Standard

Lei Huang 32 Dec 27, 2022
ICLR 2021: Pre-Training for Context Representation in Conversational Semantic Parsing

SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing This repository contains code for the ICLR 2021 paper "SCoRE: Pre-Tr

Microsoft 28 Oct 02, 2022
This is the official Pytorch-version code of FlatGCN (Flattened Graph Convolutional Networks for Recommendation).

FlatGCN This is the official Pytorch-version code of FlatGCN (Flattened Graph Convolutional Networks for Recommendation, submitted to ICASSP2022). Req

Dreamer 2 Aug 09, 2022
FinGAT: A Financial Graph Attention Networkto Recommend Top-K Profitable Stocks

FinGAT: A Financial Graph Attention Networkto Recommend Top-K Profitable Stocks This is our implementation for the paper: FinGAT: A Financial Graph At

Yu-Che Tsai 64 Dec 13, 2022
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

SimplePose Code and pre-trained models for our paper, “Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation”, a

Jia Li 256 Dec 24, 2022
Pytorch implementation of paper: "NeurMiPs: Neural Mixture of Planar Experts for View Synthesis"

NeurMips: Neural Mixture of Planar Experts for View Synthesis This is the official repo for PyTorch implementation of paper "NeurMips: Neural Mixture

James Lin 101 Dec 13, 2022
The BCNet related data and inference model.

BCNet This repository includes the some source code and related dataset of paper BCNet: Learning Body and Cloth Shape from A Single Image, ECCV 2020,

81 Dec 12, 2022
Tutorial: Introduction to Graph Machine Learning, with Jupyter notebooks

GraphMLTutorialNLDL22 Tutorial NLDL22: Introduction to Graph Machine Learning, with Jupyter notebooks This tutorial takes place during the conference

UiT Machine Learning Group 3 Jan 10, 2022