Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

Last update: Dec 05, 2022

Overview

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

This is the Pytorch implementation for sparse progressive distillation (SPD). For more details about the motivation, techniques and experimental results, refer to our paper here.

Running

Environment Preparation (using python3)
```
pip install -r requirements.txt
```
Dataset Preparation

The original GLUE dataset could be downloaded here.

BERT_base fine-tuning on GLUE

We use finetuned BERT_base as the teacher. For each task of GLUE benchmark, we obtain the finetuned model using the original huggingface transformers code with the following script.

python run_glue.py \
          --model_name_or_path $INT_DIR \
          --task_name $TASK_NAME \
          --do_train \
          --do_eval \
          --data_dir $GLUE_DIR/$TASK_NAME/ \
          --max_seq_length 128 \
          --per_gpu_train_batch_size 32 \
          --per_gpu_eval_batch_size 32 \
          --learning_rate 3e-5 \
          --num_train_epochs 4.0 \
          --output_dir $OUT_DIR \
          --evaluate_during_training \
          --overwrite_output_dir \
          --logging_steps 400 \
          --logging_dir $OUT_DIR \
          --save_steps 10000

Sparse Progressive Distillation

We use run_glue.py to run the sparse progressive distillation. --num_prune_epochs is the epochs for pruning. --num_train_epochs is the total number of epochs (pruning, progressive distillation, finetuning).

python run_glue.py \
  --model_name_or_path PATH_TO_FINETUNED_MODEL \
  --task_name $TASK_NAME \
  --do_train \
  --do_eval \
  --do_lower_case \
  --data_dir $GLUE_DIR/$TASK_NAME/ \
  --max_seq_length 128 \
  --per_gpu_train_batch_size 32 \
  --per_gpu_eval_batch_size 32 \
  --learning_rate 6.4e-4 \
  --save_steps 50 \
  --num_prune_epochs 30 \
  --num_train_epochs 60 \
  --sparsity 0.9 \
  --output_dir $OUT_DIR \
  --evaluate_during_training \
  --replacing_rate 0.8 \
  --overwrite_output_dir \
  --steps_for_replacing 0 \
  --scheduler_type linear

To Dos

Provide our teacher model for each task.
Provide best performed model checkpoint for each task.

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

Related tags

Overview

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

Running

BERT_base fine-tuning on GLUE

Sparse Progressive Distillation

To Dos

Owner

multimodal transformer

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM

A system for quickly generating training data with weak supervision

This repository contains the code for the paper ``Identifiable VAEs via Sparse Decoding''.

Video Frame Interpolation with Transformer (CVPR2022)

Surrogate- and Invariance-Boosted Contrastive Learning (SIB-CL)

Tensorflow implementation of Character-Aware Neural Language Models.

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

My solution for the 7th place / 245 in the Umoja Hack 2022 challenge

Source codes of CenterTrack++ in 2021 ICME Workshop on Big Surveillance Data Processing and Analysis

This program will stylize your photos with fast neural style transfer.

Official code for "On the Frequency Bias of Generative Models", NeurIPS 2021

Pure python implementation reverse-mode automatic differentiation

LERP : Label-dependent and event-guided interpretable disease risk prediction using EHRs

The modify PyTorch version of Siam-trackers which are speed-up by TensorRT.

Source code for our CVPR 2019 paper - PPGNet: Learning Point-Pair Graph for Line Segment Detection

InsCLR: Improving Instance Retrieval with Self-Supervision

Sarus implementation of classical ML models. The models are implemented using the Keras API of tensorflow 2. Vizualization are implemented and can be seen in tensorboard.

Vector Quantization, in Pytorch

Code for "FPS-Net: A convolutional fusion network for large-scale LiDAR point cloud segmentation".