Skip to content

Latest commit

 

History

History
23 lines (17 loc) · 1.57 KB

TRAINING.md

File metadata and controls

23 lines (17 loc) · 1.57 KB

Training

We provide training code, commands and requirements to enable running various sprase algorithms on SMC-Bench here. Please check INSTALL.md for installation instructions first.

Commonsense Reasoning

We heavily rely on the awesome repo fairseq from FACEBOOK for Commonsense Reasoning.

CommonsenseQA

The full instructions for CommonsenseQA can be found here.

More specifially, we need to

  1. cd SMC-Bench/Commonsense_Reasoning/
  2. pip install --editable ./
  3. Download CommonsenseQA dataset: bash examples/roberta/commonsense_qa/download_cqa_data.sh
  4. Download roberta.large from here.
  5. Densely or sparsely finetuning with the commands provided here.

WinoGrande

The dense training on WinoGrande dataset can be found here. To enable sparse training, or pruning, just follow the commands of CommonsenseQA.

RACE

The dense training on WinoGrande dataset can be found here. To enable sparse training, or pruning, just follow the commands of CommonsenseQA.