conda install pytorch torchvision torchaudio pytorch-cuda=11.6 -c pytorch -c nvidia
git clone https://github.com/yujiepan-work/optimum-intel.git
git checkout -b "magnitude-pruning" 01927af543eaea8678671bf8f4eb78fdb29f8930
cd optimum-intel
pip install -e .[openvino,nncf]

cd examples/openvino/text-classification/
pip install -r requirements.txt
pip install wandb # optional

NNCFCFG=/path/to/nncf/config
python run_glue.py \
--lr_scheduler_type cosine_with_restarts \
--cosine_cycle_ratios 8,6,4,4,4,4 \
--cosine_cycle_decays 1,1,1,1,1,1 \
--save_best_model_after_epoch -1 \
--save_best_model_after_sparsity 0.7999 \
--model_name_or_path textattack/bert-base-uncased-SST-2 \
--teacher_model_or_path yoshitomo-matsubara/bert-large-uncased-sst2 \
--distillation_temperature 2 \
--task_name sst2 \
--nncf_compression_config $NNCFCFG \
--distillation_weight 0.95 \
--output_dir /tmp/bert-base-uncased-sst2-int8-unstructured80-30epoch \
--run_name bert-base-uncased-sst2-int8-unstructured80-30epoch \
--overwrite_output_dir \
--do_train \
--do_eval \
--max_seq_length 128 \
--per_device_train_batch_size 32 \
--per_device_eval_batch_size 32 \
--learning_rate 5e-05 \
--optim adamw_torch \
--num_train_epochs 30 \
--logging_steps 1 \
--evaluation_strategy steps \
--eval_steps 250 \
--save_strategy steps \
--save_steps 250 \
--save_total_limit 1 \
--fp16 \
--seed 1