@ -288,6 +288,8 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
--per_device_train_batch_size 2 \
--gradient_accumulation_steps 4 \
--lr_scheduler_type cosine \
--top_k 0 \
--top_p 0.9 \
--logging_steps 10 \
--save_steps 1000 \
--learning_rate 1e-5 \