I tried running the training command you provided. On my machine, it only trained on the CPU and not on the GPU.
CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py \ --data_root data/ScienceQA/data \ --caption_file data/instruct_captions.json \ --model declare-lab/flan-alpaca-large \ --user_msg rationale --img_type vit \ --bs 2 --eval_bs 4 --epoch 50 --lr 5e-5 --output_len 512 \ --use_caption --use_generate --prompt_format QCM-E \ --output_dir experiments
I tried running the training command you provided. On my machine, it only trained on the CPU and not on the GPU.
CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py \ --data_root data/ScienceQA/data \ --caption_file data/instruct_captions.json \ --model declare-lab/flan-alpaca-large \ --user_msg rationale --img_type vit \ --bs 2 --eval_bs 4 --epoch 50 --lr 5e-5 --output_len 512 \ --use_caption --use_generate --prompt_format QCM-E \ --output_dir experiments