search

amazon-science / mm-cot

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
https://arxiv.org/abs/2302.00923
Apache License 2.0
3.77k stars 309 forks source link

killed during inference #41

Closed lonestar234028 closed 1 year ago

lonestar234028 commented 1 year ago

Hi Expert, can you give me some guidance? I have tuned some parameters, but still can not work..

Code:


CUDA_VISIBLE_DEVICES=0 python main.py \
    --model allenai/unifiedqa-t5-base \
    --user_msg rationale --img_type detr \
    --bs 1 --eval_bs 1 --eval_acc 5 --output_len 256 \
    --final_eval --prompt_format QCM-LE \
    --evaluate_dir models/MM-CoT-UnifiedQA-base-Rationale

MY env:

image

ERROR:

image

lonestar234028 commented 1 year ago

Hi expert I have fixed this issue by adding 3 other GPUs.

WeixuanXiong commented 1 year ago

Thanks for sharing. I'm wondering if you just let CUDA_VISIBLE_DEVICES=0 becomes CUDA_VISIBLE_DEVICES=0,1,2,3 to solve this problem?

lonestar234028 commented 1 year ago

@WeixuanXiong Yes, I have added another GPU, which means CUDA_VISIBLE_DEVICES=0,1