karl-tao-zhang

本地电脑起前后端遇到fetch failed问题

8


按照教程,一步一步弄的,到了训练PPO的时候, 卡到 CUDA error: device-side assert triggered

3

Using pad_token, but it is not set yet. Loading base model for ppo training... 加载base 加载lora 加载ppo WARNING:root:A model is loaded from '/root/autodl-tmp/LLM/weights/sft_lora', and no v_head weight is found. This...

DDP ok?

3

CUDA_VISIBLE_DEVICES=0 ok! but CUDA_VISIBLE_DEVICES=0,1 not ok! thanks you , (geneface) root@autodl-container-a45f4692b6-ed3c630d:~/autodl-tmp/GeneFacePlusPlus# CUDA_VISIBLE_DEVICES=0,1 python tasks/run.py --config=egs/datasets/obama/lm3d_radnerf_torso_sr.yaml --exp_name=motion2video_nerf/obama_torso --hparams=head_model_dir=checkpoints/motion2video_nerf/obama_head --reset | set_hparams Unknow hparams: [] | Hparams chains: ['egs/egs_bases/radnerf/base.yaml', 'egs/egs_bases/radnerf/lm3d_radnerf.yaml', 'egs/datasets/obama/lm3d_radnerf_torso.yaml', 'egs/datasets/obama/lm3d_radnerf_torso_sr.yaml']...