Closed jiashenggu closed 1 week ago
我启动lumina_next_t2i_mini/train_dreambooth_sd3.py,会报这个错 TypeError: JointTransformerBlock.forward() got an unexpected keyword argument 'offload_to_cpu' 我的启动脚本
torchrun --nproc-per-node=1 train_dreambooth_sd3.py \ --master_port 18181 \ --data_path ${train_data_root} \ --results_dir results/${exp_name} \ --micro_batch_size 4 \ --global_batch_size ${batch_size} --lr ${lr} \ --data_parallel sdp \ --max_steps 1000 \ --ckpt_every 1000 --log_every 10 \ --use_t5 \ --checkpointing \ --precision ${precision} --grad_precision fp32 \ --image_size ${image_size} \ --model_path ${model_path} \ --global_seed 3 \ 2>&1 | tee -a results/"$exp_name"/output_dev_"$datetime".log
顺便, https://github.com/Alpha-VLLM/Lumina-T2X/blob/2e7c7319b1b4b3dc7939f78bd0eeffa3c13822d2/lumina_t2i/train.py#L514 这是打错了吗?hsdp
JointTransformerBlock.forward()加一个**kwargs可以解决,虽然不清楚有没有隐患,反正有人这么干了 https://github.com/huggingface/transformers/issues/30523
我启动lumina_next_t2i_mini/train_dreambooth_sd3.py,会报这个错 TypeError: JointTransformerBlock.forward() got an unexpected keyword argument 'offload_to_cpu' 我的启动脚本
顺便, https://github.com/Alpha-VLLM/Lumina-T2X/blob/2e7c7319b1b4b3dc7939f78bd0eeffa3c13822d2/lumina_t2i/train.py#L514 这是打错了吗?hsdp