If I only have one GPU, how should I set the training parameters?

[lzylzylzy123456]

As mentioned, I only have one RTX 4080, and I want to replicate the paper's results as closely as possible. I'm unsure about the optimal training parameter settings as I've noticed that training takes a considerable amount of time. Do you have any prior knowledge or recommendations? This would greatly help me save time!

[SAistheBESTone]

python tools/train_net.py --num-gpus 1 --dist-url='tcp://127.0.0.1:52125' --resume --config-file ./configs/OWOD/t1/t1_train.yaml SOLVER.IMS_PER_BATCH 1 SOLVER.BASE_LR 0.0025 OUTPUT_DIR "./output/t1"

try it bro