Hyeongmin Moon
Hyeongmin Moon
I tried this. Is this correct implementation what you intended?
I think this issue already fixed&merged in #1070 . Can I ask why @you-n-g reopened this?
Hi, I made a draft PR here. I agree @OrenRele and @jinluyang's opinions cause the project is using shared object. https://github.com/oobabooga/text-generation-webui/pull/2573
@M1n9X Thank you for your answer. But I still doubt why `6.7_lora.sh` was in the `single_gpu` training script. If we finally figure out its minimum requirement is `single node` not...
@tjruwase I tried with `--offload_reference_model` but got same error.
Same here. I tried with `--num_train_epochs 3`. Result: ``` ***** Running training ***** ***** Evaluating reward, Epoch 0/3 ***** chosen_last_scores (higher is better) : 2.172806739807129, acc (higher is better) :...
Use this Fork.😉 https://github.com/HyeongminMoon/AutoCrawler