Hjh233
Results
3
comments of
Hjh233
You can first merge the weights of the LoRA adapters with the pre-trained model, as outlined in [this discussion](https://discuss.huggingface.co/t/help-with-merging-lora-weights-back-into-base-model/40968). Then, set the model path to point to the merged model.
我没有改超参数，训练一个epoch之后，cvr的auc=1.0，ctr的auc是0.62
looks like the problem has been solved.