Hi there, amazing work!
I would like to reproduce RankLLaMA. But in the README I see it points to --output_dir model_rankmistral \ --model_name_or_path mistralai/Mistral-7B-v0.1 \. So just asking: are the hyperparameters in the README the same for mistralai/Mistral-7B-v0.1 and RankLLaMA?
From the paper:
Both the retriever and reranker are trained with a batch size of 128, with 15 hard negative passages sampled for each query.
But in the README the batch size seems 16x4=64.
Furthermore, from Issues #167, I understand that I have to create the training dataset, which is not Tevatron/msmarco-passage-aug .
So, just confirming: I have to take 15 RepLLaMA hard negatives? Do you have any suggestions about how to replicate the training dataset?
Thank you for all your help!
Best Regards
Hi there, amazing work!
I would like to reproduce RankLLaMA. But in the README I see it points to
--output_dir model_rankmistral \ --model_name_or_path mistralai/Mistral-7B-v0.1 \. So just asking: are the hyperparameters in the README the same formistralai/Mistral-7B-v0.1and RankLLaMA?From the paper:
But in the README the batch size seems
16x4=64.Furthermore, from Issues #167, I understand that I have to create the training dataset, which is not
Tevatron/msmarco-passage-aug.So, just confirming: I have to take 15 RepLLaMA hard negatives? Do you have any suggestions about how to replicate the training dataset?
Thank you for all your help!
Best Regards