ghtaro

Results 7 comments of ghtaro

Hi @ratishsp , Thank you very much for sharing the code and for answering many questions for people trying to replicate your result which is very helpful to me as...

Hi @ratishsp , Thank you very much for your prompt reply. >I am not sure about the root cause of the issue you are facing. I was able to setup...

@andreaskoepf Thank you very much for your reply. I managed to run RL training with WebGPT, but will definitely try en_100_tree and visit OA discord!

@srowen @matthayes thanks. Let me rerun the training with lower LR (5e-7 would be fine?) and will check the quality of inference on test dataset. I am concerned with the...

Hi, I changed to `huggyllama/llama-7b` and applied the chanige #20. I avoided the above errors and now below* ``` Traceback (most recent call last): File "/Workspace/Repos/[email protected]/qlora/qlora.py", line 853, in train()...

@2018211801 do you have any update on the issue? The same error happens to me.