USVSN SAI PRASHANTH
USVSN SAI PRASHANTH
Update: I am currently working on grabbing data from [p3](https://huggingface.co/datasets/bigscience/P3) and trying to shape it in a format accepted by neox. The plan is to concatenate input and target of...
Is this website down? I cannot seem to manually download this data set. Any directions for the same would be highly appreciated :)
From what I have observed, as long as you keep the number of epochs and sequence length the same, your batch size (or) number of train iters should not matter...
Thank you for the review! I will try to integrate the changes into this PR soon we do have gist models with gist token after [instruction and input](https://huggingface.co/usvsnsp/Meta-Llama-3-8B-gist-finetune-instruction-input) and [only...