Open wjcldply opened 5 days ago
Hi, thanks for your question.
Thanks a lot.
I'd also appreciate it if you could clarify what # Reminder to shuffle train data in advance!
mean in run_step1.13B.sh
.
Does it mean I should load Nuo97/Dolphin-Task1
, Nuo97/Dolphin-Task1
, Nuo97/Dolphin-Task1
and merge them into a single training dataset?
Thanks a lot in advance.
Hi. You can just random sample 100-500 samples for evaluation. And we conduct mixed-task instruction tuning, you can fuse three tasks in a single file, resulting in slighly better performances.
Hi, First of all Thank you the inspirational paper. I am currently trying to re-implement the training process, but having some troubles. It would be great if you could give me some guides...
first of all, I think` but nothing seemed to happen.
What am I missing or misunderstanding?
Some advice or guides on how to re-implement training process would be greatly appreciated.
Thank You :)
Nuo97/Dolphin-DPO
dataset isn't actually on huggingface hub. The dataset card is there, but when I try to load it, it says there's no dataset in that directory.Nuo97/Dolphin_Step1
throughStep3
loaded just fine. But this is where my second question comes in, it seems like loaded data all have Train data only and not Validation Data. Yet, when I look at therun_step1.13B.sh
code for training, it seems like i have to pass the train set and validation set directories separately. Does this mean that I should load theNuo97/Dolphin_Step1~3
datasets with huggingface's load_dataset function, manually split them into train and validation sets, and save them? Also, I'd like to know how to runrun_step1.13B.sh
script exactly. I tried running the commandrun_step1.13B.sh meta-llama/Llama-2-13b . . ./Dataset/train/<train_data_filename>
./Dataset/train/