Finetuning with Bengali Dataset Fails : Need Urgent Help ?

#121
by uknowWho42 - opened

I am trying to finetune the falcon2 model with this bengali dataset:

dataset = load_dataset("rasheduzzaman/Bangla_question_answer_pair_70K_dataset", split="train")

and got stuck while using the SFTT Trainer. Is there an easy way to use other than
ùsing the formatting_prompts_func(examples)

image.png

Sign up or log in to comment