I am trying to finetune with fixed context_length and pred_length via loading train data with SimpleEvalDatasetBuilder.
However, the eval prediction result is extraordinarily large.
What's right way to finetune with fixed context_length and pred_length?
I am trying to finetune with fixed context_length and pred_length via loading train data with SimpleEvalDatasetBuilder. However, the eval prediction result is extraordinarily large. What's right way to finetune with fixed context_length and pred_length?