Can you share specifics about the loss for either training phase?

[altair199797]

Dear Authors,

Unfortunately my training is resulting in bad evaluations. Can you roughly share what the supposed loss is for:

• (Phase 1) Encoder-Only Knowledge Distillation
• (Phase 2) Prompt-in-the-Loop Knowledge Distillation

For Phase 1 my loss is: 0.0010 For Phase 2 my loss is: 0.1139

I suppose Phase 2 gives me the problems. Can you confirm?

Thank you in advance!