training loss in stage-1

dvlab-research / LLaMA-VID

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

Apache License 2.0

622 stars 39 forks source link

Open Nastu-Ho opened 2 months ago

Nastu-Ho commented 2 months ago

In the first stage of training, the final loss was around 2. Is this normal?