The final fine-tuned vision encoder

[mojtaba-komeili]

Your tables here explains very well how to fine-tune the model step by step. You also have some of the checkpoints along the way. But I cannot find the final checkpoint for the Vision model after the 3rd stage of fine-tuning. Wondering if that was missing from the list here?

[Andy1621]

Hi! The checkpoints in the table are finetuned after different stages.