After fine-tuning my base model for a new scenario,new scenario might have overridden the old one scenario?

[jr.2509]

Welcome to the Forum!

I just responded to a very similar question here:

Issues with Overwriting Context in Sequential Model Fine-Tuning

Welcome to the Forum! I am not 100% sure but I believe that this is due to you relying on entirely new data for the fourth snapshot. You might succeed in getting the fourth snapshot to retain both the existing and new system message / context if you include data for each case in your training set. That said, that would only make sense if the core task is (nearly) the same in both cases. What specifically are you fine-tuning for?

Not 100% sure but it is my best guess.