unslothai/unsloth

Evaluation loss becomes constant

Open

#1.067 geöffnet am 27. Sept. 2024

Auf GitHub ansehen
 (7 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Python (5.658 Forks)batch import
currently fixinggood first issue

Repository-Metriken

Stars
 (64.271 Stars)
PR-Merge-Metriken
 (Durchschn. Merge 3T 15h) (525 gemergte PRs in 30 T)

Beschreibung

Hi!

I am testing out unsloth to fine tune llama 3.1 8B instruct and following your notebook here.

One exception is that I have added an eval set. What is really strange is that the eval loss locks up to a specific value after around 300 steps. I mean down to the last decimal, not just flattening out. The training loss looks fine and as expected.

I have changed many parameters and tried different things but it always happens. Any idea on what can cause this?

Contributor Guide