Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +2426 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,2426 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.996074326092646,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1431,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.002093692750588851,
|
| 13 |
+
"grad_norm": 53.581159797745435,
|
| 14 |
+
"learning_rate": 6.9444444444444435e-09,
|
| 15 |
+
"logits/chosen": -0.48425233364105225,
|
| 16 |
+
"logits/rejected": -0.32109448313713074,
|
| 17 |
+
"logps/chosen": -276.5158996582031,
|
| 18 |
+
"logps/rejected": -302.22406005859375,
|
| 19 |
+
"loss": 0.6931,
|
| 20 |
+
"rewards/accuracies": 0.0,
|
| 21 |
+
"rewards/chosen": 0.0,
|
| 22 |
+
"rewards/margins": 0.0,
|
| 23 |
+
"rewards/rejected": 0.0,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02093692750588851,
|
| 28 |
+
"grad_norm": 47.92244929429545,
|
| 29 |
+
"learning_rate": 6.944444444444444e-08,
|
| 30 |
+
"logits/chosen": -0.20008452236652374,
|
| 31 |
+
"logits/rejected": -0.1900922954082489,
|
| 32 |
+
"logps/chosen": -337.452392578125,
|
| 33 |
+
"logps/rejected": -293.0785217285156,
|
| 34 |
+
"loss": 0.7231,
|
| 35 |
+
"rewards/accuracies": 0.3541666567325592,
|
| 36 |
+
"rewards/chosen": -0.022724969312548637,
|
| 37 |
+
"rewards/margins": -0.036751341074705124,
|
| 38 |
+
"rewards/rejected": 0.014026367105543613,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.04187385501177702,
|
| 43 |
+
"grad_norm": 41.37562973132045,
|
| 44 |
+
"learning_rate": 1.3888888888888888e-07,
|
| 45 |
+
"logits/chosen": -0.042457859963178635,
|
| 46 |
+
"logits/rejected": -0.12332990020513535,
|
| 47 |
+
"logps/chosen": -298.8910217285156,
|
| 48 |
+
"logps/rejected": -271.74114990234375,
|
| 49 |
+
"loss": 0.7114,
|
| 50 |
+
"rewards/accuracies": 0.4375,
|
| 51 |
+
"rewards/chosen": 0.016111990436911583,
|
| 52 |
+
"rewards/margins": -0.0034494102001190186,
|
| 53 |
+
"rewards/rejected": 0.0195614043623209,
|
| 54 |
+
"step": 20
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.06281078251766553,
|
| 58 |
+
"grad_norm": 50.166233912169,
|
| 59 |
+
"learning_rate": 2.0833333333333333e-07,
|
| 60 |
+
"logits/chosen": -0.0645759329199791,
|
| 61 |
+
"logits/rejected": -0.09565907716751099,
|
| 62 |
+
"logps/chosen": -323.93743896484375,
|
| 63 |
+
"logps/rejected": -261.7337341308594,
|
| 64 |
+
"loss": 0.7165,
|
| 65 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 66 |
+
"rewards/chosen": -0.056218355894088745,
|
| 67 |
+
"rewards/margins": 0.005095779895782471,
|
| 68 |
+
"rewards/rejected": -0.061314135789871216,
|
| 69 |
+
"step": 30
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.08374771002355404,
|
| 73 |
+
"grad_norm": 45.45611748658909,
|
| 74 |
+
"learning_rate": 2.7777777777777776e-07,
|
| 75 |
+
"logits/chosen": -0.13370418548583984,
|
| 76 |
+
"logits/rejected": -0.16684015095233917,
|
| 77 |
+
"logps/chosen": -272.07928466796875,
|
| 78 |
+
"logps/rejected": -251.01589965820312,
|
| 79 |
+
"loss": 0.7166,
|
| 80 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 81 |
+
"rewards/chosen": 0.006498994771391153,
|
| 82 |
+
"rewards/margins": 0.06555742770433426,
|
| 83 |
+
"rewards/rejected": -0.05905843526124954,
|
| 84 |
+
"step": 40
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.10468463752944256,
|
| 88 |
+
"grad_norm": 55.30410487113166,
|
| 89 |
+
"learning_rate": 3.472222222222222e-07,
|
| 90 |
+
"logits/chosen": -0.0792478546500206,
|
| 91 |
+
"logits/rejected": -0.0551227442920208,
|
| 92 |
+
"logps/chosen": -292.2696838378906,
|
| 93 |
+
"logps/rejected": -266.82965087890625,
|
| 94 |
+
"loss": 0.7243,
|
| 95 |
+
"rewards/accuracies": 0.5,
|
| 96 |
+
"rewards/chosen": -0.08804600685834885,
|
| 97 |
+
"rewards/margins": -0.04349173232913017,
|
| 98 |
+
"rewards/rejected": -0.044554274529218674,
|
| 99 |
+
"step": 50
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.12562156503533106,
|
| 103 |
+
"grad_norm": 56.63523816899612,
|
| 104 |
+
"learning_rate": 4.1666666666666667e-07,
|
| 105 |
+
"logits/chosen": -0.1644289791584015,
|
| 106 |
+
"logits/rejected": -0.19546563923358917,
|
| 107 |
+
"logps/chosen": -269.5990295410156,
|
| 108 |
+
"logps/rejected": -258.08721923828125,
|
| 109 |
+
"loss": 0.7419,
|
| 110 |
+
"rewards/accuracies": 0.518750011920929,
|
| 111 |
+
"rewards/chosen": 0.04003779590129852,
|
| 112 |
+
"rewards/margins": 0.05106702446937561,
|
| 113 |
+
"rewards/rejected": -0.011029230430722237,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.14655849254121958,
|
| 118 |
+
"grad_norm": 50.48428456914726,
|
| 119 |
+
"learning_rate": 4.861111111111111e-07,
|
| 120 |
+
"logits/chosen": -0.1528700441122055,
|
| 121 |
+
"logits/rejected": -0.12956030666828156,
|
| 122 |
+
"logps/chosen": -334.1960144042969,
|
| 123 |
+
"logps/rejected": -295.05865478515625,
|
| 124 |
+
"loss": 0.7096,
|
| 125 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 126 |
+
"rewards/chosen": -0.012429716996848583,
|
| 127 |
+
"rewards/margins": 0.03767075017094612,
|
| 128 |
+
"rewards/rejected": -0.05010046809911728,
|
| 129 |
+
"step": 70
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.16749542004710807,
|
| 133 |
+
"grad_norm": 49.10207941889299,
|
| 134 |
+
"learning_rate": 5.555555555555555e-07,
|
| 135 |
+
"logits/chosen": 0.019698064774274826,
|
| 136 |
+
"logits/rejected": -0.05375131219625473,
|
| 137 |
+
"logps/chosen": -324.42889404296875,
|
| 138 |
+
"logps/rejected": -256.3900451660156,
|
| 139 |
+
"loss": 0.7125,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.0010342865716665983,
|
| 142 |
+
"rewards/margins": 0.04288307949900627,
|
| 143 |
+
"rewards/rejected": -0.0418488010764122,
|
| 144 |
+
"step": 80
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1884323475529966,
|
| 148 |
+
"grad_norm": 48.35701594054669,
|
| 149 |
+
"learning_rate": 6.249999999999999e-07,
|
| 150 |
+
"logits/chosen": -0.18192127346992493,
|
| 151 |
+
"logits/rejected": -0.15880808234214783,
|
| 152 |
+
"logps/chosen": -282.22161865234375,
|
| 153 |
+
"logps/rejected": -251.54296875,
|
| 154 |
+
"loss": 0.6976,
|
| 155 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 156 |
+
"rewards/chosen": -0.012317812070250511,
|
| 157 |
+
"rewards/margins": -0.011760599911212921,
|
| 158 |
+
"rewards/rejected": -0.0005572110530920327,
|
| 159 |
+
"step": 90
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.2093692750588851,
|
| 163 |
+
"grad_norm": 44.92592146146067,
|
| 164 |
+
"learning_rate": 6.944444444444444e-07,
|
| 165 |
+
"logits/chosen": -0.11696960031986237,
|
| 166 |
+
"logits/rejected": -0.13915769755840302,
|
| 167 |
+
"logps/chosen": -316.96527099609375,
|
| 168 |
+
"logps/rejected": -277.3512268066406,
|
| 169 |
+
"loss": 0.6787,
|
| 170 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 171 |
+
"rewards/chosen": 0.03938128799200058,
|
| 172 |
+
"rewards/margins": 0.08465500175952911,
|
| 173 |
+
"rewards/rejected": -0.045273713767528534,
|
| 174 |
+
"step": 100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.2093692750588851,
|
| 178 |
+
"eval_logits/chosen": -0.3141140341758728,
|
| 179 |
+
"eval_logits/rejected": -0.3377441465854645,
|
| 180 |
+
"eval_logps/chosen": -310.252685546875,
|
| 181 |
+
"eval_logps/rejected": -274.4240417480469,
|
| 182 |
+
"eval_loss": 0.6966869235038757,
|
| 183 |
+
"eval_rewards/accuracies": 0.5515872836112976,
|
| 184 |
+
"eval_rewards/chosen": 0.01587979681789875,
|
| 185 |
+
"eval_rewards/margins": 0.08612197637557983,
|
| 186 |
+
"eval_rewards/rejected": -0.07024218887090683,
|
| 187 |
+
"eval_runtime": 19.212,
|
| 188 |
+
"eval_samples_per_second": 104.102,
|
| 189 |
+
"eval_steps_per_second": 3.279,
|
| 190 |
+
"step": 100
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.23030620256477363,
|
| 194 |
+
"grad_norm": 42.34774239140926,
|
| 195 |
+
"learning_rate": 7.638888888888888e-07,
|
| 196 |
+
"logits/chosen": -0.15527260303497314,
|
| 197 |
+
"logits/rejected": -0.1998877376317978,
|
| 198 |
+
"logps/chosen": -317.2166748046875,
|
| 199 |
+
"logps/rejected": -267.8033447265625,
|
| 200 |
+
"loss": 0.6869,
|
| 201 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 202 |
+
"rewards/chosen": -0.0031774670351296663,
|
| 203 |
+
"rewards/margins": 0.06427686661481857,
|
| 204 |
+
"rewards/rejected": -0.06745433807373047,
|
| 205 |
+
"step": 110
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2512431300706621,
|
| 209 |
+
"grad_norm": 42.69543501672853,
|
| 210 |
+
"learning_rate": 8.333333333333333e-07,
|
| 211 |
+
"logits/chosen": -0.08257915079593658,
|
| 212 |
+
"logits/rejected": -0.12443940341472626,
|
| 213 |
+
"logps/chosen": -275.12579345703125,
|
| 214 |
+
"logps/rejected": -245.96347045898438,
|
| 215 |
+
"loss": 0.6706,
|
| 216 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 217 |
+
"rewards/chosen": 0.050213612616062164,
|
| 218 |
+
"rewards/margins": 0.10280221700668335,
|
| 219 |
+
"rewards/rejected": -0.052588604390621185,
|
| 220 |
+
"step": 120
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2721800575765506,
|
| 224 |
+
"grad_norm": 50.775507526530916,
|
| 225 |
+
"learning_rate": 9.027777777777778e-07,
|
| 226 |
+
"logits/chosen": -0.14645054936408997,
|
| 227 |
+
"logits/rejected": -0.2005746066570282,
|
| 228 |
+
"logps/chosen": -313.00238037109375,
|
| 229 |
+
"logps/rejected": -257.37945556640625,
|
| 230 |
+
"loss": 0.6662,
|
| 231 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 232 |
+
"rewards/chosen": 0.12051638215780258,
|
| 233 |
+
"rewards/margins": 0.18545812368392944,
|
| 234 |
+
"rewards/rejected": -0.06494174152612686,
|
| 235 |
+
"step": 130
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.29311698508243916,
|
| 239 |
+
"grad_norm": 45.04510687958917,
|
| 240 |
+
"learning_rate": 9.722222222222222e-07,
|
| 241 |
+
"logits/chosen": -0.18603107333183289,
|
| 242 |
+
"logits/rejected": -0.14804694056510925,
|
| 243 |
+
"logps/chosen": -336.45330810546875,
|
| 244 |
+
"logps/rejected": -270.71844482421875,
|
| 245 |
+
"loss": 0.6837,
|
| 246 |
+
"rewards/accuracies": 0.574999988079071,
|
| 247 |
+
"rewards/chosen": 0.1061311587691307,
|
| 248 |
+
"rewards/margins": 0.20069436728954315,
|
| 249 |
+
"rewards/rejected": -0.09456320852041245,
|
| 250 |
+
"step": 140
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.31405391258832765,
|
| 254 |
+
"grad_norm": 47.07473020466515,
|
| 255 |
+
"learning_rate": 9.999463737538052e-07,
|
| 256 |
+
"logits/chosen": -0.09479381889104843,
|
| 257 |
+
"logits/rejected": -0.18823939561843872,
|
| 258 |
+
"logps/chosen": -300.7477111816406,
|
| 259 |
+
"logps/rejected": -261.5872497558594,
|
| 260 |
+
"loss": 0.6701,
|
| 261 |
+
"rewards/accuracies": 0.543749988079071,
|
| 262 |
+
"rewards/chosen": 0.014584893360733986,
|
| 263 |
+
"rewards/margins": 0.1319422572851181,
|
| 264 |
+
"rewards/rejected": -0.11735737323760986,
|
| 265 |
+
"step": 150
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.33499084009421615,
|
| 269 |
+
"grad_norm": 40.24946321953983,
|
| 270 |
+
"learning_rate": 9.996186994612174e-07,
|
| 271 |
+
"logits/chosen": -0.07166972011327744,
|
| 272 |
+
"logits/rejected": -0.05619664117693901,
|
| 273 |
+
"logps/chosen": -277.3063049316406,
|
| 274 |
+
"logps/rejected": -264.21929931640625,
|
| 275 |
+
"loss": 0.6571,
|
| 276 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 277 |
+
"rewards/chosen": -0.002465812023729086,
|
| 278 |
+
"rewards/margins": 0.21548476815223694,
|
| 279 |
+
"rewards/rejected": -0.21795055270195007,
|
| 280 |
+
"step": 160
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.3559277676001047,
|
| 284 |
+
"grad_norm": 43.25422484420196,
|
| 285 |
+
"learning_rate": 9.989933382359422e-07,
|
| 286 |
+
"logits/chosen": -0.22567839920520782,
|
| 287 |
+
"logits/rejected": -0.2581842541694641,
|
| 288 |
+
"logps/chosen": -270.6056213378906,
|
| 289 |
+
"logps/rejected": -234.0198211669922,
|
| 290 |
+
"loss": 0.6614,
|
| 291 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 292 |
+
"rewards/chosen": -0.0034525603987276554,
|
| 293 |
+
"rewards/margins": 0.24006681144237518,
|
| 294 |
+
"rewards/rejected": -0.2435193508863449,
|
| 295 |
+
"step": 170
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.3768646951059932,
|
| 299 |
+
"grad_norm": 39.47362541006732,
|
| 300 |
+
"learning_rate": 9.980706626858607e-07,
|
| 301 |
+
"logits/chosen": -0.15520626306533813,
|
| 302 |
+
"logits/rejected": -0.13547591865062714,
|
| 303 |
+
"logps/chosen": -275.5711364746094,
|
| 304 |
+
"logps/rejected": -280.95904541015625,
|
| 305 |
+
"loss": 0.6323,
|
| 306 |
+
"rewards/accuracies": 0.699999988079071,
|
| 307 |
+
"rewards/chosen": 0.01858050376176834,
|
| 308 |
+
"rewards/margins": 0.3474423885345459,
|
| 309 |
+
"rewards/rejected": -0.32886189222335815,
|
| 310 |
+
"step": 180
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.39780162261188173,
|
| 314 |
+
"grad_norm": 45.3164057858113,
|
| 315 |
+
"learning_rate": 9.968512225671258e-07,
|
| 316 |
+
"logits/chosen": -0.07492430508136749,
|
| 317 |
+
"logits/rejected": -0.07894851267337799,
|
| 318 |
+
"logps/chosen": -287.3063659667969,
|
| 319 |
+
"logps/rejected": -286.6043395996094,
|
| 320 |
+
"loss": 0.649,
|
| 321 |
+
"rewards/accuracies": 0.612500011920929,
|
| 322 |
+
"rewards/chosen": -0.07111965119838715,
|
| 323 |
+
"rewards/margins": 0.22652164101600647,
|
| 324 |
+
"rewards/rejected": -0.2976413071155548,
|
| 325 |
+
"step": 190
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4187385501177702,
|
| 329 |
+
"grad_norm": 51.9773301288437,
|
| 330 |
+
"learning_rate": 9.953357444566038e-07,
|
| 331 |
+
"logits/chosen": -0.09818016737699509,
|
| 332 |
+
"logits/rejected": -0.11751595884561539,
|
| 333 |
+
"logps/chosen": -284.3682861328125,
|
| 334 |
+
"logps/rejected": -264.2423095703125,
|
| 335 |
+
"loss": 0.645,
|
| 336 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 337 |
+
"rewards/chosen": -0.06741360574960709,
|
| 338 |
+
"rewards/margins": 0.13478204607963562,
|
| 339 |
+
"rewards/rejected": -0.2021956443786621,
|
| 340 |
+
"step": 200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.4187385501177702,
|
| 344 |
+
"eval_logits/chosen": -0.3229367136955261,
|
| 345 |
+
"eval_logits/rejected": -0.34633249044418335,
|
| 346 |
+
"eval_logps/chosen": -310.3840026855469,
|
| 347 |
+
"eval_logps/rejected": -274.8875732421875,
|
| 348 |
+
"eval_loss": 0.6491106748580933,
|
| 349 |
+
"eval_rewards/accuracies": 0.60317462682724,
|
| 350 |
+
"eval_rewards/chosen": -0.04975215345621109,
|
| 351 |
+
"eval_rewards/margins": 0.25227656960487366,
|
| 352 |
+
"eval_rewards/rejected": -0.30202868580818176,
|
| 353 |
+
"eval_runtime": 19.4848,
|
| 354 |
+
"eval_samples_per_second": 102.644,
|
| 355 |
+
"eval_steps_per_second": 3.233,
|
| 356 |
+
"step": 200
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.4396754776236587,
|
| 360 |
+
"grad_norm": 42.51852593559685,
|
| 361 |
+
"learning_rate": 9.935251313189563e-07,
|
| 362 |
+
"logits/chosen": 0.02242279052734375,
|
| 363 |
+
"logits/rejected": -0.06930123269557953,
|
| 364 |
+
"logps/chosen": -321.75689697265625,
|
| 365 |
+
"logps/rejected": -269.69781494140625,
|
| 366 |
+
"loss": 0.6528,
|
| 367 |
+
"rewards/accuracies": 0.612500011920929,
|
| 368 |
+
"rewards/chosen": -0.06879940629005432,
|
| 369 |
+
"rewards/margins": 0.2159956693649292,
|
| 370 |
+
"rewards/rejected": -0.2847950756549835,
|
| 371 |
+
"step": 210
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.46061240512954726,
|
| 375 |
+
"grad_norm": 39.56904653144407,
|
| 376 |
+
"learning_rate": 9.914204619686312e-07,
|
| 377 |
+
"logits/chosen": -0.21375274658203125,
|
| 378 |
+
"logits/rejected": -0.06523901224136353,
|
| 379 |
+
"logps/chosen": -263.26251220703125,
|
| 380 |
+
"logps/rejected": -254.17361450195312,
|
| 381 |
+
"loss": 0.6473,
|
| 382 |
+
"rewards/accuracies": 0.574999988079071,
|
| 383 |
+
"rewards/chosen": -0.09464406222105026,
|
| 384 |
+
"rewards/margins": 0.11034605652093887,
|
| 385 |
+
"rewards/rejected": -0.20499010384082794,
|
| 386 |
+
"step": 220
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.48154933263543576,
|
| 390 |
+
"grad_norm": 49.49502162405857,
|
| 391 |
+
"learning_rate": 9.89022990427073e-07,
|
| 392 |
+
"logits/chosen": -0.1386515200138092,
|
| 393 |
+
"logits/rejected": -0.027841920033097267,
|
| 394 |
+
"logps/chosen": -275.6785583496094,
|
| 395 |
+
"logps/rejected": -282.2340393066406,
|
| 396 |
+
"loss": 0.651,
|
| 397 |
+
"rewards/accuracies": 0.6875,
|
| 398 |
+
"rewards/chosen": -0.0026134043000638485,
|
| 399 |
+
"rewards/margins": 0.34593018889427185,
|
| 400 |
+
"rewards/rejected": -0.34854358434677124,
|
| 401 |
+
"step": 230
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5024862601413242,
|
| 405 |
+
"grad_norm": 42.40141104653558,
|
| 406 |
+
"learning_rate": 9.86334145175542e-07,
|
| 407 |
+
"logits/chosen": -0.16665732860565186,
|
| 408 |
+
"logits/rejected": -0.13909348845481873,
|
| 409 |
+
"logps/chosen": -282.2431640625,
|
| 410 |
+
"logps/rejected": -265.6712341308594,
|
| 411 |
+
"loss": 0.6269,
|
| 412 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 413 |
+
"rewards/chosen": -0.03417225927114487,
|
| 414 |
+
"rewards/margins": 0.2094908207654953,
|
| 415 |
+
"rewards/rejected": -0.24366307258605957,
|
| 416 |
+
"step": 240
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5234231876472127,
|
| 420 |
+
"grad_norm": 44.711963555505086,
|
| 421 |
+
"learning_rate": 9.83355528303984e-07,
|
| 422 |
+
"logits/chosen": -0.21623122692108154,
|
| 423 |
+
"logits/rejected": -0.25620579719543457,
|
| 424 |
+
"logps/chosen": -321.9479064941406,
|
| 425 |
+
"logps/rejected": -276.6851501464844,
|
| 426 |
+
"loss": 0.6483,
|
| 427 |
+
"rewards/accuracies": 0.59375,
|
| 428 |
+
"rewards/chosen": -0.033338677138090134,
|
| 429 |
+
"rewards/margins": 0.21741199493408203,
|
| 430 |
+
"rewards/rejected": -0.25075066089630127,
|
| 431 |
+
"step": 250
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.5443601151531012,
|
| 435 |
+
"grad_norm": 44.08715279117413,
|
| 436 |
+
"learning_rate": 9.800889145564616e-07,
|
| 437 |
+
"logits/chosen": -0.023601394146680832,
|
| 438 |
+
"logits/rejected": -0.08905109018087387,
|
| 439 |
+
"logps/chosen": -307.87286376953125,
|
| 440 |
+
"logps/rejected": -257.384765625,
|
| 441 |
+
"loss": 0.6489,
|
| 442 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 443 |
+
"rewards/chosen": -0.03719106689095497,
|
| 444 |
+
"rewards/margins": 0.2362823486328125,
|
| 445 |
+
"rewards/rejected": -0.2734734117984772,
|
| 446 |
+
"step": 260
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5652970426589898,
|
| 450 |
+
"grad_norm": 39.7549215734126,
|
| 451 |
+
"learning_rate": 9.765362502737097e-07,
|
| 452 |
+
"logits/chosen": -0.15661786496639252,
|
| 453 |
+
"logits/rejected": -0.1753096580505371,
|
| 454 |
+
"logps/chosen": -313.56787109375,
|
| 455 |
+
"logps/rejected": -277.8585510253906,
|
| 456 |
+
"loss": 0.6233,
|
| 457 |
+
"rewards/accuracies": 0.637499988079071,
|
| 458 |
+
"rewards/chosen": 0.07719334214925766,
|
| 459 |
+
"rewards/margins": 0.3890419602394104,
|
| 460 |
+
"rewards/rejected": -0.31184864044189453,
|
| 461 |
+
"step": 270
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.5862339701648783,
|
| 465 |
+
"grad_norm": 46.953763281596736,
|
| 466 |
+
"learning_rate": 9.726996522334514e-07,
|
| 467 |
+
"logits/chosen": -0.22773197293281555,
|
| 468 |
+
"logits/rejected": -0.25082847476005554,
|
| 469 |
+
"logps/chosen": -299.99127197265625,
|
| 470 |
+
"logps/rejected": -249.6244659423828,
|
| 471 |
+
"loss": 0.6409,
|
| 472 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 473 |
+
"rewards/chosen": -0.044135063886642456,
|
| 474 |
+
"rewards/margins": 0.2800499200820923,
|
| 475 |
+
"rewards/rejected": -0.32418501377105713,
|
| 476 |
+
"step": 280
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.6071708976707668,
|
| 480 |
+
"grad_norm": 38.382090654521065,
|
| 481 |
+
"learning_rate": 9.68581406389163e-07,
|
| 482 |
+
"logits/chosen": -0.14438043534755707,
|
| 483 |
+
"logits/rejected": -0.17269106209278107,
|
| 484 |
+
"logps/chosen": -282.90325927734375,
|
| 485 |
+
"logps/rejected": -274.38079833984375,
|
| 486 |
+
"loss": 0.6217,
|
| 487 |
+
"rewards/accuracies": 0.643750011920929,
|
| 488 |
+
"rewards/chosen": -0.009734408929944038,
|
| 489 |
+
"rewards/margins": 0.3537730574607849,
|
| 490 |
+
"rewards/rejected": -0.363507479429245,
|
| 491 |
+
"step": 290
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.6281078251766553,
|
| 495 |
+
"grad_norm": 41.7647459812509,
|
| 496 |
+
"learning_rate": 9.641839665080363e-07,
|
| 497 |
+
"logits/chosen": -0.1018938273191452,
|
| 498 |
+
"logits/rejected": -0.08353041112422943,
|
| 499 |
+
"logps/chosen": -316.49810791015625,
|
| 500 |
+
"logps/rejected": -277.4931640625,
|
| 501 |
+
"loss": 0.6161,
|
| 502 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 503 |
+
"rewards/chosen": 0.03871753811836243,
|
| 504 |
+
"rewards/margins": 0.39340126514434814,
|
| 505 |
+
"rewards/rejected": -0.3546837270259857,
|
| 506 |
+
"step": 300
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6281078251766553,
|
| 510 |
+
"eval_logits/chosen": -0.33166003227233887,
|
| 511 |
+
"eval_logits/rejected": -0.3552355170249939,
|
| 512 |
+
"eval_logps/chosen": -310.4118957519531,
|
| 513 |
+
"eval_logps/rejected": -275.1272277832031,
|
| 514 |
+
"eval_loss": 0.6316225528717041,
|
| 515 |
+
"eval_rewards/accuracies": 0.682539701461792,
|
| 516 |
+
"eval_rewards/chosen": -0.06370855122804642,
|
| 517 |
+
"eval_rewards/margins": 0.3581322431564331,
|
| 518 |
+
"eval_rewards/rejected": -0.4218408465385437,
|
| 519 |
+
"eval_runtime": 19.0833,
|
| 520 |
+
"eval_samples_per_second": 104.804,
|
| 521 |
+
"eval_steps_per_second": 3.301,
|
| 522 |
+
"step": 300
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.6490447526825438,
|
| 526 |
+
"grad_norm": 40.9716290999305,
|
| 527 |
+
"learning_rate": 9.595099527089568e-07,
|
| 528 |
+
"logits/chosen": -0.11042879521846771,
|
| 529 |
+
"logits/rejected": -0.18008281290531158,
|
| 530 |
+
"logps/chosen": -323.7516174316406,
|
| 531 |
+
"logps/rejected": -247.0631561279297,
|
| 532 |
+
"loss": 0.6007,
|
| 533 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 534 |
+
"rewards/chosen": 0.10534234344959259,
|
| 535 |
+
"rewards/margins": 0.5895902514457703,
|
| 536 |
+
"rewards/rejected": -0.48424798250198364,
|
| 537 |
+
"step": 310
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6699816801884323,
|
| 541 |
+
"grad_norm": 45.14020951986602,
|
| 542 |
+
"learning_rate": 9.545621499013618e-07,
|
| 543 |
+
"logits/chosen": -0.024479269981384277,
|
| 544 |
+
"logits/rejected": -0.038955364376306534,
|
| 545 |
+
"logps/chosen": -294.4266662597656,
|
| 546 |
+
"logps/rejected": -252.0673828125,
|
| 547 |
+
"loss": 0.5995,
|
| 548 |
+
"rewards/accuracies": 0.668749988079071,
|
| 549 |
+
"rewards/chosen": 0.06134527176618576,
|
| 550 |
+
"rewards/margins": 0.4816582202911377,
|
| 551 |
+
"rewards/rejected": -0.4203129708766937,
|
| 552 |
+
"step": 320
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.6909186076943209,
|
| 556 |
+
"grad_norm": 38.030813091938484,
|
| 557 |
+
"learning_rate": 9.493435061259129e-07,
|
| 558 |
+
"logits/chosen": -0.012772688642144203,
|
| 559 |
+
"logits/rejected": -0.030413877218961716,
|
| 560 |
+
"logps/chosen": -291.36761474609375,
|
| 561 |
+
"logps/rejected": -265.4248046875,
|
| 562 |
+
"loss": 0.6232,
|
| 563 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 564 |
+
"rewards/chosen": 0.001638062298297882,
|
| 565 |
+
"rewards/margins": 0.40076717734336853,
|
| 566 |
+
"rewards/rejected": -0.39912909269332886,
|
| 567 |
+
"step": 330
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.7118555352002094,
|
| 571 |
+
"grad_norm": 45.93570520280886,
|
| 572 |
+
"learning_rate": 9.438571307979704e-07,
|
| 573 |
+
"logits/chosen": -0.04617694020271301,
|
| 574 |
+
"logits/rejected": -0.07658630609512329,
|
| 575 |
+
"logps/chosen": -296.7699890136719,
|
| 576 |
+
"logps/rejected": -270.9905090332031,
|
| 577 |
+
"loss": 0.6096,
|
| 578 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 579 |
+
"rewards/chosen": -0.05764853209257126,
|
| 580 |
+
"rewards/margins": 0.28755250573158264,
|
| 581 |
+
"rewards/rejected": -0.34520095586776733,
|
| 582 |
+
"step": 340
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.7327924627060979,
|
| 586 |
+
"grad_norm": 44.09128545700975,
|
| 587 |
+
"learning_rate": 9.381062928549151e-07,
|
| 588 |
+
"logits/chosen": -0.12188152968883514,
|
| 589 |
+
"logits/rejected": -0.13376249372959137,
|
| 590 |
+
"logps/chosen": -282.15179443359375,
|
| 591 |
+
"logps/rejected": -247.45834350585938,
|
| 592 |
+
"loss": 0.5964,
|
| 593 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 594 |
+
"rewards/chosen": -0.09005177021026611,
|
| 595 |
+
"rewards/margins": 0.41418519616127014,
|
| 596 |
+
"rewards/rejected": -0.5042369961738586,
|
| 597 |
+
"step": 350
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.7537293902119864,
|
| 601 |
+
"grad_norm": 40.36784058818516,
|
| 602 |
+
"learning_rate": 9.320944188084241e-07,
|
| 603 |
+
"logits/chosen": -0.07130910456180573,
|
| 604 |
+
"logits/rejected": -0.18685731291770935,
|
| 605 |
+
"logps/chosen": -340.55487060546875,
|
| 606 |
+
"logps/rejected": -278.08551025390625,
|
| 607 |
+
"loss": 0.6256,
|
| 608 |
+
"rewards/accuracies": 0.65625,
|
| 609 |
+
"rewards/chosen": 0.1223798543214798,
|
| 610 |
+
"rewards/margins": 0.4791669249534607,
|
| 611 |
+
"rewards/rejected": -0.3567870557308197,
|
| 612 |
+
"step": 360
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7746663177178749,
|
| 616 |
+
"grad_norm": 37.74697617657793,
|
| 617 |
+
"learning_rate": 9.258250907028572e-07,
|
| 618 |
+
"logits/chosen": -0.2023000717163086,
|
| 619 |
+
"logits/rejected": -0.25707709789276123,
|
| 620 |
+
"logps/chosen": -306.526611328125,
|
| 621 |
+
"logps/rejected": -248.40023803710938,
|
| 622 |
+
"loss": 0.603,
|
| 623 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 624 |
+
"rewards/chosen": 0.05354640632867813,
|
| 625 |
+
"rewards/margins": 0.42885661125183105,
|
| 626 |
+
"rewards/rejected": -0.3753102421760559,
|
| 627 |
+
"step": 370
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.7956032452237635,
|
| 631 |
+
"grad_norm": 36.818935480552355,
|
| 632 |
+
"learning_rate": 9.193020439809746e-07,
|
| 633 |
+
"logits/chosen": -0.25006169080734253,
|
| 634 |
+
"logits/rejected": -0.27239733934402466,
|
| 635 |
+
"logps/chosen": -306.9652099609375,
|
| 636 |
+
"logps/rejected": -274.15850830078125,
|
| 637 |
+
"loss": 0.6108,
|
| 638 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 639 |
+
"rewards/chosen": -0.005802587606012821,
|
| 640 |
+
"rewards/margins": 0.5873938798904419,
|
| 641 |
+
"rewards/rejected": -0.5931965112686157,
|
| 642 |
+
"step": 380
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.816540172729652,
|
| 646 |
+
"grad_norm": 40.218709775991016,
|
| 647 |
+
"learning_rate": 9.125291652582547e-07,
|
| 648 |
+
"logits/chosen": -0.19798080623149872,
|
| 649 |
+
"logits/rejected": -0.16009968519210815,
|
| 650 |
+
"logps/chosen": -308.05975341796875,
|
| 651 |
+
"logps/rejected": -289.6929626464844,
|
| 652 |
+
"loss": 0.6163,
|
| 653 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 654 |
+
"rewards/chosen": 0.09920313209295273,
|
| 655 |
+
"rewards/margins": 0.47261109948158264,
|
| 656 |
+
"rewards/rejected": -0.3734079897403717,
|
| 657 |
+
"step": 390
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.8374771002355405,
|
| 661 |
+
"grad_norm": 39.13573330990029,
|
| 662 |
+
"learning_rate": 9.055104900071375e-07,
|
| 663 |
+
"logits/chosen": -0.3008892834186554,
|
| 664 |
+
"logits/rejected": -0.1968032568693161,
|
| 665 |
+
"logps/chosen": -253.58798217773438,
|
| 666 |
+
"logps/rejected": -239.539794921875,
|
| 667 |
+
"loss": 0.5964,
|
| 668 |
+
"rewards/accuracies": 0.78125,
|
| 669 |
+
"rewards/chosen": 0.14220505952835083,
|
| 670 |
+
"rewards/margins": 0.6365345120429993,
|
| 671 |
+
"rewards/rejected": -0.49432945251464844,
|
| 672 |
+
"step": 400
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.8374771002355405,
|
| 676 |
+
"eval_logits/chosen": -0.3291381299495697,
|
| 677 |
+
"eval_logits/rejected": -0.35453417897224426,
|
| 678 |
+
"eval_logps/chosen": -310.317626953125,
|
| 679 |
+
"eval_logps/rejected": -275.15972900390625,
|
| 680 |
+
"eval_loss": 0.6100037693977356,
|
| 681 |
+
"eval_rewards/accuracies": 0.658730149269104,
|
| 682 |
+
"eval_rewards/chosen": -0.016582150012254715,
|
| 683 |
+
"eval_rewards/margins": 0.42150571942329407,
|
| 684 |
+
"eval_rewards/rejected": -0.43808794021606445,
|
| 685 |
+
"eval_runtime": 19.1374,
|
| 686 |
+
"eval_samples_per_second": 104.507,
|
| 687 |
+
"eval_steps_per_second": 3.292,
|
| 688 |
+
"step": 400
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.8584140277414289,
|
| 692 |
+
"grad_norm": 41.59836395581152,
|
| 693 |
+
"learning_rate": 8.982502001525777e-07,
|
| 694 |
+
"logits/chosen": -0.05211949348449707,
|
| 695 |
+
"logits/rejected": -0.16379515826702118,
|
| 696 |
+
"logps/chosen": -334.3597717285156,
|
| 697 |
+
"logps/rejected": -280.1282043457031,
|
| 698 |
+
"loss": 0.6085,
|
| 699 |
+
"rewards/accuracies": 0.706250011920929,
|
| 700 |
+
"rewards/chosen": 0.10034932941198349,
|
| 701 |
+
"rewards/margins": 0.5413358211517334,
|
| 702 |
+
"rewards/rejected": -0.4409864842891693,
|
| 703 |
+
"step": 410
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8793509552473174,
|
| 707 |
+
"grad_norm": 43.48433949710367,
|
| 708 |
+
"learning_rate": 8.90752621580335e-07,
|
| 709 |
+
"logits/chosen": -0.10794836282730103,
|
| 710 |
+
"logits/rejected": -0.10175999253988266,
|
| 711 |
+
"logps/chosen": -289.7253723144531,
|
| 712 |
+
"logps/rejected": -290.4524841308594,
|
| 713 |
+
"loss": 0.5967,
|
| 714 |
+
"rewards/accuracies": 0.737500011920929,
|
| 715 |
+
"rewards/chosen": 0.03317990154027939,
|
| 716 |
+
"rewards/margins": 0.5273382663726807,
|
| 717 |
+
"rewards/rejected": -0.4941583275794983,
|
| 718 |
+
"step": 420
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.9002878827532059,
|
| 722 |
+
"grad_norm": 38.200809011500716,
|
| 723 |
+
"learning_rate": 8.83022221559489e-07,
|
| 724 |
+
"logits/chosen": -0.08915697038173676,
|
| 725 |
+
"logits/rejected": -0.18852075934410095,
|
| 726 |
+
"logps/chosen": -325.81707763671875,
|
| 727 |
+
"logps/rejected": -257.1981506347656,
|
| 728 |
+
"loss": 0.5916,
|
| 729 |
+
"rewards/accuracies": 0.637499988079071,
|
| 730 |
+
"rewards/chosen": 0.053056418895721436,
|
| 731 |
+
"rewards/margins": 0.5633317232131958,
|
| 732 |
+
"rewards/rejected": -0.5102753043174744,
|
| 733 |
+
"step": 430
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.9212248102590945,
|
| 737 |
+
"grad_norm": 37.18511688193762,
|
| 738 |
+
"learning_rate": 8.750636060807145e-07,
|
| 739 |
+
"logits/chosen": -0.0535130575299263,
|
| 740 |
+
"logits/rejected": -0.1133667603135109,
|
| 741 |
+
"logps/chosen": -299.4546813964844,
|
| 742 |
+
"logps/rejected": -248.877685546875,
|
| 743 |
+
"loss": 0.6032,
|
| 744 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 745 |
+
"rewards/chosen": 0.14839240908622742,
|
| 746 |
+
"rewards/margins": 0.4819253385066986,
|
| 747 |
+
"rewards/rejected": -0.3335329294204712,
|
| 748 |
+
"step": 440
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.942161737764983,
|
| 752 |
+
"grad_norm": 35.5219084800687,
|
| 753 |
+
"learning_rate": 8.668815171119019e-07,
|
| 754 |
+
"logits/chosen": -0.16904090344905853,
|
| 755 |
+
"logits/rejected": -0.12047908455133438,
|
| 756 |
+
"logps/chosen": -297.3148498535156,
|
| 757 |
+
"logps/rejected": -285.4595031738281,
|
| 758 |
+
"loss": 0.6148,
|
| 759 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 760 |
+
"rewards/chosen": 0.051097553223371506,
|
| 761 |
+
"rewards/margins": 0.505901038646698,
|
| 762 |
+
"rewards/rejected": -0.4548035264015198,
|
| 763 |
+
"step": 450
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.9630986652708715,
|
| 767 |
+
"grad_norm": 40.701223424626065,
|
| 768 |
+
"learning_rate": 8.584808297727591e-07,
|
| 769 |
+
"logits/chosen": -0.07098624855279922,
|
| 770 |
+
"logits/rejected": -0.11652670055627823,
|
| 771 |
+
"logps/chosen": -291.76434326171875,
|
| 772 |
+
"logps/rejected": -246.9138641357422,
|
| 773 |
+
"loss": 0.6087,
|
| 774 |
+
"rewards/accuracies": 0.643750011920929,
|
| 775 |
+
"rewards/chosen": 0.10639622062444687,
|
| 776 |
+
"rewards/margins": 0.5133938193321228,
|
| 777 |
+
"rewards/rejected": -0.40699753165245056,
|
| 778 |
+
"step": 460
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.98403559277676,
|
| 782 |
+
"grad_norm": 41.789096950373676,
|
| 783 |
+
"learning_rate": 8.498665494300771e-07,
|
| 784 |
+
"logits/chosen": -0.19742052257061005,
|
| 785 |
+
"logits/rejected": -0.16556285321712494,
|
| 786 |
+
"logps/chosen": -302.3099060058594,
|
| 787 |
+
"logps/rejected": -277.933837890625,
|
| 788 |
+
"loss": 0.5919,
|
| 789 |
+
"rewards/accuracies": 0.625,
|
| 790 |
+
"rewards/chosen": 0.026506727561354637,
|
| 791 |
+
"rewards/margins": 0.43121033906936646,
|
| 792 |
+
"rewards/rejected": -0.40470361709594727,
|
| 793 |
+
"step": 470
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.0049725202826485,
|
| 797 |
+
"grad_norm": 34.0036850645019,
|
| 798 |
+
"learning_rate": 8.410438087153911e-07,
|
| 799 |
+
"logits/chosen": -0.05161554738879204,
|
| 800 |
+
"logits/rejected": -0.1036214604973793,
|
| 801 |
+
"logps/chosen": -300.4537658691406,
|
| 802 |
+
"logps/rejected": -268.56048583984375,
|
| 803 |
+
"loss": 0.5867,
|
| 804 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 805 |
+
"rewards/chosen": -0.00218582758679986,
|
| 806 |
+
"rewards/margins": 0.4712887704372406,
|
| 807 |
+
"rewards/rejected": -0.4734745919704437,
|
| 808 |
+
"step": 480
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.025909447788537,
|
| 812 |
+
"grad_norm": 36.00706898235858,
|
| 813 |
+
"learning_rate": 8.320178644668141e-07,
|
| 814 |
+
"logits/chosen": -0.11621465533971786,
|
| 815 |
+
"logits/rejected": -0.18176773190498352,
|
| 816 |
+
"logps/chosen": -299.8227233886719,
|
| 817 |
+
"logps/rejected": -256.3122253417969,
|
| 818 |
+
"loss": 0.54,
|
| 819 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 820 |
+
"rewards/chosen": 0.12694445252418518,
|
| 821 |
+
"rewards/margins": 0.600742757320404,
|
| 822 |
+
"rewards/rejected": -0.47379836440086365,
|
| 823 |
+
"step": 490
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.0468463752944255,
|
| 827 |
+
"grad_norm": 36.99527595331141,
|
| 828 |
+
"learning_rate": 8.22794094596864e-07,
|
| 829 |
+
"logits/chosen": -0.1485815942287445,
|
| 830 |
+
"logits/rejected": -0.20506855845451355,
|
| 831 |
+
"logps/chosen": -305.8435363769531,
|
| 832 |
+
"logps/rejected": -270.3700256347656,
|
| 833 |
+
"loss": 0.5394,
|
| 834 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 835 |
+
"rewards/chosen": 0.029846886172890663,
|
| 836 |
+
"rewards/margins": 0.6080519556999207,
|
| 837 |
+
"rewards/rejected": -0.5782050490379333,
|
| 838 |
+
"step": 500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.0468463752944255,
|
| 842 |
+
"eval_logits/chosen": -0.33202826976776123,
|
| 843 |
+
"eval_logits/rejected": -0.35762789845466614,
|
| 844 |
+
"eval_logps/chosen": -310.303955078125,
|
| 845 |
+
"eval_logps/rejected": -275.2332458496094,
|
| 846 |
+
"eval_loss": 0.6065964102745056,
|
| 847 |
+
"eval_rewards/accuracies": 0.7103174328804016,
|
| 848 |
+
"eval_rewards/chosen": -0.009755274280905724,
|
| 849 |
+
"eval_rewards/margins": 0.465115487575531,
|
| 850 |
+
"eval_rewards/rejected": -0.4748707413673401,
|
| 851 |
+
"eval_runtime": 18.9724,
|
| 852 |
+
"eval_samples_per_second": 105.416,
|
| 853 |
+
"eval_steps_per_second": 3.321,
|
| 854 |
+
"step": 500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.067783302800314,
|
| 858 |
+
"grad_norm": 33.8725028749791,
|
| 859 |
+
"learning_rate": 8.133779948881513e-07,
|
| 860 |
+
"logits/chosen": -0.18220725655555725,
|
| 861 |
+
"logits/rejected": -0.1532759964466095,
|
| 862 |
+
"logps/chosen": -269.54156494140625,
|
| 863 |
+
"logps/rejected": -259.2676086425781,
|
| 864 |
+
"loss": 0.533,
|
| 865 |
+
"rewards/accuracies": 0.78125,
|
| 866 |
+
"rewards/chosen": 0.12358293682336807,
|
| 867 |
+
"rewards/margins": 0.7069646120071411,
|
| 868 |
+
"rewards/rejected": -0.5833816528320312,
|
| 869 |
+
"step": 510
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.0887202303062025,
|
| 873 |
+
"grad_norm": 32.98315936865049,
|
| 874 |
+
"learning_rate": 8.037751757188367e-07,
|
| 875 |
+
"logits/chosen": -0.2609891891479492,
|
| 876 |
+
"logits/rejected": -0.1464134156703949,
|
| 877 |
+
"logps/chosen": -262.7670593261719,
|
| 878 |
+
"logps/rejected": -260.43121337890625,
|
| 879 |
+
"loss": 0.5216,
|
| 880 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 881 |
+
"rewards/chosen": 0.10809774696826935,
|
| 882 |
+
"rewards/margins": 0.6094505786895752,
|
| 883 |
+
"rewards/rejected": -0.501352846622467,
|
| 884 |
+
"step": 520
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.109657157812091,
|
| 888 |
+
"grad_norm": 36.61105396566652,
|
| 889 |
+
"learning_rate": 7.939913587198095e-07,
|
| 890 |
+
"logits/chosen": -0.2482234686613083,
|
| 891 |
+
"logits/rejected": -0.3337472081184387,
|
| 892 |
+
"logps/chosen": -288.12847900390625,
|
| 893 |
+
"logps/rejected": -249.4586181640625,
|
| 894 |
+
"loss": 0.5439,
|
| 895 |
+
"rewards/accuracies": 0.71875,
|
| 896 |
+
"rewards/chosen": 0.05145542696118355,
|
| 897 |
+
"rewards/margins": 0.7037261128425598,
|
| 898 |
+
"rewards/rejected": -0.6522706747055054,
|
| 899 |
+
"step": 530
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.1305940853179797,
|
| 903 |
+
"grad_norm": 38.97199731536176,
|
| 904 |
+
"learning_rate": 7.840323733655778e-07,
|
| 905 |
+
"logits/chosen": -0.19931235909461975,
|
| 906 |
+
"logits/rejected": -0.09966816008090973,
|
| 907 |
+
"logps/chosen": -259.0215759277344,
|
| 908 |
+
"logps/rejected": -237.9501495361328,
|
| 909 |
+
"loss": 0.5534,
|
| 910 |
+
"rewards/accuracies": 0.731249988079071,
|
| 911 |
+
"rewards/chosen": 0.12085232883691788,
|
| 912 |
+
"rewards/margins": 0.6305907964706421,
|
| 913 |
+
"rewards/rejected": -0.5097384452819824,
|
| 914 |
+
"step": 540
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.151531012823868,
|
| 918 |
+
"grad_norm": 35.71159175636079,
|
| 919 |
+
"learning_rate": 7.739041535009041e-07,
|
| 920 |
+
"logits/chosen": -0.14787928760051727,
|
| 921 |
+
"logits/rejected": -0.24329273402690887,
|
| 922 |
+
"logps/chosen": -305.64697265625,
|
| 923 |
+
"logps/rejected": -244.08755493164062,
|
| 924 |
+
"loss": 0.5301,
|
| 925 |
+
"rewards/accuracies": 0.706250011920929,
|
| 926 |
+
"rewards/chosen": 0.08590878546237946,
|
| 927 |
+
"rewards/margins": 0.6826232075691223,
|
| 928 |
+
"rewards/rejected": -0.596714437007904,
|
| 929 |
+
"step": 550
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.1724679403297567,
|
| 933 |
+
"grad_norm": 40.90404154922072,
|
| 934 |
+
"learning_rate": 7.636127338052511e-07,
|
| 935 |
+
"logits/chosen": -0.10747908055782318,
|
| 936 |
+
"logits/rejected": -0.11999531090259552,
|
| 937 |
+
"logps/chosen": -294.2823486328125,
|
| 938 |
+
"logps/rejected": -265.80010986328125,
|
| 939 |
+
"loss": 0.5442,
|
| 940 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 941 |
+
"rewards/chosen": 0.1678900569677353,
|
| 942 |
+
"rewards/margins": 0.6707212924957275,
|
| 943 |
+
"rewards/rejected": -0.502831220626831,
|
| 944 |
+
"step": 560
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.193404867835645,
|
| 948 |
+
"grad_norm": 36.957100723172736,
|
| 949 |
+
"learning_rate": 7.531642461971514e-07,
|
| 950 |
+
"logits/chosen": -0.24748548865318298,
|
| 951 |
+
"logits/rejected": -0.13145090639591217,
|
| 952 |
+
"logps/chosen": -270.5980529785156,
|
| 953 |
+
"logps/rejected": -276.2918395996094,
|
| 954 |
+
"loss": 0.5296,
|
| 955 |
+
"rewards/accuracies": 0.71875,
|
| 956 |
+
"rewards/chosen": 0.1355637013912201,
|
| 957 |
+
"rewards/margins": 0.7545391917228699,
|
| 958 |
+
"rewards/rejected": -0.6189755797386169,
|
| 959 |
+
"step": 570
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.2143417953415336,
|
| 963 |
+
"grad_norm": 36.431278984426584,
|
| 964 |
+
"learning_rate": 7.425649161806352e-07,
|
| 965 |
+
"logits/chosen": -0.22467997670173645,
|
| 966 |
+
"logits/rejected": -0.20354416966438293,
|
| 967 |
+
"logps/chosen": -284.69439697265625,
|
| 968 |
+
"logps/rejected": -250.2189483642578,
|
| 969 |
+
"loss": 0.5209,
|
| 970 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 971 |
+
"rewards/chosen": 0.03756130859255791,
|
| 972 |
+
"rewards/margins": 0.7149747610092163,
|
| 973 |
+
"rewards/rejected": -0.6774134635925293,
|
| 974 |
+
"step": 580
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.235278722847422,
|
| 978 |
+
"grad_norm": 34.3971566508403,
|
| 979 |
+
"learning_rate": 7.318210591359008e-07,
|
| 980 |
+
"logits/chosen": -0.02497723139822483,
|
| 981 |
+
"logits/rejected": -0.0003952041151933372,
|
| 982 |
+
"logps/chosen": -316.3713684082031,
|
| 983 |
+
"logps/rejected": -274.1322937011719,
|
| 984 |
+
"loss": 0.5209,
|
| 985 |
+
"rewards/accuracies": 0.768750011920929,
|
| 986 |
+
"rewards/chosen": 0.07891981303691864,
|
| 987 |
+
"rewards/margins": 0.7175663113594055,
|
| 988 |
+
"rewards/rejected": -0.6386464834213257,
|
| 989 |
+
"step": 590
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.2562156503533106,
|
| 993 |
+
"grad_norm": 37.248359587110805,
|
| 994 |
+
"learning_rate": 7.209390765564318e-07,
|
| 995 |
+
"logits/chosen": -0.15565916895866394,
|
| 996 |
+
"logits/rejected": -0.10866830497980118,
|
| 997 |
+
"logps/chosen": -306.9658203125,
|
| 998 |
+
"logps/rejected": -306.49078369140625,
|
| 999 |
+
"loss": 0.5099,
|
| 1000 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1001 |
+
"rewards/chosen": 0.1327342391014099,
|
| 1002 |
+
"rewards/margins": 0.7248380780220032,
|
| 1003 |
+
"rewards/rejected": -0.5921037197113037,
|
| 1004 |
+
"step": 600
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.2562156503533106,
|
| 1008 |
+
"eval_logits/chosen": -0.33804643154144287,
|
| 1009 |
+
"eval_logits/rejected": -0.3634737432003021,
|
| 1010 |
+
"eval_logps/chosen": -310.3228759765625,
|
| 1011 |
+
"eval_logps/rejected": -275.3493347167969,
|
| 1012 |
+
"eval_loss": 0.6006649136543274,
|
| 1013 |
+
"eval_rewards/accuracies": 0.6785714030265808,
|
| 1014 |
+
"eval_rewards/chosen": -0.019210144877433777,
|
| 1015 |
+
"eval_rewards/margins": 0.5136736631393433,
|
| 1016 |
+
"eval_rewards/rejected": -0.5328837633132935,
|
| 1017 |
+
"eval_runtime": 19.1325,
|
| 1018 |
+
"eval_samples_per_second": 104.534,
|
| 1019 |
+
"eval_steps_per_second": 3.293,
|
| 1020 |
+
"step": 600
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.2771525778591992,
|
| 1024 |
+
"grad_norm": 39.48209474577774,
|
| 1025 |
+
"learning_rate": 7.099254522348064e-07,
|
| 1026 |
+
"logits/chosen": -0.09819002449512482,
|
| 1027 |
+
"logits/rejected": -0.1692955642938614,
|
| 1028 |
+
"logps/chosen": -290.13140869140625,
|
| 1029 |
+
"logps/rejected": -237.3570098876953,
|
| 1030 |
+
"loss": 0.5202,
|
| 1031 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1032 |
+
"rewards/chosen": 0.1899166852235794,
|
| 1033 |
+
"rewards/margins": 0.8487440347671509,
|
| 1034 |
+
"rewards/rejected": -0.6588274240493774,
|
| 1035 |
+
"step": 610
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.2980895053650876,
|
| 1039 |
+
"grad_norm": 35.38064058006504,
|
| 1040 |
+
"learning_rate": 6.987867483994716e-07,
|
| 1041 |
+
"logits/chosen": 0.08088377118110657,
|
| 1042 |
+
"logits/rejected": -0.028685202822089195,
|
| 1043 |
+
"logps/chosen": -286.01324462890625,
|
| 1044 |
+
"logps/rejected": -242.1278076171875,
|
| 1045 |
+
"loss": 0.5113,
|
| 1046 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1047 |
+
"rewards/chosen": 0.08664991706609726,
|
| 1048 |
+
"rewards/margins": 0.6891879439353943,
|
| 1049 |
+
"rewards/rejected": -0.6025381088256836,
|
| 1050 |
+
"step": 620
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.3190264328709762,
|
| 1054 |
+
"grad_norm": 36.280579625575726,
|
| 1055 |
+
"learning_rate": 6.875296018047809e-07,
|
| 1056 |
+
"logits/chosen": -0.15825395286083221,
|
| 1057 |
+
"logits/rejected": -0.13115188479423523,
|
| 1058 |
+
"logps/chosen": -291.768798828125,
|
| 1059 |
+
"logps/rejected": -271.0327453613281,
|
| 1060 |
+
"loss": 0.5133,
|
| 1061 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1062 |
+
"rewards/chosen": 0.25919127464294434,
|
| 1063 |
+
"rewards/margins": 0.8277707099914551,
|
| 1064 |
+
"rewards/rejected": -0.5685793161392212,
|
| 1065 |
+
"step": 630
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.3399633603768648,
|
| 1069 |
+
"grad_norm": 32.57724385812019,
|
| 1070 |
+
"learning_rate": 6.761607197766296e-07,
|
| 1071 |
+
"logits/chosen": -0.21067364513874054,
|
| 1072 |
+
"logits/rejected": -0.15081565082073212,
|
| 1073 |
+
"logps/chosen": -272.00518798828125,
|
| 1074 |
+
"logps/rejected": -279.40478515625,
|
| 1075 |
+
"loss": 0.5105,
|
| 1076 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1077 |
+
"rewards/chosen": 0.14864543080329895,
|
| 1078 |
+
"rewards/margins": 0.7687338590621948,
|
| 1079 |
+
"rewards/rejected": -0.6200884580612183,
|
| 1080 |
+
"step": 640
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.3609002878827532,
|
| 1084 |
+
"grad_norm": 37.48616481446126,
|
| 1085 |
+
"learning_rate": 6.646868762160398e-07,
|
| 1086 |
+
"logits/chosen": -0.19943957030773163,
|
| 1087 |
+
"logits/rejected": -0.161566823720932,
|
| 1088 |
+
"logps/chosen": -268.23638916015625,
|
| 1089 |
+
"logps/rejected": -252.7967987060547,
|
| 1090 |
+
"loss": 0.5372,
|
| 1091 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1092 |
+
"rewards/chosen": 0.008694097399711609,
|
| 1093 |
+
"rewards/margins": 0.623866617679596,
|
| 1094 |
+
"rewards/rejected": -0.6151725053787231,
|
| 1095 |
+
"step": 650
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3818372153886418,
|
| 1099 |
+
"grad_norm": 39.563737783736045,
|
| 1100 |
+
"learning_rate": 6.531149075630796e-07,
|
| 1101 |
+
"logits/chosen": -0.11065585911273956,
|
| 1102 |
+
"logits/rejected": -0.17729897797107697,
|
| 1103 |
+
"logps/chosen": -263.4093933105469,
|
| 1104 |
+
"logps/rejected": -251.0884246826172,
|
| 1105 |
+
"loss": 0.5323,
|
| 1106 |
+
"rewards/accuracies": 0.6875,
|
| 1107 |
+
"rewards/chosen": -0.026829296723008156,
|
| 1108 |
+
"rewards/margins": 0.4506412148475647,
|
| 1109 |
+
"rewards/rejected": -0.4774704873561859,
|
| 1110 |
+
"step": 660
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.4027741428945302,
|
| 1114 |
+
"grad_norm": 33.46296192971815,
|
| 1115 |
+
"learning_rate": 6.414517087235185e-07,
|
| 1116 |
+
"logits/chosen": -0.20335140824317932,
|
| 1117 |
+
"logits/rejected": -0.2963979244232178,
|
| 1118 |
+
"logps/chosen": -293.1023864746094,
|
| 1119 |
+
"logps/rejected": -253.64291381835938,
|
| 1120 |
+
"loss": 0.5049,
|
| 1121 |
+
"rewards/accuracies": 0.71875,
|
| 1122 |
+
"rewards/chosen": 0.00017919539823196828,
|
| 1123 |
+
"rewards/margins": 0.5864929556846619,
|
| 1124 |
+
"rewards/rejected": -0.5863137245178223,
|
| 1125 |
+
"step": 670
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.4237110704004188,
|
| 1129 |
+
"grad_norm": 40.03881951253335,
|
| 1130 |
+
"learning_rate": 6.297042289606479e-07,
|
| 1131 |
+
"logits/chosen": -0.13722732663154602,
|
| 1132 |
+
"logits/rejected": -0.1250244826078415,
|
| 1133 |
+
"logps/chosen": -295.9792785644531,
|
| 1134 |
+
"logps/rejected": -296.83038330078125,
|
| 1135 |
+
"loss": 0.5133,
|
| 1136 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1137 |
+
"rewards/chosen": -0.014182251878082752,
|
| 1138 |
+
"rewards/margins": 0.5892963409423828,
|
| 1139 |
+
"rewards/rejected": -0.6034785509109497,
|
| 1140 |
+
"step": 680
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.4446479979063072,
|
| 1144 |
+
"grad_norm": 29.250271504061402,
|
| 1145 |
+
"learning_rate": 6.178794677547137e-07,
|
| 1146 |
+
"logits/chosen": -0.18004044890403748,
|
| 1147 |
+
"logits/rejected": -0.1459943801164627,
|
| 1148 |
+
"logps/chosen": -298.6792297363281,
|
| 1149 |
+
"logps/rejected": -257.5166931152344,
|
| 1150 |
+
"loss": 0.5157,
|
| 1151 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1152 |
+
"rewards/chosen": 0.07589882612228394,
|
| 1153 |
+
"rewards/margins": 0.7056849598884583,
|
| 1154 |
+
"rewards/rejected": -0.6297860741615295,
|
| 1155 |
+
"step": 690
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.4655849254121958,
|
| 1159 |
+
"grad_norm": 32.49512416553128,
|
| 1160 |
+
"learning_rate": 6.059844706324286e-07,
|
| 1161 |
+
"logits/chosen": -0.07275749742984772,
|
| 1162 |
+
"logits/rejected": 0.005568481981754303,
|
| 1163 |
+
"logps/chosen": -314.0689697265625,
|
| 1164 |
+
"logps/rejected": -328.4625244140625,
|
| 1165 |
+
"loss": 0.5056,
|
| 1166 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1167 |
+
"rewards/chosen": 0.13801348209381104,
|
| 1168 |
+
"rewards/margins": 0.876538872718811,
|
| 1169 |
+
"rewards/rejected": -0.738525390625,
|
| 1170 |
+
"step": 700
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.4655849254121958,
|
| 1174 |
+
"eval_logits/chosen": -0.3406723737716675,
|
| 1175 |
+
"eval_logits/rejected": -0.36724287271499634,
|
| 1176 |
+
"eval_logps/chosen": -310.4104309082031,
|
| 1177 |
+
"eval_logps/rejected": -275.4717102050781,
|
| 1178 |
+
"eval_loss": 0.5875913500785828,
|
| 1179 |
+
"eval_rewards/accuracies": 0.6904761791229248,
|
| 1180 |
+
"eval_rewards/chosen": -0.06298798322677612,
|
| 1181 |
+
"eval_rewards/margins": 0.5310800671577454,
|
| 1182 |
+
"eval_rewards/rejected": -0.5940679311752319,
|
| 1183 |
+
"eval_runtime": 19.0211,
|
| 1184 |
+
"eval_samples_per_second": 105.146,
|
| 1185 |
+
"eval_steps_per_second": 3.312,
|
| 1186 |
+
"step": 700
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.4865218529180844,
|
| 1190 |
+
"grad_norm": 35.75327607918745,
|
| 1191 |
+
"learning_rate": 5.940263249690477e-07,
|
| 1192 |
+
"logits/chosen": -0.24695155024528503,
|
| 1193 |
+
"logits/rejected": -0.22096967697143555,
|
| 1194 |
+
"logps/chosen": -295.2511901855469,
|
| 1195 |
+
"logps/rejected": -276.71051025390625,
|
| 1196 |
+
"loss": 0.5132,
|
| 1197 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1198 |
+
"rewards/chosen": 0.058757662773132324,
|
| 1199 |
+
"rewards/margins": 0.7594215273857117,
|
| 1200 |
+
"rewards/rejected": -0.7006638646125793,
|
| 1201 |
+
"step": 710
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.5074587804239727,
|
| 1205 |
+
"grad_norm": 41.16638143070179,
|
| 1206 |
+
"learning_rate": 5.820121557655108e-07,
|
| 1207 |
+
"logits/chosen": -0.1299329400062561,
|
| 1208 |
+
"logits/rejected": -0.10874001681804657,
|
| 1209 |
+
"logps/chosen": -303.56732177734375,
|
| 1210 |
+
"logps/rejected": -280.8491516113281,
|
| 1211 |
+
"loss": 0.5135,
|
| 1212 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1213 |
+
"rewards/chosen": 0.11438952386379242,
|
| 1214 |
+
"rewards/margins": 0.7343131899833679,
|
| 1215 |
+
"rewards/rejected": -0.6199236512184143,
|
| 1216 |
+
"step": 720
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 1.5283957079298613,
|
| 1220 |
+
"grad_norm": 41.49005357475057,
|
| 1221 |
+
"learning_rate": 5.699491214031657e-07,
|
| 1222 |
+
"logits/chosen": -0.14048215746879578,
|
| 1223 |
+
"logits/rejected": -0.18900522589683533,
|
| 1224 |
+
"logps/chosen": -280.69598388671875,
|
| 1225 |
+
"logps/rejected": -255.81298828125,
|
| 1226 |
+
"loss": 0.5166,
|
| 1227 |
+
"rewards/accuracies": 0.8125,
|
| 1228 |
+
"rewards/chosen": 0.11929772049188614,
|
| 1229 |
+
"rewards/margins": 0.7799339294433594,
|
| 1230 |
+
"rewards/rejected": -0.6606361269950867,
|
| 1231 |
+
"step": 730
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.54933263543575,
|
| 1235 |
+
"grad_norm": 34.97801212344648,
|
| 1236 |
+
"learning_rate": 5.578444093786008e-07,
|
| 1237 |
+
"logits/chosen": 0.06411169469356537,
|
| 1238 |
+
"logits/rejected": 0.15786513686180115,
|
| 1239 |
+
"logps/chosen": -315.06182861328125,
|
| 1240 |
+
"logps/rejected": -282.93115234375,
|
| 1241 |
+
"loss": 0.5128,
|
| 1242 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1243 |
+
"rewards/chosen": 0.24365051090717316,
|
| 1244 |
+
"rewards/margins": 0.8540836572647095,
|
| 1245 |
+
"rewards/rejected": -0.6104331612586975,
|
| 1246 |
+
"step": 740
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.5702695629416383,
|
| 1250 |
+
"grad_norm": 32.53803724377542,
|
| 1251 |
+
"learning_rate": 5.457052320211339e-07,
|
| 1252 |
+
"logits/chosen": -0.22511212527751923,
|
| 1253 |
+
"logits/rejected": -0.22842809557914734,
|
| 1254 |
+
"logps/chosen": -298.0352783203125,
|
| 1255 |
+
"logps/rejected": -268.8421936035156,
|
| 1256 |
+
"loss": 0.4961,
|
| 1257 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1258 |
+
"rewards/chosen": 0.09702634066343307,
|
| 1259 |
+
"rewards/margins": 0.632623016834259,
|
| 1260 |
+
"rewards/rejected": -0.5355967283248901,
|
| 1261 |
+
"step": 750
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.5912064904475267,
|
| 1265 |
+
"grad_norm": 36.857273577646474,
|
| 1266 |
+
"learning_rate": 5.335388221955012e-07,
|
| 1267 |
+
"logits/chosen": -0.044903479516506195,
|
| 1268 |
+
"logits/rejected": 0.0046501667238771915,
|
| 1269 |
+
"logps/chosen": -358.9960632324219,
|
| 1270 |
+
"logps/rejected": -336.44354248046875,
|
| 1271 |
+
"loss": 0.4997,
|
| 1272 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1273 |
+
"rewards/chosen": 0.28686124086380005,
|
| 1274 |
+
"rewards/margins": 0.7968252301216125,
|
| 1275 |
+
"rewards/rejected": -0.5099639296531677,
|
| 1276 |
+
"step": 760
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.6121434179534153,
|
| 1280 |
+
"grad_norm": 31.737574949447513,
|
| 1281 |
+
"learning_rate": 5.213524289923126e-07,
|
| 1282 |
+
"logits/chosen": -0.03366886079311371,
|
| 1283 |
+
"logits/rejected": -0.18763691186904907,
|
| 1284 |
+
"logps/chosen": -327.0910339355469,
|
| 1285 |
+
"logps/rejected": -272.4969787597656,
|
| 1286 |
+
"loss": 0.5114,
|
| 1287 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1288 |
+
"rewards/chosen": 0.2613201141357422,
|
| 1289 |
+
"rewards/margins": 0.8974519968032837,
|
| 1290 |
+
"rewards/rejected": -0.6361318826675415,
|
| 1291 |
+
"step": 770
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.633080345459304,
|
| 1295 |
+
"grad_norm": 34.36622996446216,
|
| 1296 |
+
"learning_rate": 5.091533134088387e-07,
|
| 1297 |
+
"logits/chosen": -0.12894697487354279,
|
| 1298 |
+
"logits/rejected": -0.142494797706604,
|
| 1299 |
+
"logps/chosen": -320.5164794921875,
|
| 1300 |
+
"logps/rejected": -280.9849548339844,
|
| 1301 |
+
"loss": 0.5146,
|
| 1302 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1303 |
+
"rewards/chosen": 0.27436262369155884,
|
| 1304 |
+
"rewards/margins": 0.8554395437240601,
|
| 1305 |
+
"rewards/rejected": -0.581076979637146,
|
| 1306 |
+
"step": 780
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.6540172729651923,
|
| 1310 |
+
"grad_norm": 38.709599843434866,
|
| 1311 |
+
"learning_rate": 4.969487440227038e-07,
|
| 1312 |
+
"logits/chosen": -0.21234026551246643,
|
| 1313 |
+
"logits/rejected": -0.22163410484790802,
|
| 1314 |
+
"logps/chosen": -300.9823303222656,
|
| 1315 |
+
"logps/rejected": -276.39508056640625,
|
| 1316 |
+
"loss": 0.4852,
|
| 1317 |
+
"rewards/accuracies": 0.78125,
|
| 1318 |
+
"rewards/chosen": 0.24367956817150116,
|
| 1319 |
+
"rewards/margins": 0.9389246106147766,
|
| 1320 |
+
"rewards/rejected": -0.6952449679374695,
|
| 1321 |
+
"step": 790
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 1.674954200471081,
|
| 1325 |
+
"grad_norm": 31.812270366410278,
|
| 1326 |
+
"learning_rate": 4.847459926610619e-07,
|
| 1327 |
+
"logits/chosen": -0.018023919314146042,
|
| 1328 |
+
"logits/rejected": -0.12209578603506088,
|
| 1329 |
+
"logps/chosen": -350.00439453125,
|
| 1330 |
+
"logps/rejected": -305.96954345703125,
|
| 1331 |
+
"loss": 0.4936,
|
| 1332 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1333 |
+
"rewards/chosen": 0.1853758990764618,
|
| 1334 |
+
"rewards/margins": 0.8932290077209473,
|
| 1335 |
+
"rewards/rejected": -0.7078530788421631,
|
| 1336 |
+
"step": 800
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.674954200471081,
|
| 1340 |
+
"eval_logits/chosen": -0.3383854031562805,
|
| 1341 |
+
"eval_logits/rejected": -0.36581355333328247,
|
| 1342 |
+
"eval_logps/chosen": -310.3436584472656,
|
| 1343 |
+
"eval_logps/rejected": -275.40155029296875,
|
| 1344 |
+
"eval_loss": 0.5994271636009216,
|
| 1345 |
+
"eval_rewards/accuracies": 0.6746031641960144,
|
| 1346 |
+
"eval_rewards/chosen": -0.029591551050543785,
|
| 1347 |
+
"eval_rewards/margins": 0.5294089317321777,
|
| 1348 |
+
"eval_rewards/rejected": -0.559000551700592,
|
| 1349 |
+
"eval_runtime": 19.1971,
|
| 1350 |
+
"eval_samples_per_second": 104.182,
|
| 1351 |
+
"eval_steps_per_second": 3.282,
|
| 1352 |
+
"step": 800
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 1.6958911279769695,
|
| 1356 |
+
"grad_norm": 35.049859279627235,
|
| 1357 |
+
"learning_rate": 4.7255233006783624e-07,
|
| 1358 |
+
"logits/chosen": -0.18587855994701385,
|
| 1359 |
+
"logits/rejected": -0.16283151507377625,
|
| 1360 |
+
"logps/chosen": -307.56439208984375,
|
| 1361 |
+
"logps/rejected": -278.2900390625,
|
| 1362 |
+
"loss": 0.5055,
|
| 1363 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1364 |
+
"rewards/chosen": 0.10620725154876709,
|
| 1365 |
+
"rewards/margins": 0.892121434211731,
|
| 1366 |
+
"rewards/rejected": -0.7859140634536743,
|
| 1367 |
+
"step": 810
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.7168280554828579,
|
| 1371 |
+
"grad_norm": 34.134111938828184,
|
| 1372 |
+
"learning_rate": 4.6037502157160567e-07,
|
| 1373 |
+
"logits/chosen": -0.2755785584449768,
|
| 1374 |
+
"logits/rejected": -0.31054019927978516,
|
| 1375 |
+
"logps/chosen": -320.56695556640625,
|
| 1376 |
+
"logps/rejected": -273.4154968261719,
|
| 1377 |
+
"loss": 0.5048,
|
| 1378 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1379 |
+
"rewards/chosen": 0.20151178538799286,
|
| 1380 |
+
"rewards/margins": 0.9227310419082642,
|
| 1381 |
+
"rewards/rejected": -0.7212191820144653,
|
| 1382 |
+
"step": 820
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.7377649829887463,
|
| 1386 |
+
"grad_norm": 38.68230830225304,
|
| 1387 |
+
"learning_rate": 4.482213227567161e-07,
|
| 1388 |
+
"logits/chosen": -0.2091369926929474,
|
| 1389 |
+
"logits/rejected": -0.14194951951503754,
|
| 1390 |
+
"logps/chosen": -277.35693359375,
|
| 1391 |
+
"logps/rejected": -281.7249450683594,
|
| 1392 |
+
"loss": 0.484,
|
| 1393 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1394 |
+
"rewards/chosen": 0.10125979036092758,
|
| 1395 |
+
"rewards/margins": 0.8731620907783508,
|
| 1396 |
+
"rewards/rejected": -0.7719023823738098,
|
| 1397 |
+
"step": 830
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.7587019104946349,
|
| 1401 |
+
"grad_norm": 33.945256383172804,
|
| 1402 |
+
"learning_rate": 4.3609847514019763e-07,
|
| 1403 |
+
"logits/chosen": -0.30677181482315063,
|
| 1404 |
+
"logits/rejected": -0.1776028573513031,
|
| 1405 |
+
"logps/chosen": -261.38873291015625,
|
| 1406 |
+
"logps/rejected": -267.8268127441406,
|
| 1407 |
+
"loss": 0.5094,
|
| 1408 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1409 |
+
"rewards/chosen": 0.18778590857982635,
|
| 1410 |
+
"rewards/margins": 0.8258863687515259,
|
| 1411 |
+
"rewards/rejected": -0.6381004452705383,
|
| 1412 |
+
"step": 840
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.7796388380005235,
|
| 1416 |
+
"grad_norm": 34.20224125304341,
|
| 1417 |
+
"learning_rate": 4.240137018570661e-07,
|
| 1418 |
+
"logits/chosen": -0.11399509757757187,
|
| 1419 |
+
"logits/rejected": -0.1185418963432312,
|
| 1420 |
+
"logps/chosen": -275.3580017089844,
|
| 1421 |
+
"logps/rejected": -282.1163024902344,
|
| 1422 |
+
"loss": 0.5074,
|
| 1423 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1424 |
+
"rewards/chosen": -0.03538894280791283,
|
| 1425 |
+
"rewards/margins": 0.7777508497238159,
|
| 1426 |
+
"rewards/rejected": -0.813139796257019,
|
| 1427 |
+
"step": 850
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.8005757655064119,
|
| 1431 |
+
"grad_norm": 31.946083788257877,
|
| 1432 |
+
"learning_rate": 4.1197420335657366e-07,
|
| 1433 |
+
"logits/chosen": -0.09024197608232498,
|
| 1434 |
+
"logits/rejected": -0.20059815049171448,
|
| 1435 |
+
"logps/chosen": -298.12762451171875,
|
| 1436 |
+
"logps/rejected": -242.2689666748047,
|
| 1437 |
+
"loss": 0.5089,
|
| 1438 |
+
"rewards/accuracies": 0.75,
|
| 1439 |
+
"rewards/chosen": 0.15691380202770233,
|
| 1440 |
+
"rewards/margins": 0.8090406656265259,
|
| 1441 |
+
"rewards/rejected": -0.6521269083023071,
|
| 1442 |
+
"step": 860
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.8215126930123005,
|
| 1446 |
+
"grad_norm": 28.583891688236477,
|
| 1447 |
+
"learning_rate": 3.9998715311197783e-07,
|
| 1448 |
+
"logits/chosen": -0.1159423366189003,
|
| 1449 |
+
"logits/rejected": -0.16631600260734558,
|
| 1450 |
+
"logps/chosen": -337.1079406738281,
|
| 1451 |
+
"logps/rejected": -285.5828857421875,
|
| 1452 |
+
"loss": 0.4894,
|
| 1453 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1454 |
+
"rewards/chosen": 0.11767788976430893,
|
| 1455 |
+
"rewards/margins": 0.6672422289848328,
|
| 1456 |
+
"rewards/rejected": -0.5495643615722656,
|
| 1457 |
+
"step": 870
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.842449620518189,
|
| 1461 |
+
"grad_norm": 33.76166639382152,
|
| 1462 |
+
"learning_rate": 3.880596933463843e-07,
|
| 1463 |
+
"logits/chosen": -0.07985590398311615,
|
| 1464 |
+
"logits/rejected": -0.03050703927874565,
|
| 1465 |
+
"logps/chosen": -274.9603576660156,
|
| 1466 |
+
"logps/rejected": -266.6165771484375,
|
| 1467 |
+
"loss": 0.5075,
|
| 1468 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1469 |
+
"rewards/chosen": 0.09320048242807388,
|
| 1470 |
+
"rewards/margins": 0.7023938298225403,
|
| 1471 |
+
"rewards/rejected": -0.6091933250427246,
|
| 1472 |
+
"step": 880
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.8633865480240774,
|
| 1476 |
+
"grad_norm": 40.29693979290027,
|
| 1477 |
+
"learning_rate": 3.761989307772085e-07,
|
| 1478 |
+
"logits/chosen": -0.15825888514518738,
|
| 1479 |
+
"logits/rejected": -0.1759234219789505,
|
| 1480 |
+
"logps/chosen": -306.653076171875,
|
| 1481 |
+
"logps/rejected": -279.01177978515625,
|
| 1482 |
+
"loss": 0.5055,
|
| 1483 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 1484 |
+
"rewards/chosen": 0.16093602776527405,
|
| 1485 |
+
"rewards/margins": 0.937556266784668,
|
| 1486 |
+
"rewards/rejected": -0.7766203284263611,
|
| 1487 |
+
"step": 890
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.8843234755299658,
|
| 1491 |
+
"grad_norm": 36.002728955160904,
|
| 1492 |
+
"learning_rate": 3.6441193238179146e-07,
|
| 1493 |
+
"logits/chosen": -0.05288013815879822,
|
| 1494 |
+
"logits/rejected": -0.13031360507011414,
|
| 1495 |
+
"logps/chosen": -334.34417724609375,
|
| 1496 |
+
"logps/rejected": -269.53558349609375,
|
| 1497 |
+
"loss": 0.4904,
|
| 1498 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1499 |
+
"rewards/chosen": 0.14437799155712128,
|
| 1500 |
+
"rewards/margins": 0.8378474116325378,
|
| 1501 |
+
"rewards/rejected": -0.6934694051742554,
|
| 1502 |
+
"step": 900
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.8843234755299658,
|
| 1506 |
+
"eval_logits/chosen": -0.3443281650543213,
|
| 1507 |
+
"eval_logits/rejected": -0.3704880475997925,
|
| 1508 |
+
"eval_logps/chosen": -310.4006042480469,
|
| 1509 |
+
"eval_logps/rejected": -275.5133972167969,
|
| 1510 |
+
"eval_loss": 0.5989052653312683,
|
| 1511 |
+
"eval_rewards/accuracies": 0.6944444179534912,
|
| 1512 |
+
"eval_rewards/chosen": -0.05807310715317726,
|
| 1513 |
+
"eval_rewards/margins": 0.55684494972229,
|
| 1514 |
+
"eval_rewards/rejected": -0.614918053150177,
|
| 1515 |
+
"eval_runtime": 18.9036,
|
| 1516 |
+
"eval_samples_per_second": 105.8,
|
| 1517 |
+
"eval_steps_per_second": 3.333,
|
| 1518 |
+
"step": 900
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.9052604030358546,
|
| 1522 |
+
"grad_norm": 31.165480893885753,
|
| 1523 |
+
"learning_rate": 3.5270572118669715e-07,
|
| 1524 |
+
"logits/chosen": -0.11026148498058319,
|
| 1525 |
+
"logits/rejected": -0.16978046298027039,
|
| 1526 |
+
"logps/chosen": -278.1309509277344,
|
| 1527 |
+
"logps/rejected": -235.88150024414062,
|
| 1528 |
+
"loss": 0.5272,
|
| 1529 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1530 |
+
"rewards/chosen": 0.02903774380683899,
|
| 1531 |
+
"rewards/margins": 0.8374470472335815,
|
| 1532 |
+
"rewards/rejected": -0.8084093332290649,
|
| 1533 |
+
"step": 910
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 1.926197330541743,
|
| 1537 |
+
"grad_norm": 40.996379136014625,
|
| 1538 |
+
"learning_rate": 3.4108727208319314e-07,
|
| 1539 |
+
"logits/chosen": -0.17259056866168976,
|
| 1540 |
+
"logits/rejected": -0.20306821167469025,
|
| 1541 |
+
"logps/chosen": -312.1188049316406,
|
| 1542 |
+
"logps/rejected": -266.6794128417969,
|
| 1543 |
+
"loss": 0.5039,
|
| 1544 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1545 |
+
"rewards/chosen": 0.16847112774848938,
|
| 1546 |
+
"rewards/margins": 0.8200035095214844,
|
| 1547 |
+
"rewards/rejected": -0.6515323519706726,
|
| 1548 |
+
"step": 920
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 1.9471342580476314,
|
| 1552 |
+
"grad_norm": 31.825399091982387,
|
| 1553 |
+
"learning_rate": 3.295635076714144e-07,
|
| 1554 |
+
"logits/chosen": -0.1496247947216034,
|
| 1555 |
+
"logits/rejected": -0.17214402556419373,
|
| 1556 |
+
"logps/chosen": -301.103515625,
|
| 1557 |
+
"logps/rejected": -270.370361328125,
|
| 1558 |
+
"loss": 0.4903,
|
| 1559 |
+
"rewards/accuracies": 0.78125,
|
| 1560 |
+
"rewards/chosen": 0.16043229401111603,
|
| 1561 |
+
"rewards/margins": 0.7891928553581238,
|
| 1562 |
+
"rewards/rejected": -0.628760576248169,
|
| 1563 |
+
"step": 930
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.96807118555352,
|
| 1567 |
+
"grad_norm": 39.834235726892466,
|
| 1568 |
+
"learning_rate": 3.181412941356816e-07,
|
| 1569 |
+
"logits/chosen": -0.13259033858776093,
|
| 1570 |
+
"logits/rejected": -0.11601094901561737,
|
| 1571 |
+
"logps/chosen": -266.5997314453125,
|
| 1572 |
+
"logps/rejected": -231.60848999023438,
|
| 1573 |
+
"loss": 0.485,
|
| 1574 |
+
"rewards/accuracies": 0.78125,
|
| 1575 |
+
"rewards/chosen": 0.19742903113365173,
|
| 1576 |
+
"rewards/margins": 0.8145695924758911,
|
| 1577 |
+
"rewards/rejected": -0.6171405911445618,
|
| 1578 |
+
"step": 940
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.9890081130594086,
|
| 1582 |
+
"grad_norm": 35.65864774290716,
|
| 1583 |
+
"learning_rate": 3.068274371534356e-07,
|
| 1584 |
+
"logits/chosen": -0.11888673156499863,
|
| 1585 |
+
"logits/rejected": -0.2420310229063034,
|
| 1586 |
+
"logps/chosen": -301.62213134765625,
|
| 1587 |
+
"logps/rejected": -250.2771453857422,
|
| 1588 |
+
"loss": 0.4887,
|
| 1589 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1590 |
+
"rewards/chosen": 0.002846676157787442,
|
| 1591 |
+
"rewards/margins": 0.7688849568367004,
|
| 1592 |
+
"rewards/rejected": -0.7660382986068726,
|
| 1593 |
+
"step": 950
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.009945040565297,
|
| 1597 |
+
"grad_norm": 28.814451971980255,
|
| 1598 |
+
"learning_rate": 2.956286778402226e-07,
|
| 1599 |
+
"logits/chosen": -0.10088515281677246,
|
| 1600 |
+
"logits/rejected": -0.12641310691833496,
|
| 1601 |
+
"logps/chosen": -301.3664855957031,
|
| 1602 |
+
"logps/rejected": -283.16461181640625,
|
| 1603 |
+
"loss": 0.4567,
|
| 1604 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1605 |
+
"rewards/chosen": 0.20988380908966064,
|
| 1606 |
+
"rewards/margins": 0.9322754740715027,
|
| 1607 |
+
"rewards/rejected": -0.7223917245864868,
|
| 1608 |
+
"step": 960
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.0308819680711854,
|
| 1612 |
+
"grad_norm": 28.79413061525845,
|
| 1613 |
+
"learning_rate": 2.84551688733146e-07,
|
| 1614 |
+
"logits/chosen": -0.07364392280578613,
|
| 1615 |
+
"logits/rejected": -0.1452295333147049,
|
| 1616 |
+
"logps/chosen": -299.0059509277344,
|
| 1617 |
+
"logps/rejected": -238.53231811523438,
|
| 1618 |
+
"loss": 0.4557,
|
| 1619 |
+
"rewards/accuracies": 0.84375,
|
| 1620 |
+
"rewards/chosen": 0.166302889585495,
|
| 1621 |
+
"rewards/margins": 0.9308949708938599,
|
| 1622 |
+
"rewards/rejected": -0.7645919919013977,
|
| 1623 |
+
"step": 970
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 2.051818895577074,
|
| 1627 |
+
"grad_norm": 31.23059423273923,
|
| 1628 |
+
"learning_rate": 2.7360306981518147e-07,
|
| 1629 |
+
"logits/chosen": -0.09392131119966507,
|
| 1630 |
+
"logits/rejected": -0.047506559640169144,
|
| 1631 |
+
"logps/chosen": -262.2680969238281,
|
| 1632 |
+
"logps/rejected": -253.03271484375,
|
| 1633 |
+
"loss": 0.4445,
|
| 1634 |
+
"rewards/accuracies": 0.8125,
|
| 1635 |
+
"rewards/chosen": 0.040274180471897125,
|
| 1636 |
+
"rewards/margins": 0.7928990125656128,
|
| 1637 |
+
"rewards/rejected": -0.7526248097419739,
|
| 1638 |
+
"step": 980
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 2.0727558230829626,
|
| 1642 |
+
"grad_norm": 27.855961833782285,
|
| 1643 |
+
"learning_rate": 2.6278934458271996e-07,
|
| 1644 |
+
"logits/chosen": -0.1288485825061798,
|
| 1645 |
+
"logits/rejected": -0.1765173375606537,
|
| 1646 |
+
"logps/chosen": -314.7231750488281,
|
| 1647 |
+
"logps/rejected": -302.44964599609375,
|
| 1648 |
+
"loss": 0.4327,
|
| 1649 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1650 |
+
"rewards/chosen": 0.18189235031604767,
|
| 1651 |
+
"rewards/margins": 1.0036437511444092,
|
| 1652 |
+
"rewards/rejected": -0.8217514157295227,
|
| 1653 |
+
"step": 990
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 2.093692750588851,
|
| 1657 |
+
"grad_norm": 35.285113595842645,
|
| 1658 |
+
"learning_rate": 2.5211695615868456e-07,
|
| 1659 |
+
"logits/chosen": -0.1857554316520691,
|
| 1660 |
+
"logits/rejected": -0.3039974272251129,
|
| 1661 |
+
"logps/chosen": -281.1855163574219,
|
| 1662 |
+
"logps/rejected": -240.62710571289062,
|
| 1663 |
+
"loss": 0.4622,
|
| 1664 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1665 |
+
"rewards/chosen": 0.15526309609413147,
|
| 1666 |
+
"rewards/margins": 0.9393559694290161,
|
| 1667 |
+
"rewards/rejected": -0.7840928435325623,
|
| 1668 |
+
"step": 1000
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.093692750588851,
|
| 1672 |
+
"eval_logits/chosen": -0.3450426459312439,
|
| 1673 |
+
"eval_logits/rejected": -0.37242141366004944,
|
| 1674 |
+
"eval_logps/chosen": -310.4169006347656,
|
| 1675 |
+
"eval_logps/rejected": -275.49713134765625,
|
| 1676 |
+
"eval_loss": 0.59389328956604,
|
| 1677 |
+
"eval_rewards/accuracies": 0.6944444179534912,
|
| 1678 |
+
"eval_rewards/chosen": -0.06623569875955582,
|
| 1679 |
+
"eval_rewards/margins": 0.5405489802360535,
|
| 1680 |
+
"eval_rewards/rejected": -0.6067846417427063,
|
| 1681 |
+
"eval_runtime": 19.108,
|
| 1682 |
+
"eval_samples_per_second": 104.668,
|
| 1683 |
+
"eval_steps_per_second": 3.297,
|
| 1684 |
+
"step": 1000
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 2.11462967809474,
|
| 1688 |
+
"grad_norm": 32.59720699053956,
|
| 1689 |
+
"learning_rate": 2.4159226345353647e-07,
|
| 1690 |
+
"logits/chosen": -0.30413442850112915,
|
| 1691 |
+
"logits/rejected": -0.24426865577697754,
|
| 1692 |
+
"logps/chosen": -270.49920654296875,
|
| 1693 |
+
"logps/rejected": -255.44723510742188,
|
| 1694 |
+
"loss": 0.4508,
|
| 1695 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1696 |
+
"rewards/chosen": 0.03533598408102989,
|
| 1697 |
+
"rewards/margins": 0.7992294430732727,
|
| 1698 |
+
"rewards/rejected": -0.7638934254646301,
|
| 1699 |
+
"step": 1010
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 2.135566605600628,
|
| 1703 |
+
"grad_norm": 30.8340208692361,
|
| 1704 |
+
"learning_rate": 2.312215373764551e-07,
|
| 1705 |
+
"logits/chosen": -0.07855603843927383,
|
| 1706 |
+
"logits/rejected": -0.094606414437294,
|
| 1707 |
+
"logps/chosen": -289.9374084472656,
|
| 1708 |
+
"logps/rejected": -277.69586181640625,
|
| 1709 |
+
"loss": 0.4353,
|
| 1710 |
+
"rewards/accuracies": 0.8125,
|
| 1711 |
+
"rewards/chosen": 0.19073505699634552,
|
| 1712 |
+
"rewards/margins": 0.8868581652641296,
|
| 1713 |
+
"rewards/rejected": -0.6961231231689453,
|
| 1714 |
+
"step": 1020
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 2.1565035331065165,
|
| 1718 |
+
"grad_norm": 29.34387598294554,
|
| 1719 |
+
"learning_rate": 2.2101095709895512e-07,
|
| 1720 |
+
"logits/chosen": 0.009572875685989857,
|
| 1721 |
+
"logits/rejected": -0.09117701649665833,
|
| 1722 |
+
"logps/chosen": -282.7410583496094,
|
| 1723 |
+
"logps/rejected": -239.8011932373047,
|
| 1724 |
+
"loss": 0.438,
|
| 1725 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1726 |
+
"rewards/chosen": 0.12627363204956055,
|
| 1727 |
+
"rewards/margins": 0.8894168138504028,
|
| 1728 |
+
"rewards/rejected": -0.7631431221961975,
|
| 1729 |
+
"step": 1030
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 2.177440460612405,
|
| 1733 |
+
"grad_norm": 29.466746389871066,
|
| 1734 |
+
"learning_rate": 2.1096660637315932e-07,
|
| 1735 |
+
"logits/chosen": -0.0853545218706131,
|
| 1736 |
+
"logits/rejected": -0.1613493412733078,
|
| 1737 |
+
"logps/chosen": -309.2115783691406,
|
| 1738 |
+
"logps/rejected": -279.7373352050781,
|
| 1739 |
+
"loss": 0.4374,
|
| 1740 |
+
"rewards/accuracies": 0.856249988079071,
|
| 1741 |
+
"rewards/chosen": 0.2535983920097351,
|
| 1742 |
+
"rewards/margins": 1.087397575378418,
|
| 1743 |
+
"rewards/rejected": -0.8337991833686829,
|
| 1744 |
+
"step": 1040
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 2.1983773881182938,
|
| 1748 |
+
"grad_norm": 31.3324256474218,
|
| 1749 |
+
"learning_rate": 2.0109446990692963e-07,
|
| 1750 |
+
"logits/chosen": -0.17987683415412903,
|
| 1751 |
+
"logits/rejected": -0.24151673913002014,
|
| 1752 |
+
"logps/chosen": -323.58477783203125,
|
| 1753 |
+
"logps/rejected": -268.08111572265625,
|
| 1754 |
+
"loss": 0.4365,
|
| 1755 |
+
"rewards/accuracies": 0.75,
|
| 1756 |
+
"rewards/chosen": 0.09657944738864899,
|
| 1757 |
+
"rewards/margins": 0.8588522672653198,
|
| 1758 |
+
"rewards/rejected": -0.7622728943824768,
|
| 1759 |
+
"step": 1050
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.219314315624182,
|
| 1763 |
+
"grad_norm": 33.25666630785023,
|
| 1764 |
+
"learning_rate": 1.9140042979800737e-07,
|
| 1765 |
+
"logits/chosen": -0.13123273849487305,
|
| 1766 |
+
"logits/rejected": -0.12296972423791885,
|
| 1767 |
+
"logps/chosen": -260.5819396972656,
|
| 1768 |
+
"logps/rejected": -232.4111328125,
|
| 1769 |
+
"loss": 0.4355,
|
| 1770 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1771 |
+
"rewards/chosen": 0.05866159126162529,
|
| 1772 |
+
"rewards/margins": 0.7927514314651489,
|
| 1773 |
+
"rewards/rejected": -0.7340899109840393,
|
| 1774 |
+
"step": 1060
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.2402512431300705,
|
| 1778 |
+
"grad_norm": 27.925843344985296,
|
| 1779 |
+
"learning_rate": 1.8189026202929391e-07,
|
| 1780 |
+
"logits/chosen": -0.1511206328868866,
|
| 1781 |
+
"logits/rejected": -0.17038318514823914,
|
| 1782 |
+
"logps/chosen": -290.31951904296875,
|
| 1783 |
+
"logps/rejected": -260.115966796875,
|
| 1784 |
+
"loss": 0.4534,
|
| 1785 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1786 |
+
"rewards/chosen": 0.11966502666473389,
|
| 1787 |
+
"rewards/margins": 0.9545691609382629,
|
| 1788 |
+
"rewards/rejected": -0.8349041938781738,
|
| 1789 |
+
"step": 1070
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 2.2611881706359593,
|
| 1793 |
+
"grad_norm": 26.475722050618995,
|
| 1794 |
+
"learning_rate": 1.725696330273575e-07,
|
| 1795 |
+
"logits/chosen": -0.08606094121932983,
|
| 1796 |
+
"logits/rejected": -0.1871510148048401,
|
| 1797 |
+
"logps/chosen": -288.9709777832031,
|
| 1798 |
+
"logps/rejected": -249.9591064453125,
|
| 1799 |
+
"loss": 0.4441,
|
| 1800 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1801 |
+
"rewards/chosen": 0.19028839468955994,
|
| 1802 |
+
"rewards/margins": 1.0648086071014404,
|
| 1803 |
+
"rewards/rejected": -0.8745201826095581,
|
| 1804 |
+
"step": 1080
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 2.2821250981418477,
|
| 1808 |
+
"grad_norm": 28.63389247775027,
|
| 1809 |
+
"learning_rate": 1.634440962862148e-07,
|
| 1810 |
+
"logits/chosen": -0.05144480615854263,
|
| 1811 |
+
"logits/rejected": -0.04060221463441849,
|
| 1812 |
+
"logps/chosen": -295.44122314453125,
|
| 1813 |
+
"logps/rejected": -262.346435546875,
|
| 1814 |
+
"loss": 0.4318,
|
| 1815 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1816 |
+
"rewards/chosen": 0.20048430562019348,
|
| 1817 |
+
"rewards/margins": 0.9130541086196899,
|
| 1818 |
+
"rewards/rejected": -0.7125697135925293,
|
| 1819 |
+
"step": 1090
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 2.303062025647736,
|
| 1823 |
+
"grad_norm": 28.577071054830697,
|
| 1824 |
+
"learning_rate": 1.545190890584042e-07,
|
| 1825 |
+
"logits/chosen": -0.23821565508842468,
|
| 1826 |
+
"logits/rejected": -0.23792441189289093,
|
| 1827 |
+
"logps/chosen": -287.6651306152344,
|
| 1828 |
+
"logps/rejected": -261.96875,
|
| 1829 |
+
"loss": 0.4458,
|
| 1830 |
+
"rewards/accuracies": 0.8125,
|
| 1831 |
+
"rewards/chosen": 0.24947874248027802,
|
| 1832 |
+
"rewards/margins": 0.945774257183075,
|
| 1833 |
+
"rewards/rejected": -0.696295440196991,
|
| 1834 |
+
"step": 1100
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 2.303062025647736,
|
| 1838 |
+
"eval_logits/chosen": -0.3449550271034241,
|
| 1839 |
+
"eval_logits/rejected": -0.3728056252002716,
|
| 1840 |
+
"eval_logps/chosen": -310.3917541503906,
|
| 1841 |
+
"eval_logps/rejected": -275.5622253417969,
|
| 1842 |
+
"eval_loss": 0.5923458933830261,
|
| 1843 |
+
"eval_rewards/accuracies": 0.6944444179534912,
|
| 1844 |
+
"eval_rewards/chosen": -0.05364745110273361,
|
| 1845 |
+
"eval_rewards/margins": 0.5857000946998596,
|
| 1846 |
+
"eval_rewards/rejected": -0.639347493648529,
|
| 1847 |
+
"eval_runtime": 19.0051,
|
| 1848 |
+
"eval_samples_per_second": 105.235,
|
| 1849 |
+
"eval_steps_per_second": 3.315,
|
| 1850 |
+
"step": 1100
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.323998953153625,
|
| 1854 |
+
"grad_norm": 30.512738174296523,
|
| 1855 |
+
"learning_rate": 1.4579992911531496e-07,
|
| 1856 |
+
"logits/chosen": -0.2525126338005066,
|
| 1857 |
+
"logits/rejected": -0.3065794110298157,
|
| 1858 |
+
"logps/chosen": -325.3319091796875,
|
| 1859 |
+
"logps/rejected": -288.85089111328125,
|
| 1860 |
+
"loss": 0.4406,
|
| 1861 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 1862 |
+
"rewards/chosen": 0.28674450516700745,
|
| 1863 |
+
"rewards/margins": 1.1190677881240845,
|
| 1864 |
+
"rewards/rejected": -0.8323231935501099,
|
| 1865 |
+
"step": 1110
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.3449358806595133,
|
| 1869 |
+
"grad_norm": 28.019655950524385,
|
| 1870 |
+
"learning_rate": 1.372918115787112e-07,
|
| 1871 |
+
"logits/chosen": -0.19494856894016266,
|
| 1872 |
+
"logits/rejected": -0.16709737479686737,
|
| 1873 |
+
"logps/chosen": -269.15802001953125,
|
| 1874 |
+
"logps/rejected": -281.6461486816406,
|
| 1875 |
+
"loss": 0.4203,
|
| 1876 |
+
"rewards/accuracies": 0.862500011920929,
|
| 1877 |
+
"rewards/chosen": 0.2475571632385254,
|
| 1878 |
+
"rewards/margins": 1.078798770904541,
|
| 1879 |
+
"rewards/rejected": -0.8312416076660156,
|
| 1880 |
+
"step": 1120
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.3658728081654017,
|
| 1884 |
+
"grad_norm": 30.412163422048742,
|
| 1885 |
+
"learning_rate": 1.289998058253297e-07,
|
| 1886 |
+
"logits/chosen": -0.30280619859695435,
|
| 1887 |
+
"logits/rejected": -0.23964910209178925,
|
| 1888 |
+
"logps/chosen": -300.67291259765625,
|
| 1889 |
+
"logps/rejected": -286.5229187011719,
|
| 1890 |
+
"loss": 0.4429,
|
| 1891 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 1892 |
+
"rewards/chosen": 0.10387909412384033,
|
| 1893 |
+
"rewards/margins": 0.9766238331794739,
|
| 1894 |
+
"rewards/rejected": -0.8727447390556335,
|
| 1895 |
+
"step": 1130
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 2.38680973567129,
|
| 1899 |
+
"grad_norm": 26.079069616215104,
|
| 1900 |
+
"learning_rate": 1.209288524664029e-07,
|
| 1901 |
+
"logits/chosen": -0.09895231574773788,
|
| 1902 |
+
"logits/rejected": -0.04007222130894661,
|
| 1903 |
+
"logps/chosen": -295.33795166015625,
|
| 1904 |
+
"logps/rejected": -295.7159118652344,
|
| 1905 |
+
"loss": 0.4524,
|
| 1906 |
+
"rewards/accuracies": 0.8125,
|
| 1907 |
+
"rewards/chosen": 0.3174125850200653,
|
| 1908 |
+
"rewards/margins": 1.068551778793335,
|
| 1909 |
+
"rewards/rejected": -0.7511391639709473,
|
| 1910 |
+
"step": 1140
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 2.407746663177179,
|
| 1914 |
+
"grad_norm": 35.04317303338736,
|
| 1915 |
+
"learning_rate": 1.1308376040390344e-07,
|
| 1916 |
+
"logits/chosen": -0.2176963984966278,
|
| 1917 |
+
"logits/rejected": -0.2429191619157791,
|
| 1918 |
+
"logps/chosen": -268.51568603515625,
|
| 1919 |
+
"logps/rejected": -243.83602905273438,
|
| 1920 |
+
"loss": 0.4648,
|
| 1921 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1922 |
+
"rewards/chosen": 0.1225685253739357,
|
| 1923 |
+
"rewards/margins": 0.8287593722343445,
|
| 1924 |
+
"rewards/rejected": -0.7061909437179565,
|
| 1925 |
+
"step": 1150
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 2.4286835906830673,
|
| 1929 |
+
"grad_norm": 27.071258876733747,
|
| 1930 |
+
"learning_rate": 1.0546920396526382e-07,
|
| 1931 |
+
"logits/chosen": -0.05287874490022659,
|
| 1932 |
+
"logits/rejected": -0.08571253716945648,
|
| 1933 |
+
"logps/chosen": -345.3739013671875,
|
| 1934 |
+
"logps/rejected": -296.2100524902344,
|
| 1935 |
+
"loss": 0.4248,
|
| 1936 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1937 |
+
"rewards/chosen": 0.31707775592803955,
|
| 1938 |
+
"rewards/margins": 1.1236298084259033,
|
| 1939 |
+
"rewards/rejected": -0.8065520524978638,
|
| 1940 |
+
"step": 1160
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 2.4496205181889557,
|
| 1944 |
+
"grad_norm": 30.813022693471254,
|
| 1945 |
+
"learning_rate": 9.808972011828054e-08,
|
| 1946 |
+
"logits/chosen": -0.07085756957530975,
|
| 1947 |
+
"logits/rejected": -0.1990344077348709,
|
| 1948 |
+
"logps/chosen": -342.7474060058594,
|
| 1949 |
+
"logps/rejected": -266.599609375,
|
| 1950 |
+
"loss": 0.4366,
|
| 1951 |
+
"rewards/accuracies": 0.831250011920929,
|
| 1952 |
+
"rewards/chosen": 0.2785649299621582,
|
| 1953 |
+
"rewards/margins": 1.1454359292984009,
|
| 1954 |
+
"rewards/rejected": -0.8668708801269531,
|
| 1955 |
+
"step": 1170
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 2.470557445694844,
|
| 1959 |
+
"grad_norm": 28.23769321193845,
|
| 1960 |
+
"learning_rate": 9.094970576786032e-08,
|
| 1961 |
+
"logits/chosen": 0.02408856526017189,
|
| 1962 |
+
"logits/rejected": -0.0395381897687912,
|
| 1963 |
+
"logps/chosen": -267.3003234863281,
|
| 1964 |
+
"logps/rejected": -249.65158081054688,
|
| 1965 |
+
"loss": 0.4323,
|
| 1966 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1967 |
+
"rewards/chosen": 0.17695440351963043,
|
| 1968 |
+
"rewards/margins": 1.0320888757705688,
|
| 1969 |
+
"rewards/rejected": -0.8551343679428101,
|
| 1970 |
+
"step": 1180
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.491494373200733,
|
| 1974 |
+
"grad_norm": 30.361270294186127,
|
| 1975 |
+
"learning_rate": 8.405341513622055e-08,
|
| 1976 |
+
"logits/chosen": -0.16236011683940887,
|
| 1977 |
+
"logits/rejected": -0.20971974730491638,
|
| 1978 |
+
"logps/chosen": -324.1960754394531,
|
| 1979 |
+
"logps/rejected": -260.82647705078125,
|
| 1980 |
+
"loss": 0.4368,
|
| 1981 |
+
"rewards/accuracies": 0.831250011920929,
|
| 1982 |
+
"rewards/chosen": 0.3019522428512573,
|
| 1983 |
+
"rewards/margins": 0.9704391360282898,
|
| 1984 |
+
"rewards/rejected": -0.6684868931770325,
|
| 1985 |
+
"step": 1190
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 2.5124313007066212,
|
| 1989 |
+
"grad_norm": 29.87892753836197,
|
| 1990 |
+
"learning_rate": 7.740495722810269e-08,
|
| 1991 |
+
"logits/chosen": -0.1393619179725647,
|
| 1992 |
+
"logits/rejected": -0.17410680651664734,
|
| 1993 |
+
"logps/chosen": -275.013427734375,
|
| 1994 |
+
"logps/rejected": -218.1080322265625,
|
| 1995 |
+
"loss": 0.4462,
|
| 1996 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1997 |
+
"rewards/chosen": 0.1310921609401703,
|
| 1998 |
+
"rewards/margins": 0.8609299659729004,
|
| 1999 |
+
"rewards/rejected": -0.7298377156257629,
|
| 2000 |
+
"step": 1200
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 2.5124313007066212,
|
| 2004 |
+
"eval_logits/chosen": -0.34315019845962524,
|
| 2005 |
+
"eval_logits/rejected": -0.37096092104911804,
|
| 2006 |
+
"eval_logps/chosen": -310.3815612792969,
|
| 2007 |
+
"eval_logps/rejected": -275.54351806640625,
|
| 2008 |
+
"eval_loss": 0.589375913143158,
|
| 2009 |
+
"eval_rewards/accuracies": 0.7023809552192688,
|
| 2010 |
+
"eval_rewards/chosen": -0.04855651780962944,
|
| 2011 |
+
"eval_rewards/margins": 0.5814378261566162,
|
| 2012 |
+
"eval_rewards/rejected": -0.6299943923950195,
|
| 2013 |
+
"eval_runtime": 19.1944,
|
| 2014 |
+
"eval_samples_per_second": 104.197,
|
| 2015 |
+
"eval_steps_per_second": 3.282,
|
| 2016 |
+
"step": 1200
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 2.5333682282125096,
|
| 2020 |
+
"grad_norm": 30.713812818544117,
|
| 2021 |
+
"learning_rate": 7.100829338251146e-08,
|
| 2022 |
+
"logits/chosen": -0.10057993978261948,
|
| 2023 |
+
"logits/rejected": -0.16287049651145935,
|
| 2024 |
+
"logps/chosen": -328.2908935546875,
|
| 2025 |
+
"logps/rejected": -289.701904296875,
|
| 2026 |
+
"loss": 0.4416,
|
| 2027 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 2028 |
+
"rewards/chosen": 0.3149394094944,
|
| 2029 |
+
"rewards/margins": 1.1269749402999878,
|
| 2030 |
+
"rewards/rejected": -0.8120356798171997,
|
| 2031 |
+
"step": 1210
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 2.5543051557183984,
|
| 2035 |
+
"grad_norm": 32.721460368023834,
|
| 2036 |
+
"learning_rate": 6.486723491243778e-08,
|
| 2037 |
+
"logits/chosen": -0.14739738404750824,
|
| 2038 |
+
"logits/rejected": -0.1756991297006607,
|
| 2039 |
+
"logps/chosen": -287.8624572753906,
|
| 2040 |
+
"logps/rejected": -264.6856994628906,
|
| 2041 |
+
"loss": 0.4523,
|
| 2042 |
+
"rewards/accuracies": 0.862500011920929,
|
| 2043 |
+
"rewards/chosen": 0.20502778887748718,
|
| 2044 |
+
"rewards/margins": 0.9769600033760071,
|
| 2045 |
+
"rewards/rejected": -0.7719322443008423,
|
| 2046 |
+
"step": 1220
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 2.575242083224287,
|
| 2050 |
+
"grad_norm": 32.50553549993069,
|
| 2051 |
+
"learning_rate": 5.898544083397e-08,
|
| 2052 |
+
"logits/chosen": -0.12704332172870636,
|
| 2053 |
+
"logits/rejected": -0.1398163139820099,
|
| 2054 |
+
"logps/chosen": -319.8119201660156,
|
| 2055 |
+
"logps/rejected": -287.4822082519531,
|
| 2056 |
+
"loss": 0.4467,
|
| 2057 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 2058 |
+
"rewards/chosen": 0.2838557958602905,
|
| 2059 |
+
"rewards/margins": 1.0057270526885986,
|
| 2060 |
+
"rewards/rejected": -0.7218713164329529,
|
| 2061 |
+
"step": 1230
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.596179010730175,
|
| 2065 |
+
"grad_norm": 30.599102169827287,
|
| 2066 |
+
"learning_rate": 5.3366415686149137e-08,
|
| 2067 |
+
"logits/chosen": -0.1681247055530548,
|
| 2068 |
+
"logits/rejected": -0.15492555499076843,
|
| 2069 |
+
"logps/chosen": -248.78054809570312,
|
| 2070 |
+
"logps/rejected": -238.68106079101562,
|
| 2071 |
+
"loss": 0.4368,
|
| 2072 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2073 |
+
"rewards/chosen": 0.10712571442127228,
|
| 2074 |
+
"rewards/margins": 0.8596469759941101,
|
| 2075 |
+
"rewards/rejected": -0.7525211572647095,
|
| 2076 |
+
"step": 1240
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 2.617115938236064,
|
| 2080 |
+
"grad_norm": 31.156979603329955,
|
| 2081 |
+
"learning_rate": 4.8013507442865585e-08,
|
| 2082 |
+
"logits/chosen": -0.19022394716739655,
|
| 2083 |
+
"logits/rejected": -0.10595899820327759,
|
| 2084 |
+
"logps/chosen": -271.9454345703125,
|
| 2085 |
+
"logps/rejected": -274.1131286621094,
|
| 2086 |
+
"loss": 0.4319,
|
| 2087 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2088 |
+
"rewards/chosen": 0.17164357006549835,
|
| 2089 |
+
"rewards/margins": 0.7940610647201538,
|
| 2090 |
+
"rewards/rejected": -0.6224175095558167,
|
| 2091 |
+
"step": 1250
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 2.6380528657419524,
|
| 2095 |
+
"grad_norm": 28.881054799580607,
|
| 2096 |
+
"learning_rate": 4.292990551804171e-08,
|
| 2097 |
+
"logits/chosen": -0.08757440745830536,
|
| 2098 |
+
"logits/rejected": -0.08349265158176422,
|
| 2099 |
+
"logps/chosen": -287.8446350097656,
|
| 2100 |
+
"logps/rejected": -251.55636596679688,
|
| 2101 |
+
"loss": 0.4229,
|
| 2102 |
+
"rewards/accuracies": 0.793749988079071,
|
| 2103 |
+
"rewards/chosen": 0.27148956060409546,
|
| 2104 |
+
"rewards/margins": 1.0949037075042725,
|
| 2105 |
+
"rewards/rejected": -0.8234142065048218,
|
| 2106 |
+
"step": 1260
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 2.658989793247841,
|
| 2110 |
+
"grad_norm": 27.816379754479705,
|
| 2111 |
+
"learning_rate": 3.811863886528882e-08,
|
| 2112 |
+
"logits/chosen": -0.05129946395754814,
|
| 2113 |
+
"logits/rejected": -0.07520854473114014,
|
| 2114 |
+
"logps/chosen": -320.88092041015625,
|
| 2115 |
+
"logps/rejected": -259.69488525390625,
|
| 2116 |
+
"loss": 0.4403,
|
| 2117 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2118 |
+
"rewards/chosen": 0.1268620789051056,
|
| 2119 |
+
"rewards/margins": 0.9729422330856323,
|
| 2120 |
+
"rewards/rejected": -0.8460801839828491,
|
| 2121 |
+
"step": 1270
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 2.6799267207537296,
|
| 2125 |
+
"grad_norm": 31.45496593116063,
|
| 2126 |
+
"learning_rate": 3.358257417317095e-08,
|
| 2127 |
+
"logits/chosen": -0.08449853211641312,
|
| 2128 |
+
"logits/rejected": -0.1029936671257019,
|
| 2129 |
+
"logps/chosen": -288.6929016113281,
|
| 2130 |
+
"logps/rejected": -251.7803192138672,
|
| 2131 |
+
"loss": 0.4427,
|
| 2132 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2133 |
+
"rewards/chosen": 0.18886741995811462,
|
| 2134 |
+
"rewards/margins": 0.9686278104782104,
|
| 2135 |
+
"rewards/rejected": -0.779760479927063,
|
| 2136 |
+
"step": 1280
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 2.700863648259618,
|
| 2140 |
+
"grad_norm": 29.618711306226224,
|
| 2141 |
+
"learning_rate": 2.9324414157151367e-08,
|
| 2142 |
+
"logits/chosen": -0.1431390345096588,
|
| 2143 |
+
"logits/rejected": -0.10319207608699799,
|
| 2144 |
+
"logps/chosen": -265.52508544921875,
|
| 2145 |
+
"logps/rejected": -260.0169677734375,
|
| 2146 |
+
"loss": 0.4661,
|
| 2147 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2148 |
+
"rewards/chosen": 0.10996869951486588,
|
| 2149 |
+
"rewards/margins": 0.7998045682907104,
|
| 2150 |
+
"rewards/rejected": -0.6898358464241028,
|
| 2151 |
+
"step": 1290
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 2.7218005757655064,
|
| 2155 |
+
"grad_norm": 30.57983222127276,
|
| 2156 |
+
"learning_rate": 2.5346695949237717e-08,
|
| 2157 |
+
"logits/chosen": -0.1215812936425209,
|
| 2158 |
+
"logits/rejected": -0.1575727015733719,
|
| 2159 |
+
"logps/chosen": -285.28839111328125,
|
| 2160 |
+
"logps/rejected": -258.9991455078125,
|
| 2161 |
+
"loss": 0.4312,
|
| 2162 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 2163 |
+
"rewards/chosen": 0.16850288212299347,
|
| 2164 |
+
"rewards/margins": 0.923494815826416,
|
| 2165 |
+
"rewards/rejected": -0.7549919486045837,
|
| 2166 |
+
"step": 1300
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.7218005757655064,
|
| 2170 |
+
"eval_logits/chosen": -0.3442156910896301,
|
| 2171 |
+
"eval_logits/rejected": -0.37236616015434265,
|
| 2172 |
+
"eval_logps/chosen": -310.4347229003906,
|
| 2173 |
+
"eval_logps/rejected": -275.5621337890625,
|
| 2174 |
+
"eval_loss": 0.5860841870307922,
|
| 2175 |
+
"eval_rewards/accuracies": 0.6666666865348816,
|
| 2176 |
+
"eval_rewards/chosen": -0.07512283325195312,
|
| 2177 |
+
"eval_rewards/margins": 0.5641648769378662,
|
| 2178 |
+
"eval_rewards/rejected": -0.6392877101898193,
|
| 2179 |
+
"eval_runtime": 18.9961,
|
| 2180 |
+
"eval_samples_per_second": 105.285,
|
| 2181 |
+
"eval_steps_per_second": 3.316,
|
| 2182 |
+
"step": 1300
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 2.7427375032713948,
|
| 2186 |
+
"grad_norm": 33.466317771235126,
|
| 2187 |
+
"learning_rate": 2.165178958628744e-08,
|
| 2188 |
+
"logits/chosen": -0.2976987659931183,
|
| 2189 |
+
"logits/rejected": -0.2995850145816803,
|
| 2190 |
+
"logps/chosen": -273.274658203125,
|
| 2191 |
+
"logps/rejected": -265.376953125,
|
| 2192 |
+
"loss": 0.4557,
|
| 2193 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 2194 |
+
"rewards/chosen": 0.248153418302536,
|
| 2195 |
+
"rewards/margins": 0.9688236117362976,
|
| 2196 |
+
"rewards/rejected": -0.720670223236084,
|
| 2197 |
+
"step": 1310
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 2.7636744307772836,
|
| 2201 |
+
"grad_norm": 34.66631251738303,
|
| 2202 |
+
"learning_rate": 1.824189659787284e-08,
|
| 2203 |
+
"logits/chosen": -0.10840437561273575,
|
| 2204 |
+
"logits/rejected": -0.2128714621067047,
|
| 2205 |
+
"logps/chosen": -305.4066162109375,
|
| 2206 |
+
"logps/rejected": -265.4433288574219,
|
| 2207 |
+
"loss": 0.4569,
|
| 2208 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2209 |
+
"rewards/chosen": 0.2427886724472046,
|
| 2210 |
+
"rewards/margins": 0.9924157857894897,
|
| 2211 |
+
"rewards/rejected": -0.7496271133422852,
|
| 2212 |
+
"step": 1320
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 2.784611358283172,
|
| 2216 |
+
"grad_norm": 32.12579125137935,
|
| 2217 |
+
"learning_rate": 1.511904869454772e-08,
|
| 2218 |
+
"logits/chosen": -0.2719363570213318,
|
| 2219 |
+
"logits/rejected": -0.282664954662323,
|
| 2220 |
+
"logps/chosen": -258.68927001953125,
|
| 2221 |
+
"logps/rejected": -247.0824737548828,
|
| 2222 |
+
"loss": 0.4442,
|
| 2223 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2224 |
+
"rewards/chosen": 0.14507904648780823,
|
| 2225 |
+
"rewards/margins": 0.9792217016220093,
|
| 2226 |
+
"rewards/rejected": -0.8341425657272339,
|
| 2227 |
+
"step": 1330
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 2.8055482857890603,
|
| 2231 |
+
"grad_norm": 30.777443115008786,
|
| 2232 |
+
"learning_rate": 1.2285106557296476e-08,
|
| 2233 |
+
"logits/chosen": -0.005404007621109486,
|
| 2234 |
+
"logits/rejected": -0.11788828670978546,
|
| 2235 |
+
"logps/chosen": -291.2290954589844,
|
| 2236 |
+
"logps/rejected": -259.48468017578125,
|
| 2237 |
+
"loss": 0.4343,
|
| 2238 |
+
"rewards/accuracies": 0.856249988079071,
|
| 2239 |
+
"rewards/chosen": 0.14346763491630554,
|
| 2240 |
+
"rewards/margins": 0.9186245203018188,
|
| 2241 |
+
"rewards/rejected": -0.7751568555831909,
|
| 2242 |
+
"step": 1340
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 2.8264852132949487,
|
| 2246 |
+
"grad_norm": 30.795896785948266,
|
| 2247 |
+
"learning_rate": 9.741758728888217e-09,
|
| 2248 |
+
"logits/chosen": -0.21444204449653625,
|
| 2249 |
+
"logits/rejected": -0.22242781519889832,
|
| 2250 |
+
"logps/chosen": -273.7785949707031,
|
| 2251 |
+
"logps/rejected": -255.1972198486328,
|
| 2252 |
+
"loss": 0.4474,
|
| 2253 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2254 |
+
"rewards/chosen": 0.1873357743024826,
|
| 2255 |
+
"rewards/margins": 0.925756573677063,
|
| 2256 |
+
"rewards/rejected": -0.7384207844734192,
|
| 2257 |
+
"step": 1350
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.8474221408008376,
|
| 2261 |
+
"grad_norm": 32.2751606467674,
|
| 2262 |
+
"learning_rate": 7.490520607794981e-09,
|
| 2263 |
+
"logits/chosen": -0.23268666863441467,
|
| 2264 |
+
"logits/rejected": -0.24138864874839783,
|
| 2265 |
+
"logps/chosen": -321.114990234375,
|
| 2266 |
+
"logps/rejected": -286.67596435546875,
|
| 2267 |
+
"loss": 0.4185,
|
| 2268 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2269 |
+
"rewards/chosen": 0.2826289236545563,
|
| 2270 |
+
"rewards/margins": 1.1657564640045166,
|
| 2271 |
+
"rewards/rejected": -0.8831275701522827,
|
| 2272 |
+
"step": 1360
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 2.868359068306726,
|
| 2276 |
+
"grad_norm": 35.16124310393445,
|
| 2277 |
+
"learning_rate": 5.532733545274781e-09,
|
| 2278 |
+
"logits/chosen": -0.15783634781837463,
|
| 2279 |
+
"logits/rejected": -0.04948469251394272,
|
| 2280 |
+
"logps/chosen": -257.70880126953125,
|
| 2281 |
+
"logps/rejected": -257.0361633300781,
|
| 2282 |
+
"loss": 0.4388,
|
| 2283 |
+
"rewards/accuracies": 0.78125,
|
| 2284 |
+
"rewards/chosen": 0.09304230660200119,
|
| 2285 |
+
"rewards/margins": 0.8344671130180359,
|
| 2286 |
+
"rewards/rejected": -0.7414248585700989,
|
| 2287 |
+
"step": 1370
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 2.8892959958126143,
|
| 2291 |
+
"grad_norm": 28.606615842220055,
|
| 2292 |
+
"learning_rate": 3.869564046156459e-09,
|
| 2293 |
+
"logits/chosen": -0.187531977891922,
|
| 2294 |
+
"logits/rejected": -0.3003791868686676,
|
| 2295 |
+
"logps/chosen": -326.945068359375,
|
| 2296 |
+
"logps/rejected": -275.7688903808594,
|
| 2297 |
+
"loss": 0.4474,
|
| 2298 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2299 |
+
"rewards/chosen": 0.3150181770324707,
|
| 2300 |
+
"rewards/margins": 0.9270998239517212,
|
| 2301 |
+
"rewards/rejected": -0.6120817065238953,
|
| 2302 |
+
"step": 1380
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 2.910232923318503,
|
| 2306 |
+
"grad_norm": 29.689707753715854,
|
| 2307 |
+
"learning_rate": 2.5020030738031052e-09,
|
| 2308 |
+
"logits/chosen": -0.06661088764667511,
|
| 2309 |
+
"logits/rejected": -0.03964465484023094,
|
| 2310 |
+
"logps/chosen": -326.2409973144531,
|
| 2311 |
+
"logps/rejected": -333.43048095703125,
|
| 2312 |
+
"loss": 0.4429,
|
| 2313 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 2314 |
+
"rewards/chosen": 0.26736724376678467,
|
| 2315 |
+
"rewards/margins": 1.0932358503341675,
|
| 2316 |
+
"rewards/rejected": -0.8258686065673828,
|
| 2317 |
+
"step": 1390
|
| 2318 |
+
},
|
| 2319 |
+
{
|
| 2320 |
+
"epoch": 2.9311698508243915,
|
| 2321 |
+
"grad_norm": 28.977571013449776,
|
| 2322 |
+
"learning_rate": 1.4308654596684177e-09,
|
| 2323 |
+
"logits/chosen": -0.11069446802139282,
|
| 2324 |
+
"logits/rejected": -0.20247487723827362,
|
| 2325 |
+
"logps/chosen": -306.44610595703125,
|
| 2326 |
+
"logps/rejected": -266.9939270019531,
|
| 2327 |
+
"loss": 0.4454,
|
| 2328 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 2329 |
+
"rewards/chosen": 0.33073872327804565,
|
| 2330 |
+
"rewards/margins": 1.0625050067901611,
|
| 2331 |
+
"rewards/rejected": -0.7317661046981812,
|
| 2332 |
+
"step": 1400
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 2.9311698508243915,
|
| 2336 |
+
"eval_logits/chosen": -0.34011754393577576,
|
| 2337 |
+
"eval_logits/rejected": -0.36805158853530884,
|
| 2338 |
+
"eval_logps/chosen": -310.2955627441406,
|
| 2339 |
+
"eval_logps/rejected": -275.4775085449219,
|
| 2340 |
+
"eval_loss": 0.5941523313522339,
|
| 2341 |
+
"eval_rewards/accuracies": 0.6944444179534912,
|
| 2342 |
+
"eval_rewards/chosen": -0.005565390922129154,
|
| 2343 |
+
"eval_rewards/margins": 0.591437041759491,
|
| 2344 |
+
"eval_rewards/rejected": -0.5970024466514587,
|
| 2345 |
+
"eval_runtime": 19.2489,
|
| 2346 |
+
"eval_samples_per_second": 103.902,
|
| 2347 |
+
"eval_steps_per_second": 3.273,
|
| 2348 |
+
"step": 1400
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.95210677833028,
|
| 2352 |
+
"grad_norm": 29.74874723420356,
|
| 2353 |
+
"learning_rate": 6.567894177967325e-10,
|
| 2354 |
+
"logits/chosen": -0.046352408826351166,
|
| 2355 |
+
"logits/rejected": -0.054122112691402435,
|
| 2356 |
+
"logps/chosen": -287.88287353515625,
|
| 2357 |
+
"logps/rejected": -262.4837646484375,
|
| 2358 |
+
"loss": 0.4161,
|
| 2359 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2360 |
+
"rewards/chosen": 0.250956654548645,
|
| 2361 |
+
"rewards/margins": 1.026626706123352,
|
| 2362 |
+
"rewards/rejected": -0.775670051574707,
|
| 2363 |
+
"step": 1410
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 2.9730437058361687,
|
| 2367 |
+
"grad_norm": 29.04099364011046,
|
| 2368 |
+
"learning_rate": 1.802361645573125e-10,
|
| 2369 |
+
"logits/chosen": -0.15342023968696594,
|
| 2370 |
+
"logits/rejected": -0.1559501588344574,
|
| 2371 |
+
"logps/chosen": -272.7152404785156,
|
| 2372 |
+
"logps/rejected": -269.2229919433594,
|
| 2373 |
+
"loss": 0.4192,
|
| 2374 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2375 |
+
"rewards/chosen": 0.05591464787721634,
|
| 2376 |
+
"rewards/margins": 1.0562889575958252,
|
| 2377 |
+
"rewards/rejected": -1.000374436378479,
|
| 2378 |
+
"step": 1420
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 2.993980633342057,
|
| 2382 |
+
"grad_norm": 30.18988447303673,
|
| 2383 |
+
"learning_rate": 1.4896438384481846e-12,
|
| 2384 |
+
"logits/chosen": -0.20836491882801056,
|
| 2385 |
+
"logits/rejected": -0.19784407317638397,
|
| 2386 |
+
"logps/chosen": -317.96209716796875,
|
| 2387 |
+
"logps/rejected": -302.5794982910156,
|
| 2388 |
+
"loss": 0.4315,
|
| 2389 |
+
"rewards/accuracies": 0.78125,
|
| 2390 |
+
"rewards/chosen": 0.22425825893878937,
|
| 2391 |
+
"rewards/margins": 0.8794215321540833,
|
| 2392 |
+
"rewards/rejected": -0.6551632285118103,
|
| 2393 |
+
"step": 1430
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 2.996074326092646,
|
| 2397 |
+
"step": 1431,
|
| 2398 |
+
"total_flos": 0.0,
|
| 2399 |
+
"train_loss": 0.5334697115221363,
|
| 2400 |
+
"train_runtime": 7355.3343,
|
| 2401 |
+
"train_samples_per_second": 24.935,
|
| 2402 |
+
"train_steps_per_second": 0.195
|
| 2403 |
+
}
|
| 2404 |
+
],
|
| 2405 |
+
"logging_steps": 10,
|
| 2406 |
+
"max_steps": 1431,
|
| 2407 |
+
"num_input_tokens_seen": 0,
|
| 2408 |
+
"num_train_epochs": 3,
|
| 2409 |
+
"save_steps": 500,
|
| 2410 |
+
"stateful_callbacks": {
|
| 2411 |
+
"TrainerControl": {
|
| 2412 |
+
"args": {
|
| 2413 |
+
"should_epoch_stop": false,
|
| 2414 |
+
"should_evaluate": false,
|
| 2415 |
+
"should_log": false,
|
| 2416 |
+
"should_save": false,
|
| 2417 |
+
"should_training_stop": false
|
| 2418 |
+
},
|
| 2419 |
+
"attributes": {}
|
| 2420 |
+
}
|
| 2421 |
+
},
|
| 2422 |
+
"total_flos": 0.0,
|
| 2423 |
+
"train_batch_size": 2,
|
| 2424 |
+
"trial_name": null,
|
| 2425 |
+
"trial_params": null
|
| 2426 |
+
}
|