Model save
Browse files- trainer_state.json +1561 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,1561 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 4233,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01771793054571226,
|
| 13 |
+
"grad_norm": 0.24673239886760712,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 3.8313,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03543586109142452,
|
| 20 |
+
"grad_norm": 0.23432838916778564,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 3.6164,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05315379163713678,
|
| 27 |
+
"grad_norm": 0.4262351393699646,
|
| 28 |
+
"learning_rate": 0.0001,
|
| 29 |
+
"loss": 3.4113,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07087172218284904,
|
| 34 |
+
"grad_norm": 0.329630047082901,
|
| 35 |
+
"learning_rate": 0.0001,
|
| 36 |
+
"loss": 3.1874,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07087172218284904,
|
| 41 |
+
"eval_loss": 3.0117650032043457,
|
| 42 |
+
"eval_runtime": 31.2497,
|
| 43 |
+
"eval_samples_per_second": 9.536,
|
| 44 |
+
"eval_steps_per_second": 2.4,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0885896527285613,
|
| 49 |
+
"grad_norm": 0.39532458782196045,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 3.0928,
|
| 52 |
+
"step": 125
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.10630758327427356,
|
| 56 |
+
"grad_norm": 0.38724836707115173,
|
| 57 |
+
"learning_rate": 0.0001,
|
| 58 |
+
"loss": 2.8781,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.12402551381998582,
|
| 63 |
+
"grad_norm": 0.2721017897129059,
|
| 64 |
+
"learning_rate": 0.0001,
|
| 65 |
+
"loss": 2.9166,
|
| 66 |
+
"step": 175
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.14174344436569808,
|
| 70 |
+
"grad_norm": 0.40747421979904175,
|
| 71 |
+
"learning_rate": 0.0001,
|
| 72 |
+
"loss": 2.8756,
|
| 73 |
+
"step": 200
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.14174344436569808,
|
| 77 |
+
"eval_loss": 2.822810411453247,
|
| 78 |
+
"eval_runtime": 32.4779,
|
| 79 |
+
"eval_samples_per_second": 9.175,
|
| 80 |
+
"eval_steps_per_second": 2.309,
|
| 81 |
+
"step": 200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.15946137491141035,
|
| 85 |
+
"grad_norm": 0.4922279119491577,
|
| 86 |
+
"learning_rate": 0.0001,
|
| 87 |
+
"loss": 2.9015,
|
| 88 |
+
"step": 225
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.1771793054571226,
|
| 92 |
+
"grad_norm": 0.3577287197113037,
|
| 93 |
+
"learning_rate": 0.0001,
|
| 94 |
+
"loss": 2.8639,
|
| 95 |
+
"step": 250
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.19489723600283487,
|
| 99 |
+
"grad_norm": 0.26928216218948364,
|
| 100 |
+
"learning_rate": 0.0001,
|
| 101 |
+
"loss": 2.6776,
|
| 102 |
+
"step": 275
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.21261516654854712,
|
| 106 |
+
"grad_norm": 0.3623720109462738,
|
| 107 |
+
"learning_rate": 0.0001,
|
| 108 |
+
"loss": 2.7134,
|
| 109 |
+
"step": 300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.21261516654854712,
|
| 113 |
+
"eval_loss": 2.735769271850586,
|
| 114 |
+
"eval_runtime": 32.6152,
|
| 115 |
+
"eval_samples_per_second": 9.137,
|
| 116 |
+
"eval_steps_per_second": 2.3,
|
| 117 |
+
"step": 300
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.2303330970942594,
|
| 121 |
+
"grad_norm": 0.48846569657325745,
|
| 122 |
+
"learning_rate": 0.0001,
|
| 123 |
+
"loss": 2.7118,
|
| 124 |
+
"step": 325
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.24805102763997164,
|
| 128 |
+
"grad_norm": 0.555242657661438,
|
| 129 |
+
"learning_rate": 0.0001,
|
| 130 |
+
"loss": 2.7072,
|
| 131 |
+
"step": 350
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.2657689581856839,
|
| 135 |
+
"grad_norm": 0.3421138823032379,
|
| 136 |
+
"learning_rate": 0.0001,
|
| 137 |
+
"loss": 2.7114,
|
| 138 |
+
"step": 375
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.28348688873139616,
|
| 142 |
+
"grad_norm": 0.3518970012664795,
|
| 143 |
+
"learning_rate": 0.0001,
|
| 144 |
+
"loss": 2.6948,
|
| 145 |
+
"step": 400
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.28348688873139616,
|
| 149 |
+
"eval_loss": 2.6832730770111084,
|
| 150 |
+
"eval_runtime": 32.6428,
|
| 151 |
+
"eval_samples_per_second": 9.129,
|
| 152 |
+
"eval_steps_per_second": 2.298,
|
| 153 |
+
"step": 400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.30120481927710846,
|
| 157 |
+
"grad_norm": 0.7523891925811768,
|
| 158 |
+
"learning_rate": 0.0001,
|
| 159 |
+
"loss": 2.7691,
|
| 160 |
+
"step": 425
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.3189227498228207,
|
| 164 |
+
"grad_norm": 0.36019715666770935,
|
| 165 |
+
"learning_rate": 0.0001,
|
| 166 |
+
"loss": 2.7116,
|
| 167 |
+
"step": 450
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.33664068036853295,
|
| 171 |
+
"grad_norm": 0.47855111956596375,
|
| 172 |
+
"learning_rate": 0.0001,
|
| 173 |
+
"loss": 2.5935,
|
| 174 |
+
"step": 475
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.3543586109142452,
|
| 178 |
+
"grad_norm": 0.3621235489845276,
|
| 179 |
+
"learning_rate": 0.0001,
|
| 180 |
+
"loss": 2.6386,
|
| 181 |
+
"step": 500
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3543586109142452,
|
| 185 |
+
"eval_loss": 2.6440742015838623,
|
| 186 |
+
"eval_runtime": 32.6151,
|
| 187 |
+
"eval_samples_per_second": 9.137,
|
| 188 |
+
"eval_steps_per_second": 2.3,
|
| 189 |
+
"step": 500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.3720765414599575,
|
| 193 |
+
"grad_norm": 0.6827765703201294,
|
| 194 |
+
"learning_rate": 0.0001,
|
| 195 |
+
"loss": 2.6515,
|
| 196 |
+
"step": 525
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.38979447200566975,
|
| 200 |
+
"grad_norm": 0.5584849119186401,
|
| 201 |
+
"learning_rate": 0.0001,
|
| 202 |
+
"loss": 2.7017,
|
| 203 |
+
"step": 550
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.407512402551382,
|
| 207 |
+
"grad_norm": 0.42108777165412903,
|
| 208 |
+
"learning_rate": 0.0001,
|
| 209 |
+
"loss": 2.6605,
|
| 210 |
+
"step": 575
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.42523033309709424,
|
| 214 |
+
"grad_norm": 0.4811398684978485,
|
| 215 |
+
"learning_rate": 0.0001,
|
| 216 |
+
"loss": 2.6525,
|
| 217 |
+
"step": 600
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.42523033309709424,
|
| 221 |
+
"eval_loss": 2.6149747371673584,
|
| 222 |
+
"eval_runtime": 32.6256,
|
| 223 |
+
"eval_samples_per_second": 9.134,
|
| 224 |
+
"eval_steps_per_second": 2.299,
|
| 225 |
+
"step": 600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.44294826364280654,
|
| 229 |
+
"grad_norm": 0.3859870731830597,
|
| 230 |
+
"learning_rate": 0.0001,
|
| 231 |
+
"loss": 2.6805,
|
| 232 |
+
"step": 625
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.4606661941885188,
|
| 236 |
+
"grad_norm": 0.5074867010116577,
|
| 237 |
+
"learning_rate": 0.0001,
|
| 238 |
+
"loss": 2.66,
|
| 239 |
+
"step": 650
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.47838412473423103,
|
| 243 |
+
"grad_norm": 0.4459812343120575,
|
| 244 |
+
"learning_rate": 0.0001,
|
| 245 |
+
"loss": 2.645,
|
| 246 |
+
"step": 675
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.4961020552799433,
|
| 250 |
+
"grad_norm": 0.3960532248020172,
|
| 251 |
+
"learning_rate": 0.0001,
|
| 252 |
+
"loss": 2.6242,
|
| 253 |
+
"step": 700
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.4961020552799433,
|
| 257 |
+
"eval_loss": 2.5855672359466553,
|
| 258 |
+
"eval_runtime": 32.5667,
|
| 259 |
+
"eval_samples_per_second": 9.15,
|
| 260 |
+
"eval_steps_per_second": 2.303,
|
| 261 |
+
"step": 700
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5138199858256556,
|
| 265 |
+
"grad_norm": 0.28771647810935974,
|
| 266 |
+
"learning_rate": 0.0001,
|
| 267 |
+
"loss": 2.6985,
|
| 268 |
+
"step": 725
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5315379163713678,
|
| 272 |
+
"grad_norm": 0.3489636182785034,
|
| 273 |
+
"learning_rate": 0.0001,
|
| 274 |
+
"loss": 2.7126,
|
| 275 |
+
"step": 750
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5492558469170801,
|
| 279 |
+
"grad_norm": 0.5809263586997986,
|
| 280 |
+
"learning_rate": 0.0001,
|
| 281 |
+
"loss": 2.558,
|
| 282 |
+
"step": 775
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5669737774627923,
|
| 286 |
+
"grad_norm": 0.5202405452728271,
|
| 287 |
+
"learning_rate": 0.0001,
|
| 288 |
+
"loss": 2.6444,
|
| 289 |
+
"step": 800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5669737774627923,
|
| 293 |
+
"eval_loss": 2.5701286792755127,
|
| 294 |
+
"eval_runtime": 32.5138,
|
| 295 |
+
"eval_samples_per_second": 9.165,
|
| 296 |
+
"eval_steps_per_second": 2.307,
|
| 297 |
+
"step": 800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5846917080085046,
|
| 301 |
+
"grad_norm": 0.4100205600261688,
|
| 302 |
+
"learning_rate": 0.0001,
|
| 303 |
+
"loss": 2.5452,
|
| 304 |
+
"step": 825
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.6024096385542169,
|
| 308 |
+
"grad_norm": 0.494243323802948,
|
| 309 |
+
"learning_rate": 0.0001,
|
| 310 |
+
"loss": 2.566,
|
| 311 |
+
"step": 850
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.6201275690999292,
|
| 315 |
+
"grad_norm": 0.41979244351387024,
|
| 316 |
+
"learning_rate": 0.0001,
|
| 317 |
+
"loss": 2.6271,
|
| 318 |
+
"step": 875
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6378454996456414,
|
| 322 |
+
"grad_norm": 0.4423984885215759,
|
| 323 |
+
"learning_rate": 0.0001,
|
| 324 |
+
"loss": 2.6007,
|
| 325 |
+
"step": 900
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6378454996456414,
|
| 329 |
+
"eval_loss": 2.554037094116211,
|
| 330 |
+
"eval_runtime": 32.562,
|
| 331 |
+
"eval_samples_per_second": 9.152,
|
| 332 |
+
"eval_steps_per_second": 2.303,
|
| 333 |
+
"step": 900
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.6555634301913537,
|
| 337 |
+
"grad_norm": 0.49124300479888916,
|
| 338 |
+
"learning_rate": 0.0001,
|
| 339 |
+
"loss": 2.6006,
|
| 340 |
+
"step": 925
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.6732813607370659,
|
| 344 |
+
"grad_norm": 0.4179531931877136,
|
| 345 |
+
"learning_rate": 0.0001,
|
| 346 |
+
"loss": 2.634,
|
| 347 |
+
"step": 950
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.6909992912827781,
|
| 351 |
+
"grad_norm": 0.35822227597236633,
|
| 352 |
+
"learning_rate": 0.0001,
|
| 353 |
+
"loss": 2.5601,
|
| 354 |
+
"step": 975
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.7087172218284904,
|
| 358 |
+
"grad_norm": 0.44015607237815857,
|
| 359 |
+
"learning_rate": 0.0001,
|
| 360 |
+
"loss": 2.462,
|
| 361 |
+
"step": 1000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.7087172218284904,
|
| 365 |
+
"eval_loss": 2.5418050289154053,
|
| 366 |
+
"eval_runtime": 32.5949,
|
| 367 |
+
"eval_samples_per_second": 9.143,
|
| 368 |
+
"eval_steps_per_second": 2.301,
|
| 369 |
+
"step": 1000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.7264351523742026,
|
| 373 |
+
"grad_norm": 0.3899957835674286,
|
| 374 |
+
"learning_rate": 0.0001,
|
| 375 |
+
"loss": 2.538,
|
| 376 |
+
"step": 1025
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.744153082919915,
|
| 380 |
+
"grad_norm": 0.5775083303451538,
|
| 381 |
+
"learning_rate": 0.0001,
|
| 382 |
+
"loss": 2.5553,
|
| 383 |
+
"step": 1050
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.7618710134656272,
|
| 387 |
+
"grad_norm": 0.6485064625740051,
|
| 388 |
+
"learning_rate": 0.0001,
|
| 389 |
+
"loss": 2.5878,
|
| 390 |
+
"step": 1075
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.7795889440113395,
|
| 394 |
+
"grad_norm": 0.5756754875183105,
|
| 395 |
+
"learning_rate": 0.0001,
|
| 396 |
+
"loss": 2.5641,
|
| 397 |
+
"step": 1100
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.7795889440113395,
|
| 401 |
+
"eval_loss": 2.5314512252807617,
|
| 402 |
+
"eval_runtime": 32.673,
|
| 403 |
+
"eval_samples_per_second": 9.121,
|
| 404 |
+
"eval_steps_per_second": 2.295,
|
| 405 |
+
"step": 1100
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.7973068745570517,
|
| 409 |
+
"grad_norm": 0.46359655261039734,
|
| 410 |
+
"learning_rate": 0.0001,
|
| 411 |
+
"loss": 2.5062,
|
| 412 |
+
"step": 1125
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.815024805102764,
|
| 416 |
+
"grad_norm": 0.6569529175758362,
|
| 417 |
+
"learning_rate": 0.0001,
|
| 418 |
+
"loss": 2.5921,
|
| 419 |
+
"step": 1150
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.8327427356484762,
|
| 423 |
+
"grad_norm": 0.5323280096054077,
|
| 424 |
+
"learning_rate": 0.0001,
|
| 425 |
+
"loss": 2.4839,
|
| 426 |
+
"step": 1175
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.8504606661941885,
|
| 430 |
+
"grad_norm": 0.46269166469573975,
|
| 431 |
+
"learning_rate": 0.0001,
|
| 432 |
+
"loss": 2.4672,
|
| 433 |
+
"step": 1200
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.8504606661941885,
|
| 437 |
+
"eval_loss": 2.5238418579101562,
|
| 438 |
+
"eval_runtime": 32.6451,
|
| 439 |
+
"eval_samples_per_second": 9.128,
|
| 440 |
+
"eval_steps_per_second": 2.297,
|
| 441 |
+
"step": 1200
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.8681785967399008,
|
| 445 |
+
"grad_norm": 0.4144786596298218,
|
| 446 |
+
"learning_rate": 0.0001,
|
| 447 |
+
"loss": 2.5174,
|
| 448 |
+
"step": 1225
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.8858965272856131,
|
| 452 |
+
"grad_norm": 0.6366602182388306,
|
| 453 |
+
"learning_rate": 0.0001,
|
| 454 |
+
"loss": 2.512,
|
| 455 |
+
"step": 1250
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.9036144578313253,
|
| 459 |
+
"grad_norm": 0.490589439868927,
|
| 460 |
+
"learning_rate": 0.0001,
|
| 461 |
+
"loss": 2.5243,
|
| 462 |
+
"step": 1275
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.9213323883770376,
|
| 466 |
+
"grad_norm": 0.5880224108695984,
|
| 467 |
+
"learning_rate": 0.0001,
|
| 468 |
+
"loss": 2.5017,
|
| 469 |
+
"step": 1300
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.9213323883770376,
|
| 473 |
+
"eval_loss": 2.51455020904541,
|
| 474 |
+
"eval_runtime": 32.6422,
|
| 475 |
+
"eval_samples_per_second": 9.129,
|
| 476 |
+
"eval_steps_per_second": 2.298,
|
| 477 |
+
"step": 1300
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.9390503189227498,
|
| 481 |
+
"grad_norm": 0.5042569637298584,
|
| 482 |
+
"learning_rate": 0.0001,
|
| 483 |
+
"loss": 2.5238,
|
| 484 |
+
"step": 1325
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.9567682494684621,
|
| 488 |
+
"grad_norm": 0.3827306032180786,
|
| 489 |
+
"learning_rate": 0.0001,
|
| 490 |
+
"loss": 2.5785,
|
| 491 |
+
"step": 1350
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.9744861800141743,
|
| 495 |
+
"grad_norm": 0.4069231450557709,
|
| 496 |
+
"learning_rate": 0.0001,
|
| 497 |
+
"loss": 2.5312,
|
| 498 |
+
"step": 1375
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.9922041105598866,
|
| 502 |
+
"grad_norm": 0.5515998005867004,
|
| 503 |
+
"learning_rate": 0.0001,
|
| 504 |
+
"loss": 2.6389,
|
| 505 |
+
"step": 1400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.9922041105598866,
|
| 509 |
+
"eval_loss": 2.5082926750183105,
|
| 510 |
+
"eval_runtime": 32.6146,
|
| 511 |
+
"eval_samples_per_second": 9.137,
|
| 512 |
+
"eval_steps_per_second": 2.3,
|
| 513 |
+
"step": 1400
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.009922041105599,
|
| 517 |
+
"grad_norm": 0.34569019079208374,
|
| 518 |
+
"learning_rate": 0.0001,
|
| 519 |
+
"loss": 2.4996,
|
| 520 |
+
"step": 1425
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.0276399716513112,
|
| 524 |
+
"grad_norm": 0.4051329493522644,
|
| 525 |
+
"learning_rate": 0.0001,
|
| 526 |
+
"loss": 2.4935,
|
| 527 |
+
"step": 1450
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.0453579021970234,
|
| 531 |
+
"grad_norm": 0.5617458820343018,
|
| 532 |
+
"learning_rate": 0.0001,
|
| 533 |
+
"loss": 2.5528,
|
| 534 |
+
"step": 1475
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.0630758327427356,
|
| 538 |
+
"grad_norm": 0.7300685048103333,
|
| 539 |
+
"learning_rate": 0.0001,
|
| 540 |
+
"loss": 2.4869,
|
| 541 |
+
"step": 1500
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0630758327427356,
|
| 545 |
+
"eval_loss": 2.502122640609741,
|
| 546 |
+
"eval_runtime": 32.6521,
|
| 547 |
+
"eval_samples_per_second": 9.127,
|
| 548 |
+
"eval_steps_per_second": 2.297,
|
| 549 |
+
"step": 1500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.080793763288448,
|
| 553 |
+
"grad_norm": 0.3424386978149414,
|
| 554 |
+
"learning_rate": 0.0001,
|
| 555 |
+
"loss": 2.5036,
|
| 556 |
+
"step": 1525
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0985116938341601,
|
| 560 |
+
"grad_norm": 0.48358920216560364,
|
| 561 |
+
"learning_rate": 0.0001,
|
| 562 |
+
"loss": 2.4546,
|
| 563 |
+
"step": 1550
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.1162296243798724,
|
| 567 |
+
"grad_norm": 0.620297372341156,
|
| 568 |
+
"learning_rate": 0.0001,
|
| 569 |
+
"loss": 2.4505,
|
| 570 |
+
"step": 1575
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.1339475549255846,
|
| 574 |
+
"grad_norm": 0.41402992606163025,
|
| 575 |
+
"learning_rate": 0.0001,
|
| 576 |
+
"loss": 2.5302,
|
| 577 |
+
"step": 1600
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.1339475549255846,
|
| 581 |
+
"eval_loss": 2.4941623210906982,
|
| 582 |
+
"eval_runtime": 32.6717,
|
| 583 |
+
"eval_samples_per_second": 9.121,
|
| 584 |
+
"eval_steps_per_second": 2.296,
|
| 585 |
+
"step": 1600
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.1516654854712969,
|
| 589 |
+
"grad_norm": 0.6208804249763489,
|
| 590 |
+
"learning_rate": 0.0001,
|
| 591 |
+
"loss": 2.5035,
|
| 592 |
+
"step": 1625
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.1693834160170091,
|
| 596 |
+
"grad_norm": 0.3958500623703003,
|
| 597 |
+
"learning_rate": 0.0001,
|
| 598 |
+
"loss": 2.6296,
|
| 599 |
+
"step": 1650
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.1871013465627214,
|
| 603 |
+
"grad_norm": 0.5418444275856018,
|
| 604 |
+
"learning_rate": 0.0001,
|
| 605 |
+
"loss": 2.5194,
|
| 606 |
+
"step": 1675
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.2048192771084336,
|
| 610 |
+
"grad_norm": 0.7059912085533142,
|
| 611 |
+
"learning_rate": 0.0001,
|
| 612 |
+
"loss": 2.497,
|
| 613 |
+
"step": 1700
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.2048192771084336,
|
| 617 |
+
"eval_loss": 2.4886298179626465,
|
| 618 |
+
"eval_runtime": 32.6428,
|
| 619 |
+
"eval_samples_per_second": 9.129,
|
| 620 |
+
"eval_steps_per_second": 2.298,
|
| 621 |
+
"step": 1700
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.222537207654146,
|
| 625 |
+
"grad_norm": 0.5447824001312256,
|
| 626 |
+
"learning_rate": 0.0001,
|
| 627 |
+
"loss": 2.5098,
|
| 628 |
+
"step": 1725
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.2402551381998583,
|
| 632 |
+
"grad_norm": 0.508121132850647,
|
| 633 |
+
"learning_rate": 0.0001,
|
| 634 |
+
"loss": 2.4463,
|
| 635 |
+
"step": 1750
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.2579730687455706,
|
| 639 |
+
"grad_norm": 0.5141641497612,
|
| 640 |
+
"learning_rate": 0.0001,
|
| 641 |
+
"loss": 2.4407,
|
| 642 |
+
"step": 1775
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.2756909992912828,
|
| 646 |
+
"grad_norm": 0.7895596623420715,
|
| 647 |
+
"learning_rate": 0.0001,
|
| 648 |
+
"loss": 2.4965,
|
| 649 |
+
"step": 1800
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.2756909992912828,
|
| 653 |
+
"eval_loss": 2.4845895767211914,
|
| 654 |
+
"eval_runtime": 32.6353,
|
| 655 |
+
"eval_samples_per_second": 9.131,
|
| 656 |
+
"eval_steps_per_second": 2.298,
|
| 657 |
+
"step": 1800
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.293408929836995,
|
| 661 |
+
"grad_norm": 0.33818376064300537,
|
| 662 |
+
"learning_rate": 0.0001,
|
| 663 |
+
"loss": 2.3678,
|
| 664 |
+
"step": 1825
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.3111268603827073,
|
| 668 |
+
"grad_norm": 0.36670777201652527,
|
| 669 |
+
"learning_rate": 0.0001,
|
| 670 |
+
"loss": 2.4522,
|
| 671 |
+
"step": 1850
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.3288447909284196,
|
| 675 |
+
"grad_norm": 0.46683812141418457,
|
| 676 |
+
"learning_rate": 0.0001,
|
| 677 |
+
"loss": 2.5355,
|
| 678 |
+
"step": 1875
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.3465627214741318,
|
| 682 |
+
"grad_norm": 0.45993196964263916,
|
| 683 |
+
"learning_rate": 0.0001,
|
| 684 |
+
"loss": 2.5535,
|
| 685 |
+
"step": 1900
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.3465627214741318,
|
| 689 |
+
"eval_loss": 2.4782519340515137,
|
| 690 |
+
"eval_runtime": 32.6522,
|
| 691 |
+
"eval_samples_per_second": 9.126,
|
| 692 |
+
"eval_steps_per_second": 2.297,
|
| 693 |
+
"step": 1900
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.364280652019844,
|
| 697 |
+
"grad_norm": 0.4003180265426636,
|
| 698 |
+
"learning_rate": 0.0001,
|
| 699 |
+
"loss": 2.4353,
|
| 700 |
+
"step": 1925
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.3819985825655563,
|
| 704 |
+
"grad_norm": 0.4715386629104614,
|
| 705 |
+
"learning_rate": 0.0001,
|
| 706 |
+
"loss": 2.4086,
|
| 707 |
+
"step": 1950
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 1.3997165131112685,
|
| 711 |
+
"grad_norm": 0.4463669955730438,
|
| 712 |
+
"learning_rate": 0.0001,
|
| 713 |
+
"loss": 2.5299,
|
| 714 |
+
"step": 1975
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.4174344436569808,
|
| 718 |
+
"grad_norm": 0.6194645762443542,
|
| 719 |
+
"learning_rate": 0.0001,
|
| 720 |
+
"loss": 2.5747,
|
| 721 |
+
"step": 2000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.4174344436569808,
|
| 725 |
+
"eval_loss": 2.4732108116149902,
|
| 726 |
+
"eval_runtime": 32.5875,
|
| 727 |
+
"eval_samples_per_second": 9.145,
|
| 728 |
+
"eval_steps_per_second": 2.301,
|
| 729 |
+
"step": 2000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.4351523742026933,
|
| 733 |
+
"grad_norm": 0.4712235927581787,
|
| 734 |
+
"learning_rate": 0.0001,
|
| 735 |
+
"loss": 2.433,
|
| 736 |
+
"step": 2025
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.4528703047484055,
|
| 740 |
+
"grad_norm": 0.5619576573371887,
|
| 741 |
+
"learning_rate": 0.0001,
|
| 742 |
+
"loss": 2.4883,
|
| 743 |
+
"step": 2050
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.4705882352941178,
|
| 747 |
+
"grad_norm": 0.44078579545021057,
|
| 748 |
+
"learning_rate": 0.0001,
|
| 749 |
+
"loss": 2.5575,
|
| 750 |
+
"step": 2075
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 1.48830616583983,
|
| 754 |
+
"grad_norm": 0.44347578287124634,
|
| 755 |
+
"learning_rate": 0.0001,
|
| 756 |
+
"loss": 2.4534,
|
| 757 |
+
"step": 2100
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.48830616583983,
|
| 761 |
+
"eval_loss": 2.467924118041992,
|
| 762 |
+
"eval_runtime": 32.6469,
|
| 763 |
+
"eval_samples_per_second": 9.128,
|
| 764 |
+
"eval_steps_per_second": 2.297,
|
| 765 |
+
"step": 2100
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.5060240963855422,
|
| 769 |
+
"grad_norm": 0.4806898832321167,
|
| 770 |
+
"learning_rate": 0.0001,
|
| 771 |
+
"loss": 2.4605,
|
| 772 |
+
"step": 2125
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.5237420269312545,
|
| 776 |
+
"grad_norm": 0.4710817337036133,
|
| 777 |
+
"learning_rate": 0.0001,
|
| 778 |
+
"loss": 2.5124,
|
| 779 |
+
"step": 2150
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.5414599574769667,
|
| 783 |
+
"grad_norm": 0.4697023630142212,
|
| 784 |
+
"learning_rate": 0.0001,
|
| 785 |
+
"loss": 2.5251,
|
| 786 |
+
"step": 2175
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.559177888022679,
|
| 790 |
+
"grad_norm": 0.4275937080383301,
|
| 791 |
+
"learning_rate": 0.0001,
|
| 792 |
+
"loss": 2.4909,
|
| 793 |
+
"step": 2200
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.559177888022679,
|
| 797 |
+
"eval_loss": 2.465703248977661,
|
| 798 |
+
"eval_runtime": 32.66,
|
| 799 |
+
"eval_samples_per_second": 9.124,
|
| 800 |
+
"eval_steps_per_second": 2.296,
|
| 801 |
+
"step": 2200
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.5768958185683912,
|
| 805 |
+
"grad_norm": 0.6271502375602722,
|
| 806 |
+
"learning_rate": 0.0001,
|
| 807 |
+
"loss": 2.4563,
|
| 808 |
+
"step": 2225
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.5946137491141035,
|
| 812 |
+
"grad_norm": 0.5484246015548706,
|
| 813 |
+
"learning_rate": 0.0001,
|
| 814 |
+
"loss": 2.4781,
|
| 815 |
+
"step": 2250
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.6123316796598157,
|
| 819 |
+
"grad_norm": 0.7340563535690308,
|
| 820 |
+
"learning_rate": 0.0001,
|
| 821 |
+
"loss": 2.5204,
|
| 822 |
+
"step": 2275
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.630049610205528,
|
| 826 |
+
"grad_norm": 0.43257761001586914,
|
| 827 |
+
"learning_rate": 0.0001,
|
| 828 |
+
"loss": 2.5192,
|
| 829 |
+
"step": 2300
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.630049610205528,
|
| 833 |
+
"eval_loss": 2.461730718612671,
|
| 834 |
+
"eval_runtime": 32.5818,
|
| 835 |
+
"eval_samples_per_second": 9.146,
|
| 836 |
+
"eval_steps_per_second": 2.302,
|
| 837 |
+
"step": 2300
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.6477675407512402,
|
| 841 |
+
"grad_norm": 0.7394423484802246,
|
| 842 |
+
"learning_rate": 0.0001,
|
| 843 |
+
"loss": 2.5862,
|
| 844 |
+
"step": 2325
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.6654854712969525,
|
| 848 |
+
"grad_norm": 0.48102429509162903,
|
| 849 |
+
"learning_rate": 0.0001,
|
| 850 |
+
"loss": 2.519,
|
| 851 |
+
"step": 2350
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.6832034018426647,
|
| 855 |
+
"grad_norm": 0.5994846820831299,
|
| 856 |
+
"learning_rate": 0.0001,
|
| 857 |
+
"loss": 2.4566,
|
| 858 |
+
"step": 2375
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.700921332388377,
|
| 862 |
+
"grad_norm": 0.4805436134338379,
|
| 863 |
+
"learning_rate": 0.0001,
|
| 864 |
+
"loss": 2.4271,
|
| 865 |
+
"step": 2400
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.700921332388377,
|
| 869 |
+
"eval_loss": 2.457273006439209,
|
| 870 |
+
"eval_runtime": 32.6806,
|
| 871 |
+
"eval_samples_per_second": 9.119,
|
| 872 |
+
"eval_steps_per_second": 2.295,
|
| 873 |
+
"step": 2400
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.7186392629340892,
|
| 877 |
+
"grad_norm": 0.6208567023277283,
|
| 878 |
+
"learning_rate": 0.0001,
|
| 879 |
+
"loss": 2.3581,
|
| 880 |
+
"step": 2425
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.7363571934798014,
|
| 884 |
+
"grad_norm": 0.44081413745880127,
|
| 885 |
+
"learning_rate": 0.0001,
|
| 886 |
+
"loss": 2.4295,
|
| 887 |
+
"step": 2450
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 1.7540751240255137,
|
| 891 |
+
"grad_norm": 0.4629543721675873,
|
| 892 |
+
"learning_rate": 0.0001,
|
| 893 |
+
"loss": 2.4569,
|
| 894 |
+
"step": 2475
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.771793054571226,
|
| 898 |
+
"grad_norm": 0.518991231918335,
|
| 899 |
+
"learning_rate": 0.0001,
|
| 900 |
+
"loss": 2.4855,
|
| 901 |
+
"step": 2500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.771793054571226,
|
| 905 |
+
"eval_loss": 2.454190731048584,
|
| 906 |
+
"eval_runtime": 32.6137,
|
| 907 |
+
"eval_samples_per_second": 9.137,
|
| 908 |
+
"eval_steps_per_second": 2.3,
|
| 909 |
+
"step": 2500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.7895109851169382,
|
| 913 |
+
"grad_norm": 0.6166653037071228,
|
| 914 |
+
"learning_rate": 0.0001,
|
| 915 |
+
"loss": 2.4761,
|
| 916 |
+
"step": 2525
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.8072289156626506,
|
| 920 |
+
"grad_norm": 0.5490785241127014,
|
| 921 |
+
"learning_rate": 0.0001,
|
| 922 |
+
"loss": 2.5232,
|
| 923 |
+
"step": 2550
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.824946846208363,
|
| 927 |
+
"grad_norm": 0.6279402375221252,
|
| 928 |
+
"learning_rate": 0.0001,
|
| 929 |
+
"loss": 2.4425,
|
| 930 |
+
"step": 2575
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.8426647767540751,
|
| 934 |
+
"grad_norm": 0.606396496295929,
|
| 935 |
+
"learning_rate": 0.0001,
|
| 936 |
+
"loss": 2.4599,
|
| 937 |
+
"step": 2600
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.8426647767540751,
|
| 941 |
+
"eval_loss": 2.4530327320098877,
|
| 942 |
+
"eval_runtime": 32.6381,
|
| 943 |
+
"eval_samples_per_second": 9.13,
|
| 944 |
+
"eval_steps_per_second": 2.298,
|
| 945 |
+
"step": 2600
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.8603827072997874,
|
| 949 |
+
"grad_norm": 0.5355327129364014,
|
| 950 |
+
"learning_rate": 0.0001,
|
| 951 |
+
"loss": 2.5615,
|
| 952 |
+
"step": 2625
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.8781006378454996,
|
| 956 |
+
"grad_norm": 0.3971356451511383,
|
| 957 |
+
"learning_rate": 0.0001,
|
| 958 |
+
"loss": 2.445,
|
| 959 |
+
"step": 2650
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.8958185683912119,
|
| 963 |
+
"grad_norm": 0.48701226711273193,
|
| 964 |
+
"learning_rate": 0.0001,
|
| 965 |
+
"loss": 2.5405,
|
| 966 |
+
"step": 2675
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.9135364989369241,
|
| 970 |
+
"grad_norm": 0.5117021203041077,
|
| 971 |
+
"learning_rate": 0.0001,
|
| 972 |
+
"loss": 2.4482,
|
| 973 |
+
"step": 2700
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 1.9135364989369241,
|
| 977 |
+
"eval_loss": 2.444391965866089,
|
| 978 |
+
"eval_runtime": 32.6264,
|
| 979 |
+
"eval_samples_per_second": 9.134,
|
| 980 |
+
"eval_steps_per_second": 2.299,
|
| 981 |
+
"step": 2700
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.9312544294826366,
|
| 985 |
+
"grad_norm": 0.40752479434013367,
|
| 986 |
+
"learning_rate": 0.0001,
|
| 987 |
+
"loss": 2.421,
|
| 988 |
+
"step": 2725
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.9489723600283488,
|
| 992 |
+
"grad_norm": 0.4466327428817749,
|
| 993 |
+
"learning_rate": 0.0001,
|
| 994 |
+
"loss": 2.4286,
|
| 995 |
+
"step": 2750
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.966690290574061,
|
| 999 |
+
"grad_norm": 0.35452115535736084,
|
| 1000 |
+
"learning_rate": 0.0001,
|
| 1001 |
+
"loss": 2.4265,
|
| 1002 |
+
"step": 2775
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.9844082211197733,
|
| 1006 |
+
"grad_norm": 0.7978025674819946,
|
| 1007 |
+
"learning_rate": 0.0001,
|
| 1008 |
+
"loss": 2.493,
|
| 1009 |
+
"step": 2800
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.9844082211197733,
|
| 1013 |
+
"eval_loss": 2.444624423980713,
|
| 1014 |
+
"eval_runtime": 32.6679,
|
| 1015 |
+
"eval_samples_per_second": 9.122,
|
| 1016 |
+
"eval_steps_per_second": 2.296,
|
| 1017 |
+
"step": 2800
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.0021261516654856,
|
| 1021 |
+
"grad_norm": 0.46374988555908203,
|
| 1022 |
+
"learning_rate": 0.0001,
|
| 1023 |
+
"loss": 2.5357,
|
| 1024 |
+
"step": 2825
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.019844082211198,
|
| 1028 |
+
"grad_norm": 0.4631684422492981,
|
| 1029 |
+
"learning_rate": 0.0001,
|
| 1030 |
+
"loss": 2.4015,
|
| 1031 |
+
"step": 2850
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.03756201275691,
|
| 1035 |
+
"grad_norm": 0.4475260376930237,
|
| 1036 |
+
"learning_rate": 0.0001,
|
| 1037 |
+
"loss": 2.3658,
|
| 1038 |
+
"step": 2875
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.0552799433026223,
|
| 1042 |
+
"grad_norm": 0.47790655493736267,
|
| 1043 |
+
"learning_rate": 0.0001,
|
| 1044 |
+
"loss": 2.3527,
|
| 1045 |
+
"step": 2900
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.0552799433026223,
|
| 1049 |
+
"eval_loss": 2.441364049911499,
|
| 1050 |
+
"eval_runtime": 32.6599,
|
| 1051 |
+
"eval_samples_per_second": 9.124,
|
| 1052 |
+
"eval_steps_per_second": 2.296,
|
| 1053 |
+
"step": 2900
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.0729978738483346,
|
| 1057 |
+
"grad_norm": 0.5602151155471802,
|
| 1058 |
+
"learning_rate": 0.0001,
|
| 1059 |
+
"loss": 2.4763,
|
| 1060 |
+
"step": 2925
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.090715804394047,
|
| 1064 |
+
"grad_norm": 0.37178730964660645,
|
| 1065 |
+
"learning_rate": 0.0001,
|
| 1066 |
+
"loss": 2.4431,
|
| 1067 |
+
"step": 2950
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.108433734939759,
|
| 1071 |
+
"grad_norm": 0.47269827127456665,
|
| 1072 |
+
"learning_rate": 0.0001,
|
| 1073 |
+
"loss": 2.5528,
|
| 1074 |
+
"step": 2975
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.1261516654854713,
|
| 1078 |
+
"grad_norm": 0.5636725425720215,
|
| 1079 |
+
"learning_rate": 0.0001,
|
| 1080 |
+
"loss": 2.5243,
|
| 1081 |
+
"step": 3000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.1261516654854713,
|
| 1085 |
+
"eval_loss": 2.4375791549682617,
|
| 1086 |
+
"eval_runtime": 32.6693,
|
| 1087 |
+
"eval_samples_per_second": 9.122,
|
| 1088 |
+
"eval_steps_per_second": 2.296,
|
| 1089 |
+
"step": 3000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.1438695960311835,
|
| 1093 |
+
"grad_norm": 0.5602971315383911,
|
| 1094 |
+
"learning_rate": 0.0001,
|
| 1095 |
+
"loss": 2.4726,
|
| 1096 |
+
"step": 3025
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.161587526576896,
|
| 1100 |
+
"grad_norm": 0.7102957367897034,
|
| 1101 |
+
"learning_rate": 0.0001,
|
| 1102 |
+
"loss": 2.4513,
|
| 1103 |
+
"step": 3050
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.179305457122608,
|
| 1107 |
+
"grad_norm": 0.5028663277626038,
|
| 1108 |
+
"learning_rate": 0.0001,
|
| 1109 |
+
"loss": 2.4038,
|
| 1110 |
+
"step": 3075
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.1970233876683203,
|
| 1114 |
+
"grad_norm": 0.5358246564865112,
|
| 1115 |
+
"learning_rate": 0.0001,
|
| 1116 |
+
"loss": 2.4644,
|
| 1117 |
+
"step": 3100
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.1970233876683203,
|
| 1121 |
+
"eval_loss": 2.433030605316162,
|
| 1122 |
+
"eval_runtime": 32.6486,
|
| 1123 |
+
"eval_samples_per_second": 9.128,
|
| 1124 |
+
"eval_steps_per_second": 2.297,
|
| 1125 |
+
"step": 3100
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 2.2147413182140325,
|
| 1129 |
+
"grad_norm": 0.5380859971046448,
|
| 1130 |
+
"learning_rate": 0.0001,
|
| 1131 |
+
"loss": 2.4342,
|
| 1132 |
+
"step": 3125
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.2324592487597448,
|
| 1136 |
+
"grad_norm": 0.8703417181968689,
|
| 1137 |
+
"learning_rate": 0.0001,
|
| 1138 |
+
"loss": 2.4462,
|
| 1139 |
+
"step": 3150
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.250177179305457,
|
| 1143 |
+
"grad_norm": 0.44465309381484985,
|
| 1144 |
+
"learning_rate": 0.0001,
|
| 1145 |
+
"loss": 2.4428,
|
| 1146 |
+
"step": 3175
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.2678951098511693,
|
| 1150 |
+
"grad_norm": 0.4541110396385193,
|
| 1151 |
+
"learning_rate": 0.0001,
|
| 1152 |
+
"loss": 2.386,
|
| 1153 |
+
"step": 3200
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.2678951098511693,
|
| 1157 |
+
"eval_loss": 2.4308454990386963,
|
| 1158 |
+
"eval_runtime": 32.6678,
|
| 1159 |
+
"eval_samples_per_second": 9.122,
|
| 1160 |
+
"eval_steps_per_second": 2.296,
|
| 1161 |
+
"step": 3200
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.2856130403968815,
|
| 1165 |
+
"grad_norm": 0.6527560949325562,
|
| 1166 |
+
"learning_rate": 0.0001,
|
| 1167 |
+
"loss": 2.3964,
|
| 1168 |
+
"step": 3225
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 2.3033309709425938,
|
| 1172 |
+
"grad_norm": 0.5541362762451172,
|
| 1173 |
+
"learning_rate": 0.0001,
|
| 1174 |
+
"loss": 2.4817,
|
| 1175 |
+
"step": 3250
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.321048901488306,
|
| 1179 |
+
"grad_norm": 0.5997689366340637,
|
| 1180 |
+
"learning_rate": 0.0001,
|
| 1181 |
+
"loss": 2.496,
|
| 1182 |
+
"step": 3275
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.3387668320340183,
|
| 1186 |
+
"grad_norm": 0.5446316003799438,
|
| 1187 |
+
"learning_rate": 0.0001,
|
| 1188 |
+
"loss": 2.3762,
|
| 1189 |
+
"step": 3300
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.3387668320340183,
|
| 1193 |
+
"eval_loss": 2.428109645843506,
|
| 1194 |
+
"eval_runtime": 32.6878,
|
| 1195 |
+
"eval_samples_per_second": 9.117,
|
| 1196 |
+
"eval_steps_per_second": 2.294,
|
| 1197 |
+
"step": 3300
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.3564847625797305,
|
| 1201 |
+
"grad_norm": 0.3934761881828308,
|
| 1202 |
+
"learning_rate": 0.0001,
|
| 1203 |
+
"loss": 2.5195,
|
| 1204 |
+
"step": 3325
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 2.3742026931254427,
|
| 1208 |
+
"grad_norm": 0.47348254919052124,
|
| 1209 |
+
"learning_rate": 0.0001,
|
| 1210 |
+
"loss": 2.5055,
|
| 1211 |
+
"step": 3350
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 2.3919206236711554,
|
| 1215 |
+
"grad_norm": 0.5292345881462097,
|
| 1216 |
+
"learning_rate": 0.0001,
|
| 1217 |
+
"loss": 2.3635,
|
| 1218 |
+
"step": 3375
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.4096385542168672,
|
| 1222 |
+
"grad_norm": 0.6056796312332153,
|
| 1223 |
+
"learning_rate": 0.0001,
|
| 1224 |
+
"loss": 2.3827,
|
| 1225 |
+
"step": 3400
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 2.4096385542168672,
|
| 1229 |
+
"eval_loss": 2.4244818687438965,
|
| 1230 |
+
"eval_runtime": 32.5864,
|
| 1231 |
+
"eval_samples_per_second": 9.145,
|
| 1232 |
+
"eval_steps_per_second": 2.302,
|
| 1233 |
+
"step": 3400
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.42735648476258,
|
| 1237 |
+
"grad_norm": 0.2907162010669708,
|
| 1238 |
+
"learning_rate": 0.0001,
|
| 1239 |
+
"loss": 2.3354,
|
| 1240 |
+
"step": 3425
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 2.445074415308292,
|
| 1244 |
+
"grad_norm": 0.43741077184677124,
|
| 1245 |
+
"learning_rate": 0.0001,
|
| 1246 |
+
"loss": 2.4199,
|
| 1247 |
+
"step": 3450
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 2.4627923458540044,
|
| 1251 |
+
"grad_norm": 0.36141782999038696,
|
| 1252 |
+
"learning_rate": 0.0001,
|
| 1253 |
+
"loss": 2.4165,
|
| 1254 |
+
"step": 3475
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.4805102763997167,
|
| 1258 |
+
"grad_norm": 0.5461854338645935,
|
| 1259 |
+
"learning_rate": 0.0001,
|
| 1260 |
+
"loss": 2.3487,
|
| 1261 |
+
"step": 3500
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.4805102763997167,
|
| 1265 |
+
"eval_loss": 2.4221482276916504,
|
| 1266 |
+
"eval_runtime": 32.6681,
|
| 1267 |
+
"eval_samples_per_second": 9.122,
|
| 1268 |
+
"eval_steps_per_second": 2.296,
|
| 1269 |
+
"step": 3500
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.498228206945429,
|
| 1273 |
+
"grad_norm": 0.61762934923172,
|
| 1274 |
+
"learning_rate": 0.0001,
|
| 1275 |
+
"loss": 2.4136,
|
| 1276 |
+
"step": 3525
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.515946137491141,
|
| 1280 |
+
"grad_norm": 0.41114169359207153,
|
| 1281 |
+
"learning_rate": 0.0001,
|
| 1282 |
+
"loss": 2.3587,
|
| 1283 |
+
"step": 3550
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.5336640680368534,
|
| 1287 |
+
"grad_norm": 0.5726279020309448,
|
| 1288 |
+
"learning_rate": 0.0001,
|
| 1289 |
+
"loss": 2.5009,
|
| 1290 |
+
"step": 3575
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.5513819985825656,
|
| 1294 |
+
"grad_norm": 0.4807787239551544,
|
| 1295 |
+
"learning_rate": 0.0001,
|
| 1296 |
+
"loss": 2.4737,
|
| 1297 |
+
"step": 3600
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.5513819985825656,
|
| 1301 |
+
"eval_loss": 2.4191701412200928,
|
| 1302 |
+
"eval_runtime": 32.6743,
|
| 1303 |
+
"eval_samples_per_second": 9.12,
|
| 1304 |
+
"eval_steps_per_second": 2.295,
|
| 1305 |
+
"step": 3600
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.569099929128278,
|
| 1309 |
+
"grad_norm": 0.5931722521781921,
|
| 1310 |
+
"learning_rate": 0.0001,
|
| 1311 |
+
"loss": 2.4178,
|
| 1312 |
+
"step": 3625
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.58681785967399,
|
| 1316 |
+
"grad_norm": 0.4658395051956177,
|
| 1317 |
+
"learning_rate": 0.0001,
|
| 1318 |
+
"loss": 2.5162,
|
| 1319 |
+
"step": 3650
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.6045357902197024,
|
| 1323 |
+
"grad_norm": 0.5829235315322876,
|
| 1324 |
+
"learning_rate": 0.0001,
|
| 1325 |
+
"loss": 2.3402,
|
| 1326 |
+
"step": 3675
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.6222537207654146,
|
| 1330 |
+
"grad_norm": 0.6382436156272888,
|
| 1331 |
+
"learning_rate": 0.0001,
|
| 1332 |
+
"loss": 2.4907,
|
| 1333 |
+
"step": 3700
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.6222537207654146,
|
| 1337 |
+
"eval_loss": 2.417147397994995,
|
| 1338 |
+
"eval_runtime": 32.6259,
|
| 1339 |
+
"eval_samples_per_second": 9.134,
|
| 1340 |
+
"eval_steps_per_second": 2.299,
|
| 1341 |
+
"step": 3700
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.639971651311127,
|
| 1345 |
+
"grad_norm": 0.578823983669281,
|
| 1346 |
+
"learning_rate": 0.0001,
|
| 1347 |
+
"loss": 2.4281,
|
| 1348 |
+
"step": 3725
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.657689581856839,
|
| 1352 |
+
"grad_norm": 0.5311617255210876,
|
| 1353 |
+
"learning_rate": 0.0001,
|
| 1354 |
+
"loss": 2.4315,
|
| 1355 |
+
"step": 3750
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.6754075124025514,
|
| 1359 |
+
"grad_norm": 0.4713846743106842,
|
| 1360 |
+
"learning_rate": 0.0001,
|
| 1361 |
+
"loss": 2.4268,
|
| 1362 |
+
"step": 3775
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.6931254429482636,
|
| 1366 |
+
"grad_norm": 0.7472273111343384,
|
| 1367 |
+
"learning_rate": 0.0001,
|
| 1368 |
+
"loss": 2.3967,
|
| 1369 |
+
"step": 3800
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.6931254429482636,
|
| 1373 |
+
"eval_loss": 2.415893077850342,
|
| 1374 |
+
"eval_runtime": 32.6303,
|
| 1375 |
+
"eval_samples_per_second": 9.133,
|
| 1376 |
+
"eval_steps_per_second": 2.298,
|
| 1377 |
+
"step": 3800
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.710843373493976,
|
| 1381 |
+
"grad_norm": 0.5875506401062012,
|
| 1382 |
+
"learning_rate": 0.0001,
|
| 1383 |
+
"loss": 2.3541,
|
| 1384 |
+
"step": 3825
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 2.728561304039688,
|
| 1388 |
+
"grad_norm": 0.38152602314949036,
|
| 1389 |
+
"learning_rate": 0.0001,
|
| 1390 |
+
"loss": 2.4623,
|
| 1391 |
+
"step": 3850
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 2.7462792345854004,
|
| 1395 |
+
"grad_norm": 0.35034802556037903,
|
| 1396 |
+
"learning_rate": 0.0001,
|
| 1397 |
+
"loss": 2.4392,
|
| 1398 |
+
"step": 3875
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.7639971651311126,
|
| 1402 |
+
"grad_norm": 0.3683781027793884,
|
| 1403 |
+
"learning_rate": 0.0001,
|
| 1404 |
+
"loss": 2.4772,
|
| 1405 |
+
"step": 3900
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 2.7639971651311126,
|
| 1409 |
+
"eval_loss": 2.414635181427002,
|
| 1410 |
+
"eval_runtime": 32.6546,
|
| 1411 |
+
"eval_samples_per_second": 9.126,
|
| 1412 |
+
"eval_steps_per_second": 2.297,
|
| 1413 |
+
"step": 3900
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.781715095676825,
|
| 1417 |
+
"grad_norm": 0.632203221321106,
|
| 1418 |
+
"learning_rate": 0.0001,
|
| 1419 |
+
"loss": 2.48,
|
| 1420 |
+
"step": 3925
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.799433026222537,
|
| 1424 |
+
"grad_norm": 0.4688514173030853,
|
| 1425 |
+
"learning_rate": 0.0001,
|
| 1426 |
+
"loss": 2.4058,
|
| 1427 |
+
"step": 3950
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 2.8171509567682493,
|
| 1431 |
+
"grad_norm": 0.3703823685646057,
|
| 1432 |
+
"learning_rate": 0.0001,
|
| 1433 |
+
"loss": 2.3802,
|
| 1434 |
+
"step": 3975
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.8348688873139616,
|
| 1438 |
+
"grad_norm": 0.4395906329154968,
|
| 1439 |
+
"learning_rate": 0.0001,
|
| 1440 |
+
"loss": 2.4114,
|
| 1441 |
+
"step": 4000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.8348688873139616,
|
| 1445 |
+
"eval_loss": 2.4105727672576904,
|
| 1446 |
+
"eval_runtime": 32.6241,
|
| 1447 |
+
"eval_samples_per_second": 9.134,
|
| 1448 |
+
"eval_steps_per_second": 2.299,
|
| 1449 |
+
"step": 4000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.852586817859674,
|
| 1453 |
+
"grad_norm": 0.3975163996219635,
|
| 1454 |
+
"learning_rate": 0.0001,
|
| 1455 |
+
"loss": 2.4189,
|
| 1456 |
+
"step": 4025
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.8703047484053865,
|
| 1460 |
+
"grad_norm": 0.37457334995269775,
|
| 1461 |
+
"learning_rate": 0.0001,
|
| 1462 |
+
"loss": 2.3946,
|
| 1463 |
+
"step": 4050
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.8880226789510983,
|
| 1467 |
+
"grad_norm": 0.3786819279193878,
|
| 1468 |
+
"learning_rate": 0.0001,
|
| 1469 |
+
"loss": 2.4683,
|
| 1470 |
+
"step": 4075
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.905740609496811,
|
| 1474 |
+
"grad_norm": 0.633921205997467,
|
| 1475 |
+
"learning_rate": 0.0001,
|
| 1476 |
+
"loss": 2.4017,
|
| 1477 |
+
"step": 4100
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 2.905740609496811,
|
| 1481 |
+
"eval_loss": 2.406451463699341,
|
| 1482 |
+
"eval_runtime": 32.6727,
|
| 1483 |
+
"eval_samples_per_second": 9.121,
|
| 1484 |
+
"eval_steps_per_second": 2.295,
|
| 1485 |
+
"step": 4100
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.923458540042523,
|
| 1489 |
+
"grad_norm": 0.9005404710769653,
|
| 1490 |
+
"learning_rate": 0.0001,
|
| 1491 |
+
"loss": 2.4099,
|
| 1492 |
+
"step": 4125
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.9411764705882355,
|
| 1496 |
+
"grad_norm": 0.5802463293075562,
|
| 1497 |
+
"learning_rate": 0.0001,
|
| 1498 |
+
"loss": 2.4068,
|
| 1499 |
+
"step": 4150
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.9588944011339473,
|
| 1503 |
+
"grad_norm": 0.3155713975429535,
|
| 1504 |
+
"learning_rate": 0.0001,
|
| 1505 |
+
"loss": 2.3682,
|
| 1506 |
+
"step": 4175
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.97661233167966,
|
| 1510 |
+
"grad_norm": 0.4876560568809509,
|
| 1511 |
+
"learning_rate": 0.0001,
|
| 1512 |
+
"loss": 2.3477,
|
| 1513 |
+
"step": 4200
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 2.97661233167966,
|
| 1517 |
+
"eval_loss": 2.405850648880005,
|
| 1518 |
+
"eval_runtime": 32.6084,
|
| 1519 |
+
"eval_samples_per_second": 9.139,
|
| 1520 |
+
"eval_steps_per_second": 2.3,
|
| 1521 |
+
"step": 4200
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.9943302622253722,
|
| 1525 |
+
"grad_norm": 0.49624720215797424,
|
| 1526 |
+
"learning_rate": 0.0001,
|
| 1527 |
+
"loss": 2.445,
|
| 1528 |
+
"step": 4225
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 3.0,
|
| 1532 |
+
"step": 4233,
|
| 1533 |
+
"total_flos": 9152314711474176.0,
|
| 1534 |
+
"train_loss": 2.5398848939386913,
|
| 1535 |
+
"train_runtime": 5263.4986,
|
| 1536 |
+
"train_samples_per_second": 3.217,
|
| 1537 |
+
"train_steps_per_second": 0.804
|
| 1538 |
+
}
|
| 1539 |
+
],
|
| 1540 |
+
"logging_steps": 25,
|
| 1541 |
+
"max_steps": 4233,
|
| 1542 |
+
"num_input_tokens_seen": 0,
|
| 1543 |
+
"num_train_epochs": 3,
|
| 1544 |
+
"save_steps": 100,
|
| 1545 |
+
"stateful_callbacks": {
|
| 1546 |
+
"TrainerControl": {
|
| 1547 |
+
"args": {
|
| 1548 |
+
"should_epoch_stop": false,
|
| 1549 |
+
"should_evaluate": false,
|
| 1550 |
+
"should_log": false,
|
| 1551 |
+
"should_save": true,
|
| 1552 |
+
"should_training_stop": true
|
| 1553 |
+
},
|
| 1554 |
+
"attributes": {}
|
| 1555 |
+
}
|
| 1556 |
+
},
|
| 1557 |
+
"total_flos": 9152314711474176.0,
|
| 1558 |
+
"train_batch_size": 4,
|
| 1559 |
+
"trial_name": null,
|
| 1560 |
+
"trial_params": null
|
| 1561 |
+
}
|