Commit
·
c057932
1
Parent(s):
0d484bb
Upload trainer_state.json
Browse files- trainer_state.json +2475 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,2475 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 198580,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.987410615369121e-05,
|
| 13 |
+
"loss": 1.5195,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 4.974821230738242e-05,
|
| 19 |
+
"loss": 0.9589,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 4.962231846107363e-05,
|
| 25 |
+
"loss": 0.849,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 4.949642461476483e-05,
|
| 31 |
+
"loss": 0.7958,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.13,
|
| 36 |
+
"learning_rate": 4.937053076845604e-05,
|
| 37 |
+
"loss": 0.7606,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 4.9244636922147244e-05,
|
| 43 |
+
"loss": 0.7385,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18,
|
| 48 |
+
"learning_rate": 4.911874307583846e-05,
|
| 49 |
+
"loss": 0.7186,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 4.899284922952966e-05,
|
| 55 |
+
"loss": 0.6996,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 4.886695538322087e-05,
|
| 61 |
+
"loss": 0.6902,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.25,
|
| 66 |
+
"learning_rate": 4.874106153691208e-05,
|
| 67 |
+
"loss": 0.6809,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.28,
|
| 72 |
+
"learning_rate": 4.861516769060329e-05,
|
| 73 |
+
"loss": 0.6723,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.3,
|
| 78 |
+
"learning_rate": 4.848927384429449e-05,
|
| 79 |
+
"loss": 0.6689,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.33,
|
| 84 |
+
"learning_rate": 4.8363379997985705e-05,
|
| 85 |
+
"loss": 0.6621,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.35,
|
| 90 |
+
"learning_rate": 4.823748615167691e-05,
|
| 91 |
+
"loss": 0.6569,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.38,
|
| 96 |
+
"learning_rate": 4.811159230536812e-05,
|
| 97 |
+
"loss": 0.6519,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.4,
|
| 102 |
+
"learning_rate": 4.798569845905932e-05,
|
| 103 |
+
"loss": 0.6445,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.43,
|
| 108 |
+
"learning_rate": 4.785980461275053e-05,
|
| 109 |
+
"loss": 0.643,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.45,
|
| 114 |
+
"learning_rate": 4.7733910766441734e-05,
|
| 115 |
+
"loss": 0.6377,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.48,
|
| 120 |
+
"learning_rate": 4.760801692013295e-05,
|
| 121 |
+
"loss": 0.6386,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5,
|
| 126 |
+
"learning_rate": 4.748212307382415e-05,
|
| 127 |
+
"loss": 0.6264,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.53,
|
| 132 |
+
"learning_rate": 4.7356229227515365e-05,
|
| 133 |
+
"loss": 0.6231,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.55,
|
| 138 |
+
"learning_rate": 4.723033538120657e-05,
|
| 139 |
+
"loss": 0.6254,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.58,
|
| 144 |
+
"learning_rate": 4.710444153489778e-05,
|
| 145 |
+
"loss": 0.6205,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.6,
|
| 150 |
+
"learning_rate": 4.697854768858899e-05,
|
| 151 |
+
"loss": 0.6222,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.63,
|
| 156 |
+
"learning_rate": 4.685265384228019e-05,
|
| 157 |
+
"loss": 0.6156,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.65,
|
| 162 |
+
"learning_rate": 4.6726759995971395e-05,
|
| 163 |
+
"loss": 0.612,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.68,
|
| 168 |
+
"learning_rate": 4.660086614966261e-05,
|
| 169 |
+
"loss": 0.6182,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.71,
|
| 174 |
+
"learning_rate": 4.647497230335381e-05,
|
| 175 |
+
"loss": 0.6127,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.73,
|
| 180 |
+
"learning_rate": 4.634907845704502e-05,
|
| 181 |
+
"loss": 0.6087,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.76,
|
| 186 |
+
"learning_rate": 4.622318461073623e-05,
|
| 187 |
+
"loss": 0.6062,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.78,
|
| 192 |
+
"learning_rate": 4.609729076442744e-05,
|
| 193 |
+
"loss": 0.604,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.81,
|
| 198 |
+
"learning_rate": 4.597139691811864e-05,
|
| 199 |
+
"loss": 0.6029,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.83,
|
| 204 |
+
"learning_rate": 4.5845503071809856e-05,
|
| 205 |
+
"loss": 0.6024,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.86,
|
| 210 |
+
"learning_rate": 4.571960922550106e-05,
|
| 211 |
+
"loss": 0.599,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.88,
|
| 216 |
+
"learning_rate": 4.559371537919227e-05,
|
| 217 |
+
"loss": 0.5967,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.91,
|
| 222 |
+
"learning_rate": 4.546782153288347e-05,
|
| 223 |
+
"loss": 0.5961,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.93,
|
| 228 |
+
"learning_rate": 4.534192768657468e-05,
|
| 229 |
+
"loss": 0.5954,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.96,
|
| 234 |
+
"learning_rate": 4.521603384026589e-05,
|
| 235 |
+
"loss": 0.5927,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.98,
|
| 240 |
+
"learning_rate": 4.50901399939571e-05,
|
| 241 |
+
"loss": 0.5859,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.0,
|
| 246 |
+
"eval_loss": 0.6686062812805176,
|
| 247 |
+
"eval_runtime": 51.5648,
|
| 248 |
+
"eval_samples_per_second": 342.346,
|
| 249 |
+
"step": 19858
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.01,
|
| 253 |
+
"learning_rate": 4.49642461476483e-05,
|
| 254 |
+
"loss": 0.5871,
|
| 255 |
+
"step": 20000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.03,
|
| 259 |
+
"learning_rate": 4.4838352301339516e-05,
|
| 260 |
+
"loss": 0.579,
|
| 261 |
+
"step": 20500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.06,
|
| 265 |
+
"learning_rate": 4.471245845503072e-05,
|
| 266 |
+
"loss": 0.5806,
|
| 267 |
+
"step": 21000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.08,
|
| 271 |
+
"learning_rate": 4.458656460872193e-05,
|
| 272 |
+
"loss": 0.5788,
|
| 273 |
+
"step": 21500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.11,
|
| 277 |
+
"learning_rate": 4.446067076241314e-05,
|
| 278 |
+
"loss": 0.5765,
|
| 279 |
+
"step": 22000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.13,
|
| 283 |
+
"learning_rate": 4.433477691610434e-05,
|
| 284 |
+
"loss": 0.5756,
|
| 285 |
+
"step": 22500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.16,
|
| 289 |
+
"learning_rate": 4.4208883069795545e-05,
|
| 290 |
+
"loss": 0.5756,
|
| 291 |
+
"step": 23000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.18,
|
| 295 |
+
"learning_rate": 4.408298922348676e-05,
|
| 296 |
+
"loss": 0.5758,
|
| 297 |
+
"step": 23500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.21,
|
| 301 |
+
"learning_rate": 4.3957095377177963e-05,
|
| 302 |
+
"loss": 0.5712,
|
| 303 |
+
"step": 24000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.23,
|
| 307 |
+
"learning_rate": 4.3831201530869176e-05,
|
| 308 |
+
"loss": 0.5708,
|
| 309 |
+
"step": 24500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.26,
|
| 313 |
+
"learning_rate": 4.370530768456038e-05,
|
| 314 |
+
"loss": 0.5684,
|
| 315 |
+
"step": 25000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.28,
|
| 319 |
+
"learning_rate": 4.357941383825159e-05,
|
| 320 |
+
"loss": 0.5738,
|
| 321 |
+
"step": 25500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.31,
|
| 325 |
+
"learning_rate": 4.34535199919428e-05,
|
| 326 |
+
"loss": 0.5697,
|
| 327 |
+
"step": 26000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.33,
|
| 331 |
+
"learning_rate": 4.3327626145634006e-05,
|
| 332 |
+
"loss": 0.5659,
|
| 333 |
+
"step": 26500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.36,
|
| 337 |
+
"learning_rate": 4.320173229932521e-05,
|
| 338 |
+
"loss": 0.569,
|
| 339 |
+
"step": 27000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.38,
|
| 343 |
+
"learning_rate": 4.307583845301642e-05,
|
| 344 |
+
"loss": 0.5688,
|
| 345 |
+
"step": 27500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.41,
|
| 349 |
+
"learning_rate": 4.2949944606707624e-05,
|
| 350 |
+
"loss": 0.5695,
|
| 351 |
+
"step": 28000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.44,
|
| 355 |
+
"learning_rate": 4.282405076039883e-05,
|
| 356 |
+
"loss": 0.5659,
|
| 357 |
+
"step": 28500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.46,
|
| 361 |
+
"learning_rate": 4.269815691409004e-05,
|
| 362 |
+
"loss": 0.5641,
|
| 363 |
+
"step": 29000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.49,
|
| 367 |
+
"learning_rate": 4.257226306778125e-05,
|
| 368 |
+
"loss": 0.5628,
|
| 369 |
+
"step": 29500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.51,
|
| 373 |
+
"learning_rate": 4.2446369221472454e-05,
|
| 374 |
+
"loss": 0.5611,
|
| 375 |
+
"step": 30000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.54,
|
| 379 |
+
"learning_rate": 4.2320475375163666e-05,
|
| 380 |
+
"loss": 0.5604,
|
| 381 |
+
"step": 30500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.56,
|
| 385 |
+
"learning_rate": 4.219458152885487e-05,
|
| 386 |
+
"loss": 0.5647,
|
| 387 |
+
"step": 31000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.59,
|
| 391 |
+
"learning_rate": 4.2068687682546085e-05,
|
| 392 |
+
"loss": 0.5629,
|
| 393 |
+
"step": 31500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.61,
|
| 397 |
+
"learning_rate": 4.194279383623729e-05,
|
| 398 |
+
"loss": 0.5619,
|
| 399 |
+
"step": 32000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.64,
|
| 403 |
+
"learning_rate": 4.181689998992849e-05,
|
| 404 |
+
"loss": 0.5574,
|
| 405 |
+
"step": 32500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.66,
|
| 409 |
+
"learning_rate": 4.16910061436197e-05,
|
| 410 |
+
"loss": 0.5568,
|
| 411 |
+
"step": 33000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.69,
|
| 415 |
+
"learning_rate": 4.156511229731091e-05,
|
| 416 |
+
"loss": 0.5585,
|
| 417 |
+
"step": 33500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.71,
|
| 421 |
+
"learning_rate": 4.1439218451002114e-05,
|
| 422 |
+
"loss": 0.556,
|
| 423 |
+
"step": 34000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.74,
|
| 427 |
+
"learning_rate": 4.1313324604693327e-05,
|
| 428 |
+
"loss": 0.5582,
|
| 429 |
+
"step": 34500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.76,
|
| 433 |
+
"learning_rate": 4.118743075838453e-05,
|
| 434 |
+
"loss": 0.5541,
|
| 435 |
+
"step": 35000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.79,
|
| 439 |
+
"learning_rate": 4.106153691207574e-05,
|
| 440 |
+
"loss": 0.5524,
|
| 441 |
+
"step": 35500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.81,
|
| 445 |
+
"learning_rate": 4.093564306576695e-05,
|
| 446 |
+
"loss": 0.5565,
|
| 447 |
+
"step": 36000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.84,
|
| 451 |
+
"learning_rate": 4.0809749219458157e-05,
|
| 452 |
+
"loss": 0.5544,
|
| 453 |
+
"step": 36500
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.86,
|
| 457 |
+
"learning_rate": 4.068385537314936e-05,
|
| 458 |
+
"loss": 0.5534,
|
| 459 |
+
"step": 37000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.89,
|
| 463 |
+
"learning_rate": 4.055796152684057e-05,
|
| 464 |
+
"loss": 0.5545,
|
| 465 |
+
"step": 37500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.91,
|
| 469 |
+
"learning_rate": 4.0432067680531774e-05,
|
| 470 |
+
"loss": 0.5521,
|
| 471 |
+
"step": 38000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.94,
|
| 475 |
+
"learning_rate": 4.030617383422299e-05,
|
| 476 |
+
"loss": 0.5467,
|
| 477 |
+
"step": 38500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.96,
|
| 481 |
+
"learning_rate": 4.018027998791419e-05,
|
| 482 |
+
"loss": 0.5512,
|
| 483 |
+
"step": 39000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.99,
|
| 487 |
+
"learning_rate": 4.00543861416054e-05,
|
| 488 |
+
"loss": 0.5488,
|
| 489 |
+
"step": 39500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.0,
|
| 493 |
+
"eval_loss": 0.6351193785667419,
|
| 494 |
+
"eval_runtime": 51.4996,
|
| 495 |
+
"eval_samples_per_second": 342.779,
|
| 496 |
+
"step": 39716
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.01,
|
| 500 |
+
"learning_rate": 3.992849229529661e-05,
|
| 501 |
+
"loss": 0.5438,
|
| 502 |
+
"step": 40000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.04,
|
| 506 |
+
"learning_rate": 3.980259844898782e-05,
|
| 507 |
+
"loss": 0.5404,
|
| 508 |
+
"step": 40500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.06,
|
| 512 |
+
"learning_rate": 3.967670460267902e-05,
|
| 513 |
+
"loss": 0.5412,
|
| 514 |
+
"step": 41000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.09,
|
| 518 |
+
"learning_rate": 3.9550810756370235e-05,
|
| 519 |
+
"loss": 0.5414,
|
| 520 |
+
"step": 41500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.12,
|
| 524 |
+
"learning_rate": 3.942491691006144e-05,
|
| 525 |
+
"loss": 0.5452,
|
| 526 |
+
"step": 42000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.14,
|
| 530 |
+
"learning_rate": 3.929902306375265e-05,
|
| 531 |
+
"loss": 0.5373,
|
| 532 |
+
"step": 42500
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.17,
|
| 536 |
+
"learning_rate": 3.917312921744385e-05,
|
| 537 |
+
"loss": 0.5373,
|
| 538 |
+
"step": 43000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.19,
|
| 542 |
+
"learning_rate": 3.904723537113506e-05,
|
| 543 |
+
"loss": 0.539,
|
| 544 |
+
"step": 43500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.22,
|
| 548 |
+
"learning_rate": 3.8921341524826264e-05,
|
| 549 |
+
"loss": 0.5363,
|
| 550 |
+
"step": 44000
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.24,
|
| 554 |
+
"learning_rate": 3.879544767851748e-05,
|
| 555 |
+
"loss": 0.5376,
|
| 556 |
+
"step": 44500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.27,
|
| 560 |
+
"learning_rate": 3.866955383220868e-05,
|
| 561 |
+
"loss": 0.5421,
|
| 562 |
+
"step": 45000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.29,
|
| 566 |
+
"learning_rate": 3.8543659985899895e-05,
|
| 567 |
+
"loss": 0.5399,
|
| 568 |
+
"step": 45500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.32,
|
| 572 |
+
"learning_rate": 3.84177661395911e-05,
|
| 573 |
+
"loss": 0.5343,
|
| 574 |
+
"step": 46000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.34,
|
| 578 |
+
"learning_rate": 3.829187229328231e-05,
|
| 579 |
+
"loss": 0.5365,
|
| 580 |
+
"step": 46500
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.37,
|
| 584 |
+
"learning_rate": 3.816597844697351e-05,
|
| 585 |
+
"loss": 0.5397,
|
| 586 |
+
"step": 47000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.39,
|
| 590 |
+
"learning_rate": 3.804008460066472e-05,
|
| 591 |
+
"loss": 0.5342,
|
| 592 |
+
"step": 47500
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.42,
|
| 596 |
+
"learning_rate": 3.7914190754355925e-05,
|
| 597 |
+
"loss": 0.5327,
|
| 598 |
+
"step": 48000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.44,
|
| 602 |
+
"learning_rate": 3.778829690804714e-05,
|
| 603 |
+
"loss": 0.54,
|
| 604 |
+
"step": 48500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.47,
|
| 608 |
+
"learning_rate": 3.766240306173834e-05,
|
| 609 |
+
"loss": 0.5362,
|
| 610 |
+
"step": 49000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.49,
|
| 614 |
+
"learning_rate": 3.753650921542955e-05,
|
| 615 |
+
"loss": 0.5351,
|
| 616 |
+
"step": 49500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.52,
|
| 620 |
+
"learning_rate": 3.741061536912076e-05,
|
| 621 |
+
"loss": 0.5351,
|
| 622 |
+
"step": 50000
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.54,
|
| 626 |
+
"learning_rate": 3.728472152281197e-05,
|
| 627 |
+
"loss": 0.5284,
|
| 628 |
+
"step": 50500
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 2.57,
|
| 632 |
+
"learning_rate": 3.715882767650317e-05,
|
| 633 |
+
"loss": 0.5345,
|
| 634 |
+
"step": 51000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.59,
|
| 638 |
+
"learning_rate": 3.7032933830194386e-05,
|
| 639 |
+
"loss": 0.5352,
|
| 640 |
+
"step": 51500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.62,
|
| 644 |
+
"learning_rate": 3.690703998388559e-05,
|
| 645 |
+
"loss": 0.5328,
|
| 646 |
+
"step": 52000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.64,
|
| 650 |
+
"learning_rate": 3.67811461375768e-05,
|
| 651 |
+
"loss": 0.5362,
|
| 652 |
+
"step": 52500
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.67,
|
| 656 |
+
"learning_rate": 3.6655252291268e-05,
|
| 657 |
+
"loss": 0.5304,
|
| 658 |
+
"step": 53000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.69,
|
| 662 |
+
"learning_rate": 3.652935844495921e-05,
|
| 663 |
+
"loss": 0.5322,
|
| 664 |
+
"step": 53500
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.72,
|
| 668 |
+
"learning_rate": 3.640346459865042e-05,
|
| 669 |
+
"loss": 0.5295,
|
| 670 |
+
"step": 54000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.74,
|
| 674 |
+
"learning_rate": 3.627757075234163e-05,
|
| 675 |
+
"loss": 0.5284,
|
| 676 |
+
"step": 54500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.77,
|
| 680 |
+
"learning_rate": 3.615167690603283e-05,
|
| 681 |
+
"loss": 0.5318,
|
| 682 |
+
"step": 55000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.79,
|
| 686 |
+
"learning_rate": 3.6025783059724046e-05,
|
| 687 |
+
"loss": 0.5312,
|
| 688 |
+
"step": 55500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.82,
|
| 692 |
+
"learning_rate": 3.589988921341525e-05,
|
| 693 |
+
"loss": 0.5282,
|
| 694 |
+
"step": 56000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.85,
|
| 698 |
+
"learning_rate": 3.577399536710646e-05,
|
| 699 |
+
"loss": 0.5292,
|
| 700 |
+
"step": 56500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.87,
|
| 704 |
+
"learning_rate": 3.564810152079766e-05,
|
| 705 |
+
"loss": 0.5289,
|
| 706 |
+
"step": 57000
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.9,
|
| 710 |
+
"learning_rate": 3.552220767448887e-05,
|
| 711 |
+
"loss": 0.5293,
|
| 712 |
+
"step": 57500
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.92,
|
| 716 |
+
"learning_rate": 3.5396313828180075e-05,
|
| 717 |
+
"loss": 0.5241,
|
| 718 |
+
"step": 58000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.95,
|
| 722 |
+
"learning_rate": 3.527041998187129e-05,
|
| 723 |
+
"loss": 0.5275,
|
| 724 |
+
"step": 58500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.97,
|
| 728 |
+
"learning_rate": 3.5144526135562493e-05,
|
| 729 |
+
"loss": 0.5335,
|
| 730 |
+
"step": 59000
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.0,
|
| 734 |
+
"learning_rate": 3.5018632289253706e-05,
|
| 735 |
+
"loss": 0.5244,
|
| 736 |
+
"step": 59500
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.0,
|
| 740 |
+
"eval_loss": 0.6179068088531494,
|
| 741 |
+
"eval_runtime": 51.415,
|
| 742 |
+
"eval_samples_per_second": 343.344,
|
| 743 |
+
"step": 59574
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 3.02,
|
| 747 |
+
"learning_rate": 3.489273844294491e-05,
|
| 748 |
+
"loss": 0.5182,
|
| 749 |
+
"step": 60000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 3.05,
|
| 753 |
+
"learning_rate": 3.476684459663612e-05,
|
| 754 |
+
"loss": 0.5147,
|
| 755 |
+
"step": 60500
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 3.07,
|
| 759 |
+
"learning_rate": 3.464095075032733e-05,
|
| 760 |
+
"loss": 0.5187,
|
| 761 |
+
"step": 61000
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.1,
|
| 765 |
+
"learning_rate": 3.4515056904018536e-05,
|
| 766 |
+
"loss": 0.5201,
|
| 767 |
+
"step": 61500
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 3.12,
|
| 771 |
+
"learning_rate": 3.438916305770974e-05,
|
| 772 |
+
"loss": 0.5199,
|
| 773 |
+
"step": 62000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.15,
|
| 777 |
+
"learning_rate": 3.426326921140095e-05,
|
| 778 |
+
"loss": 0.5239,
|
| 779 |
+
"step": 62500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.17,
|
| 783 |
+
"learning_rate": 3.4137375365092154e-05,
|
| 784 |
+
"loss": 0.5176,
|
| 785 |
+
"step": 63000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.2,
|
| 789 |
+
"learning_rate": 3.401148151878336e-05,
|
| 790 |
+
"loss": 0.5199,
|
| 791 |
+
"step": 63500
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 3.22,
|
| 795 |
+
"learning_rate": 3.388558767247457e-05,
|
| 796 |
+
"loss": 0.5216,
|
| 797 |
+
"step": 64000
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.25,
|
| 801 |
+
"learning_rate": 3.375969382616578e-05,
|
| 802 |
+
"loss": 0.5152,
|
| 803 |
+
"step": 64500
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.27,
|
| 807 |
+
"learning_rate": 3.3633799979856984e-05,
|
| 808 |
+
"loss": 0.5176,
|
| 809 |
+
"step": 65000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.3,
|
| 813 |
+
"learning_rate": 3.3507906133548196e-05,
|
| 814 |
+
"loss": 0.5155,
|
| 815 |
+
"step": 65500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 3.32,
|
| 819 |
+
"learning_rate": 3.33820122872394e-05,
|
| 820 |
+
"loss": 0.5151,
|
| 821 |
+
"step": 66000
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.35,
|
| 825 |
+
"learning_rate": 3.3256118440930615e-05,
|
| 826 |
+
"loss": 0.5176,
|
| 827 |
+
"step": 66500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.37,
|
| 831 |
+
"learning_rate": 3.3130224594621814e-05,
|
| 832 |
+
"loss": 0.5144,
|
| 833 |
+
"step": 67000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 3.4,
|
| 837 |
+
"learning_rate": 3.300433074831302e-05,
|
| 838 |
+
"loss": 0.5172,
|
| 839 |
+
"step": 67500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 3.42,
|
| 843 |
+
"learning_rate": 3.287843690200423e-05,
|
| 844 |
+
"loss": 0.5173,
|
| 845 |
+
"step": 68000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.45,
|
| 849 |
+
"learning_rate": 3.275254305569544e-05,
|
| 850 |
+
"loss": 0.5172,
|
| 851 |
+
"step": 68500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 3.47,
|
| 855 |
+
"learning_rate": 3.2626649209386644e-05,
|
| 856 |
+
"loss": 0.5124,
|
| 857 |
+
"step": 69000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.5,
|
| 861 |
+
"learning_rate": 3.2500755363077856e-05,
|
| 862 |
+
"loss": 0.518,
|
| 863 |
+
"step": 69500
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.53,
|
| 867 |
+
"learning_rate": 3.237486151676906e-05,
|
| 868 |
+
"loss": 0.5164,
|
| 869 |
+
"step": 70000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.55,
|
| 873 |
+
"learning_rate": 3.224896767046027e-05,
|
| 874 |
+
"loss": 0.5175,
|
| 875 |
+
"step": 70500
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 3.58,
|
| 879 |
+
"learning_rate": 3.212307382415148e-05,
|
| 880 |
+
"loss": 0.5156,
|
| 881 |
+
"step": 71000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.6,
|
| 885 |
+
"learning_rate": 3.1997179977842687e-05,
|
| 886 |
+
"loss": 0.5164,
|
| 887 |
+
"step": 71500
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 3.63,
|
| 891 |
+
"learning_rate": 3.187128613153389e-05,
|
| 892 |
+
"loss": 0.5165,
|
| 893 |
+
"step": 72000
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 3.65,
|
| 897 |
+
"learning_rate": 3.17453922852251e-05,
|
| 898 |
+
"loss": 0.5171,
|
| 899 |
+
"step": 72500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.68,
|
| 903 |
+
"learning_rate": 3.1619498438916304e-05,
|
| 904 |
+
"loss": 0.5133,
|
| 905 |
+
"step": 73000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.7,
|
| 909 |
+
"learning_rate": 3.149360459260752e-05,
|
| 910 |
+
"loss": 0.5157,
|
| 911 |
+
"step": 73500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.73,
|
| 915 |
+
"learning_rate": 3.136771074629872e-05,
|
| 916 |
+
"loss": 0.5116,
|
| 917 |
+
"step": 74000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.75,
|
| 921 |
+
"learning_rate": 3.124181689998993e-05,
|
| 922 |
+
"loss": 0.5137,
|
| 923 |
+
"step": 74500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.78,
|
| 927 |
+
"learning_rate": 3.111592305368114e-05,
|
| 928 |
+
"loss": 0.5154,
|
| 929 |
+
"step": 75000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 3.8,
|
| 933 |
+
"learning_rate": 3.099002920737235e-05,
|
| 934 |
+
"loss": 0.5147,
|
| 935 |
+
"step": 75500
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 3.83,
|
| 939 |
+
"learning_rate": 3.086413536106355e-05,
|
| 940 |
+
"loss": 0.5158,
|
| 941 |
+
"step": 76000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.85,
|
| 945 |
+
"learning_rate": 3.0738241514754765e-05,
|
| 946 |
+
"loss": 0.5139,
|
| 947 |
+
"step": 76500
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.88,
|
| 951 |
+
"learning_rate": 3.0612347668445964e-05,
|
| 952 |
+
"loss": 0.5162,
|
| 953 |
+
"step": 77000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.9,
|
| 957 |
+
"learning_rate": 3.0486453822137173e-05,
|
| 958 |
+
"loss": 0.5133,
|
| 959 |
+
"step": 77500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.93,
|
| 963 |
+
"learning_rate": 3.0360559975828383e-05,
|
| 964 |
+
"loss": 0.5126,
|
| 965 |
+
"step": 78000
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.95,
|
| 969 |
+
"learning_rate": 3.023466612951959e-05,
|
| 970 |
+
"loss": 0.5128,
|
| 971 |
+
"step": 78500
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.98,
|
| 975 |
+
"learning_rate": 3.0108772283210794e-05,
|
| 976 |
+
"loss": 0.5135,
|
| 977 |
+
"step": 79000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 4.0,
|
| 981 |
+
"eval_loss": 0.6064777374267578,
|
| 982 |
+
"eval_runtime": 51.6259,
|
| 983 |
+
"eval_samples_per_second": 341.941,
|
| 984 |
+
"step": 79432
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.0,
|
| 988 |
+
"learning_rate": 2.9982878436902007e-05,
|
| 989 |
+
"loss": 0.507,
|
| 990 |
+
"step": 79500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.03,
|
| 994 |
+
"learning_rate": 2.9856984590593213e-05,
|
| 995 |
+
"loss": 0.4969,
|
| 996 |
+
"step": 80000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 4.05,
|
| 1000 |
+
"learning_rate": 2.9731090744284422e-05,
|
| 1001 |
+
"loss": 0.5011,
|
| 1002 |
+
"step": 80500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 4.08,
|
| 1006 |
+
"learning_rate": 2.9605196897975628e-05,
|
| 1007 |
+
"loss": 0.5023,
|
| 1008 |
+
"step": 81000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 4.1,
|
| 1012 |
+
"learning_rate": 2.9479303051666834e-05,
|
| 1013 |
+
"loss": 0.5025,
|
| 1014 |
+
"step": 81500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 4.13,
|
| 1018 |
+
"learning_rate": 2.9353409205358046e-05,
|
| 1019 |
+
"loss": 0.5032,
|
| 1020 |
+
"step": 82000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 4.15,
|
| 1024 |
+
"learning_rate": 2.9227515359049252e-05,
|
| 1025 |
+
"loss": 0.5036,
|
| 1026 |
+
"step": 82500
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 4.18,
|
| 1030 |
+
"learning_rate": 2.9101621512740458e-05,
|
| 1031 |
+
"loss": 0.5004,
|
| 1032 |
+
"step": 83000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 4.2,
|
| 1036 |
+
"learning_rate": 2.8975727666431667e-05,
|
| 1037 |
+
"loss": 0.5041,
|
| 1038 |
+
"step": 83500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 4.23,
|
| 1042 |
+
"learning_rate": 2.8849833820122873e-05,
|
| 1043 |
+
"loss": 0.505,
|
| 1044 |
+
"step": 84000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 4.26,
|
| 1048 |
+
"learning_rate": 2.872393997381408e-05,
|
| 1049 |
+
"loss": 0.5072,
|
| 1050 |
+
"step": 84500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 4.28,
|
| 1054 |
+
"learning_rate": 2.859804612750529e-05,
|
| 1055 |
+
"loss": 0.5012,
|
| 1056 |
+
"step": 85000
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.31,
|
| 1060 |
+
"learning_rate": 2.8472152281196497e-05,
|
| 1061 |
+
"loss": 0.505,
|
| 1062 |
+
"step": 85500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 4.33,
|
| 1066 |
+
"learning_rate": 2.8346258434887703e-05,
|
| 1067 |
+
"loss": 0.5039,
|
| 1068 |
+
"step": 86000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 4.36,
|
| 1072 |
+
"learning_rate": 2.8220364588578912e-05,
|
| 1073 |
+
"loss": 0.5006,
|
| 1074 |
+
"step": 86500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 4.38,
|
| 1078 |
+
"learning_rate": 2.8094470742270118e-05,
|
| 1079 |
+
"loss": 0.5061,
|
| 1080 |
+
"step": 87000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 4.41,
|
| 1084 |
+
"learning_rate": 2.796857689596133e-05,
|
| 1085 |
+
"loss": 0.5018,
|
| 1086 |
+
"step": 87500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 4.43,
|
| 1090 |
+
"learning_rate": 2.7842683049652536e-05,
|
| 1091 |
+
"loss": 0.5009,
|
| 1092 |
+
"step": 88000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 4.46,
|
| 1096 |
+
"learning_rate": 2.771678920334374e-05,
|
| 1097 |
+
"loss": 0.503,
|
| 1098 |
+
"step": 88500
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 4.48,
|
| 1102 |
+
"learning_rate": 2.759089535703495e-05,
|
| 1103 |
+
"loss": 0.5018,
|
| 1104 |
+
"step": 89000
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.51,
|
| 1108 |
+
"learning_rate": 2.7465001510726157e-05,
|
| 1109 |
+
"loss": 0.502,
|
| 1110 |
+
"step": 89500
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 4.53,
|
| 1114 |
+
"learning_rate": 2.7339107664417363e-05,
|
| 1115 |
+
"loss": 0.5039,
|
| 1116 |
+
"step": 90000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.56,
|
| 1120 |
+
"learning_rate": 2.7213213818108572e-05,
|
| 1121 |
+
"loss": 0.5044,
|
| 1122 |
+
"step": 90500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 4.58,
|
| 1126 |
+
"learning_rate": 2.7087319971799778e-05,
|
| 1127 |
+
"loss": 0.4998,
|
| 1128 |
+
"step": 91000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 4.61,
|
| 1132 |
+
"learning_rate": 2.6961426125490984e-05,
|
| 1133 |
+
"loss": 0.5046,
|
| 1134 |
+
"step": 91500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 4.63,
|
| 1138 |
+
"learning_rate": 2.6835532279182197e-05,
|
| 1139 |
+
"loss": 0.5039,
|
| 1140 |
+
"step": 92000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 4.66,
|
| 1144 |
+
"learning_rate": 2.6709638432873402e-05,
|
| 1145 |
+
"loss": 0.5024,
|
| 1146 |
+
"step": 92500
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 4.68,
|
| 1150 |
+
"learning_rate": 2.6583744586564608e-05,
|
| 1151 |
+
"loss": 0.503,
|
| 1152 |
+
"step": 93000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.71,
|
| 1156 |
+
"learning_rate": 2.6457850740255818e-05,
|
| 1157 |
+
"loss": 0.5007,
|
| 1158 |
+
"step": 93500
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 4.73,
|
| 1162 |
+
"learning_rate": 2.6331956893947023e-05,
|
| 1163 |
+
"loss": 0.5027,
|
| 1164 |
+
"step": 94000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 4.76,
|
| 1168 |
+
"learning_rate": 2.6206063047638236e-05,
|
| 1169 |
+
"loss": 0.5081,
|
| 1170 |
+
"step": 94500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 4.78,
|
| 1174 |
+
"learning_rate": 2.6080169201329442e-05,
|
| 1175 |
+
"loss": 0.5002,
|
| 1176 |
+
"step": 95000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 4.81,
|
| 1180 |
+
"learning_rate": 2.5954275355020648e-05,
|
| 1181 |
+
"loss": 0.5045,
|
| 1182 |
+
"step": 95500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 4.83,
|
| 1186 |
+
"learning_rate": 2.5828381508711857e-05,
|
| 1187 |
+
"loss": 0.4986,
|
| 1188 |
+
"step": 96000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 4.86,
|
| 1192 |
+
"learning_rate": 2.5702487662403063e-05,
|
| 1193 |
+
"loss": 0.5026,
|
| 1194 |
+
"step": 96500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 4.88,
|
| 1198 |
+
"learning_rate": 2.557659381609427e-05,
|
| 1199 |
+
"loss": 0.502,
|
| 1200 |
+
"step": 97000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.91,
|
| 1204 |
+
"learning_rate": 2.545069996978548e-05,
|
| 1205 |
+
"loss": 0.5016,
|
| 1206 |
+
"step": 97500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 4.94,
|
| 1210 |
+
"learning_rate": 2.5324806123476687e-05,
|
| 1211 |
+
"loss": 0.5056,
|
| 1212 |
+
"step": 98000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 4.96,
|
| 1216 |
+
"learning_rate": 2.519891227716789e-05,
|
| 1217 |
+
"loss": 0.4983,
|
| 1218 |
+
"step": 98500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 4.99,
|
| 1222 |
+
"learning_rate": 2.5073018430859102e-05,
|
| 1223 |
+
"loss": 0.5002,
|
| 1224 |
+
"step": 99000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 5.0,
|
| 1228 |
+
"eval_loss": 0.6010987758636475,
|
| 1229 |
+
"eval_runtime": 51.6361,
|
| 1230 |
+
"eval_samples_per_second": 341.873,
|
| 1231 |
+
"step": 99290
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 5.01,
|
| 1235 |
+
"learning_rate": 2.4947124584550308e-05,
|
| 1236 |
+
"loss": 0.4916,
|
| 1237 |
+
"step": 99500
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 5.04,
|
| 1241 |
+
"learning_rate": 2.4821230738241517e-05,
|
| 1242 |
+
"loss": 0.4912,
|
| 1243 |
+
"step": 100000
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 5.06,
|
| 1247 |
+
"learning_rate": 2.4695336891932723e-05,
|
| 1248 |
+
"loss": 0.4941,
|
| 1249 |
+
"step": 100500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 5.09,
|
| 1253 |
+
"learning_rate": 2.456944304562393e-05,
|
| 1254 |
+
"loss": 0.4876,
|
| 1255 |
+
"step": 101000
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 5.11,
|
| 1259 |
+
"learning_rate": 2.4443549199315138e-05,
|
| 1260 |
+
"loss": 0.4942,
|
| 1261 |
+
"step": 101500
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 5.14,
|
| 1265 |
+
"learning_rate": 2.4317655353006347e-05,
|
| 1266 |
+
"loss": 0.4937,
|
| 1267 |
+
"step": 102000
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 5.16,
|
| 1271 |
+
"learning_rate": 2.4191761506697556e-05,
|
| 1272 |
+
"loss": 0.4902,
|
| 1273 |
+
"step": 102500
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 5.19,
|
| 1277 |
+
"learning_rate": 2.4065867660388762e-05,
|
| 1278 |
+
"loss": 0.4909,
|
| 1279 |
+
"step": 103000
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 5.21,
|
| 1283 |
+
"learning_rate": 2.3939973814079968e-05,
|
| 1284 |
+
"loss": 0.4933,
|
| 1285 |
+
"step": 103500
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 5.24,
|
| 1289 |
+
"learning_rate": 2.3814079967771177e-05,
|
| 1290 |
+
"loss": 0.4935,
|
| 1291 |
+
"step": 104000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 5.26,
|
| 1295 |
+
"learning_rate": 2.3688186121462383e-05,
|
| 1296 |
+
"loss": 0.4951,
|
| 1297 |
+
"step": 104500
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 5.29,
|
| 1301 |
+
"learning_rate": 2.3562292275153592e-05,
|
| 1302 |
+
"loss": 0.4913,
|
| 1303 |
+
"step": 105000
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 5.31,
|
| 1307 |
+
"learning_rate": 2.3436398428844798e-05,
|
| 1308 |
+
"loss": 0.4973,
|
| 1309 |
+
"step": 105500
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 5.34,
|
| 1313 |
+
"learning_rate": 2.3310504582536007e-05,
|
| 1314 |
+
"loss": 0.49,
|
| 1315 |
+
"step": 106000
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 5.36,
|
| 1319 |
+
"learning_rate": 2.3184610736227213e-05,
|
| 1320 |
+
"loss": 0.4897,
|
| 1321 |
+
"step": 106500
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.39,
|
| 1325 |
+
"learning_rate": 2.3058716889918422e-05,
|
| 1326 |
+
"loss": 0.4929,
|
| 1327 |
+
"step": 107000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 5.41,
|
| 1331 |
+
"learning_rate": 2.293282304360963e-05,
|
| 1332 |
+
"loss": 0.4876,
|
| 1333 |
+
"step": 107500
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 5.44,
|
| 1337 |
+
"learning_rate": 2.2806929197300837e-05,
|
| 1338 |
+
"loss": 0.4951,
|
| 1339 |
+
"step": 108000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 5.46,
|
| 1343 |
+
"learning_rate": 2.2681035350992043e-05,
|
| 1344 |
+
"loss": 0.4913,
|
| 1345 |
+
"step": 108500
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 5.49,
|
| 1349 |
+
"learning_rate": 2.2555141504683252e-05,
|
| 1350 |
+
"loss": 0.4952,
|
| 1351 |
+
"step": 109000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 5.51,
|
| 1355 |
+
"learning_rate": 2.242924765837446e-05,
|
| 1356 |
+
"loss": 0.4894,
|
| 1357 |
+
"step": 109500
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 5.54,
|
| 1361 |
+
"learning_rate": 2.2303353812065667e-05,
|
| 1362 |
+
"loss": 0.4936,
|
| 1363 |
+
"step": 110000
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 5.56,
|
| 1367 |
+
"learning_rate": 2.2177459965756873e-05,
|
| 1368 |
+
"loss": 0.488,
|
| 1369 |
+
"step": 110500
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 5.59,
|
| 1373 |
+
"learning_rate": 2.2051566119448082e-05,
|
| 1374 |
+
"loss": 0.4908,
|
| 1375 |
+
"step": 111000
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 5.61,
|
| 1379 |
+
"learning_rate": 2.192567227313929e-05,
|
| 1380 |
+
"loss": 0.4935,
|
| 1381 |
+
"step": 111500
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 5.64,
|
| 1385 |
+
"learning_rate": 2.1799778426830498e-05,
|
| 1386 |
+
"loss": 0.4883,
|
| 1387 |
+
"step": 112000
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 5.67,
|
| 1391 |
+
"learning_rate": 2.1673884580521707e-05,
|
| 1392 |
+
"loss": 0.4912,
|
| 1393 |
+
"step": 112500
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 5.69,
|
| 1397 |
+
"learning_rate": 2.1547990734212913e-05,
|
| 1398 |
+
"loss": 0.4903,
|
| 1399 |
+
"step": 113000
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 5.72,
|
| 1403 |
+
"learning_rate": 2.142209688790412e-05,
|
| 1404 |
+
"loss": 0.4914,
|
| 1405 |
+
"step": 113500
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 5.74,
|
| 1409 |
+
"learning_rate": 2.1296203041595328e-05,
|
| 1410 |
+
"loss": 0.489,
|
| 1411 |
+
"step": 114000
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 5.77,
|
| 1415 |
+
"learning_rate": 2.1170309195286537e-05,
|
| 1416 |
+
"loss": 0.4929,
|
| 1417 |
+
"step": 114500
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 5.79,
|
| 1421 |
+
"learning_rate": 2.1044415348977743e-05,
|
| 1422 |
+
"loss": 0.4892,
|
| 1423 |
+
"step": 115000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 5.82,
|
| 1427 |
+
"learning_rate": 2.091852150266895e-05,
|
| 1428 |
+
"loss": 0.4854,
|
| 1429 |
+
"step": 115500
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 5.84,
|
| 1433 |
+
"learning_rate": 2.0792627656360158e-05,
|
| 1434 |
+
"loss": 0.4938,
|
| 1435 |
+
"step": 116000
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 5.87,
|
| 1439 |
+
"learning_rate": 2.0666733810051367e-05,
|
| 1440 |
+
"loss": 0.4916,
|
| 1441 |
+
"step": 116500
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 5.89,
|
| 1445 |
+
"learning_rate": 2.0540839963742573e-05,
|
| 1446 |
+
"loss": 0.4945,
|
| 1447 |
+
"step": 117000
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 5.92,
|
| 1451 |
+
"learning_rate": 2.0414946117433782e-05,
|
| 1452 |
+
"loss": 0.4901,
|
| 1453 |
+
"step": 117500
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 5.94,
|
| 1457 |
+
"learning_rate": 2.0289052271124988e-05,
|
| 1458 |
+
"loss": 0.4922,
|
| 1459 |
+
"step": 118000
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 5.97,
|
| 1463 |
+
"learning_rate": 2.0163158424816194e-05,
|
| 1464 |
+
"loss": 0.4903,
|
| 1465 |
+
"step": 118500
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 5.99,
|
| 1469 |
+
"learning_rate": 2.0037264578507403e-05,
|
| 1470 |
+
"loss": 0.4911,
|
| 1471 |
+
"step": 119000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 6.0,
|
| 1475 |
+
"eval_loss": 0.5948862433433533,
|
| 1476 |
+
"eval_runtime": 51.885,
|
| 1477 |
+
"eval_samples_per_second": 340.233,
|
| 1478 |
+
"step": 119148
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 6.02,
|
| 1482 |
+
"learning_rate": 1.9911370732198612e-05,
|
| 1483 |
+
"loss": 0.4846,
|
| 1484 |
+
"step": 119500
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 6.04,
|
| 1488 |
+
"learning_rate": 1.978547688588982e-05,
|
| 1489 |
+
"loss": 0.4849,
|
| 1490 |
+
"step": 120000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 6.07,
|
| 1494 |
+
"learning_rate": 1.9659583039581027e-05,
|
| 1495 |
+
"loss": 0.4815,
|
| 1496 |
+
"step": 120500
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 6.09,
|
| 1500 |
+
"learning_rate": 1.9533689193272233e-05,
|
| 1501 |
+
"loss": 0.4835,
|
| 1502 |
+
"step": 121000
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 6.12,
|
| 1506 |
+
"learning_rate": 1.9407795346963442e-05,
|
| 1507 |
+
"loss": 0.4802,
|
| 1508 |
+
"step": 121500
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 6.14,
|
| 1512 |
+
"learning_rate": 1.9281901500654648e-05,
|
| 1513 |
+
"loss": 0.482,
|
| 1514 |
+
"step": 122000
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 6.17,
|
| 1518 |
+
"learning_rate": 1.9156007654345857e-05,
|
| 1519 |
+
"loss": 0.4865,
|
| 1520 |
+
"step": 122500
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 6.19,
|
| 1524 |
+
"learning_rate": 1.9030113808037063e-05,
|
| 1525 |
+
"loss": 0.4846,
|
| 1526 |
+
"step": 123000
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 6.22,
|
| 1530 |
+
"learning_rate": 1.8904219961728272e-05,
|
| 1531 |
+
"loss": 0.4826,
|
| 1532 |
+
"step": 123500
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 6.24,
|
| 1536 |
+
"learning_rate": 1.8778326115419478e-05,
|
| 1537 |
+
"loss": 0.4782,
|
| 1538 |
+
"step": 124000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 6.27,
|
| 1542 |
+
"learning_rate": 1.8652432269110687e-05,
|
| 1543 |
+
"loss": 0.4839,
|
| 1544 |
+
"step": 124500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 6.29,
|
| 1548 |
+
"learning_rate": 1.8526538422801896e-05,
|
| 1549 |
+
"loss": 0.485,
|
| 1550 |
+
"step": 125000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 6.32,
|
| 1554 |
+
"learning_rate": 1.8400644576493102e-05,
|
| 1555 |
+
"loss": 0.4803,
|
| 1556 |
+
"step": 125500
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 6.35,
|
| 1560 |
+
"learning_rate": 1.8274750730184308e-05,
|
| 1561 |
+
"loss": 0.4792,
|
| 1562 |
+
"step": 126000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 6.37,
|
| 1566 |
+
"learning_rate": 1.8148856883875517e-05,
|
| 1567 |
+
"loss": 0.4859,
|
| 1568 |
+
"step": 126500
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 6.4,
|
| 1572 |
+
"learning_rate": 1.8022963037566727e-05,
|
| 1573 |
+
"loss": 0.4847,
|
| 1574 |
+
"step": 127000
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 6.42,
|
| 1578 |
+
"learning_rate": 1.7897069191257932e-05,
|
| 1579 |
+
"loss": 0.4832,
|
| 1580 |
+
"step": 127500
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 6.45,
|
| 1584 |
+
"learning_rate": 1.7771175344949138e-05,
|
| 1585 |
+
"loss": 0.4865,
|
| 1586 |
+
"step": 128000
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 6.47,
|
| 1590 |
+
"learning_rate": 1.7645281498640347e-05,
|
| 1591 |
+
"loss": 0.4836,
|
| 1592 |
+
"step": 128500
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 6.5,
|
| 1596 |
+
"learning_rate": 1.7519387652331553e-05,
|
| 1597 |
+
"loss": 0.4855,
|
| 1598 |
+
"step": 129000
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 6.52,
|
| 1602 |
+
"learning_rate": 1.7393493806022763e-05,
|
| 1603 |
+
"loss": 0.4806,
|
| 1604 |
+
"step": 129500
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 6.55,
|
| 1608 |
+
"learning_rate": 1.7267599959713972e-05,
|
| 1609 |
+
"loss": 0.4801,
|
| 1610 |
+
"step": 130000
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 6.57,
|
| 1614 |
+
"learning_rate": 1.7141706113405178e-05,
|
| 1615 |
+
"loss": 0.4807,
|
| 1616 |
+
"step": 130500
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 6.6,
|
| 1620 |
+
"learning_rate": 1.7015812267096383e-05,
|
| 1621 |
+
"loss": 0.4832,
|
| 1622 |
+
"step": 131000
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 6.62,
|
| 1626 |
+
"learning_rate": 1.6889918420787593e-05,
|
| 1627 |
+
"loss": 0.4803,
|
| 1628 |
+
"step": 131500
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 6.65,
|
| 1632 |
+
"learning_rate": 1.6764024574478802e-05,
|
| 1633 |
+
"loss": 0.4821,
|
| 1634 |
+
"step": 132000
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 6.67,
|
| 1638 |
+
"learning_rate": 1.6638130728170008e-05,
|
| 1639 |
+
"loss": 0.4792,
|
| 1640 |
+
"step": 132500
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 6.7,
|
| 1644 |
+
"learning_rate": 1.6512236881861213e-05,
|
| 1645 |
+
"loss": 0.4827,
|
| 1646 |
+
"step": 133000
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 6.72,
|
| 1650 |
+
"learning_rate": 1.6386343035552423e-05,
|
| 1651 |
+
"loss": 0.4821,
|
| 1652 |
+
"step": 133500
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 6.75,
|
| 1656 |
+
"learning_rate": 1.6260449189243632e-05,
|
| 1657 |
+
"loss": 0.4754,
|
| 1658 |
+
"step": 134000
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 6.77,
|
| 1662 |
+
"learning_rate": 1.6134555342934838e-05,
|
| 1663 |
+
"loss": 0.4822,
|
| 1664 |
+
"step": 134500
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 6.8,
|
| 1668 |
+
"learning_rate": 1.6008661496626047e-05,
|
| 1669 |
+
"loss": 0.4813,
|
| 1670 |
+
"step": 135000
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 6.82,
|
| 1674 |
+
"learning_rate": 1.5882767650317253e-05,
|
| 1675 |
+
"loss": 0.4802,
|
| 1676 |
+
"step": 135500
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 6.85,
|
| 1680 |
+
"learning_rate": 1.575687380400846e-05,
|
| 1681 |
+
"loss": 0.4835,
|
| 1682 |
+
"step": 136000
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 6.87,
|
| 1686 |
+
"learning_rate": 1.5630979957699668e-05,
|
| 1687 |
+
"loss": 0.4842,
|
| 1688 |
+
"step": 136500
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 6.9,
|
| 1692 |
+
"learning_rate": 1.5505086111390877e-05,
|
| 1693 |
+
"loss": 0.4867,
|
| 1694 |
+
"step": 137000
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 6.92,
|
| 1698 |
+
"learning_rate": 1.5379192265082086e-05,
|
| 1699 |
+
"loss": 0.4832,
|
| 1700 |
+
"step": 137500
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 6.95,
|
| 1704 |
+
"learning_rate": 1.525329841877329e-05,
|
| 1705 |
+
"loss": 0.4835,
|
| 1706 |
+
"step": 138000
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 6.97,
|
| 1710 |
+
"learning_rate": 1.5127404572464498e-05,
|
| 1711 |
+
"loss": 0.4813,
|
| 1712 |
+
"step": 138500
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 7.0,
|
| 1716 |
+
"learning_rate": 1.5001510726155707e-05,
|
| 1717 |
+
"loss": 0.4799,
|
| 1718 |
+
"step": 139000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 7.0,
|
| 1722 |
+
"eval_loss": 0.5898594856262207,
|
| 1723 |
+
"eval_runtime": 51.3831,
|
| 1724 |
+
"eval_samples_per_second": 343.557,
|
| 1725 |
+
"step": 139006
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 7.02,
|
| 1729 |
+
"learning_rate": 1.4875616879846913e-05,
|
| 1730 |
+
"loss": 0.4741,
|
| 1731 |
+
"step": 139500
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 7.05,
|
| 1735 |
+
"learning_rate": 1.474972303353812e-05,
|
| 1736 |
+
"loss": 0.4743,
|
| 1737 |
+
"step": 140000
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 7.08,
|
| 1741 |
+
"learning_rate": 1.462382918722933e-05,
|
| 1742 |
+
"loss": 0.477,
|
| 1743 |
+
"step": 140500
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 7.1,
|
| 1747 |
+
"learning_rate": 1.4497935340920537e-05,
|
| 1748 |
+
"loss": 0.476,
|
| 1749 |
+
"step": 141000
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 7.13,
|
| 1753 |
+
"learning_rate": 1.4372041494611743e-05,
|
| 1754 |
+
"loss": 0.474,
|
| 1755 |
+
"step": 141500
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 7.15,
|
| 1759 |
+
"learning_rate": 1.4246147648302952e-05,
|
| 1760 |
+
"loss": 0.4761,
|
| 1761 |
+
"step": 142000
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 7.18,
|
| 1765 |
+
"learning_rate": 1.412025380199416e-05,
|
| 1766 |
+
"loss": 0.4757,
|
| 1767 |
+
"step": 142500
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 7.2,
|
| 1771 |
+
"learning_rate": 1.3994359955685366e-05,
|
| 1772 |
+
"loss": 0.4725,
|
| 1773 |
+
"step": 143000
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 7.23,
|
| 1777 |
+
"learning_rate": 1.3868466109376573e-05,
|
| 1778 |
+
"loss": 0.4743,
|
| 1779 |
+
"step": 143500
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 7.25,
|
| 1783 |
+
"learning_rate": 1.3742572263067782e-05,
|
| 1784 |
+
"loss": 0.4789,
|
| 1785 |
+
"step": 144000
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 7.28,
|
| 1789 |
+
"learning_rate": 1.361667841675899e-05,
|
| 1790 |
+
"loss": 0.4683,
|
| 1791 |
+
"step": 144500
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 7.3,
|
| 1795 |
+
"learning_rate": 1.3490784570450196e-05,
|
| 1796 |
+
"loss": 0.4746,
|
| 1797 |
+
"step": 145000
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 7.33,
|
| 1801 |
+
"learning_rate": 1.3364890724141405e-05,
|
| 1802 |
+
"loss": 0.4698,
|
| 1803 |
+
"step": 145500
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 7.35,
|
| 1807 |
+
"learning_rate": 1.3238996877832612e-05,
|
| 1808 |
+
"loss": 0.4726,
|
| 1809 |
+
"step": 146000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 7.38,
|
| 1813 |
+
"learning_rate": 1.3113103031523818e-05,
|
| 1814 |
+
"loss": 0.4759,
|
| 1815 |
+
"step": 146500
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 7.4,
|
| 1819 |
+
"learning_rate": 1.2987209185215027e-05,
|
| 1820 |
+
"loss": 0.4727,
|
| 1821 |
+
"step": 147000
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 7.43,
|
| 1825 |
+
"learning_rate": 1.2861315338906235e-05,
|
| 1826 |
+
"loss": 0.4737,
|
| 1827 |
+
"step": 147500
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 7.45,
|
| 1831 |
+
"learning_rate": 1.2735421492597444e-05,
|
| 1832 |
+
"loss": 0.4732,
|
| 1833 |
+
"step": 148000
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 7.48,
|
| 1837 |
+
"learning_rate": 1.2609527646288648e-05,
|
| 1838 |
+
"loss": 0.476,
|
| 1839 |
+
"step": 148500
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 7.5,
|
| 1843 |
+
"learning_rate": 1.2483633799979858e-05,
|
| 1844 |
+
"loss": 0.4751,
|
| 1845 |
+
"step": 149000
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 7.53,
|
| 1849 |
+
"learning_rate": 1.2357739953671065e-05,
|
| 1850 |
+
"loss": 0.4769,
|
| 1851 |
+
"step": 149500
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 7.55,
|
| 1855 |
+
"learning_rate": 1.2231846107362273e-05,
|
| 1856 |
+
"loss": 0.4751,
|
| 1857 |
+
"step": 150000
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 7.58,
|
| 1861 |
+
"learning_rate": 1.210595226105348e-05,
|
| 1862 |
+
"loss": 0.4732,
|
| 1863 |
+
"step": 150500
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 7.6,
|
| 1867 |
+
"learning_rate": 1.1980058414744688e-05,
|
| 1868 |
+
"loss": 0.4745,
|
| 1869 |
+
"step": 151000
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 7.63,
|
| 1873 |
+
"learning_rate": 1.1854164568435895e-05,
|
| 1874 |
+
"loss": 0.471,
|
| 1875 |
+
"step": 151500
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 7.65,
|
| 1879 |
+
"learning_rate": 1.1728270722127103e-05,
|
| 1880 |
+
"loss": 0.4744,
|
| 1881 |
+
"step": 152000
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 7.68,
|
| 1885 |
+
"learning_rate": 1.160237687581831e-05,
|
| 1886 |
+
"loss": 0.4799,
|
| 1887 |
+
"step": 152500
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 7.7,
|
| 1891 |
+
"learning_rate": 1.147648302950952e-05,
|
| 1892 |
+
"loss": 0.474,
|
| 1893 |
+
"step": 153000
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 7.73,
|
| 1897 |
+
"learning_rate": 1.1350589183200725e-05,
|
| 1898 |
+
"loss": 0.4768,
|
| 1899 |
+
"step": 153500
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 7.76,
|
| 1903 |
+
"learning_rate": 1.1224695336891933e-05,
|
| 1904 |
+
"loss": 0.4751,
|
| 1905 |
+
"step": 154000
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 7.78,
|
| 1909 |
+
"learning_rate": 1.109880149058314e-05,
|
| 1910 |
+
"loss": 0.477,
|
| 1911 |
+
"step": 154500
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 7.81,
|
| 1915 |
+
"learning_rate": 1.0972907644274348e-05,
|
| 1916 |
+
"loss": 0.4759,
|
| 1917 |
+
"step": 155000
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 7.83,
|
| 1921 |
+
"learning_rate": 1.0847013797965557e-05,
|
| 1922 |
+
"loss": 0.472,
|
| 1923 |
+
"step": 155500
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 7.86,
|
| 1927 |
+
"learning_rate": 1.0721119951656763e-05,
|
| 1928 |
+
"loss": 0.4741,
|
| 1929 |
+
"step": 156000
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 7.88,
|
| 1933 |
+
"learning_rate": 1.0595226105347972e-05,
|
| 1934 |
+
"loss": 0.4776,
|
| 1935 |
+
"step": 156500
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 7.91,
|
| 1939 |
+
"learning_rate": 1.0469332259039178e-05,
|
| 1940 |
+
"loss": 0.4735,
|
| 1941 |
+
"step": 157000
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 7.93,
|
| 1945 |
+
"learning_rate": 1.0343438412730385e-05,
|
| 1946 |
+
"loss": 0.4773,
|
| 1947 |
+
"step": 157500
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 7.96,
|
| 1951 |
+
"learning_rate": 1.0217544566421595e-05,
|
| 1952 |
+
"loss": 0.474,
|
| 1953 |
+
"step": 158000
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 7.98,
|
| 1957 |
+
"learning_rate": 1.00916507201128e-05,
|
| 1958 |
+
"loss": 0.4749,
|
| 1959 |
+
"step": 158500
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 8.0,
|
| 1963 |
+
"eval_loss": 0.5894228219985962,
|
| 1964 |
+
"eval_runtime": 51.3606,
|
| 1965 |
+
"eval_samples_per_second": 343.707,
|
| 1966 |
+
"step": 158864
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 8.01,
|
| 1970 |
+
"learning_rate": 9.96575687380401e-06,
|
| 1971 |
+
"loss": 0.4705,
|
| 1972 |
+
"step": 159000
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 8.03,
|
| 1976 |
+
"learning_rate": 9.839863027495217e-06,
|
| 1977 |
+
"loss": 0.4665,
|
| 1978 |
+
"step": 159500
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 8.06,
|
| 1982 |
+
"learning_rate": 9.713969181186425e-06,
|
| 1983 |
+
"loss": 0.4634,
|
| 1984 |
+
"step": 160000
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 8.08,
|
| 1988 |
+
"learning_rate": 9.588075334877632e-06,
|
| 1989 |
+
"loss": 0.4673,
|
| 1990 |
+
"step": 160500
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 8.11,
|
| 1994 |
+
"learning_rate": 9.462181488568838e-06,
|
| 1995 |
+
"loss": 0.4659,
|
| 1996 |
+
"step": 161000
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 8.13,
|
| 2000 |
+
"learning_rate": 9.336287642260047e-06,
|
| 2001 |
+
"loss": 0.469,
|
| 2002 |
+
"step": 161500
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 8.16,
|
| 2006 |
+
"learning_rate": 9.210393795951255e-06,
|
| 2007 |
+
"loss": 0.4635,
|
| 2008 |
+
"step": 162000
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 8.18,
|
| 2012 |
+
"learning_rate": 9.084499949642462e-06,
|
| 2013 |
+
"loss": 0.4695,
|
| 2014 |
+
"step": 162500
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 8.21,
|
| 2018 |
+
"learning_rate": 8.95860610333367e-06,
|
| 2019 |
+
"loss": 0.4697,
|
| 2020 |
+
"step": 163000
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 8.23,
|
| 2024 |
+
"learning_rate": 8.832712257024877e-06,
|
| 2025 |
+
"loss": 0.4686,
|
| 2026 |
+
"step": 163500
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 8.26,
|
| 2030 |
+
"learning_rate": 8.706818410716085e-06,
|
| 2031 |
+
"loss": 0.4683,
|
| 2032 |
+
"step": 164000
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 8.28,
|
| 2036 |
+
"learning_rate": 8.580924564407292e-06,
|
| 2037 |
+
"loss": 0.4716,
|
| 2038 |
+
"step": 164500
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 8.31,
|
| 2042 |
+
"learning_rate": 8.4550307180985e-06,
|
| 2043 |
+
"loss": 0.4632,
|
| 2044 |
+
"step": 165000
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 8.33,
|
| 2048 |
+
"learning_rate": 8.329136871789707e-06,
|
| 2049 |
+
"loss": 0.4687,
|
| 2050 |
+
"step": 165500
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 8.36,
|
| 2054 |
+
"learning_rate": 8.203243025480915e-06,
|
| 2055 |
+
"loss": 0.4683,
|
| 2056 |
+
"step": 166000
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 8.38,
|
| 2060 |
+
"learning_rate": 8.077349179172123e-06,
|
| 2061 |
+
"loss": 0.4652,
|
| 2062 |
+
"step": 166500
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 8.41,
|
| 2066 |
+
"learning_rate": 7.95145533286333e-06,
|
| 2067 |
+
"loss": 0.4688,
|
| 2068 |
+
"step": 167000
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 8.43,
|
| 2072 |
+
"learning_rate": 7.825561486554538e-06,
|
| 2073 |
+
"loss": 0.4674,
|
| 2074 |
+
"step": 167500
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 8.46,
|
| 2078 |
+
"learning_rate": 7.699667640245745e-06,
|
| 2079 |
+
"loss": 0.4707,
|
| 2080 |
+
"step": 168000
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 8.49,
|
| 2084 |
+
"learning_rate": 7.573773793936953e-06,
|
| 2085 |
+
"loss": 0.4718,
|
| 2086 |
+
"step": 168500
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 8.51,
|
| 2090 |
+
"learning_rate": 7.44787994762816e-06,
|
| 2091 |
+
"loss": 0.4693,
|
| 2092 |
+
"step": 169000
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 8.54,
|
| 2096 |
+
"learning_rate": 7.3219861013193685e-06,
|
| 2097 |
+
"loss": 0.4655,
|
| 2098 |
+
"step": 169500
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 8.56,
|
| 2102 |
+
"learning_rate": 7.196092255010575e-06,
|
| 2103 |
+
"loss": 0.4683,
|
| 2104 |
+
"step": 170000
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 8.59,
|
| 2108 |
+
"learning_rate": 7.0701984087017836e-06,
|
| 2109 |
+
"loss": 0.471,
|
| 2110 |
+
"step": 170500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 8.61,
|
| 2114 |
+
"learning_rate": 6.94430456239299e-06,
|
| 2115 |
+
"loss": 0.4665,
|
| 2116 |
+
"step": 171000
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 8.64,
|
| 2120 |
+
"learning_rate": 6.818410716084198e-06,
|
| 2121 |
+
"loss": 0.4693,
|
| 2122 |
+
"step": 171500
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 8.66,
|
| 2126 |
+
"learning_rate": 6.692516869775406e-06,
|
| 2127 |
+
"loss": 0.4708,
|
| 2128 |
+
"step": 172000
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 8.69,
|
| 2132 |
+
"learning_rate": 6.566623023466613e-06,
|
| 2133 |
+
"loss": 0.468,
|
| 2134 |
+
"step": 172500
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 8.71,
|
| 2138 |
+
"learning_rate": 6.440729177157821e-06,
|
| 2139 |
+
"loss": 0.4656,
|
| 2140 |
+
"step": 173000
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 8.74,
|
| 2144 |
+
"learning_rate": 6.314835330849028e-06,
|
| 2145 |
+
"loss": 0.4693,
|
| 2146 |
+
"step": 173500
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 8.76,
|
| 2150 |
+
"learning_rate": 6.188941484540236e-06,
|
| 2151 |
+
"loss": 0.4716,
|
| 2152 |
+
"step": 174000
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 8.79,
|
| 2156 |
+
"learning_rate": 6.063047638231444e-06,
|
| 2157 |
+
"loss": 0.4671,
|
| 2158 |
+
"step": 174500
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 8.81,
|
| 2162 |
+
"learning_rate": 5.937153791922651e-06,
|
| 2163 |
+
"loss": 0.4663,
|
| 2164 |
+
"step": 175000
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 8.84,
|
| 2168 |
+
"learning_rate": 5.811259945613859e-06,
|
| 2169 |
+
"loss": 0.4729,
|
| 2170 |
+
"step": 175500
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 8.86,
|
| 2174 |
+
"learning_rate": 5.685366099305066e-06,
|
| 2175 |
+
"loss": 0.4655,
|
| 2176 |
+
"step": 176000
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 8.89,
|
| 2180 |
+
"learning_rate": 5.559472252996274e-06,
|
| 2181 |
+
"loss": 0.4647,
|
| 2182 |
+
"step": 176500
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 8.91,
|
| 2186 |
+
"learning_rate": 5.433578406687481e-06,
|
| 2187 |
+
"loss": 0.4676,
|
| 2188 |
+
"step": 177000
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 8.94,
|
| 2192 |
+
"learning_rate": 5.307684560378689e-06,
|
| 2193 |
+
"loss": 0.4658,
|
| 2194 |
+
"step": 177500
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 8.96,
|
| 2198 |
+
"learning_rate": 5.181790714069896e-06,
|
| 2199 |
+
"loss": 0.4681,
|
| 2200 |
+
"step": 178000
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 8.99,
|
| 2204 |
+
"learning_rate": 5.055896867761104e-06,
|
| 2205 |
+
"loss": 0.4675,
|
| 2206 |
+
"step": 178500
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 9.0,
|
| 2210 |
+
"eval_loss": 0.5858681201934814,
|
| 2211 |
+
"eval_runtime": 51.7912,
|
| 2212 |
+
"eval_samples_per_second": 340.849,
|
| 2213 |
+
"step": 178722
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 9.01,
|
| 2217 |
+
"learning_rate": 4.9300030214523114e-06,
|
| 2218 |
+
"loss": 0.4637,
|
| 2219 |
+
"step": 179000
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 9.04,
|
| 2223 |
+
"learning_rate": 4.80410917514352e-06,
|
| 2224 |
+
"loss": 0.4622,
|
| 2225 |
+
"step": 179500
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 9.06,
|
| 2229 |
+
"learning_rate": 4.6782153288347265e-06,
|
| 2230 |
+
"loss": 0.4619,
|
| 2231 |
+
"step": 180000
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 9.09,
|
| 2235 |
+
"learning_rate": 4.552321482525934e-06,
|
| 2236 |
+
"loss": 0.4614,
|
| 2237 |
+
"step": 180500
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 9.11,
|
| 2241 |
+
"learning_rate": 4.4264276362171415e-06,
|
| 2242 |
+
"loss": 0.4597,
|
| 2243 |
+
"step": 181000
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 9.14,
|
| 2247 |
+
"learning_rate": 4.30053378990835e-06,
|
| 2248 |
+
"loss": 0.4625,
|
| 2249 |
+
"step": 181500
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 9.17,
|
| 2253 |
+
"learning_rate": 4.174639943599557e-06,
|
| 2254 |
+
"loss": 0.464,
|
| 2255 |
+
"step": 182000
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 9.19,
|
| 2259 |
+
"learning_rate": 4.048746097290765e-06,
|
| 2260 |
+
"loss": 0.4601,
|
| 2261 |
+
"step": 182500
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 9.22,
|
| 2265 |
+
"learning_rate": 3.9228522509819725e-06,
|
| 2266 |
+
"loss": 0.4649,
|
| 2267 |
+
"step": 183000
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 9.24,
|
| 2271 |
+
"learning_rate": 3.7969584046731796e-06,
|
| 2272 |
+
"loss": 0.4634,
|
| 2273 |
+
"step": 183500
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 9.27,
|
| 2277 |
+
"learning_rate": 3.671064558364387e-06,
|
| 2278 |
+
"loss": 0.466,
|
| 2279 |
+
"step": 184000
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 9.29,
|
| 2283 |
+
"learning_rate": 3.5451707120555946e-06,
|
| 2284 |
+
"loss": 0.4663,
|
| 2285 |
+
"step": 184500
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 9.32,
|
| 2289 |
+
"learning_rate": 3.4192768657468025e-06,
|
| 2290 |
+
"loss": 0.465,
|
| 2291 |
+
"step": 185000
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 9.34,
|
| 2295 |
+
"learning_rate": 3.29338301943801e-06,
|
| 2296 |
+
"loss": 0.4639,
|
| 2297 |
+
"step": 185500
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 9.37,
|
| 2301 |
+
"learning_rate": 3.1674891731292176e-06,
|
| 2302 |
+
"loss": 0.4631,
|
| 2303 |
+
"step": 186000
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 9.39,
|
| 2307 |
+
"learning_rate": 3.041595326820425e-06,
|
| 2308 |
+
"loss": 0.4633,
|
| 2309 |
+
"step": 186500
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 9.42,
|
| 2313 |
+
"learning_rate": 2.9157014805116326e-06,
|
| 2314 |
+
"loss": 0.4609,
|
| 2315 |
+
"step": 187000
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 9.44,
|
| 2319 |
+
"learning_rate": 2.7898076342028406e-06,
|
| 2320 |
+
"loss": 0.461,
|
| 2321 |
+
"step": 187500
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 9.47,
|
| 2325 |
+
"learning_rate": 2.6639137878940477e-06,
|
| 2326 |
+
"loss": 0.4593,
|
| 2327 |
+
"step": 188000
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 9.49,
|
| 2331 |
+
"learning_rate": 2.538019941585255e-06,
|
| 2332 |
+
"loss": 0.4623,
|
| 2333 |
+
"step": 188500
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 9.52,
|
| 2337 |
+
"learning_rate": 2.412126095276463e-06,
|
| 2338 |
+
"loss": 0.4625,
|
| 2339 |
+
"step": 189000
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 9.54,
|
| 2343 |
+
"learning_rate": 2.2862322489676707e-06,
|
| 2344 |
+
"loss": 0.4607,
|
| 2345 |
+
"step": 189500
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 9.57,
|
| 2349 |
+
"learning_rate": 2.160338402658878e-06,
|
| 2350 |
+
"loss": 0.4638,
|
| 2351 |
+
"step": 190000
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 9.59,
|
| 2355 |
+
"learning_rate": 2.0344445563500857e-06,
|
| 2356 |
+
"loss": 0.4613,
|
| 2357 |
+
"step": 190500
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 9.62,
|
| 2361 |
+
"learning_rate": 1.9085507100412932e-06,
|
| 2362 |
+
"loss": 0.4652,
|
| 2363 |
+
"step": 191000
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 9.64,
|
| 2367 |
+
"learning_rate": 1.7826568637325008e-06,
|
| 2368 |
+
"loss": 0.4652,
|
| 2369 |
+
"step": 191500
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 9.67,
|
| 2373 |
+
"learning_rate": 1.6567630174237083e-06,
|
| 2374 |
+
"loss": 0.4627,
|
| 2375 |
+
"step": 192000
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 9.69,
|
| 2379 |
+
"learning_rate": 1.530869171114916e-06,
|
| 2380 |
+
"loss": 0.4628,
|
| 2381 |
+
"step": 192500
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 9.72,
|
| 2385 |
+
"learning_rate": 1.4049753248061235e-06,
|
| 2386 |
+
"loss": 0.462,
|
| 2387 |
+
"step": 193000
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 9.74,
|
| 2391 |
+
"learning_rate": 1.2790814784973313e-06,
|
| 2392 |
+
"loss": 0.4646,
|
| 2393 |
+
"step": 193500
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 9.77,
|
| 2397 |
+
"learning_rate": 1.1531876321885388e-06,
|
| 2398 |
+
"loss": 0.4626,
|
| 2399 |
+
"step": 194000
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 9.79,
|
| 2403 |
+
"learning_rate": 1.027293785879746e-06,
|
| 2404 |
+
"loss": 0.4618,
|
| 2405 |
+
"step": 194500
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 9.82,
|
| 2409 |
+
"learning_rate": 9.013999395709538e-07,
|
| 2410 |
+
"loss": 0.4622,
|
| 2411 |
+
"step": 195000
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 9.84,
|
| 2415 |
+
"learning_rate": 7.755060932621615e-07,
|
| 2416 |
+
"loss": 0.4616,
|
| 2417 |
+
"step": 195500
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 9.87,
|
| 2421 |
+
"learning_rate": 6.496122469533689e-07,
|
| 2422 |
+
"loss": 0.4631,
|
| 2423 |
+
"step": 196000
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 9.9,
|
| 2427 |
+
"learning_rate": 5.237184006445765e-07,
|
| 2428 |
+
"loss": 0.4625,
|
| 2429 |
+
"step": 196500
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 9.92,
|
| 2433 |
+
"learning_rate": 3.978245543357841e-07,
|
| 2434 |
+
"loss": 0.4621,
|
| 2435 |
+
"step": 197000
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 9.95,
|
| 2439 |
+
"learning_rate": 2.7193070802699166e-07,
|
| 2440 |
+
"loss": 0.461,
|
| 2441 |
+
"step": 197500
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 9.97,
|
| 2445 |
+
"learning_rate": 1.4603686171819923e-07,
|
| 2446 |
+
"loss": 0.4617,
|
| 2447 |
+
"step": 198000
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 10.0,
|
| 2451 |
+
"learning_rate": 2.014301540940679e-08,
|
| 2452 |
+
"loss": 0.4652,
|
| 2453 |
+
"step": 198500
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 10.0,
|
| 2457 |
+
"eval_loss": 0.5854414701461792,
|
| 2458 |
+
"eval_runtime": 51.7785,
|
| 2459 |
+
"eval_samples_per_second": 340.933,
|
| 2460 |
+
"step": 198580
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 10.0,
|
| 2464 |
+
"step": 198580,
|
| 2465 |
+
"total_flos": 1.2104979074144256e+17,
|
| 2466 |
+
"train_runtime": 21748.254,
|
| 2467 |
+
"train_samples_per_second": 9.131
|
| 2468 |
+
}
|
| 2469 |
+
],
|
| 2470 |
+
"max_steps": 198580,
|
| 2471 |
+
"num_train_epochs": 10,
|
| 2472 |
+
"total_flos": 1.2104979074144256e+17,
|
| 2473 |
+
"trial_name": null,
|
| 2474 |
+
"trial_params": null
|
| 2475 |
+
}
|