Fathom: upload expert-e7-reports/training_log.json
Browse files
adapters/expert-e7-reports/training_log.json
ADDED
|
@@ -0,0 +1,2951 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 2.0326,
|
| 4 |
+
"grad_norm": 1.0961493253707886,
|
| 5 |
+
"learning_rate": 9e-06,
|
| 6 |
+
"entropy": 1.4562864780426026,
|
| 7 |
+
"num_tokens": 113103.0,
|
| 8 |
+
"mean_token_accuracy": 0.5854019731283188,
|
| 9 |
+
"epoch": 0.0034019391052900155,
|
| 10 |
+
"step": 10
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"loss": 1.9722,
|
| 14 |
+
"grad_norm": 0.5352939963340759,
|
| 15 |
+
"learning_rate": 1.9e-05,
|
| 16 |
+
"entropy": 1.6092135667800904,
|
| 17 |
+
"num_tokens": 221983.0,
|
| 18 |
+
"mean_token_accuracy": 0.5872704654932022,
|
| 19 |
+
"epoch": 0.006803878210580031,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"loss": 1.8198,
|
| 24 |
+
"grad_norm": 0.5580214262008667,
|
| 25 |
+
"learning_rate": 2.9e-05,
|
| 26 |
+
"entropy": 1.7635144531726836,
|
| 27 |
+
"num_tokens": 343755.0,
|
| 28 |
+
"mean_token_accuracy": 0.59696926176548,
|
| 29 |
+
"epoch": 0.010205817315870046,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"loss": 1.6405,
|
| 34 |
+
"grad_norm": 0.9694721102714539,
|
| 35 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 36 |
+
"entropy": 1.6470328569412231,
|
| 37 |
+
"num_tokens": 462278.0,
|
| 38 |
+
"mean_token_accuracy": 0.6220342874526977,
|
| 39 |
+
"epoch": 0.013607756421160062,
|
| 40 |
+
"step": 40
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"loss": 1.2829,
|
| 44 |
+
"grad_norm": 0.8506905436515808,
|
| 45 |
+
"learning_rate": 4.9e-05,
|
| 46 |
+
"entropy": 1.3260977208614348,
|
| 47 |
+
"num_tokens": 580883.0,
|
| 48 |
+
"mean_token_accuracy": 0.6881176471710205,
|
| 49 |
+
"epoch": 0.017009695526450076,
|
| 50 |
+
"step": 50
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"loss": 1.0615,
|
| 54 |
+
"grad_norm": 0.5665390491485596,
|
| 55 |
+
"learning_rate": 5.9e-05,
|
| 56 |
+
"entropy": 1.0532318294048308,
|
| 57 |
+
"num_tokens": 693719.0,
|
| 58 |
+
"mean_token_accuracy": 0.7430563151836396,
|
| 59 |
+
"epoch": 0.020411634631740092,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"loss": 0.9244,
|
| 64 |
+
"grad_norm": 0.5383474230766296,
|
| 65 |
+
"learning_rate": 6.9e-05,
|
| 66 |
+
"entropy": 0.9287566632032395,
|
| 67 |
+
"num_tokens": 800049.0,
|
| 68 |
+
"mean_token_accuracy": 0.7744365096092224,
|
| 69 |
+
"epoch": 0.023813573737030108,
|
| 70 |
+
"step": 70
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"loss": 0.8564,
|
| 74 |
+
"grad_norm": 0.5389857292175293,
|
| 75 |
+
"learning_rate": 7.900000000000001e-05,
|
| 76 |
+
"entropy": 0.8546981632709503,
|
| 77 |
+
"num_tokens": 909347.0,
|
| 78 |
+
"mean_token_accuracy": 0.788225668668747,
|
| 79 |
+
"epoch": 0.027215512842320124,
|
| 80 |
+
"step": 80
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"loss": 0.7884,
|
| 84 |
+
"grad_norm": 0.5869827270507812,
|
| 85 |
+
"learning_rate": 8.900000000000001e-05,
|
| 86 |
+
"entropy": 0.7829572021961212,
|
| 87 |
+
"num_tokens": 1024214.0,
|
| 88 |
+
"mean_token_accuracy": 0.8022073119878769,
|
| 89 |
+
"epoch": 0.030617451947610137,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"loss": 0.7827,
|
| 94 |
+
"grad_norm": 0.4458995461463928,
|
| 95 |
+
"learning_rate": 9.900000000000001e-05,
|
| 96 |
+
"entropy": 0.796157357096672,
|
| 97 |
+
"num_tokens": 1145337.0,
|
| 98 |
+
"mean_token_accuracy": 0.8003427386283875,
|
| 99 |
+
"epoch": 0.03401939105290015,
|
| 100 |
+
"step": 100
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"loss": 0.7694,
|
| 104 |
+
"grad_norm": 0.4616456925868988,
|
| 105 |
+
"learning_rate": 9.999752209583493e-05,
|
| 106 |
+
"entropy": 0.7759479373693466,
|
| 107 |
+
"num_tokens": 1255483.0,
|
| 108 |
+
"mean_token_accuracy": 0.8059569209814071,
|
| 109 |
+
"epoch": 0.037421330158190165,
|
| 110 |
+
"step": 110
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"loss": 0.7328,
|
| 114 |
+
"grad_norm": 0.5324557423591614,
|
| 115 |
+
"learning_rate": 9.998895681650353e-05,
|
| 116 |
+
"entropy": 0.7250411480665206,
|
| 117 |
+
"num_tokens": 1376406.0,
|
| 118 |
+
"mean_token_accuracy": 0.8113020449876786,
|
| 119 |
+
"epoch": 0.040823269263480184,
|
| 120 |
+
"step": 120
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"loss": 0.7204,
|
| 124 |
+
"grad_norm": 0.4355196952819824,
|
| 125 |
+
"learning_rate": 9.997427461844063e-05,
|
| 126 |
+
"entropy": 0.7220166236162185,
|
| 127 |
+
"num_tokens": 1487418.0,
|
| 128 |
+
"mean_token_accuracy": 0.8159421294927597,
|
| 129 |
+
"epoch": 0.0442252083687702,
|
| 130 |
+
"step": 130
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"loss": 0.7181,
|
| 134 |
+
"grad_norm": 0.4837367534637451,
|
| 135 |
+
"learning_rate": 9.99534772982393e-05,
|
| 136 |
+
"entropy": 0.7167926013469696,
|
| 137 |
+
"num_tokens": 1603603.0,
|
| 138 |
+
"mean_token_accuracy": 0.8169557631015778,
|
| 139 |
+
"epoch": 0.047627147474060216,
|
| 140 |
+
"step": 140
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"loss": 0.7004,
|
| 144 |
+
"grad_norm": 0.42535701394081116,
|
| 145 |
+
"learning_rate": 9.992656740077193e-05,
|
| 146 |
+
"entropy": 0.7097186267375946,
|
| 147 |
+
"num_tokens": 1719331.0,
|
| 148 |
+
"mean_token_accuracy": 0.8169945359230042,
|
| 149 |
+
"epoch": 0.05102908657935023,
|
| 150 |
+
"step": 150
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"loss": 0.74,
|
| 154 |
+
"grad_norm": 0.4244067966938019,
|
| 155 |
+
"learning_rate": 9.989354821887894e-05,
|
| 156 |
+
"entropy": 0.7415460795164108,
|
| 157 |
+
"num_tokens": 1835165.0,
|
| 158 |
+
"mean_token_accuracy": 0.8098712652921677,
|
| 159 |
+
"epoch": 0.05443102568464025,
|
| 160 |
+
"step": 160
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"loss": 0.7071,
|
| 164 |
+
"grad_norm": 0.46471285820007324,
|
| 165 |
+
"learning_rate": 9.985442379296574e-05,
|
| 166 |
+
"entropy": 0.7142940938472748,
|
| 167 |
+
"num_tokens": 1955878.0,
|
| 168 |
+
"mean_token_accuracy": 0.8144379884004593,
|
| 169 |
+
"epoch": 0.05783296478993026,
|
| 170 |
+
"step": 170
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"loss": 0.6959,
|
| 174 |
+
"grad_norm": 0.48218467831611633,
|
| 175 |
+
"learning_rate": 9.980919891050836e-05,
|
| 176 |
+
"entropy": 0.7002523899078369,
|
| 177 |
+
"num_tokens": 2079862.0,
|
| 178 |
+
"mean_token_accuracy": 0.8176177382469177,
|
| 179 |
+
"epoch": 0.06123490389522027,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"loss": 0.6977,
|
| 184 |
+
"grad_norm": 0.43155911564826965,
|
| 185 |
+
"learning_rate": 9.97578791054677e-05,
|
| 186 |
+
"entropy": 0.7015494972467422,
|
| 187 |
+
"num_tokens": 2183469.0,
|
| 188 |
+
"mean_token_accuracy": 0.8218911945819855,
|
| 189 |
+
"epoch": 0.06463684300051029,
|
| 190 |
+
"step": 190
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"loss": 0.7036,
|
| 194 |
+
"grad_norm": 0.4237188398838043,
|
| 195 |
+
"learning_rate": 9.970047065761225e-05,
|
| 196 |
+
"entropy": 0.7062139421701431,
|
| 197 |
+
"num_tokens": 2297979.0,
|
| 198 |
+
"mean_token_accuracy": 0.8169696599245071,
|
| 199 |
+
"epoch": 0.0680387821058003,
|
| 200 |
+
"step": 200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"loss": 0.6896,
|
| 204 |
+
"grad_norm": 0.4372621178627014,
|
| 205 |
+
"learning_rate": 9.963698059174973e-05,
|
| 206 |
+
"entropy": 0.6874466806650161,
|
| 207 |
+
"num_tokens": 2413698.0,
|
| 208 |
+
"mean_token_accuracy": 0.8205429404973984,
|
| 209 |
+
"epoch": 0.07144072121109032,
|
| 210 |
+
"step": 210
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"loss": 0.6861,
|
| 214 |
+
"grad_norm": 0.42981356382369995,
|
| 215 |
+
"learning_rate": 9.956741667686749e-05,
|
| 216 |
+
"entropy": 0.6936574131250381,
|
| 217 |
+
"num_tokens": 2523689.0,
|
| 218 |
+
"mean_token_accuracy": 0.8207722246646881,
|
| 219 |
+
"epoch": 0.07484266031638033,
|
| 220 |
+
"step": 220
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"loss": 0.6876,
|
| 224 |
+
"grad_norm": 0.4125567078590393,
|
| 225 |
+
"learning_rate": 9.949178742518188e-05,
|
| 226 |
+
"entropy": 0.7051049053668976,
|
| 227 |
+
"num_tokens": 2629062.0,
|
| 228 |
+
"mean_token_accuracy": 0.8210607588291168,
|
| 229 |
+
"epoch": 0.07824459942167035,
|
| 230 |
+
"step": 230
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"loss": 0.7149,
|
| 234 |
+
"grad_norm": 0.3944653868675232,
|
| 235 |
+
"learning_rate": 9.941010209109653e-05,
|
| 236 |
+
"entropy": 0.7121995657682418,
|
| 237 |
+
"num_tokens": 2744221.0,
|
| 238 |
+
"mean_token_accuracy": 0.8171839863061905,
|
| 239 |
+
"epoch": 0.08164653852696037,
|
| 240 |
+
"step": 240
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"loss": 0.7041,
|
| 244 |
+
"grad_norm": 0.4692147970199585,
|
| 245 |
+
"learning_rate": 9.932237067007014e-05,
|
| 246 |
+
"entropy": 0.7010555505752564,
|
| 247 |
+
"num_tokens": 2867672.0,
|
| 248 |
+
"mean_token_accuracy": 0.8154427468776703,
|
| 249 |
+
"epoch": 0.08504847763225039,
|
| 250 |
+
"step": 250
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"loss": 0.6701,
|
| 254 |
+
"grad_norm": 0.36812499165534973,
|
| 255 |
+
"learning_rate": 9.922860389739316e-05,
|
| 256 |
+
"entropy": 0.673400056362152,
|
| 257 |
+
"num_tokens": 2969786.0,
|
| 258 |
+
"mean_token_accuracy": 0.826720854640007,
|
| 259 |
+
"epoch": 0.0884504167375404,
|
| 260 |
+
"step": 260
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"loss": 0.6828,
|
| 264 |
+
"grad_norm": 0.5079509019851685,
|
| 265 |
+
"learning_rate": 9.91288132468743e-05,
|
| 266 |
+
"entropy": 0.6830800861120224,
|
| 267 |
+
"num_tokens": 3078545.0,
|
| 268 |
+
"mean_token_accuracy": 0.8246483653783798,
|
| 269 |
+
"epoch": 0.09185235584283041,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"loss": 0.6591,
|
| 274 |
+
"grad_norm": 0.4336896538734436,
|
| 275 |
+
"learning_rate": 9.90230109294365e-05,
|
| 276 |
+
"entropy": 0.6682640433311462,
|
| 277 |
+
"num_tokens": 3202461.0,
|
| 278 |
+
"mean_token_accuracy": 0.8245112657546997,
|
| 279 |
+
"epoch": 0.09525429494812043,
|
| 280 |
+
"step": 280
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"loss": 0.6742,
|
| 284 |
+
"grad_norm": 0.38131922483444214,
|
| 285 |
+
"learning_rate": 9.891120989162277e-05,
|
| 286 |
+
"entropy": 0.6732221603393554,
|
| 287 |
+
"num_tokens": 3317749.0,
|
| 288 |
+
"mean_token_accuracy": 0.8278978168964386,
|
| 289 |
+
"epoch": 0.09865623405341044,
|
| 290 |
+
"step": 290
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"loss": 0.7072,
|
| 294 |
+
"grad_norm": 0.43391740322113037,
|
| 295 |
+
"learning_rate": 9.879342381401183e-05,
|
| 296 |
+
"entropy": 0.719240027666092,
|
| 297 |
+
"num_tokens": 3438813.0,
|
| 298 |
+
"mean_token_accuracy": 0.8140431463718414,
|
| 299 |
+
"epoch": 0.10205817315870046,
|
| 300 |
+
"step": 300
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"loss": 0.6726,
|
| 304 |
+
"grad_norm": 0.37840133905410767,
|
| 305 |
+
"learning_rate": 9.866966710954432e-05,
|
| 306 |
+
"entropy": 0.6736223340034485,
|
| 307 |
+
"num_tokens": 3558578.0,
|
| 308 |
+
"mean_token_accuracy": 0.8215447336435318,
|
| 309 |
+
"epoch": 0.10546011226399048,
|
| 310 |
+
"step": 310
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"loss": 0.6739,
|
| 314 |
+
"grad_norm": 0.36936870217323303,
|
| 315 |
+
"learning_rate": 9.853995492175894e-05,
|
| 316 |
+
"entropy": 0.6741836041212081,
|
| 317 |
+
"num_tokens": 3680797.0,
|
| 318 |
+
"mean_token_accuracy": 0.8207811802625656,
|
| 319 |
+
"epoch": 0.1088620513692805,
|
| 320 |
+
"step": 320
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"loss": 0.6462,
|
| 324 |
+
"grad_norm": 0.3381315767765045,
|
| 325 |
+
"learning_rate": 9.840430312293954e-05,
|
| 326 |
+
"entropy": 0.6454634428024292,
|
| 327 |
+
"num_tokens": 3798203.0,
|
| 328 |
+
"mean_token_accuracy": 0.8290177077054978,
|
| 329 |
+
"epoch": 0.1122639904745705,
|
| 330 |
+
"step": 330
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"loss": 0.6309,
|
| 334 |
+
"grad_norm": 0.4414357841014862,
|
| 335 |
+
"learning_rate": 9.826272831217282e-05,
|
| 336 |
+
"entropy": 0.6358878672122955,
|
| 337 |
+
"num_tokens": 3908285.0,
|
| 338 |
+
"mean_token_accuracy": 0.8346272200345993,
|
| 339 |
+
"epoch": 0.11566592957986052,
|
| 340 |
+
"step": 340
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"loss": 0.662,
|
| 344 |
+
"grad_norm": 0.3412431478500366,
|
| 345 |
+
"learning_rate": 9.811524781331726e-05,
|
| 346 |
+
"entropy": 0.669054564833641,
|
| 347 |
+
"num_tokens": 4027009.0,
|
| 348 |
+
"mean_token_accuracy": 0.823895263671875,
|
| 349 |
+
"epoch": 0.11906786868515054,
|
| 350 |
+
"step": 350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"loss": 0.6396,
|
| 354 |
+
"grad_norm": 0.4202592670917511,
|
| 355 |
+
"learning_rate": 9.796187967288317e-05,
|
| 356 |
+
"entropy": 0.6534929439425469,
|
| 357 |
+
"num_tokens": 4141379.0,
|
| 358 |
+
"mean_token_accuracy": 0.8286080300807953,
|
| 359 |
+
"epoch": 0.12246980779044055,
|
| 360 |
+
"step": 360
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"loss": 0.6462,
|
| 364 |
+
"grad_norm": 0.4112204313278198,
|
| 365 |
+
"learning_rate": 9.780264265782452e-05,
|
| 366 |
+
"entropy": 0.6516435265541076,
|
| 367 |
+
"num_tokens": 4264298.0,
|
| 368 |
+
"mean_token_accuracy": 0.8284994632005691,
|
| 369 |
+
"epoch": 0.12587174689573058,
|
| 370 |
+
"step": 370
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"loss": 0.6385,
|
| 374 |
+
"grad_norm": 0.4041576683521271,
|
| 375 |
+
"learning_rate": 9.763755625324247e-05,
|
| 376 |
+
"entropy": 0.6425079524517059,
|
| 377 |
+
"num_tokens": 4380764.0,
|
| 378 |
+
"mean_token_accuracy": 0.8293725460767746,
|
| 379 |
+
"epoch": 0.12927368600102057,
|
| 380 |
+
"step": 380
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"loss": 0.6474,
|
| 384 |
+
"grad_norm": 0.40553557872772217,
|
| 385 |
+
"learning_rate": 9.746664066000105e-05,
|
| 386 |
+
"entropy": 0.650575777888298,
|
| 387 |
+
"num_tokens": 4502319.0,
|
| 388 |
+
"mean_token_accuracy": 0.8261306613683701,
|
| 389 |
+
"epoch": 0.1326756251063106,
|
| 390 |
+
"step": 390
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"loss": 0.6208,
|
| 394 |
+
"grad_norm": 0.4033198058605194,
|
| 395 |
+
"learning_rate": 9.728991679225534e-05,
|
| 396 |
+
"entropy": 0.6212592482566833,
|
| 397 |
+
"num_tokens": 4619137.0,
|
| 398 |
+
"mean_token_accuracy": 0.8338732123374939,
|
| 399 |
+
"epoch": 0.1360775642116006,
|
| 400 |
+
"step": 400
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"loss": 0.6588,
|
| 404 |
+
"grad_norm": 0.3973551392555237,
|
| 405 |
+
"learning_rate": 9.71074062748922e-05,
|
| 406 |
+
"entropy": 0.6602439433336258,
|
| 407 |
+
"num_tokens": 4740514.0,
|
| 408 |
+
"mean_token_accuracy": 0.8240435630083084,
|
| 409 |
+
"epoch": 0.13947950331689063,
|
| 410 |
+
"step": 410
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"loss": 0.6231,
|
| 414 |
+
"grad_norm": 0.38988974690437317,
|
| 415 |
+
"learning_rate": 9.691913144088423e-05,
|
| 416 |
+
"entropy": 0.6275951579213143,
|
| 417 |
+
"num_tokens": 4849434.0,
|
| 418 |
+
"mean_token_accuracy": 0.8351284950971604,
|
| 419 |
+
"epoch": 0.14288144242218065,
|
| 420 |
+
"step": 420
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"loss": 0.6486,
|
| 424 |
+
"grad_norm": 0.4000033736228943,
|
| 425 |
+
"learning_rate": 9.672511532855695e-05,
|
| 426 |
+
"entropy": 0.6495797425508499,
|
| 427 |
+
"num_tokens": 4970677.0,
|
| 428 |
+
"mean_token_accuracy": 0.8287895292043685,
|
| 429 |
+
"epoch": 0.14628338152747067,
|
| 430 |
+
"step": 430
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"loss": 0.6369,
|
| 434 |
+
"grad_norm": 0.36982354521751404,
|
| 435 |
+
"learning_rate": 9.652538167876966e-05,
|
| 436 |
+
"entropy": 0.6435147285461426,
|
| 437 |
+
"num_tokens": 5079274.0,
|
| 438 |
+
"mean_token_accuracy": 0.8325352728366852,
|
| 439 |
+
"epoch": 0.14968532063276066,
|
| 440 |
+
"step": 440
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"loss": 0.6589,
|
| 444 |
+
"grad_norm": 0.30258873105049133,
|
| 445 |
+
"learning_rate": 9.63199549320105e-05,
|
| 446 |
+
"entropy": 0.656851077079773,
|
| 447 |
+
"num_tokens": 5199280.0,
|
| 448 |
+
"mean_token_accuracy": 0.8274909108877182,
|
| 449 |
+
"epoch": 0.15308725973805068,
|
| 450 |
+
"step": 450
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"loss": 0.6171,
|
| 454 |
+
"grad_norm": 0.40595975518226624,
|
| 455 |
+
"learning_rate": 9.610886022540558e-05,
|
| 456 |
+
"entropy": 0.6167075544595718,
|
| 457 |
+
"num_tokens": 5314855.0,
|
| 458 |
+
"mean_token_accuracy": 0.8360531657934189,
|
| 459 |
+
"epoch": 0.1564891988433407,
|
| 460 |
+
"step": 460
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"loss": 0.6535,
|
| 464 |
+
"grad_norm": 0.3571644723415375,
|
| 465 |
+
"learning_rate": 9.589212338964331e-05,
|
| 466 |
+
"entropy": 0.6573659986257553,
|
| 467 |
+
"num_tokens": 5427712.0,
|
| 468 |
+
"mean_token_accuracy": 0.826265224814415,
|
| 469 |
+
"epoch": 0.15989113794863072,
|
| 470 |
+
"step": 470
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"loss": 0.6322,
|
| 474 |
+
"grad_norm": 0.3340984880924225,
|
| 475 |
+
"learning_rate": 9.566977094581344e-05,
|
| 476 |
+
"entropy": 0.6363773226737977,
|
| 477 |
+
"num_tokens": 5555811.0,
|
| 478 |
+
"mean_token_accuracy": 0.830034053325653,
|
| 479 |
+
"epoch": 0.16329307705392074,
|
| 480 |
+
"step": 480
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"loss": 0.6505,
|
| 484 |
+
"grad_norm": 0.36710014939308167,
|
| 485 |
+
"learning_rate": 9.544183010216184e-05,
|
| 486 |
+
"entropy": 0.6666623204946518,
|
| 487 |
+
"num_tokens": 5670677.0,
|
| 488 |
+
"mean_token_accuracy": 0.8263821274042129,
|
| 489 |
+
"epoch": 0.16669501615921076,
|
| 490 |
+
"step": 490
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"loss": 0.6484,
|
| 494 |
+
"grad_norm": 0.35856229066848755,
|
| 495 |
+
"learning_rate": 9.520832875076118e-05,
|
| 496 |
+
"entropy": 0.6493088006973267,
|
| 497 |
+
"num_tokens": 5791079.0,
|
| 498 |
+
"mean_token_accuracy": 0.826611652970314,
|
| 499 |
+
"epoch": 0.17009695526450078,
|
| 500 |
+
"step": 500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"loss": 0.6395,
|
| 504 |
+
"grad_norm": 0.36879998445510864,
|
| 505 |
+
"learning_rate": 9.496929546409791e-05,
|
| 506 |
+
"entropy": 0.6355485945940018,
|
| 507 |
+
"num_tokens": 5915427.0,
|
| 508 |
+
"mean_token_accuracy": 0.8316580206155777,
|
| 509 |
+
"epoch": 0.17349889436979077,
|
| 510 |
+
"step": 510
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"loss": 0.6405,
|
| 514 |
+
"grad_norm": 0.3662184774875641,
|
| 515 |
+
"learning_rate": 9.472475949157591e-05,
|
| 516 |
+
"entropy": 0.6411178290843964,
|
| 517 |
+
"num_tokens": 6042113.0,
|
| 518 |
+
"mean_token_accuracy": 0.8287693798542023,
|
| 519 |
+
"epoch": 0.1769008334750808,
|
| 520 |
+
"step": 520
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"loss": 0.6248,
|
| 524 |
+
"grad_norm": 0.3676609992980957,
|
| 525 |
+
"learning_rate": 9.447475075593746e-05,
|
| 526 |
+
"entropy": 0.6330993086099624,
|
| 527 |
+
"num_tokens": 6158285.0,
|
| 528 |
+
"mean_token_accuracy": 0.8320850521326065,
|
| 529 |
+
"epoch": 0.1803027725803708,
|
| 530 |
+
"step": 530
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"loss": 0.605,
|
| 534 |
+
"grad_norm": 0.3490847945213318,
|
| 535 |
+
"learning_rate": 9.421929984960168e-05,
|
| 536 |
+
"entropy": 0.6043026179075242,
|
| 537 |
+
"num_tokens": 6269273.0,
|
| 538 |
+
"mean_token_accuracy": 0.8386462539434433,
|
| 539 |
+
"epoch": 0.18370471168566083,
|
| 540 |
+
"step": 540
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"loss": 0.6035,
|
| 544 |
+
"grad_norm": 0.3701430857181549,
|
| 545 |
+
"learning_rate": 9.395843803092103e-05,
|
| 546 |
+
"entropy": 0.6117337167263031,
|
| 547 |
+
"num_tokens": 6374978.0,
|
| 548 |
+
"mean_token_accuracy": 0.8389517337083816,
|
| 549 |
+
"epoch": 0.18710665079095085,
|
| 550 |
+
"step": 550
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"loss": 0.667,
|
| 554 |
+
"grad_norm": 0.37965649366378784,
|
| 555 |
+
"learning_rate": 9.369219722035657e-05,
|
| 556 |
+
"entropy": 0.6723731458187103,
|
| 557 |
+
"num_tokens": 6492671.0,
|
| 558 |
+
"mean_token_accuracy": 0.8266532897949219,
|
| 559 |
+
"epoch": 0.19050858989624087,
|
| 560 |
+
"step": 560
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"loss": 0.6473,
|
| 564 |
+
"grad_norm": 0.335111528635025,
|
| 565 |
+
"learning_rate": 9.34206099965717e-05,
|
| 566 |
+
"entropy": 0.6496838480234146,
|
| 567 |
+
"num_tokens": 6605704.0,
|
| 568 |
+
"mean_token_accuracy": 0.8288087368011474,
|
| 569 |
+
"epoch": 0.19391052900153088,
|
| 570 |
+
"step": 570
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"loss": 0.6479,
|
| 574 |
+
"grad_norm": 0.4136720895767212,
|
| 575 |
+
"learning_rate": 9.314370959244589e-05,
|
| 576 |
+
"entropy": 0.6532777503132821,
|
| 577 |
+
"num_tokens": 6724628.0,
|
| 578 |
+
"mean_token_accuracy": 0.8273604065179825,
|
| 579 |
+
"epoch": 0.19731246810682088,
|
| 580 |
+
"step": 580
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"loss": 0.6917,
|
| 584 |
+
"grad_norm": 0.349250465631485,
|
| 585 |
+
"learning_rate": 9.286152989100808e-05,
|
| 586 |
+
"entropy": 0.6956728607416153,
|
| 587 |
+
"num_tokens": 6842793.0,
|
| 588 |
+
"mean_token_accuracy": 0.8188706696033478,
|
| 589 |
+
"epoch": 0.2007144072121109,
|
| 590 |
+
"step": 590
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"loss": 0.6596,
|
| 594 |
+
"grad_norm": 0.37561726570129395,
|
| 595 |
+
"learning_rate": 9.257410542129048e-05,
|
| 596 |
+
"entropy": 0.6637489289045334,
|
| 597 |
+
"num_tokens": 6969269.0,
|
| 598 |
+
"mean_token_accuracy": 0.8233319729566574,
|
| 599 |
+
"epoch": 0.20411634631740092,
|
| 600 |
+
"step": 600
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"loss": 0.6148,
|
| 604 |
+
"grad_norm": 0.35306721925735474,
|
| 605 |
+
"learning_rate": 9.22814713541035e-05,
|
| 606 |
+
"entropy": 0.609418871998787,
|
| 607 |
+
"num_tokens": 7089158.0,
|
| 608 |
+
"mean_token_accuracy": 0.8354996383190155,
|
| 609 |
+
"epoch": 0.20751828542269093,
|
| 610 |
+
"step": 610
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"loss": 0.644,
|
| 614 |
+
"grad_norm": 0.38659054040908813,
|
| 615 |
+
"learning_rate": 9.198366349773205e-05,
|
| 616 |
+
"entropy": 0.6533850967884064,
|
| 617 |
+
"num_tokens": 7214581.0,
|
| 618 |
+
"mean_token_accuracy": 0.8262244701385498,
|
| 619 |
+
"epoch": 0.21092022452798095,
|
| 620 |
+
"step": 620
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"loss": 0.6227,
|
| 624 |
+
"grad_norm": 0.3564472794532776,
|
| 625 |
+
"learning_rate": 9.168071829355376e-05,
|
| 626 |
+
"entropy": 0.6244180202484131,
|
| 627 |
+
"num_tokens": 7332309.0,
|
| 628 |
+
"mean_token_accuracy": 0.8361935257911682,
|
| 629 |
+
"epoch": 0.21432216363327097,
|
| 630 |
+
"step": 630
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"loss": 0.6308,
|
| 634 |
+
"grad_norm": 0.3747089207172394,
|
| 635 |
+
"learning_rate": 9.137267281157999e-05,
|
| 636 |
+
"entropy": 0.6325557798147201,
|
| 637 |
+
"num_tokens": 7450413.0,
|
| 638 |
+
"mean_token_accuracy": 0.8316955536603927,
|
| 639 |
+
"epoch": 0.217724102738561,
|
| 640 |
+
"step": 640
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"loss": 0.616,
|
| 644 |
+
"grad_norm": 0.4263840913772583,
|
| 645 |
+
"learning_rate": 9.105956474591953e-05,
|
| 646 |
+
"entropy": 0.620253998041153,
|
| 647 |
+
"num_tokens": 7557132.0,
|
| 648 |
+
"mean_token_accuracy": 0.8373414397239685,
|
| 649 |
+
"epoch": 0.22112604184385098,
|
| 650 |
+
"step": 650
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"loss": 0.6176,
|
| 654 |
+
"grad_norm": 0.38803404569625854,
|
| 655 |
+
"learning_rate": 9.074143241016631e-05,
|
| 656 |
+
"entropy": 0.6201047956943512,
|
| 657 |
+
"num_tokens": 7671938.0,
|
| 658 |
+
"mean_token_accuracy": 0.8363149344921113,
|
| 659 |
+
"epoch": 0.224527980949141,
|
| 660 |
+
"step": 660
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"loss": 0.6434,
|
| 664 |
+
"grad_norm": 0.3495098054409027,
|
| 665 |
+
"learning_rate": 9.04183147327111e-05,
|
| 666 |
+
"entropy": 0.6501924157142639,
|
| 667 |
+
"num_tokens": 7798607.0,
|
| 668 |
+
"mean_token_accuracy": 0.8257293999195099,
|
| 669 |
+
"epoch": 0.22792992005443102,
|
| 670 |
+
"step": 670
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"loss": 0.6176,
|
| 674 |
+
"grad_norm": 0.34818509221076965,
|
| 675 |
+
"learning_rate": 9.009025125197792e-05,
|
| 676 |
+
"entropy": 0.6221291124820709,
|
| 677 |
+
"num_tokens": 7904767.0,
|
| 678 |
+
"mean_token_accuracy": 0.8381055980920792,
|
| 679 |
+
"epoch": 0.23133185915972104,
|
| 680 |
+
"step": 680
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"loss": 0.6194,
|
| 684 |
+
"grad_norm": 0.35937735438346863,
|
| 685 |
+
"learning_rate": 8.975728211158609e-05,
|
| 686 |
+
"entropy": 0.6223055779933929,
|
| 687 |
+
"num_tokens": 8026821.0,
|
| 688 |
+
"mean_token_accuracy": 0.8331304669380188,
|
| 689 |
+
"epoch": 0.23473379826501106,
|
| 690 |
+
"step": 690
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"loss": 0.6343,
|
| 694 |
+
"grad_norm": 0.3995741307735443,
|
| 695 |
+
"learning_rate": 8.941944805543788e-05,
|
| 696 |
+
"entropy": 0.6313437297940254,
|
| 697 |
+
"num_tokens": 8137346.0,
|
| 698 |
+
"mean_token_accuracy": 0.8347465574741364,
|
| 699 |
+
"epoch": 0.23813573737030108,
|
| 700 |
+
"step": 700
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"loss": 0.6447,
|
| 704 |
+
"grad_norm": 0.38594338297843933,
|
| 705 |
+
"learning_rate": 8.907679042273293e-05,
|
| 706 |
+
"entropy": 0.6474226981401443,
|
| 707 |
+
"num_tokens": 8241289.0,
|
| 708 |
+
"mean_token_accuracy": 0.8319136798381805,
|
| 709 |
+
"epoch": 0.24153767647559107,
|
| 710 |
+
"step": 710
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"loss": 0.605,
|
| 714 |
+
"grad_norm": 0.3661476969718933,
|
| 715 |
+
"learning_rate": 8.872935114290979e-05,
|
| 716 |
+
"entropy": 0.6085086613893509,
|
| 717 |
+
"num_tokens": 8357072.0,
|
| 718 |
+
"mean_token_accuracy": 0.8373961597681046,
|
| 719 |
+
"epoch": 0.2449396155808811,
|
| 720 |
+
"step": 720
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"loss": 0.5994,
|
| 724 |
+
"grad_norm": 0.3534446954727173,
|
| 725 |
+
"learning_rate": 8.837717273051515e-05,
|
| 726 |
+
"entropy": 0.5992837458848953,
|
| 727 |
+
"num_tokens": 8480791.0,
|
| 728 |
+
"mean_token_accuracy": 0.8372073084115982,
|
| 729 |
+
"epoch": 0.2483415546861711,
|
| 730 |
+
"step": 730
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"loss": 0.591,
|
| 734 |
+
"grad_norm": 0.3611646294593811,
|
| 735 |
+
"learning_rate": 8.802029828000156e-05,
|
| 736 |
+
"entropy": 0.5920722305774688,
|
| 737 |
+
"num_tokens": 8593584.0,
|
| 738 |
+
"mean_token_accuracy": 0.840802788734436,
|
| 739 |
+
"epoch": 0.25174349379146116,
|
| 740 |
+
"step": 740
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"loss": 0.6379,
|
| 744 |
+
"grad_norm": 0.3454264998435974,
|
| 745 |
+
"learning_rate": 8.765877146045413e-05,
|
| 746 |
+
"entropy": 0.645842906832695,
|
| 747 |
+
"num_tokens": 8697045.0,
|
| 748 |
+
"mean_token_accuracy": 0.832975035905838,
|
| 749 |
+
"epoch": 0.2551454328967511,
|
| 750 |
+
"step": 750
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"loss": 0.588,
|
| 754 |
+
"grad_norm": 0.36970141530036926,
|
| 755 |
+
"learning_rate": 8.729263651024705e-05,
|
| 756 |
+
"entropy": 0.589533594250679,
|
| 757 |
+
"num_tokens": 8810383.0,
|
| 758 |
+
"mean_token_accuracy": 0.8419877678155899,
|
| 759 |
+
"epoch": 0.25854737200204114,
|
| 760 |
+
"step": 760
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"loss": 0.6126,
|
| 764 |
+
"grad_norm": 0.30673205852508545,
|
| 765 |
+
"learning_rate": 8.692193823163017e-05,
|
| 766 |
+
"entropy": 0.603627099096775,
|
| 767 |
+
"num_tokens": 8926623.0,
|
| 768 |
+
"mean_token_accuracy": 0.8384459555149079,
|
| 769 |
+
"epoch": 0.26194931110733116,
|
| 770 |
+
"step": 770
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"loss": 0.6416,
|
| 774 |
+
"grad_norm": 0.40019306540489197,
|
| 775 |
+
"learning_rate": 8.654672198524692e-05,
|
| 776 |
+
"entropy": 0.6472606122493744,
|
| 777 |
+
"num_tokens": 9037995.0,
|
| 778 |
+
"mean_token_accuracy": 0.8314683675765991,
|
| 779 |
+
"epoch": 0.2653512502126212,
|
| 780 |
+
"step": 780
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"loss": 0.6028,
|
| 784 |
+
"grad_norm": 0.3364422917366028,
|
| 785 |
+
"learning_rate": 8.616703368458361e-05,
|
| 786 |
+
"entropy": 0.6071313232183456,
|
| 787 |
+
"num_tokens": 9159140.0,
|
| 788 |
+
"mean_token_accuracy": 0.8371691346168518,
|
| 789 |
+
"epoch": 0.2687531893179112,
|
| 790 |
+
"step": 790
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"loss": 0.6054,
|
| 794 |
+
"grad_norm": 0.3635218143463135,
|
| 795 |
+
"learning_rate": 8.578291979035132e-05,
|
| 796 |
+
"entropy": 0.615416657924652,
|
| 797 |
+
"num_tokens": 9267853.0,
|
| 798 |
+
"mean_token_accuracy": 0.8379261702299118,
|
| 799 |
+
"epoch": 0.2721551284232012,
|
| 800 |
+
"step": 800
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"loss": 0.6104,
|
| 804 |
+
"grad_norm": 0.33966347575187683,
|
| 805 |
+
"learning_rate": 8.539442730480061e-05,
|
| 806 |
+
"entropy": 0.6133037626743316,
|
| 807 |
+
"num_tokens": 9383976.0,
|
| 808 |
+
"mean_token_accuracy": 0.835821345448494,
|
| 809 |
+
"epoch": 0.27555706752849124,
|
| 810 |
+
"step": 810
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"loss": 0.5883,
|
| 814 |
+
"grad_norm": 0.3680882155895233,
|
| 815 |
+
"learning_rate": 8.500160376597016e-05,
|
| 816 |
+
"entropy": 0.5889941453933716,
|
| 817 |
+
"num_tokens": 9490262.0,
|
| 818 |
+
"mean_token_accuracy": 0.8436674028635025,
|
| 819 |
+
"epoch": 0.27895900663378126,
|
| 820 |
+
"step": 820
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"loss": 0.6011,
|
| 824 |
+
"grad_norm": 0.3962339758872986,
|
| 825 |
+
"learning_rate": 8.46044972418697e-05,
|
| 826 |
+
"entropy": 0.599892795085907,
|
| 827 |
+
"num_tokens": 9607939.0,
|
| 828 |
+
"mean_token_accuracy": 0.8401912897825241,
|
| 829 |
+
"epoch": 0.2823609457390713,
|
| 830 |
+
"step": 830
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"loss": 0.6268,
|
| 834 |
+
"grad_norm": 0.3375062644481659,
|
| 835 |
+
"learning_rate": 8.420315632459817e-05,
|
| 836 |
+
"entropy": 0.6311625123023987,
|
| 837 |
+
"num_tokens": 9722935.0,
|
| 838 |
+
"mean_token_accuracy": 0.8338307291269302,
|
| 839 |
+
"epoch": 0.2857628848443613,
|
| 840 |
+
"step": 840
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"loss": 0.638,
|
| 844 |
+
"grad_norm": 0.36880624294281006,
|
| 845 |
+
"learning_rate": 8.379763012439771e-05,
|
| 846 |
+
"entropy": 0.641839075088501,
|
| 847 |
+
"num_tokens": 9835999.0,
|
| 848 |
+
"mean_token_accuracy": 0.831251859664917,
|
| 849 |
+
"epoch": 0.2891648239496513,
|
| 850 |
+
"step": 850
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"loss": 0.5823,
|
| 854 |
+
"grad_norm": 0.35837697982788086,
|
| 855 |
+
"learning_rate": 8.338796826364437e-05,
|
| 856 |
+
"entropy": 0.5842991501092911,
|
| 857 |
+
"num_tokens": 9946974.0,
|
| 858 |
+
"mean_token_accuracy": 0.8434822201728821,
|
| 859 |
+
"epoch": 0.29256676305494134,
|
| 860 |
+
"step": 860
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"loss": 0.6356,
|
| 864 |
+
"grad_norm": 0.39383432269096375,
|
| 865 |
+
"learning_rate": 8.29742208707758e-05,
|
| 866 |
+
"entropy": 0.6413630664348602,
|
| 867 |
+
"num_tokens": 10067421.0,
|
| 868 |
+
"mean_token_accuracy": 0.8298591256141663,
|
| 869 |
+
"epoch": 0.29596870216023136,
|
| 870 |
+
"step": 870
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"loss": 0.6434,
|
| 874 |
+
"grad_norm": 0.38471469283103943,
|
| 875 |
+
"learning_rate": 8.255643857415758e-05,
|
| 876 |
+
"entropy": 0.6492842510342598,
|
| 877 |
+
"num_tokens": 10172152.0,
|
| 878 |
+
"mean_token_accuracy": 0.8317259013652801,
|
| 879 |
+
"epoch": 0.2993706412655213,
|
| 880 |
+
"step": 880
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"loss": 0.6135,
|
| 884 |
+
"grad_norm": 0.3366308808326721,
|
| 885 |
+
"learning_rate": 8.213467249588783e-05,
|
| 886 |
+
"entropy": 0.6186555951833725,
|
| 887 |
+
"num_tokens": 10290628.0,
|
| 888 |
+
"mean_token_accuracy": 0.833742293715477,
|
| 889 |
+
"epoch": 0.30277258037081134,
|
| 890 |
+
"step": 890
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"loss": 0.5787,
|
| 894 |
+
"grad_norm": 0.40084564685821533,
|
| 895 |
+
"learning_rate": 8.170897424554171e-05,
|
| 896 |
+
"entropy": 0.5826229274272918,
|
| 897 |
+
"num_tokens": 10407951.0,
|
| 898 |
+
"mean_token_accuracy": 0.8439725250005722,
|
| 899 |
+
"epoch": 0.30617451947610136,
|
| 900 |
+
"step": 900
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"loss": 0.628,
|
| 904 |
+
"grad_norm": 0.4093911051750183,
|
| 905 |
+
"learning_rate": 8.127939591385623e-05,
|
| 906 |
+
"entropy": 0.639702819287777,
|
| 907 |
+
"num_tokens": 10516552.0,
|
| 908 |
+
"mean_token_accuracy": 0.8321585863828659,
|
| 909 |
+
"epoch": 0.3095764585813914,
|
| 910 |
+
"step": 910
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"loss": 0.6622,
|
| 914 |
+
"grad_norm": 0.3402785360813141,
|
| 915 |
+
"learning_rate": 8.084599006635602e-05,
|
| 916 |
+
"entropy": 0.6612581133842468,
|
| 917 |
+
"num_tokens": 10622685.0,
|
| 918 |
+
"mean_token_accuracy": 0.8280930787324905,
|
| 919 |
+
"epoch": 0.3129783976866814,
|
| 920 |
+
"step": 920
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"loss": 0.5945,
|
| 924 |
+
"grad_norm": 0.381832093000412,
|
| 925 |
+
"learning_rate": 8.040880973692133e-05,
|
| 926 |
+
"entropy": 0.5946418136358261,
|
| 927 |
+
"num_tokens": 10740084.0,
|
| 928 |
+
"mean_token_accuracy": 0.8418374478816986,
|
| 929 |
+
"epoch": 0.3163803367919714,
|
| 930 |
+
"step": 930
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"loss": 0.6012,
|
| 934 |
+
"grad_norm": 0.36465200781822205,
|
| 935 |
+
"learning_rate": 7.996790842129834e-05,
|
| 936 |
+
"entropy": 0.6030470594763756,
|
| 937 |
+
"num_tokens": 10858519.0,
|
| 938 |
+
"mean_token_accuracy": 0.8368221133947372,
|
| 939 |
+
"epoch": 0.31978227589726144,
|
| 940 |
+
"step": 940
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"loss": 0.6109,
|
| 944 |
+
"grad_norm": 0.34183382987976074,
|
| 945 |
+
"learning_rate": 7.952334007055317e-05,
|
| 946 |
+
"entropy": 0.6180869042873383,
|
| 947 |
+
"num_tokens": 10982717.0,
|
| 948 |
+
"mean_token_accuracy": 0.835748416185379,
|
| 949 |
+
"epoch": 0.32318421500255146,
|
| 950 |
+
"step": 950
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"loss": 0.6427,
|
| 954 |
+
"grad_norm": 0.3375698924064636,
|
| 955 |
+
"learning_rate": 7.907515908447026e-05,
|
| 956 |
+
"entropy": 0.6360474318265915,
|
| 957 |
+
"num_tokens": 11109821.0,
|
| 958 |
+
"mean_token_accuracy": 0.8303357720375061,
|
| 959 |
+
"epoch": 0.3265861541078415,
|
| 960 |
+
"step": 960
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"loss": 0.6125,
|
| 964 |
+
"grad_norm": 0.33526158332824707,
|
| 965 |
+
"learning_rate": 7.862342030489548e-05,
|
| 966 |
+
"entropy": 0.6055434793233871,
|
| 967 |
+
"num_tokens": 11222141.0,
|
| 968 |
+
"mean_token_accuracy": 0.839334124326706,
|
| 969 |
+
"epoch": 0.3299880932131315,
|
| 970 |
+
"step": 970
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"loss": 0.601,
|
| 974 |
+
"grad_norm": 0.40864965319633484,
|
| 975 |
+
"learning_rate": 7.816817900902569e-05,
|
| 976 |
+
"entropy": 0.6122152507305145,
|
| 977 |
+
"num_tokens": 11334721.0,
|
| 978 |
+
"mean_token_accuracy": 0.8393468946218491,
|
| 979 |
+
"epoch": 0.3333900323184215,
|
| 980 |
+
"step": 980
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"loss": 0.6341,
|
| 984 |
+
"grad_norm": 0.35346099734306335,
|
| 985 |
+
"learning_rate": 7.77094909026444e-05,
|
| 986 |
+
"entropy": 0.6331113621592521,
|
| 987 |
+
"num_tokens": 11442226.0,
|
| 988 |
+
"mean_token_accuracy": 0.8354059338569642,
|
| 989 |
+
"epoch": 0.33679197142371153,
|
| 990 |
+
"step": 990
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"loss": 0.6021,
|
| 994 |
+
"grad_norm": 0.3349364101886749,
|
| 995 |
+
"learning_rate": 7.724741211330561e-05,
|
| 996 |
+
"entropy": 0.609099206328392,
|
| 997 |
+
"num_tokens": 11559196.0,
|
| 998 |
+
"mean_token_accuracy": 0.8378647118806839,
|
| 999 |
+
"epoch": 0.34019391052900155,
|
| 1000 |
+
"step": 1000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"loss": 0.596,
|
| 1004 |
+
"grad_norm": 0.3482501804828644,
|
| 1005 |
+
"learning_rate": 7.67819991834655e-05,
|
| 1006 |
+
"entropy": 0.6021771982312203,
|
| 1007 |
+
"num_tokens": 11674831.0,
|
| 1008 |
+
"mean_token_accuracy": 0.8393041074275971,
|
| 1009 |
+
"epoch": 0.3435958496342916,
|
| 1010 |
+
"step": 1010
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"loss": 0.5712,
|
| 1014 |
+
"grad_norm": 0.3629717528820038,
|
| 1015 |
+
"learning_rate": 7.631330906356371e-05,
|
| 1016 |
+
"entropy": 0.5844026952981949,
|
| 1017 |
+
"num_tokens": 11795718.0,
|
| 1018 |
+
"mean_token_accuracy": 0.8434269249439239,
|
| 1019 |
+
"epoch": 0.34699778873958154,
|
| 1020 |
+
"step": 1020
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"loss": 0.6058,
|
| 1024 |
+
"grad_norm": 0.3741706311702728,
|
| 1025 |
+
"learning_rate": 7.584139910505458e-05,
|
| 1026 |
+
"entropy": 0.6056048899888993,
|
| 1027 |
+
"num_tokens": 11911642.0,
|
| 1028 |
+
"mean_token_accuracy": 0.8380466908216476,
|
| 1029 |
+
"epoch": 0.35039972784487156,
|
| 1030 |
+
"step": 1030
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"loss": 0.5877,
|
| 1034 |
+
"grad_norm": 0.30570724606513977,
|
| 1035 |
+
"learning_rate": 7.536632705338929e-05,
|
| 1036 |
+
"entropy": 0.5891546666622162,
|
| 1037 |
+
"num_tokens": 12029598.0,
|
| 1038 |
+
"mean_token_accuracy": 0.8402005821466446,
|
| 1039 |
+
"epoch": 0.3538016669501616,
|
| 1040 |
+
"step": 1040
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"loss": 0.6213,
|
| 1044 |
+
"grad_norm": 0.362284779548645,
|
| 1045 |
+
"learning_rate": 7.488815104094977e-05,
|
| 1046 |
+
"entropy": 0.6238945558667183,
|
| 1047 |
+
"num_tokens": 12138307.0,
|
| 1048 |
+
"mean_token_accuracy": 0.8360639154911041,
|
| 1049 |
+
"epoch": 0.3572036060554516,
|
| 1050 |
+
"step": 1050
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"loss": 0.575,
|
| 1054 |
+
"grad_norm": 0.33959442377090454,
|
| 1055 |
+
"learning_rate": 7.440692957993543e-05,
|
| 1056 |
+
"entropy": 0.5791127294301986,
|
| 1057 |
+
"num_tokens": 12253996.0,
|
| 1058 |
+
"mean_token_accuracy": 0.8450855612754822,
|
| 1059 |
+
"epoch": 0.3606055451607416,
|
| 1060 |
+
"step": 1060
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"loss": 0.6387,
|
| 1064 |
+
"grad_norm": 0.35954946279525757,
|
| 1065 |
+
"learning_rate": 7.392272155520313e-05,
|
| 1066 |
+
"entropy": 0.6434630990028382,
|
| 1067 |
+
"num_tokens": 12367363.0,
|
| 1068 |
+
"mean_token_accuracy": 0.8307264894247055,
|
| 1069 |
+
"epoch": 0.36400748426603163,
|
| 1070 |
+
"step": 1070
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"loss": 0.6154,
|
| 1074 |
+
"grad_norm": 0.3226819932460785,
|
| 1075 |
+
"learning_rate": 7.343558621706186e-05,
|
| 1076 |
+
"entropy": 0.6265482395887375,
|
| 1077 |
+
"num_tokens": 12487636.0,
|
| 1078 |
+
"mean_token_accuracy": 0.8338571727275849,
|
| 1079 |
+
"epoch": 0.36740942337132165,
|
| 1080 |
+
"step": 1080
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"loss": 0.6088,
|
| 1084 |
+
"grad_norm": 0.3557349145412445,
|
| 1085 |
+
"learning_rate": 7.294558317402249e-05,
|
| 1086 |
+
"entropy": 0.6144857376813888,
|
| 1087 |
+
"num_tokens": 12598626.0,
|
| 1088 |
+
"mean_token_accuracy": 0.8359712421894073,
|
| 1089 |
+
"epoch": 0.3708113624766117,
|
| 1090 |
+
"step": 1090
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"loss": 0.6009,
|
| 1094 |
+
"grad_norm": 0.3251045346260071,
|
| 1095 |
+
"learning_rate": 7.24527723855037e-05,
|
| 1096 |
+
"entropy": 0.6028687685728074,
|
| 1097 |
+
"num_tokens": 12711531.0,
|
| 1098 |
+
"mean_token_accuracy": 0.8390907049179077,
|
| 1099 |
+
"epoch": 0.3742133015819017,
|
| 1100 |
+
"step": 1100
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"loss": 0.6078,
|
| 1104 |
+
"grad_norm": 0.3440212905406952,
|
| 1105 |
+
"learning_rate": 7.195721415449508e-05,
|
| 1106 |
+
"entropy": 0.61930713057518,
|
| 1107 |
+
"num_tokens": 12839137.0,
|
| 1108 |
+
"mean_token_accuracy": 0.8350177526473999,
|
| 1109 |
+
"epoch": 0.3776152406871917,
|
| 1110 |
+
"step": 1110
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"loss": 0.626,
|
| 1114 |
+
"grad_norm": 0.3647129535675049,
|
| 1115 |
+
"learning_rate": 7.14589691201782e-05,
|
| 1116 |
+
"entropy": 0.6314490288496017,
|
| 1117 |
+
"num_tokens": 12947358.0,
|
| 1118 |
+
"mean_token_accuracy": 0.8336542189121247,
|
| 1119 |
+
"epoch": 0.38101717979248173,
|
| 1120 |
+
"step": 1120
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"loss": 0.5787,
|
| 1124 |
+
"grad_norm": 0.3373214304447174,
|
| 1125 |
+
"learning_rate": 7.095809825050626e-05,
|
| 1126 |
+
"entropy": 0.5762265086174011,
|
| 1127 |
+
"num_tokens": 13066371.0,
|
| 1128 |
+
"mean_token_accuracy": 0.8430596113204956,
|
| 1129 |
+
"epoch": 0.38441911889777175,
|
| 1130 |
+
"step": 1130
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"loss": 0.6219,
|
| 1134 |
+
"grad_norm": 0.3417420983314514,
|
| 1135 |
+
"learning_rate": 7.045466283474397e-05,
|
| 1136 |
+
"entropy": 0.6200504913926125,
|
| 1137 |
+
"num_tokens": 13187362.0,
|
| 1138 |
+
"mean_token_accuracy": 0.8362764894962311,
|
| 1139 |
+
"epoch": 0.38782105800306177,
|
| 1140 |
+
"step": 1140
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"loss": 0.6018,
|
| 1144 |
+
"grad_norm": 0.37871527671813965,
|
| 1145 |
+
"learning_rate": 6.99487244759677e-05,
|
| 1146 |
+
"entropy": 0.6063272505998611,
|
| 1147 |
+
"num_tokens": 13299146.0,
|
| 1148 |
+
"mean_token_accuracy": 0.8369143933057785,
|
| 1149 |
+
"epoch": 0.39122299710835173,
|
| 1150 |
+
"step": 1150
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"loss": 0.6311,
|
| 1154 |
+
"grad_norm": 0.33044958114624023,
|
| 1155 |
+
"learning_rate": 6.944034508352745e-05,
|
| 1156 |
+
"entropy": 0.6377698928117752,
|
| 1157 |
+
"num_tokens": 13418154.0,
|
| 1158 |
+
"mean_token_accuracy": 0.831796658039093,
|
| 1159 |
+
"epoch": 0.39462493621364175,
|
| 1160 |
+
"step": 1160
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"loss": 0.5661,
|
| 1164 |
+
"grad_norm": 0.34921640157699585,
|
| 1165 |
+
"learning_rate": 6.892958686547129e-05,
|
| 1166 |
+
"entropy": 0.5706936493515968,
|
| 1167 |
+
"num_tokens": 13532234.0,
|
| 1168 |
+
"mean_token_accuracy": 0.8478675246238708,
|
| 1169 |
+
"epoch": 0.39802687531893177,
|
| 1170 |
+
"step": 1170
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"loss": 0.6017,
|
| 1174 |
+
"grad_norm": 0.3906354010105133,
|
| 1175 |
+
"learning_rate": 6.841651232093321e-05,
|
| 1176 |
+
"entropy": 0.604531979560852,
|
| 1177 |
+
"num_tokens": 13647265.0,
|
| 1178 |
+
"mean_token_accuracy": 0.8396757930517197,
|
| 1179 |
+
"epoch": 0.4014288144242218,
|
| 1180 |
+
"step": 1180
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"loss": 0.5594,
|
| 1184 |
+
"grad_norm": 0.35730934143066406,
|
| 1185 |
+
"learning_rate": 6.790118423248545e-05,
|
| 1186 |
+
"entropy": 0.5594036534428597,
|
| 1187 |
+
"num_tokens": 13762753.0,
|
| 1188 |
+
"mean_token_accuracy": 0.8494072288274765,
|
| 1189 |
+
"epoch": 0.4048307535295118,
|
| 1190 |
+
"step": 1190
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"loss": 0.6035,
|
| 1194 |
+
"grad_norm": 0.40569987893104553,
|
| 1195 |
+
"learning_rate": 6.738366565845609e-05,
|
| 1196 |
+
"entropy": 0.6062624737620353,
|
| 1197 |
+
"num_tokens": 13887573.0,
|
| 1198 |
+
"mean_token_accuracy": 0.8375277072191238,
|
| 1199 |
+
"epoch": 0.40823269263480183,
|
| 1200 |
+
"step": 1200
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"loss": 0.6,
|
| 1204 |
+
"grad_norm": 0.3749787509441376,
|
| 1205 |
+
"learning_rate": 6.686401992521274e-05,
|
| 1206 |
+
"entropy": 0.5981257140636445,
|
| 1207 |
+
"num_tokens": 14009093.0,
|
| 1208 |
+
"mean_token_accuracy": 0.839872732758522,
|
| 1209 |
+
"epoch": 0.41163463174009185,
|
| 1210 |
+
"step": 1210
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"loss": 0.5752,
|
| 1214 |
+
"grad_norm": 0.34199485182762146,
|
| 1215 |
+
"learning_rate": 6.634231061941383e-05,
|
| 1216 |
+
"entropy": 0.5763212725520134,
|
| 1217 |
+
"num_tokens": 14133014.0,
|
| 1218 |
+
"mean_token_accuracy": 0.8439627707004547,
|
| 1219 |
+
"epoch": 0.41503657084538187,
|
| 1220 |
+
"step": 1220
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"loss": 0.5881,
|
| 1224 |
+
"grad_norm": 0.38227760791778564,
|
| 1225 |
+
"learning_rate": 6.581860158022757e-05,
|
| 1226 |
+
"entropy": 0.5911096960306168,
|
| 1227 |
+
"num_tokens": 14243866.0,
|
| 1228 |
+
"mean_token_accuracy": 0.8422502607107163,
|
| 1229 |
+
"epoch": 0.4184385099506719,
|
| 1230 |
+
"step": 1230
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"loss": 0.5924,
|
| 1234 |
+
"grad_norm": 0.31732606887817383,
|
| 1235 |
+
"learning_rate": 6.529295689152042e-05,
|
| 1236 |
+
"entropy": 0.6007756769657135,
|
| 1237 |
+
"num_tokens": 14354926.0,
|
| 1238 |
+
"mean_token_accuracy": 0.841707193851471,
|
| 1239 |
+
"epoch": 0.4218404490559619,
|
| 1240 |
+
"step": 1240
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"loss": 0.564,
|
| 1244 |
+
"grad_norm": 0.3495018780231476,
|
| 1245 |
+
"learning_rate": 6.476544087401532e-05,
|
| 1246 |
+
"entropy": 0.5664652720093727,
|
| 1247 |
+
"num_tokens": 14472132.0,
|
| 1248 |
+
"mean_token_accuracy": 0.845953956246376,
|
| 1249 |
+
"epoch": 0.4252423881612519,
|
| 1250 |
+
"step": 1250
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"loss": 0.6371,
|
| 1254 |
+
"grad_norm": 0.39551210403442383,
|
| 1255 |
+
"learning_rate": 6.423611807742116e-05,
|
| 1256 |
+
"entropy": 0.6342313542962075,
|
| 1257 |
+
"num_tokens": 14595618.0,
|
| 1258 |
+
"mean_token_accuracy": 0.8320615291595459,
|
| 1259 |
+
"epoch": 0.42864432726654195,
|
| 1260 |
+
"step": 1260
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"loss": 0.5862,
|
| 1264 |
+
"grad_norm": 0.3622702360153198,
|
| 1265 |
+
"learning_rate": 6.3705053272534e-05,
|
| 1266 |
+
"entropy": 0.5873361572623252,
|
| 1267 |
+
"num_tokens": 14715491.0,
|
| 1268 |
+
"mean_token_accuracy": 0.8399784296751023,
|
| 1269 |
+
"epoch": 0.43204626637183197,
|
| 1270 |
+
"step": 1270
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"loss": 0.5878,
|
| 1274 |
+
"grad_norm": 0.3421778082847595,
|
| 1275 |
+
"learning_rate": 6.317231144331153e-05,
|
| 1276 |
+
"entropy": 0.591562668979168,
|
| 1277 |
+
"num_tokens": 14829063.0,
|
| 1278 |
+
"mean_token_accuracy": 0.8422017335891724,
|
| 1279 |
+
"epoch": 0.435448205477122,
|
| 1280 |
+
"step": 1280
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"loss": 0.556,
|
| 1284 |
+
"grad_norm": 0.33399707078933716,
|
| 1285 |
+
"learning_rate": 6.263795777892115e-05,
|
| 1286 |
+
"entropy": 0.5609270349144936,
|
| 1287 |
+
"num_tokens": 14942097.0,
|
| 1288 |
+
"mean_token_accuracy": 0.8491690754890442,
|
| 1289 |
+
"epoch": 0.43885014458241195,
|
| 1290 |
+
"step": 1290
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"loss": 0.598,
|
| 1294 |
+
"grad_norm": 0.33439555764198303,
|
| 1295 |
+
"learning_rate": 6.210205766576308e-05,
|
| 1296 |
+
"entropy": 0.6013634830713273,
|
| 1297 |
+
"num_tokens": 15063270.0,
|
| 1298 |
+
"mean_token_accuracy": 0.8379765659570694,
|
| 1299 |
+
"epoch": 0.44225208368770197,
|
| 1300 |
+
"step": 1300
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"loss": 0.5739,
|
| 1304 |
+
"grad_norm": 0.34527984261512756,
|
| 1305 |
+
"learning_rate": 6.156467667946944e-05,
|
| 1306 |
+
"entropy": 0.5805606454610824,
|
| 1307 |
+
"num_tokens": 15182142.0,
|
| 1308 |
+
"mean_token_accuracy": 0.8448573082685471,
|
| 1309 |
+
"epoch": 0.445654022792992,
|
| 1310 |
+
"step": 1310
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"loss": 0.6355,
|
| 1314 |
+
"grad_norm": 0.32778117060661316,
|
| 1315 |
+
"learning_rate": 6.1025880576879934e-05,
|
| 1316 |
+
"entropy": 0.6364081218838692,
|
| 1317 |
+
"num_tokens": 15301327.0,
|
| 1318 |
+
"mean_token_accuracy": 0.8308557868003845,
|
| 1319 |
+
"epoch": 0.449055961898282,
|
| 1320 |
+
"step": 1320
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"loss": 0.6181,
|
| 1324 |
+
"grad_norm": 0.34031936526298523,
|
| 1325 |
+
"learning_rate": 6.048573528799556e-05,
|
| 1326 |
+
"entropy": 0.6205928295850753,
|
| 1327 |
+
"num_tokens": 15420327.0,
|
| 1328 |
+
"mean_token_accuracy": 0.834335333108902,
|
| 1329 |
+
"epoch": 0.452457901003572,
|
| 1330 |
+
"step": 1330
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"loss": 0.5708,
|
| 1334 |
+
"grad_norm": 0.40162762999534607,
|
| 1335 |
+
"learning_rate": 5.994430690791102e-05,
|
| 1336 |
+
"entropy": 0.572858938574791,
|
| 1337 |
+
"num_tokens": 15527631.0,
|
| 1338 |
+
"mean_token_accuracy": 0.8488004267215729,
|
| 1339 |
+
"epoch": 0.45585984010886205,
|
| 1340 |
+
"step": 1340
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"loss": 0.6002,
|
| 1344 |
+
"grad_norm": 0.3677639961242676,
|
| 1345 |
+
"learning_rate": 5.9401661688726986e-05,
|
| 1346 |
+
"entropy": 0.6025476709008217,
|
| 1347 |
+
"num_tokens": 15645227.0,
|
| 1348 |
+
"mean_token_accuracy": 0.8378155291080475,
|
| 1349 |
+
"epoch": 0.45926177921415207,
|
| 1350 |
+
"step": 1350
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"loss": 0.6391,
|
| 1354 |
+
"grad_norm": 0.3611242175102234,
|
| 1355 |
+
"learning_rate": 5.8857866031443155e-05,
|
| 1356 |
+
"entropy": 0.6453688651323318,
|
| 1357 |
+
"num_tokens": 15755942.0,
|
| 1358 |
+
"mean_token_accuracy": 0.8302028566598892,
|
| 1359 |
+
"epoch": 0.4626637183194421,
|
| 1360 |
+
"step": 1360
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"loss": 0.5891,
|
| 1364 |
+
"grad_norm": 0.3595288097858429,
|
| 1365 |
+
"learning_rate": 5.8312986477833035e-05,
|
| 1366 |
+
"entropy": 0.6027933269739151,
|
| 1367 |
+
"num_tokens": 15862604.0,
|
| 1368 |
+
"mean_token_accuracy": 0.842942762374878,
|
| 1369 |
+
"epoch": 0.4660656574247321,
|
| 1370 |
+
"step": 1370
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"loss": 0.5901,
|
| 1374 |
+
"grad_norm": 0.3880114257335663,
|
| 1375 |
+
"learning_rate": 5.7767089702301526e-05,
|
| 1376 |
+
"entropy": 0.5783761963248253,
|
| 1377 |
+
"num_tokens": 15974317.0,
|
| 1378 |
+
"mean_token_accuracy": 0.8423945069313049,
|
| 1379 |
+
"epoch": 0.4694675965300221,
|
| 1380 |
+
"step": 1380
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"loss": 0.5735,
|
| 1384 |
+
"grad_norm": 0.33461010456085205,
|
| 1385 |
+
"learning_rate": 5.722024250372632e-05,
|
| 1386 |
+
"entropy": 0.5808866828680038,
|
| 1387 |
+
"num_tokens": 16083489.0,
|
| 1388 |
+
"mean_token_accuracy": 0.8458300411701203,
|
| 1389 |
+
"epoch": 0.47286953563531214,
|
| 1390 |
+
"step": 1390
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"loss": 0.5967,
|
| 1394 |
+
"grad_norm": 0.3592625856399536,
|
| 1395 |
+
"learning_rate": 5.667251179728398e-05,
|
| 1396 |
+
"entropy": 0.5973397344350815,
|
| 1397 |
+
"num_tokens": 16209893.0,
|
| 1398 |
+
"mean_token_accuracy": 0.8369288891553879,
|
| 1399 |
+
"epoch": 0.47627147474060216,
|
| 1400 |
+
"step": 1400
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"loss": 0.6051,
|
| 1404 |
+
"grad_norm": 0.356492817401886,
|
| 1405 |
+
"learning_rate": 5.612396460626188e-05,
|
| 1406 |
+
"entropy": 0.6047371000051498,
|
| 1407 |
+
"num_tokens": 16328112.0,
|
| 1408 |
+
"mean_token_accuracy": 0.8397100865840912,
|
| 1409 |
+
"epoch": 0.4796734138458922,
|
| 1410 |
+
"step": 1410
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"loss": 0.6526,
|
| 1414 |
+
"grad_norm": 0.3834919333457947,
|
| 1415 |
+
"learning_rate": 5.557466805385685e-05,
|
| 1416 |
+
"entropy": 0.6492822825908661,
|
| 1417 |
+
"num_tokens": 16439800.0,
|
| 1418 |
+
"mean_token_accuracy": 0.829655796289444,
|
| 1419 |
+
"epoch": 0.48307535295118215,
|
| 1420 |
+
"step": 1420
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"loss": 0.5926,
|
| 1424 |
+
"grad_norm": 0.35866421461105347,
|
| 1425 |
+
"learning_rate": 5.502468935496164e-05,
|
| 1426 |
+
"entropy": 0.6050204545259475,
|
| 1427 |
+
"num_tokens": 16553741.0,
|
| 1428 |
+
"mean_token_accuracy": 0.8413259029388428,
|
| 1429 |
+
"epoch": 0.48647729205647217,
|
| 1430 |
+
"step": 1430
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"loss": 0.5734,
|
| 1434 |
+
"grad_norm": 0.3319409191608429,
|
| 1435 |
+
"learning_rate": 5.4474095807940094e-05,
|
| 1436 |
+
"entropy": 0.5755202546715736,
|
| 1437 |
+
"num_tokens": 16673973.0,
|
| 1438 |
+
"mean_token_accuracy": 0.8435852289199829,
|
| 1439 |
+
"epoch": 0.4898792311617622,
|
| 1440 |
+
"step": 1440
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"loss": 0.586,
|
| 1444 |
+
"grad_norm": 0.3485705554485321,
|
| 1445 |
+
"learning_rate": 5.392295478639225e-05,
|
| 1446 |
+
"entropy": 0.5858001261949539,
|
| 1447 |
+
"num_tokens": 16783732.0,
|
| 1448 |
+
"mean_token_accuracy": 0.8417124092578888,
|
| 1449 |
+
"epoch": 0.4932811702670522,
|
| 1450 |
+
"step": 1450
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"loss": 0.612,
|
| 1454 |
+
"grad_norm": 0.3999135494232178,
|
| 1455 |
+
"learning_rate": 5.3371333730910035e-05,
|
| 1456 |
+
"entropy": 0.6123771637678146,
|
| 1457 |
+
"num_tokens": 16899108.0,
|
| 1458 |
+
"mean_token_accuracy": 0.8361808478832244,
|
| 1459 |
+
"epoch": 0.4966831093723422,
|
| 1460 |
+
"step": 1460
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"loss": 0.5768,
|
| 1464 |
+
"grad_norm": 0.37186917662620544,
|
| 1465 |
+
"learning_rate": 5.2819300140824924e-05,
|
| 1466 |
+
"entropy": 0.5769275650382042,
|
| 1467 |
+
"num_tokens": 17015498.0,
|
| 1468 |
+
"mean_token_accuracy": 0.8437288701534271,
|
| 1469 |
+
"epoch": 0.5000850484776322,
|
| 1470 |
+
"step": 1470
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"loss": 0.6068,
|
| 1474 |
+
"grad_norm": 0.36763256788253784,
|
| 1475 |
+
"learning_rate": 5.22669215659484e-05,
|
| 1476 |
+
"entropy": 0.6088968113064765,
|
| 1477 |
+
"num_tokens": 17122826.0,
|
| 1478 |
+
"mean_token_accuracy": 0.8394175559282303,
|
| 1479 |
+
"epoch": 0.5034869875829223,
|
| 1480 |
+
"step": 1480
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"loss": 0.6024,
|
| 1484 |
+
"grad_norm": 0.33930572867393494,
|
| 1485 |
+
"learning_rate": 5.17142655983061e-05,
|
| 1486 |
+
"entropy": 0.6036048322916031,
|
| 1487 |
+
"num_tokens": 17248073.0,
|
| 1488 |
+
"mean_token_accuracy": 0.838006791472435,
|
| 1489 |
+
"epoch": 0.5068889266882123,
|
| 1490 |
+
"step": 1490
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"loss": 0.5755,
|
| 1494 |
+
"grad_norm": 0.355539470911026,
|
| 1495 |
+
"learning_rate": 5.116139986386695e-05,
|
| 1496 |
+
"entropy": 0.57216976583004,
|
| 1497 |
+
"num_tokens": 17353849.0,
|
| 1498 |
+
"mean_token_accuracy": 0.8462014138698578,
|
| 1499 |
+
"epoch": 0.5102908657935022,
|
| 1500 |
+
"step": 1500
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"loss": 0.5785,
|
| 1504 |
+
"grad_norm": 0.3130170702934265,
|
| 1505 |
+
"learning_rate": 5.0608392014268093e-05,
|
| 1506 |
+
"entropy": 0.5841953173279762,
|
| 1507 |
+
"num_tokens": 17465362.0,
|
| 1508 |
+
"mean_token_accuracy": 0.8455700755119324,
|
| 1509 |
+
"epoch": 0.5136928048987923,
|
| 1510 |
+
"step": 1510
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"loss": 0.5854,
|
| 1514 |
+
"grad_norm": 0.34390658140182495,
|
| 1515 |
+
"learning_rate": 5.005530971853661e-05,
|
| 1516 |
+
"entropy": 0.588604536652565,
|
| 1517 |
+
"num_tokens": 17583990.0,
|
| 1518 |
+
"mean_token_accuracy": 0.8393468260765076,
|
| 1519 |
+
"epoch": 0.5170947440040823,
|
| 1520 |
+
"step": 1520
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"loss": 0.5412,
|
| 1524 |
+
"grad_norm": 0.3938881456851959,
|
| 1525 |
+
"learning_rate": 4.950222065480926e-05,
|
| 1526 |
+
"entropy": 0.5458601832389831,
|
| 1527 |
+
"num_tokens": 17695756.0,
|
| 1528 |
+
"mean_token_accuracy": 0.8516582667827606,
|
| 1529 |
+
"epoch": 0.5204966831093724,
|
| 1530 |
+
"step": 1530
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"loss": 0.6066,
|
| 1534 |
+
"grad_norm": 0.36709338426589966,
|
| 1535 |
+
"learning_rate": 4.894919250205095e-05,
|
| 1536 |
+
"entropy": 0.6080822870135307,
|
| 1537 |
+
"num_tokens": 17819124.0,
|
| 1538 |
+
"mean_token_accuracy": 0.8351925998926163,
|
| 1539 |
+
"epoch": 0.5238986222146623,
|
| 1540 |
+
"step": 1540
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"loss": 0.603,
|
| 1544 |
+
"grad_norm": 0.3591138422489166,
|
| 1545 |
+
"learning_rate": 4.8396292931773194e-05,
|
| 1546 |
+
"entropy": 0.6067529514431953,
|
| 1547 |
+
"num_tokens": 17942151.0,
|
| 1548 |
+
"mean_token_accuracy": 0.8357031852006912,
|
| 1549 |
+
"epoch": 0.5273005613199524,
|
| 1550 |
+
"step": 1550
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"loss": 0.5889,
|
| 1554 |
+
"grad_norm": 0.32743504643440247,
|
| 1555 |
+
"learning_rate": 4.7843589599753436e-05,
|
| 1556 |
+
"entropy": 0.5867392048239708,
|
| 1557 |
+
"num_tokens": 18051775.0,
|
| 1558 |
+
"mean_token_accuracy": 0.8451169669628144,
|
| 1559 |
+
"epoch": 0.5307025004252424,
|
| 1560 |
+
"step": 1560
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"loss": 0.5827,
|
| 1564 |
+
"grad_norm": 0.34111034870147705,
|
| 1565 |
+
"learning_rate": 4.729115013775639e-05,
|
| 1566 |
+
"entropy": 0.5817334815859795,
|
| 1567 |
+
"num_tokens": 18174207.0,
|
| 1568 |
+
"mean_token_accuracy": 0.8418365478515625,
|
| 1569 |
+
"epoch": 0.5341044395305324,
|
| 1570 |
+
"step": 1570
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"loss": 0.5605,
|
| 1574 |
+
"grad_norm": 0.40375614166259766,
|
| 1575 |
+
"learning_rate": 4.673904214525817e-05,
|
| 1576 |
+
"entropy": 0.5690050527453423,
|
| 1577 |
+
"num_tokens": 18296847.0,
|
| 1578 |
+
"mean_token_accuracy": 0.8457064211368561,
|
| 1579 |
+
"epoch": 0.5375063786358224,
|
| 1580 |
+
"step": 1580
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"loss": 0.6214,
|
| 1584 |
+
"grad_norm": 0.34886664152145386,
|
| 1585 |
+
"learning_rate": 4.618733318117453e-05,
|
| 1586 |
+
"entropy": 0.613763065636158,
|
| 1587 |
+
"num_tokens": 18411175.0,
|
| 1588 |
+
"mean_token_accuracy": 0.8373794168233871,
|
| 1589 |
+
"epoch": 0.5409083177411125,
|
| 1590 |
+
"step": 1590
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"loss": 0.5932,
|
| 1594 |
+
"grad_norm": 0.4052237868309021,
|
| 1595 |
+
"learning_rate": 4.56360907555939e-05,
|
| 1596 |
+
"entropy": 0.5990845367312432,
|
| 1597 |
+
"num_tokens": 18523679.0,
|
| 1598 |
+
"mean_token_accuracy": 0.8415322303771973,
|
| 1599 |
+
"epoch": 0.5443102568464024,
|
| 1600 |
+
"step": 1600
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"loss": 0.5587,
|
| 1604 |
+
"grad_norm": 0.33428770303726196,
|
| 1605 |
+
"learning_rate": 4.508538232151659e-05,
|
| 1606 |
+
"entropy": 0.5686810597777366,
|
| 1607 |
+
"num_tokens": 18638795.0,
|
| 1608 |
+
"mean_token_accuracy": 0.8485085606575012,
|
| 1609 |
+
"epoch": 0.5477121959516925,
|
| 1610 |
+
"step": 1610
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"loss": 0.5528,
|
| 1614 |
+
"grad_norm": 0.3429810106754303,
|
| 1615 |
+
"learning_rate": 4.453527526660079e-05,
|
| 1616 |
+
"entropy": 0.5541219785809517,
|
| 1617 |
+
"num_tokens": 18757690.0,
|
| 1618 |
+
"mean_token_accuracy": 0.8475034803152084,
|
| 1619 |
+
"epoch": 0.5511141350569825,
|
| 1620 |
+
"step": 1620
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"loss": 0.5896,
|
| 1624 |
+
"grad_norm": 0.36002102494239807,
|
| 1625 |
+
"learning_rate": 4.398583690491673e-05,
|
| 1626 |
+
"entropy": 0.594765892624855,
|
| 1627 |
+
"num_tokens": 18870237.0,
|
| 1628 |
+
"mean_token_accuracy": 0.841697883605957,
|
| 1629 |
+
"epoch": 0.5545160741622724,
|
| 1630 |
+
"step": 1630
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"loss": 0.5583,
|
| 1634 |
+
"grad_norm": 0.3443513810634613,
|
| 1635 |
+
"learning_rate": 4.3437134468709684e-05,
|
| 1636 |
+
"entropy": 0.5576672151684761,
|
| 1637 |
+
"num_tokens": 18989654.0,
|
| 1638 |
+
"mean_token_accuracy": 0.8470352560281753,
|
| 1639 |
+
"epoch": 0.5579180132675625,
|
| 1640 |
+
"step": 1640
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"loss": 0.5715,
|
| 1644 |
+
"grad_norm": 0.3210230767726898,
|
| 1645 |
+
"learning_rate": 4.2889235100173117e-05,
|
| 1646 |
+
"entropy": 0.5803326085209847,
|
| 1647 |
+
"num_tokens": 19111873.0,
|
| 1648 |
+
"mean_token_accuracy": 0.8444038182497025,
|
| 1649 |
+
"epoch": 0.5613199523728525,
|
| 1650 |
+
"step": 1650
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"loss": 0.579,
|
| 1654 |
+
"grad_norm": 0.3320671617984772,
|
| 1655 |
+
"learning_rate": 4.2342205843232815e-05,
|
| 1656 |
+
"entropy": 0.5725411295890808,
|
| 1657 |
+
"num_tokens": 19227912.0,
|
| 1658 |
+
"mean_token_accuracy": 0.8457438528537751,
|
| 1659 |
+
"epoch": 0.5647218914781426,
|
| 1660 |
+
"step": 1660
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"loss": 0.587,
|
| 1664 |
+
"grad_norm": 0.38086163997650146,
|
| 1665 |
+
"learning_rate": 4.1796113635342995e-05,
|
| 1666 |
+
"entropy": 0.5874329909682274,
|
| 1667 |
+
"num_tokens": 19349977.0,
|
| 1668 |
+
"mean_token_accuracy": 0.840248167514801,
|
| 1669 |
+
"epoch": 0.5681238305834325,
|
| 1670 |
+
"step": 1670
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"loss": 0.5847,
|
| 1674 |
+
"grad_norm": 0.3494766652584076,
|
| 1675 |
+
"learning_rate": 4.1251025299295484e-05,
|
| 1676 |
+
"entropy": 0.5962051749229431,
|
| 1677 |
+
"num_tokens": 19463971.0,
|
| 1678 |
+
"mean_token_accuracy": 0.8411266356706619,
|
| 1679 |
+
"epoch": 0.5715257696887226,
|
| 1680 |
+
"step": 1680
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"loss": 0.5886,
|
| 1684 |
+
"grad_norm": 0.34530606865882874,
|
| 1685 |
+
"learning_rate": 4.0707007535042965e-05,
|
| 1686 |
+
"entropy": 0.5932681888341904,
|
| 1687 |
+
"num_tokens": 19584720.0,
|
| 1688 |
+
"mean_token_accuracy": 0.8420757114887237,
|
| 1689 |
+
"epoch": 0.5749277087940126,
|
| 1690 |
+
"step": 1690
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"loss": 0.6255,
|
| 1694 |
+
"grad_norm": 0.39939698576927185,
|
| 1695 |
+
"learning_rate": 4.0164126911537124e-05,
|
| 1696 |
+
"entropy": 0.6298390612006187,
|
| 1697 |
+
"num_tokens": 19707943.0,
|
| 1698 |
+
"mean_token_accuracy": 0.8327343821525574,
|
| 1699 |
+
"epoch": 0.5783296478993026,
|
| 1700 |
+
"step": 1700
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"loss": 0.5829,
|
| 1704 |
+
"grad_norm": 0.39982014894485474,
|
| 1705 |
+
"learning_rate": 3.9622449858583e-05,
|
| 1706 |
+
"entropy": 0.5805615946650505,
|
| 1707 |
+
"num_tokens": 19821092.0,
|
| 1708 |
+
"mean_token_accuracy": 0.8441908627748489,
|
| 1709 |
+
"epoch": 0.5817315870045926,
|
| 1710 |
+
"step": 1710
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"loss": 0.5546,
|
| 1714 |
+
"grad_norm": 0.3315586447715759,
|
| 1715 |
+
"learning_rate": 3.908204265871024e-05,
|
| 1716 |
+
"entropy": 0.5536176040768623,
|
| 1717 |
+
"num_tokens": 19926967.0,
|
| 1718 |
+
"mean_token_accuracy": 0.8505498200654984,
|
| 1719 |
+
"epoch": 0.5851335261098827,
|
| 1720 |
+
"step": 1720
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"loss": 0.6144,
|
| 1724 |
+
"grad_norm": 0.38606083393096924,
|
| 1725 |
+
"learning_rate": 3.8542971439062375e-05,
|
| 1726 |
+
"entropy": 0.6170039817690849,
|
| 1727 |
+
"num_tokens": 20050273.0,
|
| 1728 |
+
"mean_token_accuracy": 0.8357849180698395,
|
| 1729 |
+
"epoch": 0.5885354652151726,
|
| 1730 |
+
"step": 1730
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"loss": 0.6018,
|
| 1734 |
+
"grad_norm": 0.35552018880844116,
|
| 1735 |
+
"learning_rate": 3.800530216330522e-05,
|
| 1736 |
+
"entropy": 0.6068514689803124,
|
| 1737 |
+
"num_tokens": 20168367.0,
|
| 1738 |
+
"mean_token_accuracy": 0.8391161382198333,
|
| 1739 |
+
"epoch": 0.5919374043204627,
|
| 1740 |
+
"step": 1740
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"loss": 0.6014,
|
| 1744 |
+
"grad_norm": 0.408333957195282,
|
| 1745 |
+
"learning_rate": 3.746910062355514e-05,
|
| 1746 |
+
"entropy": 0.6115496993064881,
|
| 1747 |
+
"num_tokens": 20275208.0,
|
| 1748 |
+
"mean_token_accuracy": 0.837997031211853,
|
| 1749 |
+
"epoch": 0.5953393434257527,
|
| 1750 |
+
"step": 1750
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"loss": 0.5656,
|
| 1754 |
+
"grad_norm": 0.3675805628299713,
|
| 1755 |
+
"learning_rate": 3.693443243232839e-05,
|
| 1756 |
+
"entropy": 0.5659057840704917,
|
| 1757 |
+
"num_tokens": 20395513.0,
|
| 1758 |
+
"mean_token_accuracy": 0.846270963549614,
|
| 1759 |
+
"epoch": 0.5987412825310426,
|
| 1760 |
+
"step": 1760
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"loss": 0.5876,
|
| 1764 |
+
"grad_norm": 0.34130120277404785,
|
| 1765 |
+
"learning_rate": 3.6401363014512465e-05,
|
| 1766 |
+
"entropy": 0.5852897882461547,
|
| 1767 |
+
"num_tokens": 20513840.0,
|
| 1768 |
+
"mean_token_accuracy": 0.8406417429447174,
|
| 1769 |
+
"epoch": 0.6021432216363327,
|
| 1770 |
+
"step": 1770
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"loss": 0.5846,
|
| 1774 |
+
"grad_norm": 0.3448680341243744,
|
| 1775 |
+
"learning_rate": 3.586995759936027e-05,
|
| 1776 |
+
"entropy": 0.5861192226409913,
|
| 1777 |
+
"num_tokens": 20626418.0,
|
| 1778 |
+
"mean_token_accuracy": 0.8443343281745911,
|
| 1779 |
+
"epoch": 0.6055451607416227,
|
| 1780 |
+
"step": 1780
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"loss": 0.5629,
|
| 1784 |
+
"grad_norm": 0.33498626947402954,
|
| 1785 |
+
"learning_rate": 3.5340281212508355e-05,
|
| 1786 |
+
"entropy": 0.5744142100214958,
|
| 1787 |
+
"num_tokens": 20743700.0,
|
| 1788 |
+
"mean_token_accuracy": 0.8447044044733047,
|
| 1789 |
+
"epoch": 0.6089470998469128,
|
| 1790 |
+
"step": 1790
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"loss": 0.5491,
|
| 1794 |
+
"grad_norm": 0.3723412752151489,
|
| 1795 |
+
"learning_rate": 3.481239866802003e-05,
|
| 1796 |
+
"entropy": 0.5503455892205238,
|
| 1797 |
+
"num_tokens": 20848890.0,
|
| 1798 |
+
"mean_token_accuracy": 0.8521771311759949,
|
| 1799 |
+
"epoch": 0.6123490389522027,
|
| 1800 |
+
"step": 1800
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"loss": 0.5728,
|
| 1804 |
+
"grad_norm": 0.37624675035476685,
|
| 1805 |
+
"learning_rate": 3.428637456045438e-05,
|
| 1806 |
+
"entropy": 0.5796245783567429,
|
| 1807 |
+
"num_tokens": 20959919.0,
|
| 1808 |
+
"mean_token_accuracy": 0.8451456815004349,
|
| 1809 |
+
"epoch": 0.6157509780574928,
|
| 1810 |
+
"step": 1810
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"loss": 0.6005,
|
| 1814 |
+
"grad_norm": 0.4184034466743469,
|
| 1815 |
+
"learning_rate": 3.3762273256962115e-05,
|
| 1816 |
+
"entropy": 0.6072939783334732,
|
| 1817 |
+
"num_tokens": 21068427.0,
|
| 1818 |
+
"mean_token_accuracy": 0.8402355641126633,
|
| 1819 |
+
"epoch": 0.6191529171627828,
|
| 1820 |
+
"step": 1820
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"loss": 0.6061,
|
| 1824 |
+
"grad_norm": 0.38452163338661194,
|
| 1825 |
+
"learning_rate": 3.324015888940925e-05,
|
| 1826 |
+
"entropy": 0.6065735876560211,
|
| 1827 |
+
"num_tokens": 21184885.0,
|
| 1828 |
+
"mean_token_accuracy": 0.8360267549753189,
|
| 1829 |
+
"epoch": 0.6225548562680728,
|
| 1830 |
+
"step": 1830
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"loss": 0.5824,
|
| 1834 |
+
"grad_norm": 0.4377152919769287,
|
| 1835 |
+
"learning_rate": 3.2720095346529566e-05,
|
| 1836 |
+
"entropy": 0.5836168915033341,
|
| 1837 |
+
"num_tokens": 21298789.0,
|
| 1838 |
+
"mean_token_accuracy": 0.8420229732990265,
|
| 1839 |
+
"epoch": 0.6259567953733628,
|
| 1840 |
+
"step": 1840
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"loss": 0.5761,
|
| 1844 |
+
"grad_norm": 0.3785684406757355,
|
| 1845 |
+
"learning_rate": 3.220214626610689e-05,
|
| 1846 |
+
"entropy": 0.5765029028058052,
|
| 1847 |
+
"num_tokens": 21424296.0,
|
| 1848 |
+
"mean_token_accuracy": 0.8433551669120789,
|
| 1849 |
+
"epoch": 0.6293587344786529,
|
| 1850 |
+
"step": 1850
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"loss": 0.572,
|
| 1854 |
+
"grad_norm": 0.37199345231056213,
|
| 1855 |
+
"learning_rate": 3.168637502718798e-05,
|
| 1856 |
+
"entropy": 0.5756848677992821,
|
| 1857 |
+
"num_tokens": 21534093.0,
|
| 1858 |
+
"mean_token_accuracy": 0.8463689625263214,
|
| 1859 |
+
"epoch": 0.6327606735839428,
|
| 1860 |
+
"step": 1860
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"loss": 0.5863,
|
| 1864 |
+
"grad_norm": 0.38243773579597473,
|
| 1865 |
+
"learning_rate": 3.117284474232717e-05,
|
| 1866 |
+
"entropy": 0.5788663312792778,
|
| 1867 |
+
"num_tokens": 21656220.0,
|
| 1868 |
+
"mean_token_accuracy": 0.8417115867137909,
|
| 1869 |
+
"epoch": 0.6361626126892329,
|
| 1870 |
+
"step": 1870
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"loss": 0.5986,
|
| 1874 |
+
"grad_norm": 0.3821103274822235,
|
| 1875 |
+
"learning_rate": 3.066161824986352e-05,
|
| 1876 |
+
"entropy": 0.5999485164880752,
|
| 1877 |
+
"num_tokens": 21770257.0,
|
| 1878 |
+
"mean_token_accuracy": 0.8380926698446274,
|
| 1879 |
+
"epoch": 0.6395645517945229,
|
| 1880 |
+
"step": 1880
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"loss": 0.577,
|
| 1884 |
+
"grad_norm": 0.33614298701286316,
|
| 1885 |
+
"learning_rate": 3.0152758106231642e-05,
|
| 1886 |
+
"entropy": 0.5815630614757538,
|
| 1887 |
+
"num_tokens": 21896451.0,
|
| 1888 |
+
"mean_token_accuracy": 0.8430263727903367,
|
| 1889 |
+
"epoch": 0.642966490899813,
|
| 1890 |
+
"step": 1890
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"loss": 0.6131,
|
| 1894 |
+
"grad_norm": 0.39611414074897766,
|
| 1895 |
+
"learning_rate": 2.9646326578306915e-05,
|
| 1896 |
+
"entropy": 0.6189764007925987,
|
| 1897 |
+
"num_tokens": 22003560.0,
|
| 1898 |
+
"mean_token_accuracy": 0.8391340941190719,
|
| 1899 |
+
"epoch": 0.6463684300051029,
|
| 1900 |
+
"step": 1900
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"loss": 0.5443,
|
| 1904 |
+
"grad_norm": 0.33414164185523987,
|
| 1905 |
+
"learning_rate": 2.914238563578618e-05,
|
| 1906 |
+
"entropy": 0.5429508209228515,
|
| 1907 |
+
"num_tokens": 22117872.0,
|
| 1908 |
+
"mean_token_accuracy": 0.8526928842067718,
|
| 1909 |
+
"epoch": 0.6497703691103929,
|
| 1910 |
+
"step": 1910
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"loss": 0.6123,
|
| 1914 |
+
"grad_norm": 0.4099610447883606,
|
| 1915 |
+
"learning_rate": 2.864099694360479e-05,
|
| 1916 |
+
"entropy": 0.6225771173834801,
|
| 1917 |
+
"num_tokens": 22222509.0,
|
| 1918 |
+
"mean_token_accuracy": 0.8378654181957245,
|
| 1919 |
+
"epoch": 0.653172308215683,
|
| 1920 |
+
"step": 1920
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"loss": 0.5621,
|
| 1924 |
+
"grad_norm": 0.3818487823009491,
|
| 1925 |
+
"learning_rate": 2.814222185439098e-05,
|
| 1926 |
+
"entropy": 0.5593055367469788,
|
| 1927 |
+
"num_tokens": 22335582.0,
|
| 1928 |
+
"mean_token_accuracy": 0.8501265943050385,
|
| 1929 |
+
"epoch": 0.6565742473209729,
|
| 1930 |
+
"step": 1930
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"loss": 0.6008,
|
| 1934 |
+
"grad_norm": 0.4001128673553467,
|
| 1935 |
+
"learning_rate": 2.764612140095839e-05,
|
| 1936 |
+
"entropy": 0.6034526154398918,
|
| 1937 |
+
"num_tokens": 22448701.0,
|
| 1938 |
+
"mean_token_accuracy": 0.8390175521373748,
|
| 1939 |
+
"epoch": 0.659976186426263,
|
| 1940 |
+
"step": 1940
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"loss": 0.5682,
|
| 1944 |
+
"grad_norm": 0.3717249035835266,
|
| 1945 |
+
"learning_rate": 2.715275628883781e-05,
|
| 1946 |
+
"entropy": 0.5757593274116516,
|
| 1947 |
+
"num_tokens": 22565429.0,
|
| 1948 |
+
"mean_token_accuracy": 0.8461737126111984,
|
| 1949 |
+
"epoch": 0.663378125531553,
|
| 1950 |
+
"step": 1950
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"loss": 0.5819,
|
| 1954 |
+
"grad_norm": 0.31234627962112427,
|
| 1955 |
+
"learning_rate": 2.6662186888848862e-05,
|
| 1956 |
+
"entropy": 0.5898503661155701,
|
| 1957 |
+
"num_tokens": 22690809.0,
|
| 1958 |
+
"mean_token_accuracy": 0.8421528667211533,
|
| 1959 |
+
"epoch": 0.666780064636843,
|
| 1960 |
+
"step": 1960
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"loss": 0.5795,
|
| 1964 |
+
"grad_norm": 0.43498075008392334,
|
| 1965 |
+
"learning_rate": 2.6174473229712758e-05,
|
| 1966 |
+
"entropy": 0.5725113779306412,
|
| 1967 |
+
"num_tokens": 22808337.0,
|
| 1968 |
+
"mean_token_accuracy": 0.8442942827939988,
|
| 1969 |
+
"epoch": 0.670182003742133,
|
| 1970 |
+
"step": 1970
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"loss": 0.5602,
|
| 1974 |
+
"grad_norm": 0.35489723086357117,
|
| 1975 |
+
"learning_rate": 2.5689674990706813e-05,
|
| 1976 |
+
"entropy": 0.5673380747437478,
|
| 1977 |
+
"num_tokens": 22924233.0,
|
| 1978 |
+
"mean_token_accuracy": 0.8477986544370651,
|
| 1979 |
+
"epoch": 0.6735839428474231,
|
| 1980 |
+
"step": 1980
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"loss": 0.616,
|
| 1984 |
+
"grad_norm": 0.3546064496040344,
|
| 1985 |
+
"learning_rate": 2.520785149436181e-05,
|
| 1986 |
+
"entropy": 0.6025599181652069,
|
| 1987 |
+
"num_tokens": 23040709.0,
|
| 1988 |
+
"mean_token_accuracy": 0.8388166666030884,
|
| 1989 |
+
"epoch": 0.676985881952713,
|
| 1990 |
+
"step": 1990
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"loss": 0.5866,
|
| 1994 |
+
"grad_norm": 0.3466935455799103,
|
| 1995 |
+
"learning_rate": 2.4729061699202933e-05,
|
| 1996 |
+
"entropy": 0.5931081950664521,
|
| 1997 |
+
"num_tokens": 23168281.0,
|
| 1998 |
+
"mean_token_accuracy": 0.8412128478288651,
|
| 1999 |
+
"epoch": 0.6803878210580031,
|
| 2000 |
+
"step": 2000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"loss": 0.5745,
|
| 2004 |
+
"grad_norm": 0.36624687910079956,
|
| 2005 |
+
"learning_rate": 2.4253364192535348e-05,
|
| 2006 |
+
"entropy": 0.5797276377677918,
|
| 2007 |
+
"num_tokens": 23265650.0,
|
| 2008 |
+
"mean_token_accuracy": 0.8477521270513535,
|
| 2009 |
+
"epoch": 0.6837897601632931,
|
| 2010 |
+
"step": 2010
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"loss": 0.6003,
|
| 2014 |
+
"grad_norm": 0.3339534401893616,
|
| 2015 |
+
"learning_rate": 2.3780817183275057e-05,
|
| 2016 |
+
"entropy": 0.5999033793807029,
|
| 2017 |
+
"num_tokens": 23380810.0,
|
| 2018 |
+
"mean_token_accuracy": 0.8395819336175918,
|
| 2019 |
+
"epoch": 0.6871916992685831,
|
| 2020 |
+
"step": 2020
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"loss": 0.6001,
|
| 2024 |
+
"grad_norm": 0.3682357370853424,
|
| 2025 |
+
"learning_rate": 2.331147849482619e-05,
|
| 2026 |
+
"entropy": 0.6057513281702995,
|
| 2027 |
+
"num_tokens": 23488800.0,
|
| 2028 |
+
"mean_token_accuracy": 0.8401612430810929,
|
| 2029 |
+
"epoch": 0.6905936383738731,
|
| 2030 |
+
"step": 2030
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"loss": 0.5681,
|
| 2034 |
+
"grad_norm": 0.40995046496391296,
|
| 2035 |
+
"learning_rate": 2.2845405558005428e-05,
|
| 2036 |
+
"entropy": 0.5787547707557679,
|
| 2037 |
+
"num_tokens": 23603230.0,
|
| 2038 |
+
"mean_token_accuracy": 0.8451647937297821,
|
| 2039 |
+
"epoch": 0.6939955774791631,
|
| 2040 |
+
"step": 2040
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"loss": 0.5821,
|
| 2044 |
+
"grad_norm": 0.37340083718299866,
|
| 2045 |
+
"learning_rate": 2.2382655404014447e-05,
|
| 2046 |
+
"entropy": 0.5805535346269608,
|
| 2047 |
+
"num_tokens": 23722605.0,
|
| 2048 |
+
"mean_token_accuracy": 0.844177857041359,
|
| 2049 |
+
"epoch": 0.6973975165844531,
|
| 2050 |
+
"step": 2050
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"loss": 0.5787,
|
| 2054 |
+
"grad_norm": 0.4327142536640167,
|
| 2055 |
+
"learning_rate": 2.1923284657461258e-05,
|
| 2056 |
+
"entropy": 0.5828775107860565,
|
| 2057 |
+
"num_tokens": 23835961.0,
|
| 2058 |
+
"mean_token_accuracy": 0.842606109380722,
|
| 2059 |
+
"epoch": 0.7007994556897431,
|
| 2060 |
+
"step": 2060
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"loss": 0.5982,
|
| 2064 |
+
"grad_norm": 0.4304671287536621,
|
| 2065 |
+
"learning_rate": 2.1467349529431317e-05,
|
| 2066 |
+
"entropy": 0.5941863551735878,
|
| 2067 |
+
"num_tokens": 23949131.0,
|
| 2068 |
+
"mean_token_accuracy": 0.8400673478841781,
|
| 2069 |
+
"epoch": 0.7042013947950332,
|
| 2070 |
+
"step": 2070
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"loss": 0.5679,
|
| 2074 |
+
"grad_norm": 0.37865591049194336,
|
| 2075 |
+
"learning_rate": 2.10149058106093e-05,
|
| 2076 |
+
"entropy": 0.5765653476119041,
|
| 2077 |
+
"num_tokens": 24070739.0,
|
| 2078 |
+
"mean_token_accuracy": 0.8449007272720337,
|
| 2079 |
+
"epoch": 0.7076033339003232,
|
| 2080 |
+
"step": 2080
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"loss": 0.5886,
|
| 2084 |
+
"grad_norm": 0.3672359585762024,
|
| 2085 |
+
"learning_rate": 2.056600886445213e-05,
|
| 2086 |
+
"entropy": 0.5881167098879814,
|
| 2087 |
+
"num_tokens": 24178837.0,
|
| 2088 |
+
"mean_token_accuracy": 0.8434468775987625,
|
| 2089 |
+
"epoch": 0.7110052730056132,
|
| 2090 |
+
"step": 2090
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"loss": 0.5956,
|
| 2094 |
+
"grad_norm": 0.36181676387786865,
|
| 2095 |
+
"learning_rate": 2.01207136204145e-05,
|
| 2096 |
+
"entropy": 0.591875921189785,
|
| 2097 |
+
"num_tokens": 24297729.0,
|
| 2098 |
+
"mean_token_accuracy": 0.8414703428745269,
|
| 2099 |
+
"epoch": 0.7144072121109032,
|
| 2100 |
+
"step": 2100
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"loss": 0.5599,
|
| 2104 |
+
"grad_norm": 0.35588833689689636,
|
| 2105 |
+
"learning_rate": 1.967907456722738e-05,
|
| 2106 |
+
"entropy": 0.5663163229823113,
|
| 2107 |
+
"num_tokens": 24408243.0,
|
| 2108 |
+
"mean_token_accuracy": 0.8491099238395691,
|
| 2109 |
+
"epoch": 0.7178091512161933,
|
| 2110 |
+
"step": 2110
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"loss": 0.5644,
|
| 2114 |
+
"grad_norm": 0.38050028681755066,
|
| 2115 |
+
"learning_rate": 1.9241145746230478e-05,
|
| 2116 |
+
"entropy": 0.5726602435111999,
|
| 2117 |
+
"num_tokens": 24512247.0,
|
| 2118 |
+
"mean_token_accuracy": 0.8495869427919388,
|
| 2119 |
+
"epoch": 0.7212110903214832,
|
| 2120 |
+
"step": 2120
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"loss": 0.5693,
|
| 2124 |
+
"grad_norm": 0.3819943964481354,
|
| 2125 |
+
"learning_rate": 1.8806980744759445e-05,
|
| 2126 |
+
"entropy": 0.5744548887014389,
|
| 2127 |
+
"num_tokens": 24627020.0,
|
| 2128 |
+
"mean_token_accuracy": 0.842121011018753,
|
| 2129 |
+
"epoch": 0.7246130294267733,
|
| 2130 |
+
"step": 2130
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"loss": 0.6092,
|
| 2134 |
+
"grad_norm": 0.3454561233520508,
|
| 2135 |
+
"learning_rate": 1.837663268958867e-05,
|
| 2136 |
+
"entropy": 0.6237739801406861,
|
| 2137 |
+
"num_tokens": 24736398.0,
|
| 2138 |
+
"mean_token_accuracy": 0.8370961755514145,
|
| 2139 |
+
"epoch": 0.7280149685320633,
|
| 2140 |
+
"step": 2140
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"loss": 0.6223,
|
| 2144 |
+
"grad_norm": 0.35335883498191833,
|
| 2145 |
+
"learning_rate": 1.795015424043035e-05,
|
| 2146 |
+
"entropy": 0.6208432152867317,
|
| 2147 |
+
"num_tokens": 24861135.0,
|
| 2148 |
+
"mean_token_accuracy": 0.8354604303836822,
|
| 2149 |
+
"epoch": 0.7314169076373533,
|
| 2150 |
+
"step": 2150
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"loss": 0.5919,
|
| 2154 |
+
"grad_norm": 0.3348969519138336,
|
| 2155 |
+
"learning_rate": 1.7527597583490822e-05,
|
| 2156 |
+
"entropy": 0.5919017851352691,
|
| 2157 |
+
"num_tokens": 24974197.0,
|
| 2158 |
+
"mean_token_accuracy": 0.840225774049759,
|
| 2159 |
+
"epoch": 0.7348188467426433,
|
| 2160 |
+
"step": 2160
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"loss": 0.5706,
|
| 2164 |
+
"grad_norm": 0.3716595470905304,
|
| 2165 |
+
"learning_rate": 1.7109014425084725e-05,
|
| 2166 |
+
"entropy": 0.5833111733198166,
|
| 2167 |
+
"num_tokens": 25091846.0,
|
| 2168 |
+
"mean_token_accuracy": 0.8445227384567261,
|
| 2169 |
+
"epoch": 0.7382207858479333,
|
| 2170 |
+
"step": 2170
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"loss": 0.5679,
|
| 2174 |
+
"grad_norm": 0.32632264494895935,
|
| 2175 |
+
"learning_rate": 1.669445598530796e-05,
|
| 2176 |
+
"entropy": 0.5681742131710052,
|
| 2177 |
+
"num_tokens": 25210289.0,
|
| 2178 |
+
"mean_token_accuracy": 0.8463738948106766,
|
| 2179 |
+
"epoch": 0.7416227249532233,
|
| 2180 |
+
"step": 2180
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"loss": 0.6147,
|
| 2184 |
+
"grad_norm": 0.3877134621143341,
|
| 2185 |
+
"learning_rate": 1.628397299177013e-05,
|
| 2186 |
+
"entropy": 0.6165782377123833,
|
| 2187 |
+
"num_tokens": 25334926.0,
|
| 2188 |
+
"mean_token_accuracy": 0.8343934565782547,
|
| 2189 |
+
"epoch": 0.7450246640585133,
|
| 2190 |
+
"step": 2190
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"loss": 0.5806,
|
| 2194 |
+
"grad_norm": 0.38453352451324463,
|
| 2195 |
+
"learning_rate": 1.5877615673387215e-05,
|
| 2196 |
+
"entropy": 0.5809252455830574,
|
| 2197 |
+
"num_tokens": 25453005.0,
|
| 2198 |
+
"mean_token_accuracy": 0.8436485230922699,
|
| 2199 |
+
"epoch": 0.7484266031638034,
|
| 2200 |
+
"step": 2200
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"loss": 0.5584,
|
| 2204 |
+
"grad_norm": 0.3705204725265503,
|
| 2205 |
+
"learning_rate": 1.5475433754235312e-05,
|
| 2206 |
+
"entropy": 0.5579630300402642,
|
| 2207 |
+
"num_tokens": 25568378.0,
|
| 2208 |
+
"mean_token_accuracy": 0.8482485413551331,
|
| 2209 |
+
"epoch": 0.7518285422690933,
|
| 2210 |
+
"step": 2210
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"loss": 0.5846,
|
| 2214 |
+
"grad_norm": 0.4126192331314087,
|
| 2215 |
+
"learning_rate": 1.5077476447466115e-05,
|
| 2216 |
+
"entropy": 0.5949768751859665,
|
| 2217 |
+
"num_tokens": 25679312.0,
|
| 2218 |
+
"mean_token_accuracy": 0.8417560040950776,
|
| 2219 |
+
"epoch": 0.7552304813743834,
|
| 2220 |
+
"step": 2220
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"loss": 0.5992,
|
| 2224 |
+
"grad_norm": 0.369003564119339,
|
| 2225 |
+
"learning_rate": 1.4683792449284922e-05,
|
| 2226 |
+
"entropy": 0.5958976864814758,
|
| 2227 |
+
"num_tokens": 25802476.0,
|
| 2228 |
+
"mean_token_accuracy": 0.8378436207771301,
|
| 2229 |
+
"epoch": 0.7586324204796734,
|
| 2230 |
+
"step": 2230
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"loss": 0.5845,
|
| 2234 |
+
"grad_norm": 0.3608800768852234,
|
| 2235 |
+
"learning_rate": 1.429442993299191e-05,
|
| 2236 |
+
"entropy": 0.5774736061692238,
|
| 2237 |
+
"num_tokens": 25917526.0,
|
| 2238 |
+
"mean_token_accuracy": 0.8448121935129166,
|
| 2239 |
+
"epoch": 0.7620343595849635,
|
| 2240 |
+
"step": 2240
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"loss": 0.533,
|
| 2244 |
+
"grad_norm": 0.35715219378471375,
|
| 2245 |
+
"learning_rate": 1.3909436543087428e-05,
|
| 2246 |
+
"entropy": 0.5421435713768006,
|
| 2247 |
+
"num_tokens": 26022101.0,
|
| 2248 |
+
"mean_token_accuracy": 0.8561456590890885,
|
| 2249 |
+
"epoch": 0.7654362986902534,
|
| 2250 |
+
"step": 2250
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"loss": 0.5595,
|
| 2254 |
+
"grad_norm": 0.36197429895401,
|
| 2255 |
+
"learning_rate": 1.352885938944189e-05,
|
| 2256 |
+
"entropy": 0.564231875538826,
|
| 2257 |
+
"num_tokens": 26132618.0,
|
| 2258 |
+
"mean_token_accuracy": 0.8467835336923599,
|
| 2259 |
+
"epoch": 0.7688382377955435,
|
| 2260 |
+
"step": 2260
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"loss": 0.5394,
|
| 2264 |
+
"grad_norm": 0.34464767575263977,
|
| 2265 |
+
"learning_rate": 1.3152745041531201e-05,
|
| 2266 |
+
"entropy": 0.5447842225432395,
|
| 2267 |
+
"num_tokens": 26251170.0,
|
| 2268 |
+
"mean_token_accuracy": 0.852738481760025,
|
| 2269 |
+
"epoch": 0.7722401769008335,
|
| 2270 |
+
"step": 2270
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"loss": 0.6081,
|
| 2274 |
+
"grad_norm": 0.34223926067352295,
|
| 2275 |
+
"learning_rate": 1.2781139522738239e-05,
|
| 2276 |
+
"entropy": 0.6099189713597297,
|
| 2277 |
+
"num_tokens": 26366238.0,
|
| 2278 |
+
"mean_token_accuracy": 0.8368343204259873,
|
| 2279 |
+
"epoch": 0.7756421160061235,
|
| 2280 |
+
"step": 2280
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"loss": 0.5608,
|
| 2284 |
+
"grad_norm": 0.40201887488365173,
|
| 2285 |
+
"learning_rate": 1.2414088304721234e-05,
|
| 2286 |
+
"entropy": 0.5682180404663086,
|
| 2287 |
+
"num_tokens": 26481121.0,
|
| 2288 |
+
"mean_token_accuracy": 0.8468090683221817,
|
| 2289 |
+
"epoch": 0.7790440551114135,
|
| 2290 |
+
"step": 2290
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"loss": 0.5831,
|
| 2294 |
+
"grad_norm": 0.3707852363586426,
|
| 2295 |
+
"learning_rate": 1.2051636301849539e-05,
|
| 2296 |
+
"entropy": 0.5816125243902206,
|
| 2297 |
+
"num_tokens": 26591544.0,
|
| 2298 |
+
"mean_token_accuracy": 0.8441601723432541,
|
| 2299 |
+
"epoch": 0.7824459942167035,
|
| 2300 |
+
"step": 2300
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"loss": 0.644,
|
| 2304 |
+
"grad_norm": 0.42641323804855347,
|
| 2305 |
+
"learning_rate": 1.1693827865707729e-05,
|
| 2306 |
+
"entropy": 0.6465028315782547,
|
| 2307 |
+
"num_tokens": 26701423.0,
|
| 2308 |
+
"mean_token_accuracy": 0.8323942631483078,
|
| 2309 |
+
"epoch": 0.7858479333219935,
|
| 2310 |
+
"step": 2310
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"loss": 0.5624,
|
| 2314 |
+
"grad_norm": 0.3720209300518036,
|
| 2315 |
+
"learning_rate": 1.1340706779668464e-05,
|
| 2316 |
+
"entropy": 0.568995788693428,
|
| 2317 |
+
"num_tokens": 26821407.0,
|
| 2318 |
+
"mean_token_accuracy": 0.844905823469162,
|
| 2319 |
+
"epoch": 0.7892498724272835,
|
| 2320 |
+
"step": 2320
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"loss": 0.562,
|
| 2324 |
+
"grad_norm": 0.33470767736434937,
|
| 2325 |
+
"learning_rate": 1.099231625353494e-05,
|
| 2326 |
+
"entropy": 0.5680811256170273,
|
| 2327 |
+
"num_tokens": 26942232.0,
|
| 2328 |
+
"mean_token_accuracy": 0.8472270101308823,
|
| 2329 |
+
"epoch": 0.7926518115325736,
|
| 2330 |
+
"step": 2330
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"loss": 0.5871,
|
| 2334 |
+
"grad_norm": 0.35473379492759705,
|
| 2335 |
+
"learning_rate": 1.0648698918253474e-05,
|
| 2336 |
+
"entropy": 0.5944129660725593,
|
| 2337 |
+
"num_tokens": 27054063.0,
|
| 2338 |
+
"mean_token_accuracy": 0.8423294246196746,
|
| 2339 |
+
"epoch": 0.7960537506378635,
|
| 2340 |
+
"step": 2340
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"loss": 0.5813,
|
| 2344 |
+
"grad_norm": 0.336117684841156,
|
| 2345 |
+
"learning_rate": 1.0309896820697002e-05,
|
| 2346 |
+
"entropy": 0.5846550479531288,
|
| 2347 |
+
"num_tokens": 27170010.0,
|
| 2348 |
+
"mean_token_accuracy": 0.8445548832416534,
|
| 2349 |
+
"epoch": 0.7994556897431536,
|
| 2350 |
+
"step": 2350
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"loss": 0.5587,
|
| 2354 |
+
"grad_norm": 0.36509907245635986,
|
| 2355 |
+
"learning_rate": 9.975951418519941e-06,
|
| 2356 |
+
"entropy": 0.565837450325489,
|
| 2357 |
+
"num_tokens": 27288934.0,
|
| 2358 |
+
"mean_token_accuracy": 0.8460572957992554,
|
| 2359 |
+
"epoch": 0.8028576288484436,
|
| 2360 |
+
"step": 2360
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"loss": 0.5744,
|
| 2364 |
+
"grad_norm": 0.37850871682167053,
|
| 2365 |
+
"learning_rate": 9.646903575085236e-06,
|
| 2366 |
+
"entropy": 0.5862236008048057,
|
| 2367 |
+
"num_tokens": 27405172.0,
|
| 2368 |
+
"mean_token_accuracy": 0.8447532653808594,
|
| 2369 |
+
"epoch": 0.8062595679537337,
|
| 2370 |
+
"step": 2370
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"loss": 0.5813,
|
| 2374 |
+
"grad_norm": 0.3511059582233429,
|
| 2375 |
+
"learning_rate": 9.32279355446411e-06,
|
| 2376 |
+
"entropy": 0.5788961902260781,
|
| 2377 |
+
"num_tokens": 27518997.0,
|
| 2378 |
+
"mean_token_accuracy": 0.8418603748083114,
|
| 2379 |
+
"epoch": 0.8096615070590236,
|
| 2380 |
+
"step": 2380
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"loss": 0.5855,
|
| 2384 |
+
"grad_norm": 0.3253343999385834,
|
| 2385 |
+
"learning_rate": 9.003661016509102e-06,
|
| 2386 |
+
"entropy": 0.5858073383569717,
|
| 2387 |
+
"num_tokens": 27644298.0,
|
| 2388 |
+
"mean_token_accuracy": 0.8415432572364807,
|
| 2389 |
+
"epoch": 0.8130634461643137,
|
| 2390 |
+
"step": 2390
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"loss": 0.5595,
|
| 2394 |
+
"grad_norm": 0.36334091424942017,
|
| 2395 |
+
"learning_rate": 8.689545012001083e-06,
|
| 2396 |
+
"entropy": 0.5582752287387848,
|
| 2397 |
+
"num_tokens": 27753242.0,
|
| 2398 |
+
"mean_token_accuracy": 0.8509968429803848,
|
| 2399 |
+
"epoch": 0.8164653852696037,
|
| 2400 |
+
"step": 2400
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"loss": 0.5706,
|
| 2404 |
+
"grad_norm": 0.32456502318382263,
|
| 2405 |
+
"learning_rate": 8.380483977870834e-06,
|
| 2406 |
+
"entropy": 0.5666798010468483,
|
| 2407 |
+
"num_tokens": 27882376.0,
|
| 2408 |
+
"mean_token_accuracy": 0.84336639046669,
|
| 2409 |
+
"epoch": 0.8198673243748937,
|
| 2410 |
+
"step": 2410
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"loss": 0.5394,
|
| 2414 |
+
"grad_norm": 0.3463776707649231,
|
| 2415 |
+
"learning_rate": 8.076515732495626e-06,
|
| 2416 |
+
"entropy": 0.5584284573793411,
|
| 2417 |
+
"num_tokens": 28000308.0,
|
| 2418 |
+
"mean_token_accuracy": 0.8512558758258819,
|
| 2419 |
+
"epoch": 0.8232692634801837,
|
| 2420 |
+
"step": 2420
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"loss": 0.6075,
|
| 2424 |
+
"grad_norm": 0.35784080624580383,
|
| 2425 |
+
"learning_rate": 7.777677471071614e-06,
|
| 2426 |
+
"entropy": 0.6100872978568077,
|
| 2427 |
+
"num_tokens": 28115648.0,
|
| 2428 |
+
"mean_token_accuracy": 0.8378289490938187,
|
| 2429 |
+
"epoch": 0.8266712025854738,
|
| 2430 |
+
"step": 2430
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"loss": 0.5815,
|
| 2434 |
+
"grad_norm": 0.351990282535553,
|
| 2435 |
+
"learning_rate": 7.484005761062391e-06,
|
| 2436 |
+
"entropy": 0.5808347776532173,
|
| 2437 |
+
"num_tokens": 28222592.0,
|
| 2438 |
+
"mean_token_accuracy": 0.8474200069904327,
|
| 2439 |
+
"epoch": 0.8300731416907637,
|
| 2440 |
+
"step": 2440
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"loss": 0.5889,
|
| 2444 |
+
"grad_norm": 0.3908417224884033,
|
| 2445 |
+
"learning_rate": 7.195536537724429e-06,
|
| 2446 |
+
"entropy": 0.5958179652690887,
|
| 2447 |
+
"num_tokens": 28325239.0,
|
| 2448 |
+
"mean_token_accuracy": 0.845181006193161,
|
| 2449 |
+
"epoch": 0.8334750807960537,
|
| 2450 |
+
"step": 2450
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"loss": 0.5846,
|
| 2454 |
+
"grad_norm": 0.38566815853118896,
|
| 2455 |
+
"learning_rate": 6.912305099709831e-06,
|
| 2456 |
+
"entropy": 0.5907109215855598,
|
| 2457 |
+
"num_tokens": 28445952.0,
|
| 2458 |
+
"mean_token_accuracy": 0.84410340487957,
|
| 2459 |
+
"epoch": 0.8368770199013438,
|
| 2460 |
+
"step": 2460
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"loss": 0.5876,
|
| 2464 |
+
"grad_norm": 0.4085163474082947,
|
| 2465 |
+
"learning_rate": 6.634346104746997e-06,
|
| 2466 |
+
"entropy": 0.5830874457955361,
|
| 2467 |
+
"num_tokens": 28554611.0,
|
| 2468 |
+
"mean_token_accuracy": 0.8452066659927369,
|
| 2469 |
+
"epoch": 0.8402789590066337,
|
| 2470 |
+
"step": 2470
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"loss": 0.5575,
|
| 2474 |
+
"grad_norm": 0.352285236120224,
|
| 2475 |
+
"learning_rate": 6.36169356539974e-06,
|
| 2476 |
+
"entropy": 0.5569544598460198,
|
| 2477 |
+
"num_tokens": 28659685.0,
|
| 2478 |
+
"mean_token_accuracy": 0.851721253991127,
|
| 2479 |
+
"epoch": 0.8436808981119238,
|
| 2480 |
+
"step": 2480
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"loss": 0.5667,
|
| 2484 |
+
"grad_norm": 0.365980863571167,
|
| 2485 |
+
"learning_rate": 6.094380844905278e-06,
|
| 2486 |
+
"entropy": 0.5703560188412666,
|
| 2487 |
+
"num_tokens": 28768833.0,
|
| 2488 |
+
"mean_token_accuracy": 0.8493399202823639,
|
| 2489 |
+
"epoch": 0.8470828372172138,
|
| 2490 |
+
"step": 2490
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"loss": 0.6135,
|
| 2494 |
+
"grad_norm": 0.4027390480041504,
|
| 2495 |
+
"learning_rate": 5.832440653091775e-06,
|
| 2496 |
+
"entropy": 0.6129578873515129,
|
| 2497 |
+
"num_tokens": 28885843.0,
|
| 2498 |
+
"mean_token_accuracy": 0.8367623895406723,
|
| 2499 |
+
"epoch": 0.8504847763225039,
|
| 2500 |
+
"step": 2500
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"loss": 0.559,
|
| 2504 |
+
"grad_norm": 0.37476834654808044,
|
| 2505 |
+
"learning_rate": 5.575905042375751e-06,
|
| 2506 |
+
"entropy": 0.5681184902787209,
|
| 2507 |
+
"num_tokens": 29003923.0,
|
| 2508 |
+
"mean_token_accuracy": 0.8465311348438262,
|
| 2509 |
+
"epoch": 0.8538867154277938,
|
| 2510 |
+
"step": 2510
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"loss": 0.5571,
|
| 2514 |
+
"grad_norm": 0.3746230900287628,
|
| 2515 |
+
"learning_rate": 5.324805403840006e-06,
|
| 2516 |
+
"entropy": 0.5609279617667198,
|
| 2517 |
+
"num_tokens": 29114669.0,
|
| 2518 |
+
"mean_token_accuracy": 0.8491218000650406,
|
| 2519 |
+
"epoch": 0.8572886545330839,
|
| 2520 |
+
"step": 2520
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"loss": 0.6017,
|
| 2524 |
+
"grad_norm": 0.3442933261394501,
|
| 2525 |
+
"learning_rate": 5.079172463392434e-06,
|
| 2526 |
+
"entropy": 0.6076221778988838,
|
| 2527 |
+
"num_tokens": 29237873.0,
|
| 2528 |
+
"mean_token_accuracy": 0.8369300574064255,
|
| 2529 |
+
"epoch": 0.8606905936383739,
|
| 2530 |
+
"step": 2530
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"loss": 0.5838,
|
| 2534 |
+
"grad_norm": 0.34637150168418884,
|
| 2535 |
+
"learning_rate": 4.839036278006215e-06,
|
| 2536 |
+
"entropy": 0.5847443833947181,
|
| 2537 |
+
"num_tokens": 29356084.0,
|
| 2538 |
+
"mean_token_accuracy": 0.8435145944356919,
|
| 2539 |
+
"epoch": 0.8640925327436639,
|
| 2540 |
+
"step": 2540
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"loss": 0.5735,
|
| 2544 |
+
"grad_norm": 0.3903183937072754,
|
| 2545 |
+
"learning_rate": 4.6044262320418915e-06,
|
| 2546 |
+
"entropy": 0.5809785157442093,
|
| 2547 |
+
"num_tokens": 29466199.0,
|
| 2548 |
+
"mean_token_accuracy": 0.8461235493421555,
|
| 2549 |
+
"epoch": 0.8674944718489539,
|
| 2550 |
+
"step": 2550
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"loss": 0.5468,
|
| 2554 |
+
"grad_norm": 0.38433846831321716,
|
| 2555 |
+
"learning_rate": 4.375371033651754e-06,
|
| 2556 |
+
"entropy": 0.5522323742508888,
|
| 2557 |
+
"num_tokens": 29585003.0,
|
| 2558 |
+
"mean_token_accuracy": 0.8522881597280503,
|
| 2559 |
+
"epoch": 0.870896410954244,
|
| 2560 |
+
"step": 2560
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"loss": 0.5747,
|
| 2564 |
+
"grad_norm": 0.38316574692726135,
|
| 2565 |
+
"learning_rate": 4.151898711266932e-06,
|
| 2566 |
+
"entropy": 0.5752411767840385,
|
| 2567 |
+
"num_tokens": 29697951.0,
|
| 2568 |
+
"mean_token_accuracy": 0.8458108186721802,
|
| 2569 |
+
"epoch": 0.8742983500595339,
|
| 2570 |
+
"step": 2570
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"loss": 0.5561,
|
| 2574 |
+
"grad_norm": 0.37862345576286316,
|
| 2575 |
+
"learning_rate": 3.934036610167696e-06,
|
| 2576 |
+
"entropy": 0.5635033801198006,
|
| 2577 |
+
"num_tokens": 29814806.0,
|
| 2578 |
+
"mean_token_accuracy": 0.8486339598894119,
|
| 2579 |
+
"epoch": 0.8777002891648239,
|
| 2580 |
+
"step": 2580
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"loss": 0.5879,
|
| 2584 |
+
"grad_norm": 0.40011560916900635,
|
| 2585 |
+
"learning_rate": 3.721811389137353e-06,
|
| 2586 |
+
"entropy": 0.5901739224791527,
|
| 2587 |
+
"num_tokens": 29938190.0,
|
| 2588 |
+
"mean_token_accuracy": 0.8400143891572952,
|
| 2589 |
+
"epoch": 0.881102228270114,
|
| 2590 |
+
"step": 2590
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"loss": 0.5741,
|
| 2594 |
+
"grad_norm": 0.36540430784225464,
|
| 2595 |
+
"learning_rate": 3.5152490172001116e-06,
|
| 2596 |
+
"entropy": 0.5728347212076187,
|
| 2597 |
+
"num_tokens": 30057305.0,
|
| 2598 |
+
"mean_token_accuracy": 0.8454901963472367,
|
| 2599 |
+
"epoch": 0.8845041673754039,
|
| 2600 |
+
"step": 2600
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"loss": 0.6221,
|
| 2604 |
+
"grad_norm": 0.3713492751121521,
|
| 2605 |
+
"learning_rate": 3.314374770443379e-06,
|
| 2606 |
+
"entropy": 0.6258899614214897,
|
| 2607 |
+
"num_tokens": 30172939.0,
|
| 2608 |
+
"mean_token_accuracy": 0.8357624322175979,
|
| 2609 |
+
"epoch": 0.887906106480694,
|
| 2610 |
+
"step": 2610
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"loss": 0.5946,
|
| 2614 |
+
"grad_norm": 0.3445519208908081,
|
| 2615 |
+
"learning_rate": 3.1192132289248497e-06,
|
| 2616 |
+
"entropy": 0.596692156791687,
|
| 2617 |
+
"num_tokens": 30300574.0,
|
| 2618 |
+
"mean_token_accuracy": 0.8411296546459198,
|
| 2619 |
+
"epoch": 0.891308045585984,
|
| 2620 |
+
"step": 2620
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"loss": 0.5774,
|
| 2624 |
+
"grad_norm": 0.37687185406684875,
|
| 2625 |
+
"learning_rate": 2.9297882736647574e-06,
|
| 2626 |
+
"entropy": 0.5851211875677109,
|
| 2627 |
+
"num_tokens": 30411366.0,
|
| 2628 |
+
"mean_token_accuracy": 0.8454822093248368,
|
| 2629 |
+
"epoch": 0.894709984691274,
|
| 2630 |
+
"step": 2630
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"loss": 0.6138,
|
| 2634 |
+
"grad_norm": 0.3559032678604126,
|
| 2635 |
+
"learning_rate": 2.746123083723656e-06,
|
| 2636 |
+
"entropy": 0.612051984667778,
|
| 2637 |
+
"num_tokens": 30533680.0,
|
| 2638 |
+
"mean_token_accuracy": 0.8369055807590484,
|
| 2639 |
+
"epoch": 0.898111923796564,
|
| 2640 |
+
"step": 2640
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"loss": 0.5639,
|
| 2644 |
+
"grad_norm": 0.37055504322052,
|
| 2645 |
+
"learning_rate": 2.5682401333661067e-06,
|
| 2646 |
+
"entropy": 0.5725692048668861,
|
| 2647 |
+
"num_tokens": 30643544.0,
|
| 2648 |
+
"mean_token_accuracy": 0.8459548681974411,
|
| 2649 |
+
"epoch": 0.9015138629018541,
|
| 2650 |
+
"step": 2650
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"loss": 0.5329,
|
| 2654 |
+
"grad_norm": 0.3881671130657196,
|
| 2655 |
+
"learning_rate": 2.396161189310603e-06,
|
| 2656 |
+
"entropy": 0.5357650727033615,
|
| 2657 |
+
"num_tokens": 30753201.0,
|
| 2658 |
+
"mean_token_accuracy": 0.8559219360351562,
|
| 2659 |
+
"epoch": 0.904915802007144,
|
| 2660 |
+
"step": 2660
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"loss": 0.5647,
|
| 2664 |
+
"grad_norm": 0.3779488205909729,
|
| 2665 |
+
"learning_rate": 2.2299073080660926e-06,
|
| 2666 |
+
"entropy": 0.5651383563876152,
|
| 2667 |
+
"num_tokens": 30866789.0,
|
| 2668 |
+
"mean_token_accuracy": 0.8465316832065582,
|
| 2669 |
+
"epoch": 0.9083177411124341,
|
| 2670 |
+
"step": 2670
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"loss": 0.5846,
|
| 2674 |
+
"grad_norm": 0.3553813397884369,
|
| 2675 |
+
"learning_rate": 2.069498833355371e-06,
|
| 2676 |
+
"entropy": 0.5878252282738685,
|
| 2677 |
+
"num_tokens": 30980359.0,
|
| 2678 |
+
"mean_token_accuracy": 0.846244278550148,
|
| 2679 |
+
"epoch": 0.9117196802177241,
|
| 2680 |
+
"step": 2680
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"loss": 0.5718,
|
| 2684 |
+
"grad_norm": 0.36092498898506165,
|
| 2685 |
+
"learning_rate": 1.914955393625717e-06,
|
| 2686 |
+
"entropy": 0.5731380596756935,
|
| 2687 |
+
"num_tokens": 31096112.0,
|
| 2688 |
+
"mean_token_accuracy": 0.8443791717290878,
|
| 2689 |
+
"epoch": 0.9151216193230142,
|
| 2690 |
+
"step": 2690
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"loss": 0.5533,
|
| 2694 |
+
"grad_norm": 0.39117369055747986,
|
| 2695 |
+
"learning_rate": 1.7662958996470635e-06,
|
| 2696 |
+
"entropy": 0.5589064419269562,
|
| 2697 |
+
"num_tokens": 31211039.0,
|
| 2698 |
+
"mean_token_accuracy": 0.8504908055067062,
|
| 2699 |
+
"epoch": 0.9185235584283041,
|
| 2700 |
+
"step": 2700
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"loss": 0.5676,
|
| 2704 |
+
"grad_norm": 0.37049877643585205,
|
| 2705 |
+
"learning_rate": 1.6235385421979555e-06,
|
| 2706 |
+
"entropy": 0.5745102554559708,
|
| 2707 |
+
"num_tokens": 31323209.0,
|
| 2708 |
+
"mean_token_accuracy": 0.8450854837894439,
|
| 2709 |
+
"epoch": 0.9219254975335941,
|
| 2710 |
+
"step": 2710
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"loss": 0.5449,
|
| 2714 |
+
"grad_norm": 0.36490964889526367,
|
| 2715 |
+
"learning_rate": 1.4867007898396457e-06,
|
| 2716 |
+
"entropy": 0.5510489344596863,
|
| 2717 |
+
"num_tokens": 31436438.0,
|
| 2718 |
+
"mean_token_accuracy": 0.8506697177886963,
|
| 2719 |
+
"epoch": 0.9253274366388842,
|
| 2720 |
+
"step": 2720
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"loss": 0.5585,
|
| 2724 |
+
"grad_norm": 0.3628520965576172,
|
| 2725 |
+
"learning_rate": 1.3557993867785335e-06,
|
| 2726 |
+
"entropy": 0.5683807358145714,
|
| 2727 |
+
"num_tokens": 31553624.0,
|
| 2728 |
+
"mean_token_accuracy": 0.8480296969413758,
|
| 2729 |
+
"epoch": 0.9287293757441741,
|
| 2730 |
+
"step": 2730
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"loss": 0.5956,
|
| 2734 |
+
"grad_norm": 0.34894460439682007,
|
| 2735 |
+
"learning_rate": 1.230850350817253e-06,
|
| 2736 |
+
"entropy": 0.6040398806333542,
|
| 2737 |
+
"num_tokens": 31669977.0,
|
| 2738 |
+
"mean_token_accuracy": 0.8400009006261826,
|
| 2739 |
+
"epoch": 0.9321313148494642,
|
| 2740 |
+
"step": 2740
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"loss": 0.5967,
|
| 2744 |
+
"grad_norm": 0.3939131200313568,
|
| 2745 |
+
"learning_rate": 1.1118689713946529e-06,
|
| 2746 |
+
"entropy": 0.5958102196455002,
|
| 2747 |
+
"num_tokens": 31790332.0,
|
| 2748 |
+
"mean_token_accuracy": 0.8398540407419205,
|
| 2749 |
+
"epoch": 0.9355332539547542,
|
| 2750 |
+
"step": 2750
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"loss": 0.5696,
|
| 2754 |
+
"grad_norm": 0.38736289739608765,
|
| 2755 |
+
"learning_rate": 9.98869807714914e-07,
|
| 2756 |
+
"entropy": 0.573664478957653,
|
| 2757 |
+
"num_tokens": 31897948.0,
|
| 2758 |
+
"mean_token_accuracy": 0.8483406931161881,
|
| 2759 |
+
"epoch": 0.9389351930600442,
|
| 2760 |
+
"step": 2760
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"loss": 0.6001,
|
| 2764 |
+
"grad_norm": 0.35055264830589294,
|
| 2765 |
+
"learning_rate": 8.918666869659642e-07,
|
| 2766 |
+
"entropy": 0.6001556605100632,
|
| 2767 |
+
"num_tokens": 32026504.0,
|
| 2768 |
+
"mean_token_accuracy": 0.8378526538610458,
|
| 2769 |
+
"epoch": 0.9423371321653342,
|
| 2770 |
+
"step": 2770
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"loss": 0.5759,
|
| 2774 |
+
"grad_norm": 0.39700019359588623,
|
| 2775 |
+
"learning_rate": 7.908727026275597e-07,
|
| 2776 |
+
"entropy": 0.5858756378293037,
|
| 2777 |
+
"num_tokens": 32140548.0,
|
| 2778 |
+
"mean_token_accuracy": 0.8406315892934799,
|
| 2779 |
+
"epoch": 0.9457390712706243,
|
| 2780 |
+
"step": 2780
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"loss": 0.5991,
|
| 2784 |
+
"grad_norm": 0.39454156160354614,
|
| 2785 |
+
"learning_rate": 6.959002128690606e-07,
|
| 2786 |
+
"entropy": 0.5967293009161949,
|
| 2787 |
+
"num_tokens": 32258820.0,
|
| 2788 |
+
"mean_token_accuracy": 0.8434277713298798,
|
| 2789 |
+
"epoch": 0.9491410103759143,
|
| 2790 |
+
"step": 2790
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"loss": 0.5897,
|
| 2794 |
+
"grad_norm": 0.42352262139320374,
|
| 2795 |
+
"learning_rate": 6.069608390372294e-07,
|
| 2796 |
+
"entropy": 0.5910201713442802,
|
| 2797 |
+
"num_tokens": 32370310.0,
|
| 2798 |
+
"mean_token_accuracy": 0.8437776923179626,
|
| 2799 |
+
"epoch": 0.9525429494812043,
|
| 2800 |
+
"step": 2800
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"loss": 0.5704,
|
| 2804 |
+
"grad_norm": 0.33332422375679016,
|
| 2805 |
+
"learning_rate": 5.240654642341913e-07,
|
| 2806 |
+
"entropy": 0.5700356841087342,
|
| 2807 |
+
"num_tokens": 32488521.0,
|
| 2808 |
+
"mean_token_accuracy": 0.8457501322031021,
|
| 2809 |
+
"epoch": 0.9559448885864943,
|
| 2810 |
+
"step": 2810
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"loss": 0.5863,
|
| 2814 |
+
"grad_norm": 0.3759448826313019,
|
| 2815 |
+
"learning_rate": 4.4722423198568785e-07,
|
| 2816 |
+
"entropy": 0.5873485445976258,
|
| 2817 |
+
"num_tokens": 32604586.0,
|
| 2818 |
+
"mean_token_accuracy": 0.8435898423194885,
|
| 2819 |
+
"epoch": 0.9593468276917844,
|
| 2820 |
+
"step": 2820
|
| 2821 |
+
},
|
| 2822 |
+
{
|
| 2823 |
+
"loss": 0.5712,
|
| 2824 |
+
"grad_norm": 0.3626145124435425,
|
| 2825 |
+
"learning_rate": 3.764465449999033e-07,
|
| 2826 |
+
"entropy": 0.5771880641579628,
|
| 2827 |
+
"num_tokens": 32720534.0,
|
| 2828 |
+
"mean_token_accuracy": 0.8457781076431274,
|
| 2829 |
+
"epoch": 0.9627487667970743,
|
| 2830 |
+
"step": 2830
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"loss": 0.5665,
|
| 2834 |
+
"grad_norm": 0.3542146384716034,
|
| 2835 |
+
"learning_rate": 3.1174106401686274e-07,
|
| 2836 |
+
"entropy": 0.5678144678473472,
|
| 2837 |
+
"num_tokens": 32842877.0,
|
| 2838 |
+
"mean_token_accuracy": 0.8448899626731873,
|
| 2839 |
+
"epoch": 0.9661507059023643,
|
| 2840 |
+
"step": 2840
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"loss": 0.5471,
|
| 2844 |
+
"grad_norm": 0.33239731192588806,
|
| 2845 |
+
"learning_rate": 2.5311570674867444e-07,
|
| 2846 |
+
"entropy": 0.5530853852629661,
|
| 2847 |
+
"num_tokens": 32951936.0,
|
| 2848 |
+
"mean_token_accuracy": 0.850860059261322,
|
| 2849 |
+
"epoch": 0.9695526450076544,
|
| 2850 |
+
"step": 2850
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"loss": 0.5992,
|
| 2854 |
+
"grad_norm": 0.3345488905906677,
|
| 2855 |
+
"learning_rate": 2.0057764691067127e-07,
|
| 2856 |
+
"entropy": 0.5983069583773613,
|
| 2857 |
+
"num_tokens": 33071421.0,
|
| 2858 |
+
"mean_token_accuracy": 0.839891204237938,
|
| 2859 |
+
"epoch": 0.9729545841129443,
|
| 2860 |
+
"step": 2860
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"loss": 0.5621,
|
| 2864 |
+
"grad_norm": 0.3342396020889282,
|
| 2865 |
+
"learning_rate": 1.5413331334360182e-07,
|
| 2866 |
+
"entropy": 0.5691981092095375,
|
| 2867 |
+
"num_tokens": 33189424.0,
|
| 2868 |
+
"mean_token_accuracy": 0.8471813201904297,
|
| 2869 |
+
"epoch": 0.9763565232182344,
|
| 2870 |
+
"step": 2870
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"loss": 0.6094,
|
| 2874 |
+
"grad_norm": 0.3459620475769043,
|
| 2875 |
+
"learning_rate": 1.1378838922694868e-07,
|
| 2876 |
+
"entropy": 0.6119711980223655,
|
| 2877 |
+
"num_tokens": 33306193.0,
|
| 2878 |
+
"mean_token_accuracy": 0.8373264789581298,
|
| 2879 |
+
"epoch": 0.9797584623235244,
|
| 2880 |
+
"step": 2880
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"loss": 0.5924,
|
| 2884 |
+
"grad_norm": 0.39813292026519775,
|
| 2885 |
+
"learning_rate": 7.954781138351241e-08,
|
| 2886 |
+
"entropy": 0.5946994125843048,
|
| 2887 |
+
"num_tokens": 33423283.0,
|
| 2888 |
+
"mean_token_accuracy": 0.8413377672433853,
|
| 2889 |
+
"epoch": 0.9831604014288144,
|
| 2890 |
+
"step": 2890
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"loss": 0.559,
|
| 2894 |
+
"grad_norm": 0.38787519931793213,
|
| 2895 |
+
"learning_rate": 5.141576967533368e-08,
|
| 2896 |
+
"entropy": 0.5609085857868195,
|
| 2897 |
+
"num_tokens": 33538638.0,
|
| 2898 |
+
"mean_token_accuracy": 0.8481513082981109,
|
| 2899 |
+
"epoch": 0.9865623405341044,
|
| 2900 |
+
"step": 2900
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"loss": 0.5985,
|
| 2904 |
+
"grad_norm": 0.4220837354660034,
|
| 2905 |
+
"learning_rate": 2.9395706490958907e-08,
|
| 2906 |
+
"entropy": 0.5978995203971863,
|
| 2907 |
+
"num_tokens": 33653798.0,
|
| 2908 |
+
"mean_token_accuracy": 0.8422107011079788,
|
| 2909 |
+
"epoch": 0.9899642796393945,
|
| 2910 |
+
"step": 2910
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"loss": 0.5694,
|
| 2914 |
+
"grad_norm": 0.3267785906791687,
|
| 2915 |
+
"learning_rate": 1.3490316324249463e-08,
|
| 2916 |
+
"entropy": 0.5705890819430351,
|
| 2917 |
+
"num_tokens": 33766910.0,
|
| 2918 |
+
"mean_token_accuracy": 0.8483996599912643,
|
| 2919 |
+
"epoch": 0.9933662187446844,
|
| 2920 |
+
"step": 2920
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"loss": 0.5656,
|
| 2924 |
+
"grad_norm": 0.38315078616142273,
|
| 2925 |
+
"learning_rate": 3.7015454446398536e-09,
|
| 2926 |
+
"entropy": 0.563205997645855,
|
| 2927 |
+
"num_tokens": 33880183.0,
|
| 2928 |
+
"mean_token_accuracy": 0.8477971255779266,
|
| 2929 |
+
"epoch": 0.9967681578499745,
|
| 2930 |
+
"step": 2930
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"loss": 0.565,
|
| 2934 |
+
"grad_norm": 0.5500030517578125,
|
| 2935 |
+
"learning_rate": 3.059165900598515e-11,
|
| 2936 |
+
"entropy": 0.5684452543133184,
|
| 2937 |
+
"num_tokens": 33988110.0,
|
| 2938 |
+
"mean_token_accuracy": 0.8478908413334897,
|
| 2939 |
+
"epoch": 1.0,
|
| 2940 |
+
"step": 2940
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"train_runtime": 22288.508,
|
| 2944 |
+
"train_samples_per_second": 4.22,
|
| 2945 |
+
"train_steps_per_second": 0.132,
|
| 2946 |
+
"total_flos": 2.46979541812514e+19,
|
| 2947 |
+
"train_loss": 0.6280506309197873,
|
| 2948 |
+
"epoch": 1.0,
|
| 2949 |
+
"step": 2940
|
| 2950 |
+
}
|
| 2951 |
+
]
|