Upload results/eval_difficulty/checkpoint-18779_metrics.json
Browse files
results/eval_difficulty/checkpoint-18779_metrics.json
ADDED
|
@@ -0,0 +1,1979 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "checkpoint-18779",
|
| 3 |
+
"id": {
|
| 4 |
+
"answer_accuracy": 0.9630347222222222,
|
| 5 |
+
"avg_response_len": 201.21272916666666,
|
| 6 |
+
"avg_loss": 6.54602900314331,
|
| 7 |
+
"count": 1152000,
|
| 8 |
+
"validation_metrics": {},
|
| 9 |
+
"pass_at_k": {
|
| 10 |
+
"pass@1": 0.9630347222222222,
|
| 11 |
+
"pass@2": 0.9784445264654293,
|
| 12 |
+
"pass@4": 0.9859757670187062,
|
| 13 |
+
"pass@8": 0.9905464808595384,
|
| 14 |
+
"pass@16": 0.9936741909013082,
|
| 15 |
+
"pass@32": 0.9958726768097093,
|
| 16 |
+
"pass@64": 0.9973773311067934,
|
| 17 |
+
"pass@128": 0.9983333333333333
|
| 18 |
+
},
|
| 19 |
+
"per_op_pass_at_k": {
|
| 20 |
+
"10": {
|
| 21 |
+
"pass@1": 0.89534375,
|
| 22 |
+
"pass@2": 0.9316516978346466,
|
| 23 |
+
"pass@4": 0.9502444778777662,
|
| 24 |
+
"pass@8": 0.9628981587488723,
|
| 25 |
+
"pass@16": 0.9732652153333301,
|
| 26 |
+
"pass@32": 0.9817272204905513,
|
| 27 |
+
"pass@64": 0.9875005300252477,
|
| 28 |
+
"pass@128": 0.991
|
| 29 |
+
},
|
| 30 |
+
"2": {
|
| 31 |
+
"pass@1": 0.9994453125,
|
| 32 |
+
"pass@2": 0.9998784448818898,
|
| 33 |
+
"pass@4": 0.999987270247469,
|
| 34 |
+
"pass@8": 0.9999998760353234,
|
| 35 |
+
"pass@16": 0.9999999999955357,
|
| 36 |
+
"pass@32": 1.0,
|
| 37 |
+
"pass@64": 1.0,
|
| 38 |
+
"pass@128": 1.0
|
| 39 |
+
},
|
| 40 |
+
"3": {
|
| 41 |
+
"pass@1": 0.9896953125,
|
| 42 |
+
"pass@2": 0.9956350885826775,
|
| 43 |
+
"pass@4": 0.998029471128609,
|
| 44 |
+
"pass@8": 0.9990296020970205,
|
| 45 |
+
"pass@16": 0.9994722941030695,
|
| 46 |
+
"pass@32": 0.999768854949753,
|
| 47 |
+
"pass@64": 0.9999711811022791,
|
| 48 |
+
"pass@128": 1.0
|
| 49 |
+
},
|
| 50 |
+
"4": {
|
| 51 |
+
"pass@1": 0.9968125,
|
| 52 |
+
"pass@2": 0.9986126968503938,
|
| 53 |
+
"pass@4": 0.9994299414135731,
|
| 54 |
+
"pass@8": 0.9998706652443888,
|
| 55 |
+
"pass@16": 0.999993190320664,
|
| 56 |
+
"pass@32": 0.9999999900668188,
|
| 57 |
+
"pass@64": 0.9999999999999999,
|
| 58 |
+
"pass@128": 1.0
|
| 59 |
+
},
|
| 60 |
+
"5": {
|
| 61 |
+
"pass@1": 0.95453125,
|
| 62 |
+
"pass@2": 0.9673741387795279,
|
| 63 |
+
"pass@4": 0.9768552553430826,
|
| 64 |
+
"pass@8": 0.9845504029004547,
|
| 65 |
+
"pass@16": 0.9905860749032567,
|
| 66 |
+
"pass@32": 0.9947039335217139,
|
| 67 |
+
"pass@64": 0.9972231304095797,
|
| 68 |
+
"pass@128": 0.999
|
| 69 |
+
},
|
| 70 |
+
"6": {
|
| 71 |
+
"pass@1": 0.9755546875,
|
| 72 |
+
"pass@2": 0.9871010088582685,
|
| 73 |
+
"pass@4": 0.9931382349081366,
|
| 74 |
+
"pass@8": 0.9961125829051054,
|
| 75 |
+
"pass@16": 0.9972334916240602,
|
| 76 |
+
"pass@32": 0.9976868579347262,
|
| 77 |
+
"pass@64": 0.998251968426333,
|
| 78 |
+
"pass@128": 0.999
|
| 79 |
+
},
|
| 80 |
+
"7": {
|
| 81 |
+
"pass@1": 0.9665546875,
|
| 82 |
+
"pass@2": 0.980099409448819,
|
| 83 |
+
"pass@4": 0.9868899991563556,
|
| 84 |
+
"pass@8": 0.9912036930431989,
|
| 85 |
+
"pass@16": 0.9940644245074017,
|
| 86 |
+
"pass@32": 0.9960585379187011,
|
| 87 |
+
"pass@64": 0.9974804599031311,
|
| 88 |
+
"pass@128": 0.998
|
| 89 |
+
},
|
| 90 |
+
"8": {
|
| 91 |
+
"pass@1": 0.95003125,
|
| 92 |
+
"pass@2": 0.9737233021653545,
|
| 93 |
+
"pass@4": 0.984498448537683,
|
| 94 |
+
"pass@8": 0.9902565507718185,
|
| 95 |
+
"pass@16": 0.9939245919129133,
|
| 96 |
+
"pass@32": 0.996586911336722,
|
| 97 |
+
"pass@64": 0.998538493317924,
|
| 98 |
+
"pass@128": 1.0
|
| 99 |
+
},
|
| 100 |
+
"9": {
|
| 101 |
+
"pass@1": 0.93934375,
|
| 102 |
+
"pass@2": 0.9719249507874034,
|
| 103 |
+
"pass@4": 0.98470880455568,
|
| 104 |
+
"pass@8": 0.990996795989665,
|
| 105 |
+
"pass@16": 0.9945284354115372,
|
| 106 |
+
"pass@32": 0.9963217850684021,
|
| 107 |
+
"pass@64": 0.9974302167766392,
|
| 108 |
+
"pass@128": 0.998
|
| 109 |
+
}
|
| 110 |
+
},
|
| 111 |
+
"per_op_accuracy": {
|
| 112 |
+
"10": 0.89534375,
|
| 113 |
+
"2": 0.9994453125,
|
| 114 |
+
"3": 0.9896953125,
|
| 115 |
+
"4": 0.9968125,
|
| 116 |
+
"5": 0.95453125,
|
| 117 |
+
"6": 0.9755546875,
|
| 118 |
+
"7": 0.9665546875,
|
| 119 |
+
"8": 0.95003125,
|
| 120 |
+
"9": 0.93934375
|
| 121 |
+
},
|
| 122 |
+
"per_op_avg_response_len": {
|
| 123 |
+
"10": 279.685734375,
|
| 124 |
+
"2": 116.979234375,
|
| 125 |
+
"3": 147.114546875,
|
| 126 |
+
"4": 160.9594765625,
|
| 127 |
+
"5": 176.0514453125,
|
| 128 |
+
"6": 200.8557890625,
|
| 129 |
+
"7": 225.0676796875,
|
| 130 |
+
"8": 244.2956640625,
|
| 131 |
+
"9": 259.9049921875
|
| 132 |
+
},
|
| 133 |
+
"per_op_avg_loss": {
|
| 134 |
+
"10": 0.13990753173828124,
|
| 135 |
+
"2": 0.15822406005859374,
|
| 136 |
+
"3": 0.15319696044921874,
|
| 137 |
+
"4": 0.1460938720703125,
|
| 138 |
+
"5": 0.1487813720703125,
|
| 139 |
+
"6": 0.14940606689453126,
|
| 140 |
+
"7": 0.14932769775390625,
|
| 141 |
+
"8": 0.14807330322265624,
|
| 142 |
+
"9": 0.1509442138671875
|
| 143 |
+
},
|
| 144 |
+
"per_op_length": {
|
| 145 |
+
"10": 279.685734375,
|
| 146 |
+
"2": 116.979234375,
|
| 147 |
+
"3": 147.114546875,
|
| 148 |
+
"4": 160.9594765625,
|
| 149 |
+
"5": 176.0514453125,
|
| 150 |
+
"6": 200.8557890625,
|
| 151 |
+
"7": 225.0676796875,
|
| 152 |
+
"8": 244.2956640625,
|
| 153 |
+
"9": 259.9049921875
|
| 154 |
+
},
|
| 155 |
+
"per_op_loss": {
|
| 156 |
+
"10": 0.13990753173828124,
|
| 157 |
+
"2": 0.15822406005859374,
|
| 158 |
+
"3": 0.15319696044921874,
|
| 159 |
+
"4": 0.1460938720703125,
|
| 160 |
+
"5": 0.1487813720703125,
|
| 161 |
+
"6": 0.14940606689453126,
|
| 162 |
+
"7": 0.14932769775390625,
|
| 163 |
+
"8": 0.14807330322265624,
|
| 164 |
+
"9": 0.1509442138671875
|
| 165 |
+
},
|
| 166 |
+
"per_template": {
|
| 167 |
+
"crazy_zootopia": {
|
| 168 |
+
"count": 379008,
|
| 169 |
+
"correct": 364061,
|
| 170 |
+
"answer_accuracy": 0.960562837723742,
|
| 171 |
+
"avg_response_len": 191.88788099459643,
|
| 172 |
+
"resp_tokens_sum": 72727042,
|
| 173 |
+
"pass_at_k": {
|
| 174 |
+
"pass@1": 0.960562837723742,
|
| 175 |
+
"pass@2": 0.9772055171959906,
|
| 176 |
+
"pass@4": 0.985136322815272,
|
| 177 |
+
"pass@8": 0.9899132907085476,
|
| 178 |
+
"pass@16": 0.9932574318987277,
|
| 179 |
+
"pass@32": 0.9956698086202027,
|
| 180 |
+
"pass@64": 0.9972163254747021,
|
| 181 |
+
"pass@128": 0.9979736575481256
|
| 182 |
+
},
|
| 183 |
+
"per_op_pass_at_k": {
|
| 184 |
+
"10": {
|
| 185 |
+
"pass@1": 0.8994976032448377,
|
| 186 |
+
"pass@2": 0.9366747090795067,
|
| 187 |
+
"pass@4": 0.954640098361598,
|
| 188 |
+
"pass@8": 0.9671935395338649,
|
| 189 |
+
"pass@16": 0.9780409476989385,
|
| 190 |
+
"pass@32": 0.9873672705205916,
|
| 191 |
+
"pass@64": 0.9931124421272916,
|
| 192 |
+
"pass@128": 0.9941002949852508
|
| 193 |
+
},
|
| 194 |
+
"2": {
|
| 195 |
+
"pass@1": 0.9997322819314641,
|
| 196 |
+
"pass@2": 0.9999915679348491,
|
| 197 |
+
"pass@4": 0.9999999897793149,
|
| 198 |
+
"pass@8": 1.0,
|
| 199 |
+
"pass@16": 1.0,
|
| 200 |
+
"pass@32": 1.0,
|
| 201 |
+
"pass@64": 1.0,
|
| 202 |
+
"pass@128": 1.0
|
| 203 |
+
},
|
| 204 |
+
"3": {
|
| 205 |
+
"pass@1": 0.9875525611620795,
|
| 206 |
+
"pass@2": 0.9937483445303281,
|
| 207 |
+
"pass@4": 0.9960841566249173,
|
| 208 |
+
"pass@8": 0.9973945614382809,
|
| 209 |
+
"pass@16": 0.9984052318072489,
|
| 210 |
+
"pass@32": 0.9992931754002767,
|
| 211 |
+
"pass@64": 0.9999118688143109,
|
| 212 |
+
"pass@128": 1.0
|
| 213 |
+
},
|
| 214 |
+
"4": {
|
| 215 |
+
"pass@1": 0.996337890625,
|
| 216 |
+
"pass@2": 0.9982602577509845,
|
| 217 |
+
"pass@4": 0.9992694307742784,
|
| 218 |
+
"pass@8": 0.9998455780548049,
|
| 219 |
+
"pass@16": 0.9999940908757206,
|
| 220 |
+
"pass@32": 0.9999999967265157,
|
| 221 |
+
"pass@64": 1.0,
|
| 222 |
+
"pass@128": 1.0
|
| 223 |
+
},
|
| 224 |
+
"5": {
|
| 225 |
+
"pass@1": 0.9481150793650793,
|
| 226 |
+
"pass@2": 0.9641533089613797,
|
| 227 |
+
"pass@4": 0.9757381440415184,
|
| 228 |
+
"pass@8": 0.9837977641761237,
|
| 229 |
+
"pass@16": 0.9891567790393069,
|
| 230 |
+
"pass@32": 0.9924331098404072,
|
| 231 |
+
"pass@64": 0.9948057827917357,
|
| 232 |
+
"pass@128": 0.9968253968253968
|
| 233 |
+
},
|
| 234 |
+
"6": {
|
| 235 |
+
"pass@1": 0.9665746631736527,
|
| 236 |
+
"pass@2": 0.9810815131547932,
|
| 237 |
+
"pass@4": 0.9889092237347574,
|
| 238 |
+
"pass@8": 0.992817054998713,
|
| 239 |
+
"pass@16": 0.9942118482404367,
|
| 240 |
+
"pass@32": 0.9947566055669427,
|
| 241 |
+
"pass@64": 0.9955089818359227,
|
| 242 |
+
"pass@128": 0.9970059880239521
|
| 243 |
+
},
|
| 244 |
+
"7": {
|
| 245 |
+
"pass@1": 0.9575397559171598,
|
| 246 |
+
"pass@2": 0.9706686361412663,
|
| 247 |
+
"pass@4": 0.9781720887884576,
|
| 248 |
+
"pass@8": 0.9836457175352227,
|
| 249 |
+
"pass@16": 0.9877211930993773,
|
| 250 |
+
"pass@32": 0.991030454111008,
|
| 251 |
+
"pass@64": 0.9934560055493304,
|
| 252 |
+
"pass@128": 0.9940828402366864
|
| 253 |
+
},
|
| 254 |
+
"8": {
|
| 255 |
+
"pass@1": 0.9534755608974359,
|
| 256 |
+
"pass@2": 0.9758759684786995,
|
| 257 |
+
"pass@4": 0.9847553208493165,
|
| 258 |
+
"pass@8": 0.9897007291187125,
|
| 259 |
+
"pass@16": 0.9935694000922215,
|
| 260 |
+
"pass@32": 0.9965151373391712,
|
| 261 |
+
"pass@64": 0.998300039303945,
|
| 262 |
+
"pass@128": 1.0
|
| 263 |
+
},
|
| 264 |
+
"9": {
|
| 265 |
+
"pass@1": 0.9408450704225352,
|
| 266 |
+
"pass@2": 0.9764160751913055,
|
| 267 |
+
"pass@4": 0.9897490211610868,
|
| 268 |
+
"pass@8": 0.9954928597779902,
|
| 269 |
+
"pass@16": 0.9986146363237696,
|
| 270 |
+
"pass@32": 0.9998472651017836,
|
| 271 |
+
"pass@64": 0.9999990904114461,
|
| 272 |
+
"pass@128": 1.0
|
| 273 |
+
}
|
| 274 |
+
}
|
| 275 |
+
},
|
| 276 |
+
"teachers_in_school": {
|
| 277 |
+
"count": 390656,
|
| 278 |
+
"correct": 376417,
|
| 279 |
+
"answer_accuracy": 0.9635510525884666,
|
| 280 |
+
"avg_response_len": 199.2523191759502,
|
| 281 |
+
"resp_tokens_sum": 77839114,
|
| 282 |
+
"pass_at_k": {
|
| 283 |
+
"pass@1": 0.9635510525884666,
|
| 284 |
+
"pass@2": 0.978026663489027,
|
| 285 |
+
"pass@4": 0.9851850014079184,
|
| 286 |
+
"pass@8": 0.9897531921524919,
|
| 287 |
+
"pass@16": 0.9930249781079535,
|
| 288 |
+
"pass@32": 0.9953635939722416,
|
| 289 |
+
"pass@64": 0.9969830500068908,
|
| 290 |
+
"pass@128": 0.9980340760157274
|
| 291 |
+
},
|
| 292 |
+
"per_op_pass_at_k": {
|
| 293 |
+
"10": {
|
| 294 |
+
"pass@1": 0.8878930214723927,
|
| 295 |
+
"pass@2": 0.9240016333751996,
|
| 296 |
+
"pass@4": 0.9427751138086263,
|
| 297 |
+
"pass@8": 0.9559837013558444,
|
| 298 |
+
"pass@16": 0.9669589357176731,
|
| 299 |
+
"pass@32": 0.9757400698048759,
|
| 300 |
+
"pass@64": 0.9820426961144421,
|
| 301 |
+
"pass@128": 0.9877300613496932
|
| 302 |
+
},
|
| 303 |
+
"2": {
|
| 304 |
+
"pass@1": 0.9987177051671733,
|
| 305 |
+
"pass@2": 0.9996395064978579,
|
| 306 |
+
"pass@4": 0.9999613177152248,
|
| 307 |
+
"pass@8": 0.9999996232076699,
|
| 308 |
+
"pass@16": 0.9999999999864305,
|
| 309 |
+
"pass@32": 1.0,
|
| 310 |
+
"pass@64": 1.0,
|
| 311 |
+
"pass@128": 1.0
|
| 312 |
+
},
|
| 313 |
+
"3": {
|
| 314 |
+
"pass@1": 0.9907670454545454,
|
| 315 |
+
"pass@2": 0.9960163892865667,
|
| 316 |
+
"pass@4": 0.9985778993534897,
|
| 317 |
+
"pass@8": 0.9996915957072215,
|
| 318 |
+
"pass@16": 0.9999815253902985,
|
| 319 |
+
"pass@32": 0.99999995938087,
|
| 320 |
+
"pass@64": 0.9999999999999987,
|
| 321 |
+
"pass@128": 1.0
|
| 322 |
+
},
|
| 323 |
+
"4": {
|
| 324 |
+
"pass@1": 0.9982664571005917,
|
| 325 |
+
"pass@2": 0.9998132687648512,
|
| 326 |
+
"pass@4": 0.999995557138198,
|
| 327 |
+
"pass@8": 0.9999999967656203,
|
| 328 |
+
"pass@16": 0.9999999999999998,
|
| 329 |
+
"pass@32": 1.0,
|
| 330 |
+
"pass@64": 1.0,
|
| 331 |
+
"pass@128": 1.0
|
| 332 |
+
},
|
| 333 |
+
"5": {
|
| 334 |
+
"pass@1": 0.9600317028985508,
|
| 335 |
+
"pass@2": 0.9691975493552438,
|
| 336 |
+
"pass@4": 0.9763000869456536,
|
| 337 |
+
"pass@8": 0.9828931121195829,
|
| 338 |
+
"pass@16": 0.989036439654314,
|
| 339 |
+
"pass@32": 0.9944838684919953,
|
| 340 |
+
"pass@64": 0.9981653755234783,
|
| 341 |
+
"pass@128": 1.0
|
| 342 |
+
},
|
| 343 |
+
"6": {
|
| 344 |
+
"pass@1": 0.9823379297994269,
|
| 345 |
+
"pass@2": 0.9910194058389551,
|
| 346 |
+
"pass@4": 0.9946701218221643,
|
| 347 |
+
"pass@8": 0.9965445299840145,
|
| 348 |
+
"pass@16": 0.9976712739922713,
|
| 349 |
+
"pass@32": 0.9983904225804993,
|
| 350 |
+
"pass@64": 0.9992893080034889,
|
| 351 |
+
"pass@128": 1.0
|
| 352 |
+
},
|
| 353 |
+
"7": {
|
| 354 |
+
"pass@1": 0.9681855130057804,
|
| 355 |
+
"pass@2": 0.9832421146056164,
|
| 356 |
+
"pass@4": 0.9914642009163593,
|
| 357 |
+
"pass@8": 0.9964758591421767,
|
| 358 |
+
"pass@16": 0.9990374180123244,
|
| 359 |
+
"pass@32": 0.9999126056145744,
|
| 360 |
+
"pass@64": 0.9999997855847184,
|
| 361 |
+
"pass@128": 1.0
|
| 362 |
+
},
|
| 363 |
+
"8": {
|
| 364 |
+
"pass@1": 0.9455765845070423,
|
| 365 |
+
"pass@2": 0.9712158284351782,
|
| 366 |
+
"pass@4": 0.9835400283591312,
|
| 367 |
+
"pass@8": 0.9910390348371692,
|
| 368 |
+
"pass@16": 0.9955726997113149,
|
| 369 |
+
"pass@32": 0.9980539040490879,
|
| 370 |
+
"pass@64": 0.9995741614459047,
|
| 371 |
+
"pass@128": 1.0
|
| 372 |
+
},
|
| 373 |
+
"9": {
|
| 374 |
+
"pass@1": 0.9390437874251497,
|
| 375 |
+
"pass@2": 0.9670264539818006,
|
| 376 |
+
"pass@4": 0.9783135702722786,
|
| 377 |
+
"pass@8": 0.9840906736702117,
|
| 378 |
+
"pass@16": 0.9879928605789021,
|
| 379 |
+
"pass@32": 0.9908513468886352,
|
| 380 |
+
"pass@64": 0.9930496212972972,
|
| 381 |
+
"pass@128": 0.9940119760479041
|
| 382 |
+
}
|
| 383 |
+
}
|
| 384 |
+
},
|
| 385 |
+
"movie_festival_awards": {
|
| 386 |
+
"count": 382336,
|
| 387 |
+
"correct": 368938,
|
| 388 |
+
"answer_accuracy": 0.9649575242718447,
|
| 389 |
+
"avg_response_len": 212.4594806662203,
|
| 390 |
+
"resp_tokens_sum": 81230908,
|
| 391 |
+
"pass_at_k": {
|
| 392 |
+
"pass@1": 0.9649575242718447,
|
| 393 |
+
"pass@2": 0.9800997069980434,
|
| 394 |
+
"pass@4": 0.9876158778089633,
|
| 395 |
+
"pass@8": 0.9919847109134324,
|
| 396 |
+
"pass@16": 0.9947506625624947,
|
| 397 |
+
"pass@32": 0.9965939401271129,
|
| 398 |
+
"pass@64": 0.9979397963205583,
|
| 399 |
+
"pass@128": 0.9989956478071644
|
| 400 |
+
},
|
| 401 |
+
"per_op_pass_at_k": {
|
| 402 |
+
"10": {
|
| 403 |
+
"pass@1": 0.8983908582089553,
|
| 404 |
+
"pass@2": 0.9340132506757551,
|
| 405 |
+
"pass@4": 0.9530650669599133,
|
| 406 |
+
"pass@8": 0.9652801856862316,
|
| 407 |
+
"pass@16": 0.9745693164759084,
|
| 408 |
+
"pass@32": 0.9818461284408381,
|
| 409 |
+
"pass@64": 0.9871328155545905,
|
| 410 |
+
"pass@128": 0.991044776119403
|
| 411 |
+
},
|
| 412 |
+
"2": {
|
| 413 |
+
"pass@1": 0.9998660714285714,
|
| 414 |
+
"pass@2": 0.9999992969628797,
|
| 415 |
+
"pass@4": 1.0,
|
| 416 |
+
"pass@8": 1.0,
|
| 417 |
+
"pass@16": 1.0,
|
| 418 |
+
"pass@32": 1.0,
|
| 419 |
+
"pass@64": 1.0,
|
| 420 |
+
"pass@128": 1.0
|
| 421 |
+
},
|
| 422 |
+
"3": {
|
| 423 |
+
"pass@1": 0.9907069970845481,
|
| 424 |
+
"pass@2": 0.9970669721769471,
|
| 425 |
+
"pass@4": 0.9993563997831172,
|
| 426 |
+
"pass@8": 0.9999514691641971,
|
| 427 |
+
"pass@16": 0.9999996499221584,
|
| 428 |
+
"pass@32": 0.9999999999946803,
|
| 429 |
+
"pass@64": 1.0,
|
| 430 |
+
"pass@128": 1.0
|
| 431 |
+
},
|
| 432 |
+
"4": {
|
| 433 |
+
"pass@1": 0.9958196271929824,
|
| 434 |
+
"pass@2": 0.9977559342911083,
|
| 435 |
+
"pass@4": 0.9990211264710332,
|
| 436 |
+
"pass@8": 0.9997663197662907,
|
| 437 |
+
"pass@16": 0.9999856176620865,
|
| 438 |
+
"pass@32": 0.9999999740185194,
|
| 439 |
+
"pass@64": 0.9999999999999997,
|
| 440 |
+
"pass@128": 1.0
|
| 441 |
+
},
|
| 442 |
+
"5": {
|
| 443 |
+
"pass@1": 0.9548943014705882,
|
| 444 |
+
"pass@2": 0.9685079174386292,
|
| 445 |
+
"pass@4": 0.9784535587463331,
|
| 446 |
+
"pass@8": 0.9869293632462349,
|
| 447 |
+
"pass@16": 0.9934826994856965,
|
| 448 |
+
"pass@32": 0.9970310861536675,
|
| 449 |
+
"pass@64": 0.9985066302193607,
|
| 450 |
+
"pass@128": 1.0
|
| 451 |
+
},
|
| 452 |
+
"6": {
|
| 453 |
+
"pass@1": 0.9775483044164038,
|
| 454 |
+
"pass@2": 0.9891293716932861,
|
| 455 |
+
"pass@4": 0.9959075131381444,
|
| 456 |
+
"pass@8": 0.9991092920224423,
|
| 457 |
+
"pass@16": 0.9999352040645176,
|
| 458 |
+
"pass@32": 0.9999996662295679,
|
| 459 |
+
"pass@64": 0.9999999999997393,
|
| 460 |
+
"pass@128": 1.0
|
| 461 |
+
},
|
| 462 |
+
"7": {
|
| 463 |
+
"pass@1": 0.9744115901898734,
|
| 464 |
+
"pass@2": 0.9867456923402768,
|
| 465 |
+
"pass@4": 0.9912063912303684,
|
| 466 |
+
"pass@8": 0.9935151685224703,
|
| 467 |
+
"pass@16": 0.9954041601504686,
|
| 468 |
+
"pass@32": 0.9972167179953726,
|
| 469 |
+
"pass@64": 0.9990265956175474,
|
| 470 |
+
"pass@128": 1.0
|
| 471 |
+
},
|
| 472 |
+
"8": {
|
| 473 |
+
"pass@1": 0.9515531156156156,
|
| 474 |
+
"pass@2": 0.9743795222387744,
|
| 475 |
+
"pass@4": 0.9852795146102226,
|
| 476 |
+
"pass@8": 0.9899431408996546,
|
| 477 |
+
"pass@16": 0.9925003924523234,
|
| 478 |
+
"pass@32": 0.9950902478963195,
|
| 479 |
+
"pass@64": 0.9976578190444356,
|
| 480 |
+
"pass@128": 1.0
|
| 481 |
+
},
|
| 482 |
+
"9": {
|
| 483 |
+
"pass@1": 0.9379521704180064,
|
| 484 |
+
"pass@2": 0.9720591912043948,
|
| 485 |
+
"pass@4": 0.9858236963747689,
|
| 486 |
+
"pass@8": 0.9932814976290268,
|
| 487 |
+
"pass@16": 0.9968830356374474,
|
| 488 |
+
"pass@32": 0.9981725276413653,
|
| 489 |
+
"pass@64": 0.9992024635603814,
|
| 490 |
+
"pass@128": 1.0
|
| 491 |
+
}
|
| 492 |
+
}
|
| 493 |
+
}
|
| 494 |
+
}
|
| 495 |
+
},
|
| 496 |
+
"ood": {
|
| 497 |
+
"answer_accuracy": 0.25220703125,
|
| 498 |
+
"avg_response_len": 284.85050390625,
|
| 499 |
+
"avg_loss": 5.825457085227966,
|
| 500 |
+
"count": 1280000,
|
| 501 |
+
"validation_metrics": {},
|
| 502 |
+
"pass_at_k": {
|
| 503 |
+
"pass@1": 0.25220703125,
|
| 504 |
+
"pass@2": 0.3026185285433113,
|
| 505 |
+
"pass@4": 0.34743800927071905,
|
| 506 |
+
"pass@8": 0.38810959550625124,
|
| 507 |
+
"pass@16": 0.42553433372274274,
|
| 508 |
+
"pass@32": 0.4601746364651569,
|
| 509 |
+
"pass@64": 0.49276390746466214,
|
| 510 |
+
"pass@128": 0.5238
|
| 511 |
+
},
|
| 512 |
+
"per_op_pass_at_k": {
|
| 513 |
+
"11": {
|
| 514 |
+
"pass@1": 0.7491953125,
|
| 515 |
+
"pass@2": 0.8267459399606308,
|
| 516 |
+
"pass@4": 0.8755285344956877,
|
| 517 |
+
"pass@8": 0.907201192042703,
|
| 518 |
+
"pass@16": 0.9291708873567505,
|
| 519 |
+
"pass@32": 0.9454073394478061,
|
| 520 |
+
"pass@64": 0.9574549244959281,
|
| 521 |
+
"pass@128": 0.967
|
| 522 |
+
},
|
| 523 |
+
"12": {
|
| 524 |
+
"pass@1": 0.42375,
|
| 525 |
+
"pass@2": 0.5180041830708659,
|
| 526 |
+
"pass@4": 0.593009113235845,
|
| 527 |
+
"pass@8": 0.6523426553791513,
|
| 528 |
+
"pass@16": 0.702357863892847,
|
| 529 |
+
"pass@32": 0.745694824334505,
|
| 530 |
+
"pass@64": 0.7831121214310477,
|
| 531 |
+
"pass@128": 0.816
|
| 532 |
+
},
|
| 533 |
+
"13": {
|
| 534 |
+
"pass@1": 0.2113984375,
|
| 535 |
+
"pass@2": 0.25608120078740143,
|
| 536 |
+
"pass@4": 0.3006886397637793,
|
| 537 |
+
"pass@8": 0.3447306794463938,
|
| 538 |
+
"pass@16": 0.38799260684503434,
|
| 539 |
+
"pass@32": 0.43170338099033495,
|
| 540 |
+
"pass@64": 0.4761056180149899,
|
| 541 |
+
"pass@128": 0.519
|
| 542 |
+
},
|
| 543 |
+
"14": {
|
| 544 |
+
"pass@1": 0.200171875,
|
| 545 |
+
"pass@2": 0.2479451279527559,
|
| 546 |
+
"pass@4": 0.29500759055118103,
|
| 547 |
+
"pass@8": 0.34113887630208256,
|
| 548 |
+
"pass@16": 0.38481813556379674,
|
| 549 |
+
"pass@32": 0.4260044402977936,
|
| 550 |
+
"pass@64": 0.4671482956865662,
|
| 551 |
+
"pass@128": 0.51
|
| 552 |
+
},
|
| 553 |
+
"15": {
|
| 554 |
+
"pass@1": 0.17846875,
|
| 555 |
+
"pass@2": 0.23154035433070885,
|
| 556 |
+
"pass@4": 0.28250203355830483,
|
| 557 |
+
"pass@8": 0.3294688278958133,
|
| 558 |
+
"pass@16": 0.3735511399431241,
|
| 559 |
+
"pass@32": 0.4152404384047447,
|
| 560 |
+
"pass@64": 0.4535175002619446,
|
| 561 |
+
"pass@128": 0.485
|
| 562 |
+
},
|
| 563 |
+
"16": {
|
| 564 |
+
"pass@1": 0.158390625,
|
| 565 |
+
"pass@2": 0.1908997293307087,
|
| 566 |
+
"pass@4": 0.22120489895013098,
|
| 567 |
+
"pass@8": 0.2515841984680904,
|
| 568 |
+
"pass@16": 0.2832809698127581,
|
| 569 |
+
"pass@32": 0.3157377911008275,
|
| 570 |
+
"pass@64": 0.3483624231356763,
|
| 571 |
+
"pass@128": 0.383
|
| 572 |
+
},
|
| 573 |
+
"17": {
|
| 574 |
+
"pass@1": 0.15778125,
|
| 575 |
+
"pass@2": 0.19822810039370062,
|
| 576 |
+
"pass@4": 0.23773755933633278,
|
| 577 |
+
"pass@8": 0.2756691021575299,
|
| 578 |
+
"pass@16": 0.31012296220189073,
|
| 579 |
+
"pass@32": 0.34113294654797527,
|
| 580 |
+
"pass@64": 0.370247222269346,
|
| 581 |
+
"pass@128": 0.399
|
| 582 |
+
},
|
| 583 |
+
"18": {
|
| 584 |
+
"pass@1": 0.1607265625,
|
| 585 |
+
"pass@2": 0.1996240157480314,
|
| 586 |
+
"pass@4": 0.23766353665166848,
|
| 587 |
+
"pass@8": 0.27507361063539393,
|
| 588 |
+
"pass@16": 0.31047573197015055,
|
| 589 |
+
"pass@32": 0.342168030163979,
|
| 590 |
+
"pass@64": 0.37123232750738133,
|
| 591 |
+
"pass@128": 0.4
|
| 592 |
+
},
|
| 593 |
+
"19": {
|
| 594 |
+
"pass@1": 0.142859375,
|
| 595 |
+
"pass@2": 0.17847379429133842,
|
| 596 |
+
"pass@4": 0.21176526481064853,
|
| 597 |
+
"pass@8": 0.24360403095909056,
|
| 598 |
+
"pass@16": 0.27449561265010364,
|
| 599 |
+
"pass@32": 0.305123051282576,
|
| 600 |
+
"pass@64": 0.3363755503535671,
|
| 601 |
+
"pass@128": 0.369
|
| 602 |
+
},
|
| 603 |
+
"20": {
|
| 604 |
+
"pass@1": 0.139328125,
|
| 605 |
+
"pass@2": 0.17864283956692892,
|
| 606 |
+
"pass@4": 0.2192729213535806,
|
| 607 |
+
"pass@8": 0.26028278177620573,
|
| 608 |
+
"pass@16": 0.2990774269909148,
|
| 609 |
+
"pass@32": 0.33353412208103916,
|
| 610 |
+
"pass@64": 0.3640830914901839,
|
| 611 |
+
"pass@128": 0.39
|
| 612 |
+
}
|
| 613 |
+
},
|
| 614 |
+
"per_op_accuracy": {
|
| 615 |
+
"11": 0.7491953125,
|
| 616 |
+
"12": 0.42375,
|
| 617 |
+
"13": 0.2113984375,
|
| 618 |
+
"14": 0.200171875,
|
| 619 |
+
"15": 0.17846875,
|
| 620 |
+
"16": 0.158390625,
|
| 621 |
+
"17": 0.15778125,
|
| 622 |
+
"18": 0.1607265625,
|
| 623 |
+
"19": 0.142859375,
|
| 624 |
+
"20": 0.139328125
|
| 625 |
+
},
|
| 626 |
+
"per_op_avg_response_len": {
|
| 627 |
+
"11": 291.4343515625,
|
| 628 |
+
"12": 288.3101484375,
|
| 629 |
+
"13": 282.0749140625,
|
| 630 |
+
"14": 284.6130234375,
|
| 631 |
+
"15": 282.3583984375,
|
| 632 |
+
"16": 284.9855,
|
| 633 |
+
"17": 285.6167265625,
|
| 634 |
+
"18": 284.2999609375,
|
| 635 |
+
"19": 281.3561640625,
|
| 636 |
+
"20": 283.4558515625
|
| 637 |
+
},
|
| 638 |
+
"per_op_avg_loss": {
|
| 639 |
+
"11": 0.1496517333984375,
|
| 640 |
+
"12": 0.160320068359375,
|
| 641 |
+
"13": 0.18829949951171876,
|
| 642 |
+
"14": 0.2179671630859375,
|
| 643 |
+
"15": 0.24814111328125,
|
| 644 |
+
"16": 0.280107177734375,
|
| 645 |
+
"17": 0.3107010498046875,
|
| 646 |
+
"18": 0.3399879150390625,
|
| 647 |
+
"19": 0.40024169921875,
|
| 648 |
+
"20": 0.419079345703125
|
| 649 |
+
},
|
| 650 |
+
"per_op_length": {
|
| 651 |
+
"11": 291.4343515625,
|
| 652 |
+
"12": 288.3101484375,
|
| 653 |
+
"13": 282.0749140625,
|
| 654 |
+
"14": 284.6130234375,
|
| 655 |
+
"15": 282.3583984375,
|
| 656 |
+
"16": 284.9855,
|
| 657 |
+
"17": 285.6167265625,
|
| 658 |
+
"18": 284.2999609375,
|
| 659 |
+
"19": 281.3561640625,
|
| 660 |
+
"20": 283.4558515625
|
| 661 |
+
},
|
| 662 |
+
"per_op_loss": {
|
| 663 |
+
"11": 0.1496517333984375,
|
| 664 |
+
"12": 0.160320068359375,
|
| 665 |
+
"13": 0.18829949951171876,
|
| 666 |
+
"14": 0.2179671630859375,
|
| 667 |
+
"15": 0.24814111328125,
|
| 668 |
+
"16": 0.280107177734375,
|
| 669 |
+
"17": 0.3107010498046875,
|
| 670 |
+
"18": 0.3399879150390625,
|
| 671 |
+
"19": 0.40024169921875,
|
| 672 |
+
"20": 0.419079345703125
|
| 673 |
+
},
|
| 674 |
+
"per_template": {
|
| 675 |
+
"crazy_zootopia": {
|
| 676 |
+
"count": 430720,
|
| 677 |
+
"correct": 113067,
|
| 678 |
+
"answer_accuracy": 0.2625069650817236,
|
| 679 |
+
"avg_response_len": 273.8302725668648,
|
| 680 |
+
"resp_tokens_sum": 117944175,
|
| 681 |
+
"pass_at_k": {
|
| 682 |
+
"pass@1": 0.2625069650817236,
|
| 683 |
+
"pass@2": 0.31366907342841527,
|
| 684 |
+
"pass@4": 0.3583084888720263,
|
| 685 |
+
"pass@8": 0.3983932569435031,
|
| 686 |
+
"pass@16": 0.4355776055864389,
|
| 687 |
+
"pass@32": 0.47017903805797134,
|
| 688 |
+
"pass@64": 0.5024705719566711,
|
| 689 |
+
"pass@128": 0.5337295690936107
|
| 690 |
+
},
|
| 691 |
+
"per_op_pass_at_k": {
|
| 692 |
+
"11": {
|
| 693 |
+
"pass@1": 0.7521689093484419,
|
| 694 |
+
"pass@2": 0.8267172826838576,
|
| 695 |
+
"pass@4": 0.8749963240253604,
|
| 696 |
+
"pass@8": 0.9072539747181511,
|
| 697 |
+
"pass@16": 0.9305891455160197,
|
| 698 |
+
"pass@32": 0.9482171914771189,
|
| 699 |
+
"pass@64": 0.9598296757598728,
|
| 700 |
+
"pass@128": 0.9660056657223796
|
| 701 |
+
},
|
| 702 |
+
"12": {
|
| 703 |
+
"pass@1": 0.4268626412429379,
|
| 704 |
+
"pass@2": 0.5226548250589441,
|
| 705 |
+
"pass@4": 0.5947451512946471,
|
| 706 |
+
"pass@8": 0.6499540700619184,
|
| 707 |
+
"pass@16": 0.697671407935311,
|
| 708 |
+
"pass@32": 0.7391764349175001,
|
| 709 |
+
"pass@64": 0.7728700105439386,
|
| 710 |
+
"pass@128": 0.8022598870056498
|
| 711 |
+
},
|
| 712 |
+
"13": {
|
| 713 |
+
"pass@1": 0.226048197492163,
|
| 714 |
+
"pass@2": 0.2745025516500875,
|
| 715 |
+
"pass@4": 0.32170087379359735,
|
| 716 |
+
"pass@8": 0.36726090847720233,
|
| 717 |
+
"pass@16": 0.4118837384913241,
|
| 718 |
+
"pass@32": 0.4577964268716136,
|
| 719 |
+
"pass@64": 0.5060004900301981,
|
| 720 |
+
"pass@128": 0.554858934169279
|
| 721 |
+
},
|
| 722 |
+
"14": {
|
| 723 |
+
"pass@1": 0.1970404984423676,
|
| 724 |
+
"pass@2": 0.2447659871955257,
|
| 725 |
+
"pass@4": 0.2905214605183697,
|
| 726 |
+
"pass@8": 0.33432116638118264,
|
| 727 |
+
"pass@16": 0.37689919457954874,
|
| 728 |
+
"pass@32": 0.41849874775311363,
|
| 729 |
+
"pass@64": 0.46201871752633594,
|
| 730 |
+
"pass@128": 0.5109034267912772
|
| 731 |
+
},
|
| 732 |
+
"15": {
|
| 733 |
+
"pass@1": 0.190774024566474,
|
| 734 |
+
"pass@2": 0.24494681910245306,
|
| 735 |
+
"pass@4": 0.29680882700356104,
|
| 736 |
+
"pass@8": 0.3440605324830605,
|
| 737 |
+
"pass@16": 0.38846742937996726,
|
| 738 |
+
"pass@32": 0.43008799604881653,
|
| 739 |
+
"pass@64": 0.4654618905817254,
|
| 740 |
+
"pass@128": 0.4913294797687861
|
| 741 |
+
},
|
| 742 |
+
"16": {
|
| 743 |
+
"pass@1": 0.1630796370967742,
|
| 744 |
+
"pass@2": 0.1964297053594107,
|
| 745 |
+
"pass@4": 0.23033826426938572,
|
| 746 |
+
"pass@8": 0.2660781043146322,
|
| 747 |
+
"pass@16": 0.3019958633560044,
|
| 748 |
+
"pass@32": 0.33569879011745574,
|
| 749 |
+
"pass@64": 0.3686862876847773,
|
| 750 |
+
"pass@128": 0.4064516129032258
|
| 751 |
+
},
|
| 752 |
+
"17": {
|
| 753 |
+
"pass@1": 0.1676300578034682,
|
| 754 |
+
"pass@2": 0.20699551397296437,
|
| 755 |
+
"pass@4": 0.2408987041359715,
|
| 756 |
+
"pass@8": 0.271017564290959,
|
| 757 |
+
"pass@16": 0.29876652985892266,
|
| 758 |
+
"pass@32": 0.3264747152113181,
|
| 759 |
+
"pass@64": 0.3549548508714773,
|
| 760 |
+
"pass@128": 0.38439306358381503
|
| 761 |
+
},
|
| 762 |
+
"18": {
|
| 763 |
+
"pass@1": 0.1616517857142857,
|
| 764 |
+
"pass@2": 0.19595648200224966,
|
| 765 |
+
"pass@4": 0.23106420322459695,
|
| 766 |
+
"pass@8": 0.26888622832851616,
|
| 767 |
+
"pass@16": 0.3071732341417159,
|
| 768 |
+
"pass@32": 0.3420263056744111,
|
| 769 |
+
"pass@64": 0.3714714335108666,
|
| 770 |
+
"pass@128": 0.39714285714285713
|
| 771 |
+
},
|
| 772 |
+
"19": {
|
| 773 |
+
"pass@1": 0.15040822072072071,
|
| 774 |
+
"pass@2": 0.1915057281691139,
|
| 775 |
+
"pass@4": 0.2273034600967671,
|
| 776 |
+
"pass@8": 0.2598221642368353,
|
| 777 |
+
"pass@16": 0.2905735616301428,
|
| 778 |
+
"pass@32": 0.32042698971733125,
|
| 779 |
+
"pass@64": 0.35124146512270843,
|
| 780 |
+
"pass@128": 0.3843843843843844
|
| 781 |
+
},
|
| 782 |
+
"20": {
|
| 783 |
+
"pass@1": 0.15052552552552553,
|
| 784 |
+
"pass@2": 0.18885223806483653,
|
| 785 |
+
"pass@4": 0.22942468621602477,
|
| 786 |
+
"pass@8": 0.26979999128432536,
|
| 787 |
+
"pass@16": 0.30689533475643643,
|
| 788 |
+
"pass@32": 0.3397581402934893,
|
| 789 |
+
"pass@64": 0.370991289408613,
|
| 790 |
+
"pass@128": 0.4024024024024024
|
| 791 |
+
}
|
| 792 |
+
}
|
| 793 |
+
},
|
| 794 |
+
"teachers_in_school": {
|
| 795 |
+
"count": 430464,
|
| 796 |
+
"correct": 107386,
|
| 797 |
+
"answer_accuracy": 0.24946569283377937,
|
| 798 |
+
"avg_response_len": 281.4464322219744,
|
| 799 |
+
"resp_tokens_sum": 121152557,
|
| 800 |
+
"pass_at_k": {
|
| 801 |
+
"pass@1": 0.24946569283377937,
|
| 802 |
+
"pass@2": 0.30024583617224077,
|
| 803 |
+
"pass@4": 0.34601646702614464,
|
| 804 |
+
"pass@8": 0.3878270818735659,
|
| 805 |
+
"pass@16": 0.42574861408875925,
|
| 806 |
+
"pass@32": 0.4604748763552623,
|
| 807 |
+
"pass@64": 0.492562625136877,
|
| 808 |
+
"pass@128": 0.5212607790663099
|
| 809 |
+
},
|
| 810 |
+
"per_op_pass_at_k": {
|
| 811 |
+
"11": {
|
| 812 |
+
"pass@1": 0.7309864457831325,
|
| 813 |
+
"pass@2": 0.811214839673655,
|
| 814 |
+
"pass@4": 0.8645121111555325,
|
| 815 |
+
"pass@8": 0.9001346785530842,
|
| 816 |
+
"pass@16": 0.9235781504819824,
|
| 817 |
+
"pass@32": 0.939017807747773,
|
| 818 |
+
"pass@64": 0.9485292552001391,
|
| 819 |
+
"pass@128": 0.9548192771084337
|
| 820 |
+
},
|
| 821 |
+
"12": {
|
| 822 |
+
"pass@1": 0.439042907523511,
|
| 823 |
+
"pass@2": 0.5317378835188704,
|
| 824 |
+
"pass@4": 0.6075961422729685,
|
| 825 |
+
"pass@8": 0.6683062360710545,
|
| 826 |
+
"pass@16": 0.7177272091161964,
|
| 827 |
+
"pass@32": 0.7598458853246168,
|
| 828 |
+
"pass@64": 0.7942021269976,
|
| 829 |
+
"pass@128": 0.8213166144200627
|
| 830 |
+
},
|
| 831 |
+
"13": {
|
| 832 |
+
"pass@1": 0.19227065826330533,
|
| 833 |
+
"pass@2": 0.23474754074858276,
|
| 834 |
+
"pass@4": 0.27791213361985206,
|
| 835 |
+
"pass@8": 0.32123267772057174,
|
| 836 |
+
"pass@16": 0.36547236780648024,
|
| 837 |
+
"pass@32": 0.412591392141311,
|
| 838 |
+
"pass@64": 0.46083134462740805,
|
| 839 |
+
"pass@128": 0.5042016806722689
|
| 840 |
+
},
|
| 841 |
+
"14": {
|
| 842 |
+
"pass@1": 0.20837902046783627,
|
| 843 |
+
"pass@2": 0.2522699670764838,
|
| 844 |
+
"pass@4": 0.2964683594923442,
|
| 845 |
+
"pass@8": 0.3416618793696011,
|
| 846 |
+
"pass@16": 0.3841336779597966,
|
| 847 |
+
"pass@32": 0.42375806001618826,
|
| 848 |
+
"pass@64": 0.4632207639904677,
|
| 849 |
+
"pass@128": 0.5029239766081871
|
| 850 |
+
},
|
| 851 |
+
"15": {
|
| 852 |
+
"pass@1": 0.19093276515151514,
|
| 853 |
+
"pass@2": 0.24199400501073715,
|
| 854 |
+
"pass@4": 0.2891956014020975,
|
| 855 |
+
"pass@8": 0.3326345282383242,
|
| 856 |
+
"pass@16": 0.37366558323041027,
|
| 857 |
+
"pass@32": 0.4128573661812689,
|
| 858 |
+
"pass@64": 0.4483166035224402,
|
| 859 |
+
"pass@128": 0.4727272727272727
|
| 860 |
+
},
|
| 861 |
+
"16": {
|
| 862 |
+
"pass@1": 0.15642806267806267,
|
| 863 |
+
"pass@2": 0.1904278691926329,
|
| 864 |
+
"pass@4": 0.22132350069489173,
|
| 865 |
+
"pass@8": 0.251268169779741,
|
| 866 |
+
"pass@16": 0.28180434335829546,
|
| 867 |
+
"pass@32": 0.3122157586188942,
|
| 868 |
+
"pass@64": 0.34211985927431315,
|
| 869 |
+
"pass@128": 0.3732193732193732
|
| 870 |
+
},
|
| 871 |
+
"17": {
|
| 872 |
+
"pass@1": 0.16779891304347827,
|
| 873 |
+
"pass@2": 0.21377104526336374,
|
| 874 |
+
"pass@4": 0.2616579632708955,
|
| 875 |
+
"pass@8": 0.3084358591590647,
|
| 876 |
+
"pass@16": 0.3485515761094292,
|
| 877 |
+
"pass@32": 0.38192734451252297,
|
| 878 |
+
"pass@64": 0.4116145438455866,
|
| 879 |
+
"pass@128": 0.43788819875776397
|
| 880 |
+
},
|
| 881 |
+
"18": {
|
| 882 |
+
"pass@1": 0.1518612132352941,
|
| 883 |
+
"pass@2": 0.1958187384205651,
|
| 884 |
+
"pass@4": 0.23828893419572547,
|
| 885 |
+
"pass@8": 0.27971765090438966,
|
| 886 |
+
"pass@16": 0.31909231139592203,
|
| 887 |
+
"pass@32": 0.3541919542192856,
|
| 888 |
+
"pass@64": 0.3879892602530647,
|
| 889 |
+
"pass@128": 0.4235294117647059
|
| 890 |
+
},
|
| 891 |
+
"19": {
|
| 892 |
+
"pass@1": 0.14004371279761904,
|
| 893 |
+
"pass@2": 0.17627703763592056,
|
| 894 |
+
"pass@4": 0.21033196631671033,
|
| 895 |
+
"pass@8": 0.24241868591666452,
|
| 896 |
+
"pass@16": 0.2725452956766527,
|
| 897 |
+
"pass@32": 0.3023936104609465,
|
| 898 |
+
"pass@64": 0.331830773125219,
|
| 899 |
+
"pass@128": 0.3601190476190476
|
| 900 |
+
},
|
| 901 |
+
"20": {
|
| 902 |
+
"pass@1": 0.1367421407185629,
|
| 903 |
+
"pass@2": 0.17771825934744678,
|
| 904 |
+
"pass@4": 0.21898993408009634,
|
| 905 |
+
"pass@8": 0.260066157867715,
|
| 906 |
+
"pass@16": 0.2989195527821917,
|
| 907 |
+
"pass@32": 0.3334463816599912,
|
| 908 |
+
"pass@64": 0.3631967204725436,
|
| 909 |
+
"pass@128": 0.38622754491017963
|
| 910 |
+
}
|
| 911 |
+
}
|
| 912 |
+
},
|
| 913 |
+
"movie_festival_awards": {
|
| 914 |
+
"count": 418816,
|
| 915 |
+
"correct": 102372,
|
| 916 |
+
"answer_accuracy": 0.24443192237163813,
|
| 917 |
+
"avg_response_len": 299.6827079194682,
|
| 918 |
+
"resp_tokens_sum": 125511913,
|
| 919 |
+
"pass_at_k": {
|
| 920 |
+
"pass@1": 0.24443192237163813,
|
| 921 |
+
"pass@2": 0.2936925752748208,
|
| 922 |
+
"pass@4": 0.3377196360158527,
|
| 923 |
+
"pass@8": 0.3778240125631929,
|
| 924 |
+
"pass@16": 0.414985362239759,
|
| 925 |
+
"pass@32": 0.44957728985444445,
|
| 926 |
+
"pass@64": 0.48298823095266347,
|
| 927 |
+
"pass@128": 0.51619804400978
|
| 928 |
+
},
|
| 929 |
+
"per_op_pass_at_k": {
|
| 930 |
+
"11": {
|
| 931 |
+
"pass@1": 0.7650545634920635,
|
| 932 |
+
"pass@2": 0.8431473409573809,
|
| 933 |
+
"pass@4": 0.8877359086066622,
|
| 934 |
+
"pass@8": 0.9145899228176874,
|
| 935 |
+
"pass@16": 0.9334761048558039,
|
| 936 |
+
"pass@32": 0.9489928847114996,
|
| 937 |
+
"pass@64": 0.9642010673849086,
|
| 938 |
+
"pass@128": 0.9809523809523809
|
| 939 |
+
},
|
| 940 |
+
"12": {
|
| 941 |
+
"pass@1": 0.4054615825688073,
|
| 942 |
+
"pass@2": 0.49957183534397626,
|
| 943 |
+
"pass@4": 0.5768995727598271,
|
| 944 |
+
"pass@8": 0.639355428961972,
|
| 945 |
+
"pass@16": 0.6924379381519293,
|
| 946 |
+
"pass@32": 0.7389465717283092,
|
| 947 |
+
"pass@64": 0.7833812207530858,
|
| 948 |
+
"pass@128": 0.8256880733944955
|
| 949 |
+
},
|
| 950 |
+
"13": {
|
| 951 |
+
"pass@1": 0.21805073302469136,
|
| 952 |
+
"pass@2": 0.2614506628511712,
|
| 953 |
+
"pass@4": 0.30509700407819385,
|
| 954 |
+
"pass@8": 0.34843945585161107,
|
| 955 |
+
"pass@16": 0.3892841325907048,
|
| 956 |
+
"pass@32": 0.42707158587605587,
|
| 957 |
+
"pass@64": 0.46350207303509766,
|
| 958 |
+
"pass@128": 0.5
|
| 959 |
+
},
|
| 960 |
+
"14": {
|
| 961 |
+
"pass@1": 0.19482566765578635,
|
| 962 |
+
"pass@2": 0.24658432440010283,
|
| 963 |
+
"pass@4": 0.2977982871762691,
|
| 964 |
+
"pass@8": 0.34710213397424194,
|
| 965 |
+
"pass@16": 0.39305571585018145,
|
| 966 |
+
"pass@32": 0.4354334888531387,
|
| 967 |
+
"pass@64": 0.4760201367236571,
|
| 968 |
+
"pass@128": 0.516320474777448
|
| 969 |
+
},
|
| 970 |
+
"15": {
|
| 971 |
+
"pass@1": 0.15263310185185186,
|
| 972 |
+
"pass@2": 0.20657633724603863,
|
| 973 |
+
"pass@4": 0.26040626837154607,
|
| 974 |
+
"pass@8": 0.31066200412971595,
|
| 975 |
+
"pass@16": 0.3575054534309268,
|
| 976 |
+
"pass@32": 0.40181191645690056,
|
| 977 |
+
"pass@64": 0.4460592807353767,
|
| 978 |
+
"pass@128": 0.49074074074074076
|
| 979 |
+
},
|
| 980 |
+
"16": {
|
| 981 |
+
"pass@1": 0.15613477138643067,
|
| 982 |
+
"pass@2": 0.1863313822497852,
|
| 983 |
+
"pass@4": 0.21273005393131156,
|
| 984 |
+
"pass@8": 0.23865739981671225,
|
| 985 |
+
"pass@16": 0.2676959517806339,
|
| 986 |
+
"pass@32": 0.3011310763692745,
|
| 987 |
+
"pass@64": 0.3362407178410369,
|
| 988 |
+
"pass@128": 0.37168141592920356
|
| 989 |
+
},
|
| 990 |
+
"17": {
|
| 991 |
+
"pass@1": 0.1378012048192771,
|
| 992 |
+
"pass@2": 0.17401619272365054,
|
| 993 |
+
"pass@4": 0.21124320340981484,
|
| 994 |
+
"pass@8": 0.24873698272180494,
|
| 995 |
+
"pass@16": 0.28468715470923933,
|
| 996 |
+
"pass@32": 0.31684364503562207,
|
| 997 |
+
"pass@64": 0.3460631347877581,
|
| 998 |
+
"pass@128": 0.37650602409638556
|
| 999 |
+
},
|
| 1000 |
+
"18": {
|
| 1001 |
+
"pass@1": 0.16940524193548387,
|
| 1002 |
+
"pass@2": 0.20793830962661927,
|
| 1003 |
+
"pass@4": 0.24442847708552565,
|
| 1004 |
+
"pass@8": 0.27696590133200394,
|
| 1005 |
+
"pass@16": 0.3047539165997947,
|
| 1006 |
+
"pass@32": 0.329140512075412,
|
| 1007 |
+
"pass@64": 0.3525837977178592,
|
| 1008 |
+
"pass@128": 0.3774193548387097
|
| 1009 |
+
},
|
| 1010 |
+
"19": {
|
| 1011 |
+
"pass@1": 0.13812311178247735,
|
| 1012 |
+
"pass@2": 0.16759305790137258,
|
| 1013 |
+
"pass@4": 0.19758813267676884,
|
| 1014 |
+
"pass@8": 0.2284911534750015,
|
| 1015 |
+
"pass@16": 0.2603002938970115,
|
| 1016 |
+
"pass@32": 0.29249731296624343,
|
| 1017 |
+
"pass@64": 0.3260332407783438,
|
| 1018 |
+
"pass@128": 0.36253776435045315
|
| 1019 |
+
},
|
| 1020 |
+
"20": {
|
| 1021 |
+
"pass@1": 0.13072447447447447,
|
| 1022 |
+
"pass@2": 0.16936079780567978,
|
| 1023 |
+
"pass@4": 0.2094049935762534,
|
| 1024 |
+
"pass@8": 0.25098284669882537,
|
| 1025 |
+
"pass@16": 0.291417867530838,
|
| 1026 |
+
"pass@32": 0.32739810777438544,
|
| 1027 |
+
"pass@64": 0.35806392636422313,
|
| 1028 |
+
"pass@128": 0.3813813813813814
|
| 1029 |
+
}
|
| 1030 |
+
}
|
| 1031 |
+
}
|
| 1032 |
+
}
|
| 1033 |
+
},
|
| 1034 |
+
"total": {
|
| 1035 |
+
"answer_accuracy": 0.588914884868421,
|
| 1036 |
+
"avg_loss": 6.166780625293129,
|
| 1037 |
+
"count": 2432000,
|
| 1038 |
+
"validation_metrics": {
|
| 1039 |
+
"id": {},
|
| 1040 |
+
"ood": {}
|
| 1041 |
+
},
|
| 1042 |
+
"pass_at_k": {
|
| 1043 |
+
"pass@1": 0.588914884868421,
|
| 1044 |
+
"pass@2": 0.6227466328221948,
|
| 1045 |
+
"pass@4": 0.6499032629408014,
|
| 1046 |
+
"pass@8": 0.6734744359367607,
|
| 1047 |
+
"pass@16": 0.6946532134389145,
|
| 1048 |
+
"pass@32": 0.7139263397862728,
|
| 1049 |
+
"pass@64": 0.7317913186635674,
|
| 1050 |
+
"pass@128": 0.748578947368421
|
| 1051 |
+
},
|
| 1052 |
+
"per_op_pass_at_k": {
|
| 1053 |
+
"10": {
|
| 1054 |
+
"pass@1": 0.89534375,
|
| 1055 |
+
"pass@2": 0.9316516978346466,
|
| 1056 |
+
"pass@4": 0.9502444778777662,
|
| 1057 |
+
"pass@8": 0.9628981587488723,
|
| 1058 |
+
"pass@16": 0.9732652153333301,
|
| 1059 |
+
"pass@32": 0.9817272204905513,
|
| 1060 |
+
"pass@64": 0.9875005300252477,
|
| 1061 |
+
"pass@128": 0.991
|
| 1062 |
+
},
|
| 1063 |
+
"2": {
|
| 1064 |
+
"pass@1": 0.9994453125,
|
| 1065 |
+
"pass@2": 0.9998784448818898,
|
| 1066 |
+
"pass@4": 0.999987270247469,
|
| 1067 |
+
"pass@8": 0.9999998760353234,
|
| 1068 |
+
"pass@16": 0.9999999999955357,
|
| 1069 |
+
"pass@32": 1.0,
|
| 1070 |
+
"pass@64": 1.0,
|
| 1071 |
+
"pass@128": 1.0
|
| 1072 |
+
},
|
| 1073 |
+
"3": {
|
| 1074 |
+
"pass@1": 0.9896953125,
|
| 1075 |
+
"pass@2": 0.9956350885826775,
|
| 1076 |
+
"pass@4": 0.998029471128609,
|
| 1077 |
+
"pass@8": 0.9990296020970205,
|
| 1078 |
+
"pass@16": 0.9994722941030695,
|
| 1079 |
+
"pass@32": 0.999768854949753,
|
| 1080 |
+
"pass@64": 0.9999711811022791,
|
| 1081 |
+
"pass@128": 1.0
|
| 1082 |
+
},
|
| 1083 |
+
"4": {
|
| 1084 |
+
"pass@1": 0.9968125,
|
| 1085 |
+
"pass@2": 0.9986126968503938,
|
| 1086 |
+
"pass@4": 0.9994299414135731,
|
| 1087 |
+
"pass@8": 0.9998706652443888,
|
| 1088 |
+
"pass@16": 0.999993190320664,
|
| 1089 |
+
"pass@32": 0.9999999900668188,
|
| 1090 |
+
"pass@64": 0.9999999999999999,
|
| 1091 |
+
"pass@128": 1.0
|
| 1092 |
+
},
|
| 1093 |
+
"5": {
|
| 1094 |
+
"pass@1": 0.95453125,
|
| 1095 |
+
"pass@2": 0.9673741387795279,
|
| 1096 |
+
"pass@4": 0.9768552553430826,
|
| 1097 |
+
"pass@8": 0.9845504029004547,
|
| 1098 |
+
"pass@16": 0.9905860749032567,
|
| 1099 |
+
"pass@32": 0.9947039335217139,
|
| 1100 |
+
"pass@64": 0.9972231304095797,
|
| 1101 |
+
"pass@128": 0.999
|
| 1102 |
+
},
|
| 1103 |
+
"6": {
|
| 1104 |
+
"pass@1": 0.9755546875,
|
| 1105 |
+
"pass@2": 0.9871010088582685,
|
| 1106 |
+
"pass@4": 0.9931382349081366,
|
| 1107 |
+
"pass@8": 0.9961125829051054,
|
| 1108 |
+
"pass@16": 0.9972334916240602,
|
| 1109 |
+
"pass@32": 0.9976868579347262,
|
| 1110 |
+
"pass@64": 0.998251968426333,
|
| 1111 |
+
"pass@128": 0.999
|
| 1112 |
+
},
|
| 1113 |
+
"7": {
|
| 1114 |
+
"pass@1": 0.9665546875,
|
| 1115 |
+
"pass@2": 0.980099409448819,
|
| 1116 |
+
"pass@4": 0.9868899991563556,
|
| 1117 |
+
"pass@8": 0.9912036930431989,
|
| 1118 |
+
"pass@16": 0.9940644245074017,
|
| 1119 |
+
"pass@32": 0.9960585379187011,
|
| 1120 |
+
"pass@64": 0.9974804599031311,
|
| 1121 |
+
"pass@128": 0.998
|
| 1122 |
+
},
|
| 1123 |
+
"8": {
|
| 1124 |
+
"pass@1": 0.95003125,
|
| 1125 |
+
"pass@2": 0.9737233021653545,
|
| 1126 |
+
"pass@4": 0.984498448537683,
|
| 1127 |
+
"pass@8": 0.9902565507718185,
|
| 1128 |
+
"pass@16": 0.9939245919129133,
|
| 1129 |
+
"pass@32": 0.996586911336722,
|
| 1130 |
+
"pass@64": 0.998538493317924,
|
| 1131 |
+
"pass@128": 1.0
|
| 1132 |
+
},
|
| 1133 |
+
"9": {
|
| 1134 |
+
"pass@1": 0.93934375,
|
| 1135 |
+
"pass@2": 0.9719249507874034,
|
| 1136 |
+
"pass@4": 0.98470880455568,
|
| 1137 |
+
"pass@8": 0.990996795989665,
|
| 1138 |
+
"pass@16": 0.9945284354115372,
|
| 1139 |
+
"pass@32": 0.9963217850684021,
|
| 1140 |
+
"pass@64": 0.9974302167766392,
|
| 1141 |
+
"pass@128": 0.998
|
| 1142 |
+
},
|
| 1143 |
+
"11": {
|
| 1144 |
+
"pass@1": 0.7491953125,
|
| 1145 |
+
"pass@2": 0.8267459399606308,
|
| 1146 |
+
"pass@4": 0.8755285344956877,
|
| 1147 |
+
"pass@8": 0.907201192042703,
|
| 1148 |
+
"pass@16": 0.9291708873567505,
|
| 1149 |
+
"pass@32": 0.9454073394478061,
|
| 1150 |
+
"pass@64": 0.9574549244959281,
|
| 1151 |
+
"pass@128": 0.967
|
| 1152 |
+
},
|
| 1153 |
+
"12": {
|
| 1154 |
+
"pass@1": 0.42375,
|
| 1155 |
+
"pass@2": 0.5180041830708659,
|
| 1156 |
+
"pass@4": 0.593009113235845,
|
| 1157 |
+
"pass@8": 0.6523426553791513,
|
| 1158 |
+
"pass@16": 0.702357863892847,
|
| 1159 |
+
"pass@32": 0.745694824334505,
|
| 1160 |
+
"pass@64": 0.7831121214310477,
|
| 1161 |
+
"pass@128": 0.816
|
| 1162 |
+
},
|
| 1163 |
+
"13": {
|
| 1164 |
+
"pass@1": 0.2113984375,
|
| 1165 |
+
"pass@2": 0.25608120078740143,
|
| 1166 |
+
"pass@4": 0.3006886397637793,
|
| 1167 |
+
"pass@8": 0.3447306794463938,
|
| 1168 |
+
"pass@16": 0.38799260684503434,
|
| 1169 |
+
"pass@32": 0.43170338099033495,
|
| 1170 |
+
"pass@64": 0.4761056180149899,
|
| 1171 |
+
"pass@128": 0.519
|
| 1172 |
+
},
|
| 1173 |
+
"14": {
|
| 1174 |
+
"pass@1": 0.200171875,
|
| 1175 |
+
"pass@2": 0.2479451279527559,
|
| 1176 |
+
"pass@4": 0.29500759055118103,
|
| 1177 |
+
"pass@8": 0.34113887630208256,
|
| 1178 |
+
"pass@16": 0.38481813556379674,
|
| 1179 |
+
"pass@32": 0.4260044402977936,
|
| 1180 |
+
"pass@64": 0.4671482956865662,
|
| 1181 |
+
"pass@128": 0.51
|
| 1182 |
+
},
|
| 1183 |
+
"15": {
|
| 1184 |
+
"pass@1": 0.17846875,
|
| 1185 |
+
"pass@2": 0.23154035433070885,
|
| 1186 |
+
"pass@4": 0.28250203355830483,
|
| 1187 |
+
"pass@8": 0.3294688278958133,
|
| 1188 |
+
"pass@16": 0.3735511399431241,
|
| 1189 |
+
"pass@32": 0.4152404384047447,
|
| 1190 |
+
"pass@64": 0.4535175002619446,
|
| 1191 |
+
"pass@128": 0.485
|
| 1192 |
+
},
|
| 1193 |
+
"16": {
|
| 1194 |
+
"pass@1": 0.158390625,
|
| 1195 |
+
"pass@2": 0.1908997293307087,
|
| 1196 |
+
"pass@4": 0.22120489895013098,
|
| 1197 |
+
"pass@8": 0.2515841984680904,
|
| 1198 |
+
"pass@16": 0.2832809698127581,
|
| 1199 |
+
"pass@32": 0.3157377911008275,
|
| 1200 |
+
"pass@64": 0.3483624231356763,
|
| 1201 |
+
"pass@128": 0.383
|
| 1202 |
+
},
|
| 1203 |
+
"17": {
|
| 1204 |
+
"pass@1": 0.15778125,
|
| 1205 |
+
"pass@2": 0.19822810039370062,
|
| 1206 |
+
"pass@4": 0.23773755933633278,
|
| 1207 |
+
"pass@8": 0.2756691021575299,
|
| 1208 |
+
"pass@16": 0.31012296220189073,
|
| 1209 |
+
"pass@32": 0.34113294654797527,
|
| 1210 |
+
"pass@64": 0.370247222269346,
|
| 1211 |
+
"pass@128": 0.399
|
| 1212 |
+
},
|
| 1213 |
+
"18": {
|
| 1214 |
+
"pass@1": 0.1607265625,
|
| 1215 |
+
"pass@2": 0.1996240157480314,
|
| 1216 |
+
"pass@4": 0.23766353665166848,
|
| 1217 |
+
"pass@8": 0.27507361063539393,
|
| 1218 |
+
"pass@16": 0.31047573197015055,
|
| 1219 |
+
"pass@32": 0.342168030163979,
|
| 1220 |
+
"pass@64": 0.37123232750738133,
|
| 1221 |
+
"pass@128": 0.4
|
| 1222 |
+
},
|
| 1223 |
+
"19": {
|
| 1224 |
+
"pass@1": 0.142859375,
|
| 1225 |
+
"pass@2": 0.17847379429133842,
|
| 1226 |
+
"pass@4": 0.21176526481064853,
|
| 1227 |
+
"pass@8": 0.24360403095909056,
|
| 1228 |
+
"pass@16": 0.27449561265010364,
|
| 1229 |
+
"pass@32": 0.305123051282576,
|
| 1230 |
+
"pass@64": 0.3363755503535671,
|
| 1231 |
+
"pass@128": 0.369
|
| 1232 |
+
},
|
| 1233 |
+
"20": {
|
| 1234 |
+
"pass@1": 0.139328125,
|
| 1235 |
+
"pass@2": 0.17864283956692892,
|
| 1236 |
+
"pass@4": 0.2192729213535806,
|
| 1237 |
+
"pass@8": 0.26028278177620573,
|
| 1238 |
+
"pass@16": 0.2990774269909148,
|
| 1239 |
+
"pass@32": 0.33353412208103916,
|
| 1240 |
+
"pass@64": 0.3640830914901839,
|
| 1241 |
+
"pass@128": 0.39
|
| 1242 |
+
}
|
| 1243 |
+
},
|
| 1244 |
+
"per_op_accuracy": {
|
| 1245 |
+
"10": 0.89534375,
|
| 1246 |
+
"2": 0.9994453125,
|
| 1247 |
+
"3": 0.9896953125,
|
| 1248 |
+
"4": 0.9968125,
|
| 1249 |
+
"5": 0.95453125,
|
| 1250 |
+
"6": 0.9755546875,
|
| 1251 |
+
"7": 0.9665546875,
|
| 1252 |
+
"8": 0.95003125,
|
| 1253 |
+
"9": 0.93934375,
|
| 1254 |
+
"11": 0.7491953125,
|
| 1255 |
+
"12": 0.42375,
|
| 1256 |
+
"13": 0.2113984375,
|
| 1257 |
+
"14": 0.200171875,
|
| 1258 |
+
"15": 0.17846875,
|
| 1259 |
+
"16": 0.158390625,
|
| 1260 |
+
"17": 0.15778125,
|
| 1261 |
+
"18": 0.1607265625,
|
| 1262 |
+
"19": 0.142859375,
|
| 1263 |
+
"20": 0.139328125
|
| 1264 |
+
},
|
| 1265 |
+
"per_op_avg_response_len": {
|
| 1266 |
+
"10": 279.685734375,
|
| 1267 |
+
"2": 116.979234375,
|
| 1268 |
+
"3": 147.114546875,
|
| 1269 |
+
"4": 160.9594765625,
|
| 1270 |
+
"5": 176.0514453125,
|
| 1271 |
+
"6": 200.8557890625,
|
| 1272 |
+
"7": 225.0676796875,
|
| 1273 |
+
"8": 244.2956640625,
|
| 1274 |
+
"9": 259.9049921875,
|
| 1275 |
+
"11": 291.4343515625,
|
| 1276 |
+
"12": 288.3101484375,
|
| 1277 |
+
"13": 282.0749140625,
|
| 1278 |
+
"14": 284.6130234375,
|
| 1279 |
+
"15": 282.3583984375,
|
| 1280 |
+
"16": 284.9855,
|
| 1281 |
+
"17": 285.6167265625,
|
| 1282 |
+
"18": 284.2999609375,
|
| 1283 |
+
"19": 281.3561640625,
|
| 1284 |
+
"20": 283.4558515625
|
| 1285 |
+
},
|
| 1286 |
+
"per_op_avg_loss": {
|
| 1287 |
+
"10": 0.13990753173828124,
|
| 1288 |
+
"2": 0.15822406005859374,
|
| 1289 |
+
"3": 0.15319696044921874,
|
| 1290 |
+
"4": 0.1460938720703125,
|
| 1291 |
+
"5": 0.1487813720703125,
|
| 1292 |
+
"6": 0.14940606689453126,
|
| 1293 |
+
"7": 0.14932769775390625,
|
| 1294 |
+
"8": 0.14807330322265624,
|
| 1295 |
+
"9": 0.1509442138671875,
|
| 1296 |
+
"11": 0.1496517333984375,
|
| 1297 |
+
"12": 0.160320068359375,
|
| 1298 |
+
"13": 0.18829949951171876,
|
| 1299 |
+
"14": 0.2179671630859375,
|
| 1300 |
+
"15": 0.24814111328125,
|
| 1301 |
+
"16": 0.280107177734375,
|
| 1302 |
+
"17": 0.3107010498046875,
|
| 1303 |
+
"18": 0.3399879150390625,
|
| 1304 |
+
"19": 0.40024169921875,
|
| 1305 |
+
"20": 0.419079345703125
|
| 1306 |
+
},
|
| 1307 |
+
"per_op_length": {
|
| 1308 |
+
"10": 279.685734375,
|
| 1309 |
+
"2": 116.979234375,
|
| 1310 |
+
"3": 147.114546875,
|
| 1311 |
+
"4": 160.9594765625,
|
| 1312 |
+
"5": 176.0514453125,
|
| 1313 |
+
"6": 200.8557890625,
|
| 1314 |
+
"7": 225.0676796875,
|
| 1315 |
+
"8": 244.2956640625,
|
| 1316 |
+
"9": 259.9049921875,
|
| 1317 |
+
"11": 291.4343515625,
|
| 1318 |
+
"12": 288.3101484375,
|
| 1319 |
+
"13": 282.0749140625,
|
| 1320 |
+
"14": 284.6130234375,
|
| 1321 |
+
"15": 282.3583984375,
|
| 1322 |
+
"16": 284.9855,
|
| 1323 |
+
"17": 285.6167265625,
|
| 1324 |
+
"18": 284.2999609375,
|
| 1325 |
+
"19": 281.3561640625,
|
| 1326 |
+
"20": 283.4558515625
|
| 1327 |
+
},
|
| 1328 |
+
"per_op_loss": {
|
| 1329 |
+
"10": 0.13990753173828124,
|
| 1330 |
+
"2": 0.15822406005859374,
|
| 1331 |
+
"3": 0.15319696044921874,
|
| 1332 |
+
"4": 0.1460938720703125,
|
| 1333 |
+
"5": 0.1487813720703125,
|
| 1334 |
+
"6": 0.14940606689453126,
|
| 1335 |
+
"7": 0.14932769775390625,
|
| 1336 |
+
"8": 0.14807330322265624,
|
| 1337 |
+
"9": 0.1509442138671875,
|
| 1338 |
+
"11": 0.1496517333984375,
|
| 1339 |
+
"12": 0.160320068359375,
|
| 1340 |
+
"13": 0.18829949951171876,
|
| 1341 |
+
"14": 0.2179671630859375,
|
| 1342 |
+
"15": 0.24814111328125,
|
| 1343 |
+
"16": 0.280107177734375,
|
| 1344 |
+
"17": 0.3107010498046875,
|
| 1345 |
+
"18": 0.3399879150390625,
|
| 1346 |
+
"19": 0.40024169921875,
|
| 1347 |
+
"20": 0.419079345703125
|
| 1348 |
+
},
|
| 1349 |
+
"per_template": {
|
| 1350 |
+
"crazy_zootopia": {
|
| 1351 |
+
"count": 809728,
|
| 1352 |
+
"correct": 477128,
|
| 1353 |
+
"answer_accuracy": 0.5892447834334492,
|
| 1354 |
+
"avg_response_len": 235.475637498024,
|
| 1355 |
+
"resp_tokens_sum": 190671217,
|
| 1356 |
+
"pass_at_k": {
|
| 1357 |
+
"pass@1": 0.5892447834334492,
|
| 1358 |
+
"pass@2": 0.6242494417489666,
|
| 1359 |
+
"pass@4": 0.6517067209785661,
|
| 1360 |
+
"pass@8": 0.6752650274111465,
|
| 1361 |
+
"pass@16": 0.6966098480320178,
|
| 1362 |
+
"pass@32": 0.7161446042348242,
|
| 1363 |
+
"pass@64": 0.7340453705919688,
|
| 1364 |
+
"pass@128": 0.7510275055327221
|
| 1365 |
+
},
|
| 1366 |
+
"per_op_pass_at_k": {
|
| 1367 |
+
"10": {
|
| 1368 |
+
"pass@1": 0.8994976032448377,
|
| 1369 |
+
"pass@2": 0.9366747090795067,
|
| 1370 |
+
"pass@4": 0.954640098361598,
|
| 1371 |
+
"pass@8": 0.9671935395338649,
|
| 1372 |
+
"pass@16": 0.9780409476989385,
|
| 1373 |
+
"pass@32": 0.9873672705205916,
|
| 1374 |
+
"pass@64": 0.9931124421272916,
|
| 1375 |
+
"pass@128": 0.9941002949852508
|
| 1376 |
+
},
|
| 1377 |
+
"2": {
|
| 1378 |
+
"pass@1": 0.9997322819314641,
|
| 1379 |
+
"pass@2": 0.9999915679348491,
|
| 1380 |
+
"pass@4": 0.9999999897793149,
|
| 1381 |
+
"pass@8": 1.0,
|
| 1382 |
+
"pass@16": 1.0,
|
| 1383 |
+
"pass@32": 1.0,
|
| 1384 |
+
"pass@64": 1.0,
|
| 1385 |
+
"pass@128": 1.0
|
| 1386 |
+
},
|
| 1387 |
+
"3": {
|
| 1388 |
+
"pass@1": 0.9875525611620795,
|
| 1389 |
+
"pass@2": 0.9937483445303281,
|
| 1390 |
+
"pass@4": 0.9960841566249173,
|
| 1391 |
+
"pass@8": 0.9973945614382809,
|
| 1392 |
+
"pass@16": 0.9984052318072489,
|
| 1393 |
+
"pass@32": 0.9992931754002767,
|
| 1394 |
+
"pass@64": 0.9999118688143109,
|
| 1395 |
+
"pass@128": 1.0
|
| 1396 |
+
},
|
| 1397 |
+
"4": {
|
| 1398 |
+
"pass@1": 0.996337890625,
|
| 1399 |
+
"pass@2": 0.9982602577509845,
|
| 1400 |
+
"pass@4": 0.9992694307742784,
|
| 1401 |
+
"pass@8": 0.9998455780548049,
|
| 1402 |
+
"pass@16": 0.9999940908757206,
|
| 1403 |
+
"pass@32": 0.9999999967265157,
|
| 1404 |
+
"pass@64": 1.0,
|
| 1405 |
+
"pass@128": 1.0
|
| 1406 |
+
},
|
| 1407 |
+
"5": {
|
| 1408 |
+
"pass@1": 0.9481150793650793,
|
| 1409 |
+
"pass@2": 0.9641533089613797,
|
| 1410 |
+
"pass@4": 0.9757381440415184,
|
| 1411 |
+
"pass@8": 0.9837977641761237,
|
| 1412 |
+
"pass@16": 0.9891567790393069,
|
| 1413 |
+
"pass@32": 0.9924331098404072,
|
| 1414 |
+
"pass@64": 0.9948057827917357,
|
| 1415 |
+
"pass@128": 0.9968253968253968
|
| 1416 |
+
},
|
| 1417 |
+
"6": {
|
| 1418 |
+
"pass@1": 0.9665746631736527,
|
| 1419 |
+
"pass@2": 0.9810815131547932,
|
| 1420 |
+
"pass@4": 0.9889092237347574,
|
| 1421 |
+
"pass@8": 0.992817054998713,
|
| 1422 |
+
"pass@16": 0.9942118482404367,
|
| 1423 |
+
"pass@32": 0.9947566055669427,
|
| 1424 |
+
"pass@64": 0.9955089818359227,
|
| 1425 |
+
"pass@128": 0.9970059880239521
|
| 1426 |
+
},
|
| 1427 |
+
"7": {
|
| 1428 |
+
"pass@1": 0.9575397559171598,
|
| 1429 |
+
"pass@2": 0.9706686361412663,
|
| 1430 |
+
"pass@4": 0.9781720887884576,
|
| 1431 |
+
"pass@8": 0.9836457175352227,
|
| 1432 |
+
"pass@16": 0.9877211930993773,
|
| 1433 |
+
"pass@32": 0.991030454111008,
|
| 1434 |
+
"pass@64": 0.9934560055493304,
|
| 1435 |
+
"pass@128": 0.9940828402366864
|
| 1436 |
+
},
|
| 1437 |
+
"8": {
|
| 1438 |
+
"pass@1": 0.9534755608974359,
|
| 1439 |
+
"pass@2": 0.9758759684786995,
|
| 1440 |
+
"pass@4": 0.9847553208493165,
|
| 1441 |
+
"pass@8": 0.9897007291187125,
|
| 1442 |
+
"pass@16": 0.9935694000922215,
|
| 1443 |
+
"pass@32": 0.9965151373391712,
|
| 1444 |
+
"pass@64": 0.998300039303945,
|
| 1445 |
+
"pass@128": 1.0
|
| 1446 |
+
},
|
| 1447 |
+
"9": {
|
| 1448 |
+
"pass@1": 0.9408450704225352,
|
| 1449 |
+
"pass@2": 0.9764160751913055,
|
| 1450 |
+
"pass@4": 0.9897490211610868,
|
| 1451 |
+
"pass@8": 0.9954928597779902,
|
| 1452 |
+
"pass@16": 0.9986146363237696,
|
| 1453 |
+
"pass@32": 0.9998472651017836,
|
| 1454 |
+
"pass@64": 0.9999990904114461,
|
| 1455 |
+
"pass@128": 1.0
|
| 1456 |
+
},
|
| 1457 |
+
"11": {
|
| 1458 |
+
"pass@1": 0.7521689093484419,
|
| 1459 |
+
"pass@2": 0.8267172826838576,
|
| 1460 |
+
"pass@4": 0.8749963240253604,
|
| 1461 |
+
"pass@8": 0.9072539747181511,
|
| 1462 |
+
"pass@16": 0.9305891455160197,
|
| 1463 |
+
"pass@32": 0.9482171914771189,
|
| 1464 |
+
"pass@64": 0.9598296757598728,
|
| 1465 |
+
"pass@128": 0.9660056657223796
|
| 1466 |
+
},
|
| 1467 |
+
"12": {
|
| 1468 |
+
"pass@1": 0.4268626412429379,
|
| 1469 |
+
"pass@2": 0.5226548250589441,
|
| 1470 |
+
"pass@4": 0.5947451512946471,
|
| 1471 |
+
"pass@8": 0.6499540700619184,
|
| 1472 |
+
"pass@16": 0.697671407935311,
|
| 1473 |
+
"pass@32": 0.7391764349175001,
|
| 1474 |
+
"pass@64": 0.7728700105439386,
|
| 1475 |
+
"pass@128": 0.8022598870056498
|
| 1476 |
+
},
|
| 1477 |
+
"13": {
|
| 1478 |
+
"pass@1": 0.226048197492163,
|
| 1479 |
+
"pass@2": 0.2745025516500875,
|
| 1480 |
+
"pass@4": 0.32170087379359735,
|
| 1481 |
+
"pass@8": 0.36726090847720233,
|
| 1482 |
+
"pass@16": 0.4118837384913241,
|
| 1483 |
+
"pass@32": 0.4577964268716136,
|
| 1484 |
+
"pass@64": 0.5060004900301981,
|
| 1485 |
+
"pass@128": 0.554858934169279
|
| 1486 |
+
},
|
| 1487 |
+
"14": {
|
| 1488 |
+
"pass@1": 0.1970404984423676,
|
| 1489 |
+
"pass@2": 0.2447659871955257,
|
| 1490 |
+
"pass@4": 0.2905214605183697,
|
| 1491 |
+
"pass@8": 0.33432116638118264,
|
| 1492 |
+
"pass@16": 0.37689919457954874,
|
| 1493 |
+
"pass@32": 0.41849874775311363,
|
| 1494 |
+
"pass@64": 0.46201871752633594,
|
| 1495 |
+
"pass@128": 0.5109034267912772
|
| 1496 |
+
},
|
| 1497 |
+
"15": {
|
| 1498 |
+
"pass@1": 0.190774024566474,
|
| 1499 |
+
"pass@2": 0.24494681910245306,
|
| 1500 |
+
"pass@4": 0.29680882700356104,
|
| 1501 |
+
"pass@8": 0.3440605324830605,
|
| 1502 |
+
"pass@16": 0.38846742937996726,
|
| 1503 |
+
"pass@32": 0.43008799604881653,
|
| 1504 |
+
"pass@64": 0.4654618905817254,
|
| 1505 |
+
"pass@128": 0.4913294797687861
|
| 1506 |
+
},
|
| 1507 |
+
"16": {
|
| 1508 |
+
"pass@1": 0.1630796370967742,
|
| 1509 |
+
"pass@2": 0.1964297053594107,
|
| 1510 |
+
"pass@4": 0.23033826426938572,
|
| 1511 |
+
"pass@8": 0.2660781043146322,
|
| 1512 |
+
"pass@16": 0.3019958633560044,
|
| 1513 |
+
"pass@32": 0.33569879011745574,
|
| 1514 |
+
"pass@64": 0.3686862876847773,
|
| 1515 |
+
"pass@128": 0.4064516129032258
|
| 1516 |
+
},
|
| 1517 |
+
"17": {
|
| 1518 |
+
"pass@1": 0.1676300578034682,
|
| 1519 |
+
"pass@2": 0.20699551397296437,
|
| 1520 |
+
"pass@4": 0.2408987041359715,
|
| 1521 |
+
"pass@8": 0.271017564290959,
|
| 1522 |
+
"pass@16": 0.29876652985892266,
|
| 1523 |
+
"pass@32": 0.3264747152113181,
|
| 1524 |
+
"pass@64": 0.3549548508714773,
|
| 1525 |
+
"pass@128": 0.38439306358381503
|
| 1526 |
+
},
|
| 1527 |
+
"18": {
|
| 1528 |
+
"pass@1": 0.1616517857142857,
|
| 1529 |
+
"pass@2": 0.19595648200224966,
|
| 1530 |
+
"pass@4": 0.23106420322459695,
|
| 1531 |
+
"pass@8": 0.26888622832851616,
|
| 1532 |
+
"pass@16": 0.3071732341417159,
|
| 1533 |
+
"pass@32": 0.3420263056744111,
|
| 1534 |
+
"pass@64": 0.3714714335108666,
|
| 1535 |
+
"pass@128": 0.39714285714285713
|
| 1536 |
+
},
|
| 1537 |
+
"19": {
|
| 1538 |
+
"pass@1": 0.15040822072072071,
|
| 1539 |
+
"pass@2": 0.1915057281691139,
|
| 1540 |
+
"pass@4": 0.2273034600967671,
|
| 1541 |
+
"pass@8": 0.2598221642368353,
|
| 1542 |
+
"pass@16": 0.2905735616301428,
|
| 1543 |
+
"pass@32": 0.32042698971733125,
|
| 1544 |
+
"pass@64": 0.35124146512270843,
|
| 1545 |
+
"pass@128": 0.3843843843843844
|
| 1546 |
+
},
|
| 1547 |
+
"20": {
|
| 1548 |
+
"pass@1": 0.15052552552552553,
|
| 1549 |
+
"pass@2": 0.18885223806483653,
|
| 1550 |
+
"pass@4": 0.22942468621602477,
|
| 1551 |
+
"pass@8": 0.26979999128432536,
|
| 1552 |
+
"pass@16": 0.30689533475643643,
|
| 1553 |
+
"pass@32": 0.3397581402934893,
|
| 1554 |
+
"pass@64": 0.370991289408613,
|
| 1555 |
+
"pass@128": 0.4024024024024024
|
| 1556 |
+
}
|
| 1557 |
+
}
|
| 1558 |
+
},
|
| 1559 |
+
"teachers_in_school": {
|
| 1560 |
+
"count": 821120,
|
| 1561 |
+
"correct": 483803,
|
| 1562 |
+
"answer_accuracy": 0.5891988990646921,
|
| 1563 |
+
"avg_response_len": 242.341766124318,
|
| 1564 |
+
"resp_tokens_sum": 198991671,
|
| 1565 |
+
"pass_at_k": {
|
| 1566 |
+
"pass@1": 0.5891988990646921,
|
| 1567 |
+
"pass@2": 0.6227068003142299,
|
| 1568 |
+
"pass@4": 0.650107249088997,
|
| 1569 |
+
"pass@8": 0.6741994105674554,
|
| 1570 |
+
"pass@16": 0.6956359816626693,
|
| 1571 |
+
"pass@32": 0.7149534992963424,
|
| 1572 |
+
"pass@64": 0.7325456550204769,
|
| 1573 |
+
"pass@128": 0.7480904130943102
|
| 1574 |
+
},
|
| 1575 |
+
"per_op_pass_at_k": {
|
| 1576 |
+
"10": {
|
| 1577 |
+
"pass@1": 0.8878930214723927,
|
| 1578 |
+
"pass@2": 0.9240016333751996,
|
| 1579 |
+
"pass@4": 0.9427751138086263,
|
| 1580 |
+
"pass@8": 0.9559837013558444,
|
| 1581 |
+
"pass@16": 0.9669589357176731,
|
| 1582 |
+
"pass@32": 0.9757400698048759,
|
| 1583 |
+
"pass@64": 0.9820426961144421,
|
| 1584 |
+
"pass@128": 0.9877300613496932
|
| 1585 |
+
},
|
| 1586 |
+
"2": {
|
| 1587 |
+
"pass@1": 0.9987177051671733,
|
| 1588 |
+
"pass@2": 0.9996395064978579,
|
| 1589 |
+
"pass@4": 0.9999613177152248,
|
| 1590 |
+
"pass@8": 0.9999996232076699,
|
| 1591 |
+
"pass@16": 0.9999999999864305,
|
| 1592 |
+
"pass@32": 1.0,
|
| 1593 |
+
"pass@64": 1.0,
|
| 1594 |
+
"pass@128": 1.0
|
| 1595 |
+
},
|
| 1596 |
+
"3": {
|
| 1597 |
+
"pass@1": 0.9907670454545454,
|
| 1598 |
+
"pass@2": 0.9960163892865667,
|
| 1599 |
+
"pass@4": 0.9985778993534897,
|
| 1600 |
+
"pass@8": 0.9996915957072215,
|
| 1601 |
+
"pass@16": 0.9999815253902985,
|
| 1602 |
+
"pass@32": 0.99999995938087,
|
| 1603 |
+
"pass@64": 0.9999999999999987,
|
| 1604 |
+
"pass@128": 1.0
|
| 1605 |
+
},
|
| 1606 |
+
"4": {
|
| 1607 |
+
"pass@1": 0.9982664571005917,
|
| 1608 |
+
"pass@2": 0.9998132687648512,
|
| 1609 |
+
"pass@4": 0.999995557138198,
|
| 1610 |
+
"pass@8": 0.9999999967656203,
|
| 1611 |
+
"pass@16": 0.9999999999999998,
|
| 1612 |
+
"pass@32": 1.0,
|
| 1613 |
+
"pass@64": 1.0,
|
| 1614 |
+
"pass@128": 1.0
|
| 1615 |
+
},
|
| 1616 |
+
"5": {
|
| 1617 |
+
"pass@1": 0.9600317028985508,
|
| 1618 |
+
"pass@2": 0.9691975493552438,
|
| 1619 |
+
"pass@4": 0.9763000869456536,
|
| 1620 |
+
"pass@8": 0.9828931121195829,
|
| 1621 |
+
"pass@16": 0.989036439654314,
|
| 1622 |
+
"pass@32": 0.9944838684919953,
|
| 1623 |
+
"pass@64": 0.9981653755234783,
|
| 1624 |
+
"pass@128": 1.0
|
| 1625 |
+
},
|
| 1626 |
+
"6": {
|
| 1627 |
+
"pass@1": 0.9823379297994269,
|
| 1628 |
+
"pass@2": 0.9910194058389551,
|
| 1629 |
+
"pass@4": 0.9946701218221643,
|
| 1630 |
+
"pass@8": 0.9965445299840145,
|
| 1631 |
+
"pass@16": 0.9976712739922713,
|
| 1632 |
+
"pass@32": 0.9983904225804993,
|
| 1633 |
+
"pass@64": 0.9992893080034889,
|
| 1634 |
+
"pass@128": 1.0
|
| 1635 |
+
},
|
| 1636 |
+
"7": {
|
| 1637 |
+
"pass@1": 0.9681855130057804,
|
| 1638 |
+
"pass@2": 0.9832421146056164,
|
| 1639 |
+
"pass@4": 0.9914642009163593,
|
| 1640 |
+
"pass@8": 0.9964758591421767,
|
| 1641 |
+
"pass@16": 0.9990374180123244,
|
| 1642 |
+
"pass@32": 0.9999126056145744,
|
| 1643 |
+
"pass@64": 0.9999997855847184,
|
| 1644 |
+
"pass@128": 1.0
|
| 1645 |
+
},
|
| 1646 |
+
"8": {
|
| 1647 |
+
"pass@1": 0.9455765845070423,
|
| 1648 |
+
"pass@2": 0.9712158284351782,
|
| 1649 |
+
"pass@4": 0.9835400283591312,
|
| 1650 |
+
"pass@8": 0.9910390348371692,
|
| 1651 |
+
"pass@16": 0.9955726997113149,
|
| 1652 |
+
"pass@32": 0.9980539040490879,
|
| 1653 |
+
"pass@64": 0.9995741614459047,
|
| 1654 |
+
"pass@128": 1.0
|
| 1655 |
+
},
|
| 1656 |
+
"9": {
|
| 1657 |
+
"pass@1": 0.9390437874251497,
|
| 1658 |
+
"pass@2": 0.9670264539818006,
|
| 1659 |
+
"pass@4": 0.9783135702722786,
|
| 1660 |
+
"pass@8": 0.9840906736702117,
|
| 1661 |
+
"pass@16": 0.9879928605789021,
|
| 1662 |
+
"pass@32": 0.9908513468886352,
|
| 1663 |
+
"pass@64": 0.9930496212972972,
|
| 1664 |
+
"pass@128": 0.9940119760479041
|
| 1665 |
+
},
|
| 1666 |
+
"11": {
|
| 1667 |
+
"pass@1": 0.7309864457831325,
|
| 1668 |
+
"pass@2": 0.811214839673655,
|
| 1669 |
+
"pass@4": 0.8645121111555325,
|
| 1670 |
+
"pass@8": 0.9001346785530842,
|
| 1671 |
+
"pass@16": 0.9235781504819824,
|
| 1672 |
+
"pass@32": 0.939017807747773,
|
| 1673 |
+
"pass@64": 0.9485292552001391,
|
| 1674 |
+
"pass@128": 0.9548192771084337
|
| 1675 |
+
},
|
| 1676 |
+
"12": {
|
| 1677 |
+
"pass@1": 0.439042907523511,
|
| 1678 |
+
"pass@2": 0.5317378835188704,
|
| 1679 |
+
"pass@4": 0.6075961422729685,
|
| 1680 |
+
"pass@8": 0.6683062360710545,
|
| 1681 |
+
"pass@16": 0.7177272091161964,
|
| 1682 |
+
"pass@32": 0.7598458853246168,
|
| 1683 |
+
"pass@64": 0.7942021269976,
|
| 1684 |
+
"pass@128": 0.8213166144200627
|
| 1685 |
+
},
|
| 1686 |
+
"13": {
|
| 1687 |
+
"pass@1": 0.19227065826330533,
|
| 1688 |
+
"pass@2": 0.23474754074858276,
|
| 1689 |
+
"pass@4": 0.27791213361985206,
|
| 1690 |
+
"pass@8": 0.32123267772057174,
|
| 1691 |
+
"pass@16": 0.36547236780648024,
|
| 1692 |
+
"pass@32": 0.412591392141311,
|
| 1693 |
+
"pass@64": 0.46083134462740805,
|
| 1694 |
+
"pass@128": 0.5042016806722689
|
| 1695 |
+
},
|
| 1696 |
+
"14": {
|
| 1697 |
+
"pass@1": 0.20837902046783627,
|
| 1698 |
+
"pass@2": 0.2522699670764838,
|
| 1699 |
+
"pass@4": 0.2964683594923442,
|
| 1700 |
+
"pass@8": 0.3416618793696011,
|
| 1701 |
+
"pass@16": 0.3841336779597966,
|
| 1702 |
+
"pass@32": 0.42375806001618826,
|
| 1703 |
+
"pass@64": 0.4632207639904677,
|
| 1704 |
+
"pass@128": 0.5029239766081871
|
| 1705 |
+
},
|
| 1706 |
+
"15": {
|
| 1707 |
+
"pass@1": 0.19093276515151514,
|
| 1708 |
+
"pass@2": 0.24199400501073715,
|
| 1709 |
+
"pass@4": 0.2891956014020975,
|
| 1710 |
+
"pass@8": 0.3326345282383242,
|
| 1711 |
+
"pass@16": 0.37366558323041027,
|
| 1712 |
+
"pass@32": 0.4128573661812689,
|
| 1713 |
+
"pass@64": 0.4483166035224402,
|
| 1714 |
+
"pass@128": 0.4727272727272727
|
| 1715 |
+
},
|
| 1716 |
+
"16": {
|
| 1717 |
+
"pass@1": 0.15642806267806267,
|
| 1718 |
+
"pass@2": 0.1904278691926329,
|
| 1719 |
+
"pass@4": 0.22132350069489173,
|
| 1720 |
+
"pass@8": 0.251268169779741,
|
| 1721 |
+
"pass@16": 0.28180434335829546,
|
| 1722 |
+
"pass@32": 0.3122157586188942,
|
| 1723 |
+
"pass@64": 0.34211985927431315,
|
| 1724 |
+
"pass@128": 0.3732193732193732
|
| 1725 |
+
},
|
| 1726 |
+
"17": {
|
| 1727 |
+
"pass@1": 0.16779891304347827,
|
| 1728 |
+
"pass@2": 0.21377104526336374,
|
| 1729 |
+
"pass@4": 0.2616579632708955,
|
| 1730 |
+
"pass@8": 0.3084358591590647,
|
| 1731 |
+
"pass@16": 0.3485515761094292,
|
| 1732 |
+
"pass@32": 0.38192734451252297,
|
| 1733 |
+
"pass@64": 0.4116145438455866,
|
| 1734 |
+
"pass@128": 0.43788819875776397
|
| 1735 |
+
},
|
| 1736 |
+
"18": {
|
| 1737 |
+
"pass@1": 0.1518612132352941,
|
| 1738 |
+
"pass@2": 0.1958187384205651,
|
| 1739 |
+
"pass@4": 0.23828893419572547,
|
| 1740 |
+
"pass@8": 0.27971765090438966,
|
| 1741 |
+
"pass@16": 0.31909231139592203,
|
| 1742 |
+
"pass@32": 0.3541919542192856,
|
| 1743 |
+
"pass@64": 0.3879892602530647,
|
| 1744 |
+
"pass@128": 0.4235294117647059
|
| 1745 |
+
},
|
| 1746 |
+
"19": {
|
| 1747 |
+
"pass@1": 0.14004371279761904,
|
| 1748 |
+
"pass@2": 0.17627703763592056,
|
| 1749 |
+
"pass@4": 0.21033196631671033,
|
| 1750 |
+
"pass@8": 0.24241868591666452,
|
| 1751 |
+
"pass@16": 0.2725452956766527,
|
| 1752 |
+
"pass@32": 0.3023936104609465,
|
| 1753 |
+
"pass@64": 0.331830773125219,
|
| 1754 |
+
"pass@128": 0.3601190476190476
|
| 1755 |
+
},
|
| 1756 |
+
"20": {
|
| 1757 |
+
"pass@1": 0.1367421407185629,
|
| 1758 |
+
"pass@2": 0.17771825934744678,
|
| 1759 |
+
"pass@4": 0.21898993408009634,
|
| 1760 |
+
"pass@8": 0.260066157867715,
|
| 1761 |
+
"pass@16": 0.2989195527821917,
|
| 1762 |
+
"pass@32": 0.3334463816599912,
|
| 1763 |
+
"pass@64": 0.3631967204725436,
|
| 1764 |
+
"pass@128": 0.38622754491017963
|
| 1765 |
+
}
|
| 1766 |
+
}
|
| 1767 |
+
},
|
| 1768 |
+
"movie_festival_awards": {
|
| 1769 |
+
"count": 801152,
|
| 1770 |
+
"correct": 471310,
|
| 1771 |
+
"answer_accuracy": 0.5882903618788944,
|
| 1772 |
+
"avg_response_len": 258.0569242790382,
|
| 1773 |
+
"resp_tokens_sum": 206742821,
|
| 1774 |
+
"pass_at_k": {
|
| 1775 |
+
"pass@1": 0.5882903618788944,
|
| 1776 |
+
"pass@2": 0.6212685622467475,
|
| 1777 |
+
"pass@4": 0.6478714293112718,
|
| 1778 |
+
"pass@8": 0.6709216329453926,
|
| 1779 |
+
"pass@16": 0.6916683710373397,
|
| 1780 |
+
"pass@32": 0.7106315691905148,
|
| 1781 |
+
"pass@64": 0.728740000525103,
|
| 1782 |
+
"pass@128": 0.7466048889598977
|
| 1783 |
+
},
|
| 1784 |
+
"per_op_pass_at_k": {
|
| 1785 |
+
"10": {
|
| 1786 |
+
"pass@1": 0.8983908582089553,
|
| 1787 |
+
"pass@2": 0.9340132506757551,
|
| 1788 |
+
"pass@4": 0.9530650669599133,
|
| 1789 |
+
"pass@8": 0.9652801856862316,
|
| 1790 |
+
"pass@16": 0.9745693164759084,
|
| 1791 |
+
"pass@32": 0.9818461284408381,
|
| 1792 |
+
"pass@64": 0.9871328155545905,
|
| 1793 |
+
"pass@128": 0.991044776119403
|
| 1794 |
+
},
|
| 1795 |
+
"2": {
|
| 1796 |
+
"pass@1": 0.9998660714285714,
|
| 1797 |
+
"pass@2": 0.9999992969628797,
|
| 1798 |
+
"pass@4": 1.0,
|
| 1799 |
+
"pass@8": 1.0,
|
| 1800 |
+
"pass@16": 1.0,
|
| 1801 |
+
"pass@32": 1.0,
|
| 1802 |
+
"pass@64": 1.0,
|
| 1803 |
+
"pass@128": 1.0
|
| 1804 |
+
},
|
| 1805 |
+
"3": {
|
| 1806 |
+
"pass@1": 0.9907069970845481,
|
| 1807 |
+
"pass@2": 0.9970669721769471,
|
| 1808 |
+
"pass@4": 0.9993563997831172,
|
| 1809 |
+
"pass@8": 0.9999514691641971,
|
| 1810 |
+
"pass@16": 0.9999996499221584,
|
| 1811 |
+
"pass@32": 0.9999999999946803,
|
| 1812 |
+
"pass@64": 1.0,
|
| 1813 |
+
"pass@128": 1.0
|
| 1814 |
+
},
|
| 1815 |
+
"4": {
|
| 1816 |
+
"pass@1": 0.9958196271929824,
|
| 1817 |
+
"pass@2": 0.9977559342911083,
|
| 1818 |
+
"pass@4": 0.9990211264710332,
|
| 1819 |
+
"pass@8": 0.9997663197662907,
|
| 1820 |
+
"pass@16": 0.9999856176620865,
|
| 1821 |
+
"pass@32": 0.9999999740185194,
|
| 1822 |
+
"pass@64": 0.9999999999999997,
|
| 1823 |
+
"pass@128": 1.0
|
| 1824 |
+
},
|
| 1825 |
+
"5": {
|
| 1826 |
+
"pass@1": 0.9548943014705882,
|
| 1827 |
+
"pass@2": 0.9685079174386292,
|
| 1828 |
+
"pass@4": 0.9784535587463331,
|
| 1829 |
+
"pass@8": 0.9869293632462349,
|
| 1830 |
+
"pass@16": 0.9934826994856965,
|
| 1831 |
+
"pass@32": 0.9970310861536675,
|
| 1832 |
+
"pass@64": 0.9985066302193607,
|
| 1833 |
+
"pass@128": 1.0
|
| 1834 |
+
},
|
| 1835 |
+
"6": {
|
| 1836 |
+
"pass@1": 0.9775483044164038,
|
| 1837 |
+
"pass@2": 0.9891293716932861,
|
| 1838 |
+
"pass@4": 0.9959075131381444,
|
| 1839 |
+
"pass@8": 0.9991092920224423,
|
| 1840 |
+
"pass@16": 0.9999352040645176,
|
| 1841 |
+
"pass@32": 0.9999996662295679,
|
| 1842 |
+
"pass@64": 0.9999999999997393,
|
| 1843 |
+
"pass@128": 1.0
|
| 1844 |
+
},
|
| 1845 |
+
"7": {
|
| 1846 |
+
"pass@1": 0.9744115901898734,
|
| 1847 |
+
"pass@2": 0.9867456923402768,
|
| 1848 |
+
"pass@4": 0.9912063912303684,
|
| 1849 |
+
"pass@8": 0.9935151685224703,
|
| 1850 |
+
"pass@16": 0.9954041601504686,
|
| 1851 |
+
"pass@32": 0.9972167179953726,
|
| 1852 |
+
"pass@64": 0.9990265956175474,
|
| 1853 |
+
"pass@128": 1.0
|
| 1854 |
+
},
|
| 1855 |
+
"8": {
|
| 1856 |
+
"pass@1": 0.9515531156156156,
|
| 1857 |
+
"pass@2": 0.9743795222387744,
|
| 1858 |
+
"pass@4": 0.9852795146102226,
|
| 1859 |
+
"pass@8": 0.9899431408996546,
|
| 1860 |
+
"pass@16": 0.9925003924523234,
|
| 1861 |
+
"pass@32": 0.9950902478963195,
|
| 1862 |
+
"pass@64": 0.9976578190444356,
|
| 1863 |
+
"pass@128": 1.0
|
| 1864 |
+
},
|
| 1865 |
+
"9": {
|
| 1866 |
+
"pass@1": 0.9379521704180064,
|
| 1867 |
+
"pass@2": 0.9720591912043948,
|
| 1868 |
+
"pass@4": 0.9858236963747689,
|
| 1869 |
+
"pass@8": 0.9932814976290268,
|
| 1870 |
+
"pass@16": 0.9968830356374474,
|
| 1871 |
+
"pass@32": 0.9981725276413653,
|
| 1872 |
+
"pass@64": 0.9992024635603814,
|
| 1873 |
+
"pass@128": 1.0
|
| 1874 |
+
},
|
| 1875 |
+
"11": {
|
| 1876 |
+
"pass@1": 0.7650545634920635,
|
| 1877 |
+
"pass@2": 0.8431473409573809,
|
| 1878 |
+
"pass@4": 0.8877359086066622,
|
| 1879 |
+
"pass@8": 0.9145899228176874,
|
| 1880 |
+
"pass@16": 0.9334761048558039,
|
| 1881 |
+
"pass@32": 0.9489928847114996,
|
| 1882 |
+
"pass@64": 0.9642010673849086,
|
| 1883 |
+
"pass@128": 0.9809523809523809
|
| 1884 |
+
},
|
| 1885 |
+
"12": {
|
| 1886 |
+
"pass@1": 0.4054615825688073,
|
| 1887 |
+
"pass@2": 0.49957183534397626,
|
| 1888 |
+
"pass@4": 0.5768995727598271,
|
| 1889 |
+
"pass@8": 0.639355428961972,
|
| 1890 |
+
"pass@16": 0.6924379381519293,
|
| 1891 |
+
"pass@32": 0.7389465717283092,
|
| 1892 |
+
"pass@64": 0.7833812207530858,
|
| 1893 |
+
"pass@128": 0.8256880733944955
|
| 1894 |
+
},
|
| 1895 |
+
"13": {
|
| 1896 |
+
"pass@1": 0.21805073302469136,
|
| 1897 |
+
"pass@2": 0.2614506628511712,
|
| 1898 |
+
"pass@4": 0.30509700407819385,
|
| 1899 |
+
"pass@8": 0.34843945585161107,
|
| 1900 |
+
"pass@16": 0.3892841325907048,
|
| 1901 |
+
"pass@32": 0.42707158587605587,
|
| 1902 |
+
"pass@64": 0.46350207303509766,
|
| 1903 |
+
"pass@128": 0.5
|
| 1904 |
+
},
|
| 1905 |
+
"14": {
|
| 1906 |
+
"pass@1": 0.19482566765578635,
|
| 1907 |
+
"pass@2": 0.24658432440010283,
|
| 1908 |
+
"pass@4": 0.2977982871762691,
|
| 1909 |
+
"pass@8": 0.34710213397424194,
|
| 1910 |
+
"pass@16": 0.39305571585018145,
|
| 1911 |
+
"pass@32": 0.4354334888531387,
|
| 1912 |
+
"pass@64": 0.4760201367236571,
|
| 1913 |
+
"pass@128": 0.516320474777448
|
| 1914 |
+
},
|
| 1915 |
+
"15": {
|
| 1916 |
+
"pass@1": 0.15263310185185186,
|
| 1917 |
+
"pass@2": 0.20657633724603863,
|
| 1918 |
+
"pass@4": 0.26040626837154607,
|
| 1919 |
+
"pass@8": 0.31066200412971595,
|
| 1920 |
+
"pass@16": 0.3575054534309268,
|
| 1921 |
+
"pass@32": 0.40181191645690056,
|
| 1922 |
+
"pass@64": 0.4460592807353767,
|
| 1923 |
+
"pass@128": 0.49074074074074076
|
| 1924 |
+
},
|
| 1925 |
+
"16": {
|
| 1926 |
+
"pass@1": 0.15613477138643067,
|
| 1927 |
+
"pass@2": 0.1863313822497852,
|
| 1928 |
+
"pass@4": 0.21273005393131156,
|
| 1929 |
+
"pass@8": 0.23865739981671225,
|
| 1930 |
+
"pass@16": 0.2676959517806339,
|
| 1931 |
+
"pass@32": 0.3011310763692745,
|
| 1932 |
+
"pass@64": 0.3362407178410369,
|
| 1933 |
+
"pass@128": 0.37168141592920356
|
| 1934 |
+
},
|
| 1935 |
+
"17": {
|
| 1936 |
+
"pass@1": 0.1378012048192771,
|
| 1937 |
+
"pass@2": 0.17401619272365054,
|
| 1938 |
+
"pass@4": 0.21124320340981484,
|
| 1939 |
+
"pass@8": 0.24873698272180494,
|
| 1940 |
+
"pass@16": 0.28468715470923933,
|
| 1941 |
+
"pass@32": 0.31684364503562207,
|
| 1942 |
+
"pass@64": 0.3460631347877581,
|
| 1943 |
+
"pass@128": 0.37650602409638556
|
| 1944 |
+
},
|
| 1945 |
+
"18": {
|
| 1946 |
+
"pass@1": 0.16940524193548387,
|
| 1947 |
+
"pass@2": 0.20793830962661927,
|
| 1948 |
+
"pass@4": 0.24442847708552565,
|
| 1949 |
+
"pass@8": 0.27696590133200394,
|
| 1950 |
+
"pass@16": 0.3047539165997947,
|
| 1951 |
+
"pass@32": 0.329140512075412,
|
| 1952 |
+
"pass@64": 0.3525837977178592,
|
| 1953 |
+
"pass@128": 0.3774193548387097
|
| 1954 |
+
},
|
| 1955 |
+
"19": {
|
| 1956 |
+
"pass@1": 0.13812311178247735,
|
| 1957 |
+
"pass@2": 0.16759305790137258,
|
| 1958 |
+
"pass@4": 0.19758813267676884,
|
| 1959 |
+
"pass@8": 0.2284911534750015,
|
| 1960 |
+
"pass@16": 0.2603002938970115,
|
| 1961 |
+
"pass@32": 0.29249731296624343,
|
| 1962 |
+
"pass@64": 0.3260332407783438,
|
| 1963 |
+
"pass@128": 0.36253776435045315
|
| 1964 |
+
},
|
| 1965 |
+
"20": {
|
| 1966 |
+
"pass@1": 0.13072447447447447,
|
| 1967 |
+
"pass@2": 0.16936079780567978,
|
| 1968 |
+
"pass@4": 0.2094049935762534,
|
| 1969 |
+
"pass@8": 0.25098284669882537,
|
| 1970 |
+
"pass@16": 0.291417867530838,
|
| 1971 |
+
"pass@32": 0.32739810777438544,
|
| 1972 |
+
"pass@64": 0.35806392636422313,
|
| 1973 |
+
"pass@128": 0.3813813813813814
|
| 1974 |
+
}
|
| 1975 |
+
}
|
| 1976 |
+
}
|
| 1977 |
+
}
|
| 1978 |
+
}
|
| 1979 |
+
}
|