Upload extrapolation artifact: 050302 pretrain checkpoint-18586 graph aggregate results
Browse files
050302/evals/pretrain_050302_ckpt18586/graph_results/results.json
ADDED
|
@@ -0,0 +1,1780 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"files": {
|
| 3 |
+
"pretrain_050302_ckpt18586_ood_generations.jsonl.graph_results.jsonl": {
|
| 4 |
+
"per_template": {
|
| 5 |
+
"crazy_zootopia": {
|
| 6 |
+
"per_op_pass_at_k": {
|
| 7 |
+
"11": {
|
| 8 |
+
"pass@1": 0.2804532577903683,
|
| 9 |
+
"pass@2": 0.33994334277620397,
|
| 10 |
+
"pass@4": 0.3654390934844193,
|
| 11 |
+
"pass@8": 0.3909348441926346,
|
| 12 |
+
"pass@16": 0.40793201133144474,
|
| 13 |
+
"pass@32": 0.4164305949008499,
|
| 14 |
+
"pass@64": 0.43626062322946174,
|
| 15 |
+
"pass@128": 0.45609065155807366
|
| 16 |
+
},
|
| 17 |
+
"12": {
|
| 18 |
+
"pass@1": 0.2514124293785311,
|
| 19 |
+
"pass@2": 0.3333333333333333,
|
| 20 |
+
"pass@4": 0.3785310734463277,
|
| 21 |
+
"pass@8": 0.4124293785310734,
|
| 22 |
+
"pass@16": 0.4293785310734463,
|
| 23 |
+
"pass@32": 0.4519774011299435,
|
| 24 |
+
"pass@64": 0.4576271186440678,
|
| 25 |
+
"pass@128": 0.4745762711864407
|
| 26 |
+
},
|
| 27 |
+
"13": {
|
| 28 |
+
"pass@1": 0.08150470219435736,
|
| 29 |
+
"pass@2": 0.11598746081504702,
|
| 30 |
+
"pass@4": 0.13793103448275862,
|
| 31 |
+
"pass@8": 0.16614420062695925,
|
| 32 |
+
"pass@16": 0.20689655172413793,
|
| 33 |
+
"pass@32": 0.23824451410658307,
|
| 34 |
+
"pass@64": 0.25705329153605017,
|
| 35 |
+
"pass@128": 0.27899686520376177
|
| 36 |
+
},
|
| 37 |
+
"14": {
|
| 38 |
+
"pass@1": 0.009345794392523364,
|
| 39 |
+
"pass@2": 0.009345794392523364,
|
| 40 |
+
"pass@4": 0.012461059190031152,
|
| 41 |
+
"pass@8": 0.012461059190031152,
|
| 42 |
+
"pass@16": 0.03115264797507788,
|
| 43 |
+
"pass@32": 0.03426791277258567,
|
| 44 |
+
"pass@64": 0.040498442367601244,
|
| 45 |
+
"pass@128": 0.06542056074766354
|
| 46 |
+
},
|
| 47 |
+
"15": {
|
| 48 |
+
"pass@1": 0.0,
|
| 49 |
+
"pass@2": 0.0,
|
| 50 |
+
"pass@4": 0.0,
|
| 51 |
+
"pass@8": 0.002890173410404624,
|
| 52 |
+
"pass@16": 0.002890173410404624,
|
| 53 |
+
"pass@32": 0.005780346820809248,
|
| 54 |
+
"pass@64": 0.005780346820809248,
|
| 55 |
+
"pass@128": 0.005780346820809248
|
| 56 |
+
},
|
| 57 |
+
"16": {
|
| 58 |
+
"pass@1": 0.0,
|
| 59 |
+
"pass@2": 0.0,
|
| 60 |
+
"pass@4": 0.0,
|
| 61 |
+
"pass@8": 0.0,
|
| 62 |
+
"pass@16": 0.0,
|
| 63 |
+
"pass@32": 0.0,
|
| 64 |
+
"pass@64": 0.0,
|
| 65 |
+
"pass@128": 0.0
|
| 66 |
+
},
|
| 67 |
+
"17": {
|
| 68 |
+
"pass@1": 0.0,
|
| 69 |
+
"pass@2": 0.0,
|
| 70 |
+
"pass@4": 0.0,
|
| 71 |
+
"pass@8": 0.0,
|
| 72 |
+
"pass@16": 0.0,
|
| 73 |
+
"pass@32": 0.0,
|
| 74 |
+
"pass@64": 0.0,
|
| 75 |
+
"pass@128": 0.0
|
| 76 |
+
},
|
| 77 |
+
"18": {
|
| 78 |
+
"pass@1": 0.0,
|
| 79 |
+
"pass@2": 0.0,
|
| 80 |
+
"pass@4": 0.0,
|
| 81 |
+
"pass@8": 0.0,
|
| 82 |
+
"pass@16": 0.0,
|
| 83 |
+
"pass@32": 0.0,
|
| 84 |
+
"pass@64": 0.0,
|
| 85 |
+
"pass@128": 0.0
|
| 86 |
+
},
|
| 87 |
+
"19": {
|
| 88 |
+
"pass@1": 0.0,
|
| 89 |
+
"pass@2": 0.0,
|
| 90 |
+
"pass@4": 0.0,
|
| 91 |
+
"pass@8": 0.0,
|
| 92 |
+
"pass@16": 0.0,
|
| 93 |
+
"pass@32": 0.0,
|
| 94 |
+
"pass@64": 0.0,
|
| 95 |
+
"pass@128": 0.0
|
| 96 |
+
},
|
| 97 |
+
"20": {
|
| 98 |
+
"pass@1": 0.0,
|
| 99 |
+
"pass@2": 0.0,
|
| 100 |
+
"pass@4": 0.0,
|
| 101 |
+
"pass@8": 0.0,
|
| 102 |
+
"pass@16": 0.0,
|
| 103 |
+
"pass@32": 0.0,
|
| 104 |
+
"pass@64": 0.0,
|
| 105 |
+
"pass@128": 0.0
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"per_op_pass_at_columns": {
|
| 109 |
+
"pass@1": {
|
| 110 |
+
"11": 0.2804532577903683,
|
| 111 |
+
"12": 0.2514124293785311,
|
| 112 |
+
"13": 0.08150470219435736,
|
| 113 |
+
"14": 0.009345794392523364,
|
| 114 |
+
"15": 0.0,
|
| 115 |
+
"16": 0.0,
|
| 116 |
+
"17": 0.0,
|
| 117 |
+
"18": 0.0,
|
| 118 |
+
"19": 0.0,
|
| 119 |
+
"20": 0.0
|
| 120 |
+
},
|
| 121 |
+
"pass@2": {
|
| 122 |
+
"11": 0.33994334277620397,
|
| 123 |
+
"12": 0.3333333333333333,
|
| 124 |
+
"13": 0.11598746081504702,
|
| 125 |
+
"14": 0.009345794392523364,
|
| 126 |
+
"15": 0.0,
|
| 127 |
+
"16": 0.0,
|
| 128 |
+
"17": 0.0,
|
| 129 |
+
"18": 0.0,
|
| 130 |
+
"19": 0.0,
|
| 131 |
+
"20": 0.0
|
| 132 |
+
},
|
| 133 |
+
"pass@4": {
|
| 134 |
+
"11": 0.3654390934844193,
|
| 135 |
+
"12": 0.3785310734463277,
|
| 136 |
+
"13": 0.13793103448275862,
|
| 137 |
+
"14": 0.012461059190031152,
|
| 138 |
+
"15": 0.0,
|
| 139 |
+
"16": 0.0,
|
| 140 |
+
"17": 0.0,
|
| 141 |
+
"18": 0.0,
|
| 142 |
+
"19": 0.0,
|
| 143 |
+
"20": 0.0
|
| 144 |
+
},
|
| 145 |
+
"pass@8": {
|
| 146 |
+
"11": 0.3909348441926346,
|
| 147 |
+
"12": 0.4124293785310734,
|
| 148 |
+
"13": 0.16614420062695925,
|
| 149 |
+
"14": 0.012461059190031152,
|
| 150 |
+
"15": 0.002890173410404624,
|
| 151 |
+
"16": 0.0,
|
| 152 |
+
"17": 0.0,
|
| 153 |
+
"18": 0.0,
|
| 154 |
+
"19": 0.0,
|
| 155 |
+
"20": 0.0
|
| 156 |
+
},
|
| 157 |
+
"pass@16": {
|
| 158 |
+
"11": 0.40793201133144474,
|
| 159 |
+
"12": 0.4293785310734463,
|
| 160 |
+
"13": 0.20689655172413793,
|
| 161 |
+
"14": 0.03115264797507788,
|
| 162 |
+
"15": 0.002890173410404624,
|
| 163 |
+
"16": 0.0,
|
| 164 |
+
"17": 0.0,
|
| 165 |
+
"18": 0.0,
|
| 166 |
+
"19": 0.0,
|
| 167 |
+
"20": 0.0
|
| 168 |
+
},
|
| 169 |
+
"pass@32": {
|
| 170 |
+
"11": 0.4164305949008499,
|
| 171 |
+
"12": 0.4519774011299435,
|
| 172 |
+
"13": 0.23824451410658307,
|
| 173 |
+
"14": 0.03426791277258567,
|
| 174 |
+
"15": 0.005780346820809248,
|
| 175 |
+
"16": 0.0,
|
| 176 |
+
"17": 0.0,
|
| 177 |
+
"18": 0.0,
|
| 178 |
+
"19": 0.0,
|
| 179 |
+
"20": 0.0
|
| 180 |
+
},
|
| 181 |
+
"pass@64": {
|
| 182 |
+
"11": 0.43626062322946174,
|
| 183 |
+
"12": 0.4576271186440678,
|
| 184 |
+
"13": 0.25705329153605017,
|
| 185 |
+
"14": 0.040498442367601244,
|
| 186 |
+
"15": 0.005780346820809248,
|
| 187 |
+
"16": 0.0,
|
| 188 |
+
"17": 0.0,
|
| 189 |
+
"18": 0.0,
|
| 190 |
+
"19": 0.0,
|
| 191 |
+
"20": 0.0
|
| 192 |
+
},
|
| 193 |
+
"pass@128": {
|
| 194 |
+
"11": 0.45609065155807366,
|
| 195 |
+
"12": 0.4745762711864407,
|
| 196 |
+
"13": 0.27899686520376177,
|
| 197 |
+
"14": 0.06542056074766354,
|
| 198 |
+
"15": 0.005780346820809248,
|
| 199 |
+
"16": 0.0,
|
| 200 |
+
"17": 0.0,
|
| 201 |
+
"18": 0.0,
|
| 202 |
+
"19": 0.0,
|
| 203 |
+
"20": 0.0
|
| 204 |
+
}
|
| 205 |
+
},
|
| 206 |
+
"total_pass_at_k": {
|
| 207 |
+
"pass@1": 0.06448736998514117,
|
| 208 |
+
"pass@2": 0.08261515601783061,
|
| 209 |
+
"pass@4": 0.0924219910846954,
|
| 210 |
+
"pass@8": 0.10163447251114413,
|
| 211 |
+
"pass@16": 0.11084695393759286,
|
| 212 |
+
"pass@32": 0.11768202080237741,
|
| 213 |
+
"pass@64": 0.12273402674591381,
|
| 214 |
+
"pass@128": 0.1310549777117385
|
| 215 |
+
}
|
| 216 |
+
},
|
| 217 |
+
"movie_festival_awards": {
|
| 218 |
+
"per_op_pass_at_k": {
|
| 219 |
+
"11": {
|
| 220 |
+
"pass@1": 0.2920634920634921,
|
| 221 |
+
"pass@2": 0.35873015873015873,
|
| 222 |
+
"pass@4": 0.3904761904761905,
|
| 223 |
+
"pass@8": 0.4253968253968254,
|
| 224 |
+
"pass@16": 0.4444444444444444,
|
| 225 |
+
"pass@32": 0.45396825396825397,
|
| 226 |
+
"pass@64": 0.4634920634920635,
|
| 227 |
+
"pass@128": 0.4793650793650794
|
| 228 |
+
},
|
| 229 |
+
"12": {
|
| 230 |
+
"pass@1": 0.24464831804281345,
|
| 231 |
+
"pass@2": 0.3302752293577982,
|
| 232 |
+
"pass@4": 0.37920489296636084,
|
| 233 |
+
"pass@8": 0.41896024464831805,
|
| 234 |
+
"pass@16": 0.44036697247706424,
|
| 235 |
+
"pass@32": 0.4434250764525994,
|
| 236 |
+
"pass@64": 0.45871559633027525,
|
| 237 |
+
"pass@128": 0.4709480122324159
|
| 238 |
+
},
|
| 239 |
+
"13": {
|
| 240 |
+
"pass@1": 0.08333333333333333,
|
| 241 |
+
"pass@2": 0.10802469135802469,
|
| 242 |
+
"pass@4": 0.1388888888888889,
|
| 243 |
+
"pass@8": 0.17592592592592593,
|
| 244 |
+
"pass@16": 0.19753086419753085,
|
| 245 |
+
"pass@32": 0.2222222222222222,
|
| 246 |
+
"pass@64": 0.24691358024691357,
|
| 247 |
+
"pass@128": 0.2654320987654321
|
| 248 |
+
},
|
| 249 |
+
"14": {
|
| 250 |
+
"pass@1": 0.002967359050445104,
|
| 251 |
+
"pass@2": 0.005934718100890208,
|
| 252 |
+
"pass@4": 0.01483679525222552,
|
| 253 |
+
"pass@8": 0.01483679525222552,
|
| 254 |
+
"pass@16": 0.017804154302670624,
|
| 255 |
+
"pass@32": 0.026706231454005934,
|
| 256 |
+
"pass@64": 0.032640949554896145,
|
| 257 |
+
"pass@128": 0.04451038575667656
|
| 258 |
+
},
|
| 259 |
+
"15": {
|
| 260 |
+
"pass@1": 0.0,
|
| 261 |
+
"pass@2": 0.0,
|
| 262 |
+
"pass@4": 0.0,
|
| 263 |
+
"pass@8": 0.0,
|
| 264 |
+
"pass@16": 0.0,
|
| 265 |
+
"pass@32": 0.0,
|
| 266 |
+
"pass@64": 0.0,
|
| 267 |
+
"pass@128": 0.0
|
| 268 |
+
},
|
| 269 |
+
"16": {
|
| 270 |
+
"pass@1": 0.0,
|
| 271 |
+
"pass@2": 0.0,
|
| 272 |
+
"pass@4": 0.0,
|
| 273 |
+
"pass@8": 0.0,
|
| 274 |
+
"pass@16": 0.0,
|
| 275 |
+
"pass@32": 0.0,
|
| 276 |
+
"pass@64": 0.0,
|
| 277 |
+
"pass@128": 0.0
|
| 278 |
+
},
|
| 279 |
+
"17": {
|
| 280 |
+
"pass@1": 0.0,
|
| 281 |
+
"pass@2": 0.0,
|
| 282 |
+
"pass@4": 0.0,
|
| 283 |
+
"pass@8": 0.0,
|
| 284 |
+
"pass@16": 0.0,
|
| 285 |
+
"pass@32": 0.0,
|
| 286 |
+
"pass@64": 0.0,
|
| 287 |
+
"pass@128": 0.0
|
| 288 |
+
},
|
| 289 |
+
"18": {
|
| 290 |
+
"pass@1": 0.0,
|
| 291 |
+
"pass@2": 0.0,
|
| 292 |
+
"pass@4": 0.0,
|
| 293 |
+
"pass@8": 0.0,
|
| 294 |
+
"pass@16": 0.0,
|
| 295 |
+
"pass@32": 0.0,
|
| 296 |
+
"pass@64": 0.0,
|
| 297 |
+
"pass@128": 0.0
|
| 298 |
+
},
|
| 299 |
+
"19": {
|
| 300 |
+
"pass@1": 0.0,
|
| 301 |
+
"pass@2": 0.0,
|
| 302 |
+
"pass@4": 0.0,
|
| 303 |
+
"pass@8": 0.0,
|
| 304 |
+
"pass@16": 0.0,
|
| 305 |
+
"pass@32": 0.0,
|
| 306 |
+
"pass@64": 0.0,
|
| 307 |
+
"pass@128": 0.0
|
| 308 |
+
},
|
| 309 |
+
"20": {
|
| 310 |
+
"pass@1": 0.0,
|
| 311 |
+
"pass@2": 0.0,
|
| 312 |
+
"pass@4": 0.0,
|
| 313 |
+
"pass@8": 0.0,
|
| 314 |
+
"pass@16": 0.0,
|
| 315 |
+
"pass@32": 0.0,
|
| 316 |
+
"pass@64": 0.0,
|
| 317 |
+
"pass@128": 0.0
|
| 318 |
+
}
|
| 319 |
+
},
|
| 320 |
+
"per_op_pass_at_columns": {
|
| 321 |
+
"pass@1": {
|
| 322 |
+
"11": 0.2920634920634921,
|
| 323 |
+
"12": 0.24464831804281345,
|
| 324 |
+
"13": 0.08333333333333333,
|
| 325 |
+
"14": 0.002967359050445104,
|
| 326 |
+
"15": 0.0,
|
| 327 |
+
"16": 0.0,
|
| 328 |
+
"17": 0.0,
|
| 329 |
+
"18": 0.0,
|
| 330 |
+
"19": 0.0,
|
| 331 |
+
"20": 0.0
|
| 332 |
+
},
|
| 333 |
+
"pass@2": {
|
| 334 |
+
"11": 0.35873015873015873,
|
| 335 |
+
"12": 0.3302752293577982,
|
| 336 |
+
"13": 0.10802469135802469,
|
| 337 |
+
"14": 0.005934718100890208,
|
| 338 |
+
"15": 0.0,
|
| 339 |
+
"16": 0.0,
|
| 340 |
+
"17": 0.0,
|
| 341 |
+
"18": 0.0,
|
| 342 |
+
"19": 0.0,
|
| 343 |
+
"20": 0.0
|
| 344 |
+
},
|
| 345 |
+
"pass@4": {
|
| 346 |
+
"11": 0.3904761904761905,
|
| 347 |
+
"12": 0.37920489296636084,
|
| 348 |
+
"13": 0.1388888888888889,
|
| 349 |
+
"14": 0.01483679525222552,
|
| 350 |
+
"15": 0.0,
|
| 351 |
+
"16": 0.0,
|
| 352 |
+
"17": 0.0,
|
| 353 |
+
"18": 0.0,
|
| 354 |
+
"19": 0.0,
|
| 355 |
+
"20": 0.0
|
| 356 |
+
},
|
| 357 |
+
"pass@8": {
|
| 358 |
+
"11": 0.4253968253968254,
|
| 359 |
+
"12": 0.41896024464831805,
|
| 360 |
+
"13": 0.17592592592592593,
|
| 361 |
+
"14": 0.01483679525222552,
|
| 362 |
+
"15": 0.0,
|
| 363 |
+
"16": 0.0,
|
| 364 |
+
"17": 0.0,
|
| 365 |
+
"18": 0.0,
|
| 366 |
+
"19": 0.0,
|
| 367 |
+
"20": 0.0
|
| 368 |
+
},
|
| 369 |
+
"pass@16": {
|
| 370 |
+
"11": 0.4444444444444444,
|
| 371 |
+
"12": 0.44036697247706424,
|
| 372 |
+
"13": 0.19753086419753085,
|
| 373 |
+
"14": 0.017804154302670624,
|
| 374 |
+
"15": 0.0,
|
| 375 |
+
"16": 0.0,
|
| 376 |
+
"17": 0.0,
|
| 377 |
+
"18": 0.0,
|
| 378 |
+
"19": 0.0,
|
| 379 |
+
"20": 0.0
|
| 380 |
+
},
|
| 381 |
+
"pass@32": {
|
| 382 |
+
"11": 0.45396825396825397,
|
| 383 |
+
"12": 0.4434250764525994,
|
| 384 |
+
"13": 0.2222222222222222,
|
| 385 |
+
"14": 0.026706231454005934,
|
| 386 |
+
"15": 0.0,
|
| 387 |
+
"16": 0.0,
|
| 388 |
+
"17": 0.0,
|
| 389 |
+
"18": 0.0,
|
| 390 |
+
"19": 0.0,
|
| 391 |
+
"20": 0.0
|
| 392 |
+
},
|
| 393 |
+
"pass@64": {
|
| 394 |
+
"11": 0.4634920634920635,
|
| 395 |
+
"12": 0.45871559633027525,
|
| 396 |
+
"13": 0.24691358024691357,
|
| 397 |
+
"14": 0.032640949554896145,
|
| 398 |
+
"15": 0.0,
|
| 399 |
+
"16": 0.0,
|
| 400 |
+
"17": 0.0,
|
| 401 |
+
"18": 0.0,
|
| 402 |
+
"19": 0.0,
|
| 403 |
+
"20": 0.0
|
| 404 |
+
},
|
| 405 |
+
"pass@128": {
|
| 406 |
+
"11": 0.4793650793650794,
|
| 407 |
+
"12": 0.4709480122324159,
|
| 408 |
+
"13": 0.2654320987654321,
|
| 409 |
+
"14": 0.04451038575667656,
|
| 410 |
+
"15": 0.0,
|
| 411 |
+
"16": 0.0,
|
| 412 |
+
"17": 0.0,
|
| 413 |
+
"18": 0.0,
|
| 414 |
+
"19": 0.0,
|
| 415 |
+
"20": 0.0
|
| 416 |
+
}
|
| 417 |
+
},
|
| 418 |
+
"total_pass_at_k": {
|
| 419 |
+
"pass@1": 0.061124694376528114,
|
| 420 |
+
"pass@2": 0.07885085574572127,
|
| 421 |
+
"pass@4": 0.09077017114914425,
|
| 422 |
+
"pass@8": 0.10177261613691932,
|
| 423 |
+
"pass@16": 0.10819070904645477,
|
| 424 |
+
"pass@32": 0.11277506112469438,
|
| 425 |
+
"pass@64": 0.1182762836185819,
|
| 426 |
+
"pass@128": 0.12408312958435208
|
| 427 |
+
}
|
| 428 |
+
},
|
| 429 |
+
"teachers_in_school": {
|
| 430 |
+
"per_op_pass_at_k": {
|
| 431 |
+
"11": {
|
| 432 |
+
"pass@1": 0.31626506024096385,
|
| 433 |
+
"pass@2": 0.39156626506024095,
|
| 434 |
+
"pass@4": 0.4367469879518072,
|
| 435 |
+
"pass@8": 0.463855421686747,
|
| 436 |
+
"pass@16": 0.5090361445783133,
|
| 437 |
+
"pass@32": 0.5271084337349398,
|
| 438 |
+
"pass@64": 0.5451807228915663,
|
| 439 |
+
"pass@128": 0.5632530120481928
|
| 440 |
+
},
|
| 441 |
+
"12": {
|
| 442 |
+
"pass@1": 0.19435736677115986,
|
| 443 |
+
"pass@2": 0.27899686520376177,
|
| 444 |
+
"pass@4": 0.31974921630094044,
|
| 445 |
+
"pass@8": 0.3667711598746082,
|
| 446 |
+
"pass@16": 0.3887147335423197,
|
| 447 |
+
"pass@32": 0.4043887147335423,
|
| 448 |
+
"pass@64": 0.4200626959247649,
|
| 449 |
+
"pass@128": 0.42946708463949845
|
| 450 |
+
},
|
| 451 |
+
"13": {
|
| 452 |
+
"pass@1": 0.10084033613445378,
|
| 453 |
+
"pass@2": 0.15406162464985995,
|
| 454 |
+
"pass@4": 0.18487394957983194,
|
| 455 |
+
"pass@8": 0.21288515406162464,
|
| 456 |
+
"pass@16": 0.25210084033613445,
|
| 457 |
+
"pass@32": 0.27170868347338933,
|
| 458 |
+
"pass@64": 0.2913165266106443,
|
| 459 |
+
"pass@128": 0.3137254901960784
|
| 460 |
+
},
|
| 461 |
+
"14": {
|
| 462 |
+
"pass@1": 0.0029239766081871343,
|
| 463 |
+
"pass@2": 0.008771929824561403,
|
| 464 |
+
"pass@4": 0.011695906432748537,
|
| 465 |
+
"pass@8": 0.014619883040935672,
|
| 466 |
+
"pass@16": 0.02046783625730994,
|
| 467 |
+
"pass@32": 0.02631578947368421,
|
| 468 |
+
"pass@64": 0.04093567251461988,
|
| 469 |
+
"pass@128": 0.04678362573099415
|
| 470 |
+
},
|
| 471 |
+
"15": {
|
| 472 |
+
"pass@1": 0.0,
|
| 473 |
+
"pass@2": 0.0,
|
| 474 |
+
"pass@4": 0.0,
|
| 475 |
+
"pass@8": 0.0,
|
| 476 |
+
"pass@16": 0.0,
|
| 477 |
+
"pass@32": 0.0,
|
| 478 |
+
"pass@64": 0.0,
|
| 479 |
+
"pass@128": 0.006060606060606061
|
| 480 |
+
},
|
| 481 |
+
"16": {
|
| 482 |
+
"pass@1": 0.0,
|
| 483 |
+
"pass@2": 0.0,
|
| 484 |
+
"pass@4": 0.0,
|
| 485 |
+
"pass@8": 0.0,
|
| 486 |
+
"pass@16": 0.0,
|
| 487 |
+
"pass@32": 0.0,
|
| 488 |
+
"pass@64": 0.0,
|
| 489 |
+
"pass@128": 0.002849002849002849
|
| 490 |
+
},
|
| 491 |
+
"17": {
|
| 492 |
+
"pass@1": 0.0,
|
| 493 |
+
"pass@2": 0.0,
|
| 494 |
+
"pass@4": 0.0,
|
| 495 |
+
"pass@8": 0.0,
|
| 496 |
+
"pass@16": 0.0,
|
| 497 |
+
"pass@32": 0.0,
|
| 498 |
+
"pass@64": 0.0,
|
| 499 |
+
"pass@128": 0.0
|
| 500 |
+
},
|
| 501 |
+
"18": {
|
| 502 |
+
"pass@1": 0.0,
|
| 503 |
+
"pass@2": 0.0,
|
| 504 |
+
"pass@4": 0.0,
|
| 505 |
+
"pass@8": 0.0,
|
| 506 |
+
"pass@16": 0.0,
|
| 507 |
+
"pass@32": 0.0,
|
| 508 |
+
"pass@64": 0.0,
|
| 509 |
+
"pass@128": 0.0
|
| 510 |
+
},
|
| 511 |
+
"19": {
|
| 512 |
+
"pass@1": 0.0,
|
| 513 |
+
"pass@2": 0.0,
|
| 514 |
+
"pass@4": 0.0,
|
| 515 |
+
"pass@8": 0.0,
|
| 516 |
+
"pass@16": 0.0,
|
| 517 |
+
"pass@32": 0.0,
|
| 518 |
+
"pass@64": 0.0,
|
| 519 |
+
"pass@128": 0.0
|
| 520 |
+
},
|
| 521 |
+
"20": {
|
| 522 |
+
"pass@1": 0.0,
|
| 523 |
+
"pass@2": 0.0,
|
| 524 |
+
"pass@4": 0.0,
|
| 525 |
+
"pass@8": 0.0,
|
| 526 |
+
"pass@16": 0.0,
|
| 527 |
+
"pass@32": 0.0,
|
| 528 |
+
"pass@64": 0.0,
|
| 529 |
+
"pass@128": 0.0
|
| 530 |
+
}
|
| 531 |
+
},
|
| 532 |
+
"per_op_pass_at_columns": {
|
| 533 |
+
"pass@1": {
|
| 534 |
+
"11": 0.31626506024096385,
|
| 535 |
+
"12": 0.19435736677115986,
|
| 536 |
+
"13": 0.10084033613445378,
|
| 537 |
+
"14": 0.0029239766081871343,
|
| 538 |
+
"15": 0.0,
|
| 539 |
+
"16": 0.0,
|
| 540 |
+
"17": 0.0,
|
| 541 |
+
"18": 0.0,
|
| 542 |
+
"19": 0.0,
|
| 543 |
+
"20": 0.0
|
| 544 |
+
},
|
| 545 |
+
"pass@2": {
|
| 546 |
+
"11": 0.39156626506024095,
|
| 547 |
+
"12": 0.27899686520376177,
|
| 548 |
+
"13": 0.15406162464985995,
|
| 549 |
+
"14": 0.008771929824561403,
|
| 550 |
+
"15": 0.0,
|
| 551 |
+
"16": 0.0,
|
| 552 |
+
"17": 0.0,
|
| 553 |
+
"18": 0.0,
|
| 554 |
+
"19": 0.0,
|
| 555 |
+
"20": 0.0
|
| 556 |
+
},
|
| 557 |
+
"pass@4": {
|
| 558 |
+
"11": 0.4367469879518072,
|
| 559 |
+
"12": 0.31974921630094044,
|
| 560 |
+
"13": 0.18487394957983194,
|
| 561 |
+
"14": 0.011695906432748537,
|
| 562 |
+
"15": 0.0,
|
| 563 |
+
"16": 0.0,
|
| 564 |
+
"17": 0.0,
|
| 565 |
+
"18": 0.0,
|
| 566 |
+
"19": 0.0,
|
| 567 |
+
"20": 0.0
|
| 568 |
+
},
|
| 569 |
+
"pass@8": {
|
| 570 |
+
"11": 0.463855421686747,
|
| 571 |
+
"12": 0.3667711598746082,
|
| 572 |
+
"13": 0.21288515406162464,
|
| 573 |
+
"14": 0.014619883040935672,
|
| 574 |
+
"15": 0.0,
|
| 575 |
+
"16": 0.0,
|
| 576 |
+
"17": 0.0,
|
| 577 |
+
"18": 0.0,
|
| 578 |
+
"19": 0.0,
|
| 579 |
+
"20": 0.0
|
| 580 |
+
},
|
| 581 |
+
"pass@16": {
|
| 582 |
+
"11": 0.5090361445783133,
|
| 583 |
+
"12": 0.3887147335423197,
|
| 584 |
+
"13": 0.25210084033613445,
|
| 585 |
+
"14": 0.02046783625730994,
|
| 586 |
+
"15": 0.0,
|
| 587 |
+
"16": 0.0,
|
| 588 |
+
"17": 0.0,
|
| 589 |
+
"18": 0.0,
|
| 590 |
+
"19": 0.0,
|
| 591 |
+
"20": 0.0
|
| 592 |
+
},
|
| 593 |
+
"pass@32": {
|
| 594 |
+
"11": 0.5271084337349398,
|
| 595 |
+
"12": 0.4043887147335423,
|
| 596 |
+
"13": 0.27170868347338933,
|
| 597 |
+
"14": 0.02631578947368421,
|
| 598 |
+
"15": 0.0,
|
| 599 |
+
"16": 0.0,
|
| 600 |
+
"17": 0.0,
|
| 601 |
+
"18": 0.0,
|
| 602 |
+
"19": 0.0,
|
| 603 |
+
"20": 0.0
|
| 604 |
+
},
|
| 605 |
+
"pass@64": {
|
| 606 |
+
"11": 0.5451807228915663,
|
| 607 |
+
"12": 0.4200626959247649,
|
| 608 |
+
"13": 0.2913165266106443,
|
| 609 |
+
"14": 0.04093567251461988,
|
| 610 |
+
"15": 0.0,
|
| 611 |
+
"16": 0.0,
|
| 612 |
+
"17": 0.0,
|
| 613 |
+
"18": 0.0,
|
| 614 |
+
"19": 0.0,
|
| 615 |
+
"20": 0.0
|
| 616 |
+
},
|
| 617 |
+
"pass@128": {
|
| 618 |
+
"11": 0.5632530120481928,
|
| 619 |
+
"12": 0.42946708463949845,
|
| 620 |
+
"13": 0.3137254901960784,
|
| 621 |
+
"14": 0.04678362573099415,
|
| 622 |
+
"15": 0.006060606060606061,
|
| 623 |
+
"16": 0.002849002849002849,
|
| 624 |
+
"17": 0.0,
|
| 625 |
+
"18": 0.0,
|
| 626 |
+
"19": 0.0,
|
| 627 |
+
"20": 0.0
|
| 628 |
+
}
|
| 629 |
+
},
|
| 630 |
+
"total_pass_at_k": {
|
| 631 |
+
"pass@1": 0.060660124888492414,
|
| 632 |
+
"pass@2": 0.0823669342848647,
|
| 633 |
+
"pass@4": 0.09426107641986321,
|
| 634 |
+
"pass@8": 0.10466845078798692,
|
| 635 |
+
"pass@16": 0.1159678858162355,
|
| 636 |
+
"pass@32": 0.12191495688373476,
|
| 637 |
+
"pass@64": 0.1287540886113589,
|
| 638 |
+
"pass@128": 0.1352958667856081
|
| 639 |
+
}
|
| 640 |
+
}
|
| 641 |
+
},
|
| 642 |
+
"total": {
|
| 643 |
+
"per_op_pass_at_k": {
|
| 644 |
+
"11": {
|
| 645 |
+
"pass@1": 0.296,
|
| 646 |
+
"pass@2": 0.363,
|
| 647 |
+
"pass@4": 0.397,
|
| 648 |
+
"pass@8": 0.426,
|
| 649 |
+
"pass@16": 0.453,
|
| 650 |
+
"pass@32": 0.465,
|
| 651 |
+
"pass@64": 0.481,
|
| 652 |
+
"pass@128": 0.499
|
| 653 |
+
},
|
| 654 |
+
"12": {
|
| 655 |
+
"pass@1": 0.231,
|
| 656 |
+
"pass@2": 0.315,
|
| 657 |
+
"pass@4": 0.36,
|
| 658 |
+
"pass@8": 0.4,
|
| 659 |
+
"pass@16": 0.42,
|
| 660 |
+
"pass@32": 0.434,
|
| 661 |
+
"pass@64": 0.446,
|
| 662 |
+
"pass@128": 0.459
|
| 663 |
+
},
|
| 664 |
+
"13": {
|
| 665 |
+
"pass@1": 0.089,
|
| 666 |
+
"pass@2": 0.127,
|
| 667 |
+
"pass@4": 0.155,
|
| 668 |
+
"pass@8": 0.186,
|
| 669 |
+
"pass@16": 0.22,
|
| 670 |
+
"pass@32": 0.245,
|
| 671 |
+
"pass@64": 0.266,
|
| 672 |
+
"pass@128": 0.287
|
| 673 |
+
},
|
| 674 |
+
"14": {
|
| 675 |
+
"pass@1": 0.005,
|
| 676 |
+
"pass@2": 0.008,
|
| 677 |
+
"pass@4": 0.013,
|
| 678 |
+
"pass@8": 0.014,
|
| 679 |
+
"pass@16": 0.023,
|
| 680 |
+
"pass@32": 0.029,
|
| 681 |
+
"pass@64": 0.038,
|
| 682 |
+
"pass@128": 0.052
|
| 683 |
+
},
|
| 684 |
+
"15": {
|
| 685 |
+
"pass@1": 0.0,
|
| 686 |
+
"pass@2": 0.0,
|
| 687 |
+
"pass@4": 0.0,
|
| 688 |
+
"pass@8": 0.001,
|
| 689 |
+
"pass@16": 0.001,
|
| 690 |
+
"pass@32": 0.002,
|
| 691 |
+
"pass@64": 0.002,
|
| 692 |
+
"pass@128": 0.004
|
| 693 |
+
},
|
| 694 |
+
"16": {
|
| 695 |
+
"pass@1": 0.0,
|
| 696 |
+
"pass@2": 0.0,
|
| 697 |
+
"pass@4": 0.0,
|
| 698 |
+
"pass@8": 0.0,
|
| 699 |
+
"pass@16": 0.0,
|
| 700 |
+
"pass@32": 0.0,
|
| 701 |
+
"pass@64": 0.0,
|
| 702 |
+
"pass@128": 0.001
|
| 703 |
+
},
|
| 704 |
+
"17": {
|
| 705 |
+
"pass@1": 0.0,
|
| 706 |
+
"pass@2": 0.0,
|
| 707 |
+
"pass@4": 0.0,
|
| 708 |
+
"pass@8": 0.0,
|
| 709 |
+
"pass@16": 0.0,
|
| 710 |
+
"pass@32": 0.0,
|
| 711 |
+
"pass@64": 0.0,
|
| 712 |
+
"pass@128": 0.0
|
| 713 |
+
},
|
| 714 |
+
"18": {
|
| 715 |
+
"pass@1": 0.0,
|
| 716 |
+
"pass@2": 0.0,
|
| 717 |
+
"pass@4": 0.0,
|
| 718 |
+
"pass@8": 0.0,
|
| 719 |
+
"pass@16": 0.0,
|
| 720 |
+
"pass@32": 0.0,
|
| 721 |
+
"pass@64": 0.0,
|
| 722 |
+
"pass@128": 0.0
|
| 723 |
+
},
|
| 724 |
+
"19": {
|
| 725 |
+
"pass@1": 0.0,
|
| 726 |
+
"pass@2": 0.0,
|
| 727 |
+
"pass@4": 0.0,
|
| 728 |
+
"pass@8": 0.0,
|
| 729 |
+
"pass@16": 0.0,
|
| 730 |
+
"pass@32": 0.0,
|
| 731 |
+
"pass@64": 0.0,
|
| 732 |
+
"pass@128": 0.0
|
| 733 |
+
},
|
| 734 |
+
"20": {
|
| 735 |
+
"pass@1": 0.0,
|
| 736 |
+
"pass@2": 0.0,
|
| 737 |
+
"pass@4": 0.0,
|
| 738 |
+
"pass@8": 0.0,
|
| 739 |
+
"pass@16": 0.0,
|
| 740 |
+
"pass@32": 0.0,
|
| 741 |
+
"pass@64": 0.0,
|
| 742 |
+
"pass@128": 0.0
|
| 743 |
+
}
|
| 744 |
+
},
|
| 745 |
+
"per_op_pass_at_columns": {
|
| 746 |
+
"pass@1": {
|
| 747 |
+
"11": 0.296,
|
| 748 |
+
"12": 0.231,
|
| 749 |
+
"13": 0.089,
|
| 750 |
+
"14": 0.005,
|
| 751 |
+
"15": 0.0,
|
| 752 |
+
"16": 0.0,
|
| 753 |
+
"17": 0.0,
|
| 754 |
+
"18": 0.0,
|
| 755 |
+
"19": 0.0,
|
| 756 |
+
"20": 0.0
|
| 757 |
+
},
|
| 758 |
+
"pass@2": {
|
| 759 |
+
"11": 0.363,
|
| 760 |
+
"12": 0.315,
|
| 761 |
+
"13": 0.127,
|
| 762 |
+
"14": 0.008,
|
| 763 |
+
"15": 0.0,
|
| 764 |
+
"16": 0.0,
|
| 765 |
+
"17": 0.0,
|
| 766 |
+
"18": 0.0,
|
| 767 |
+
"19": 0.0,
|
| 768 |
+
"20": 0.0
|
| 769 |
+
},
|
| 770 |
+
"pass@4": {
|
| 771 |
+
"11": 0.397,
|
| 772 |
+
"12": 0.36,
|
| 773 |
+
"13": 0.155,
|
| 774 |
+
"14": 0.013,
|
| 775 |
+
"15": 0.0,
|
| 776 |
+
"16": 0.0,
|
| 777 |
+
"17": 0.0,
|
| 778 |
+
"18": 0.0,
|
| 779 |
+
"19": 0.0,
|
| 780 |
+
"20": 0.0
|
| 781 |
+
},
|
| 782 |
+
"pass@8": {
|
| 783 |
+
"11": 0.426,
|
| 784 |
+
"12": 0.4,
|
| 785 |
+
"13": 0.186,
|
| 786 |
+
"14": 0.014,
|
| 787 |
+
"15": 0.001,
|
| 788 |
+
"16": 0.0,
|
| 789 |
+
"17": 0.0,
|
| 790 |
+
"18": 0.0,
|
| 791 |
+
"19": 0.0,
|
| 792 |
+
"20": 0.0
|
| 793 |
+
},
|
| 794 |
+
"pass@16": {
|
| 795 |
+
"11": 0.453,
|
| 796 |
+
"12": 0.42,
|
| 797 |
+
"13": 0.22,
|
| 798 |
+
"14": 0.023,
|
| 799 |
+
"15": 0.001,
|
| 800 |
+
"16": 0.0,
|
| 801 |
+
"17": 0.0,
|
| 802 |
+
"18": 0.0,
|
| 803 |
+
"19": 0.0,
|
| 804 |
+
"20": 0.0
|
| 805 |
+
},
|
| 806 |
+
"pass@32": {
|
| 807 |
+
"11": 0.465,
|
| 808 |
+
"12": 0.434,
|
| 809 |
+
"13": 0.245,
|
| 810 |
+
"14": 0.029,
|
| 811 |
+
"15": 0.002,
|
| 812 |
+
"16": 0.0,
|
| 813 |
+
"17": 0.0,
|
| 814 |
+
"18": 0.0,
|
| 815 |
+
"19": 0.0,
|
| 816 |
+
"20": 0.0
|
| 817 |
+
},
|
| 818 |
+
"pass@64": {
|
| 819 |
+
"11": 0.481,
|
| 820 |
+
"12": 0.446,
|
| 821 |
+
"13": 0.266,
|
| 822 |
+
"14": 0.038,
|
| 823 |
+
"15": 0.002,
|
| 824 |
+
"16": 0.0,
|
| 825 |
+
"17": 0.0,
|
| 826 |
+
"18": 0.0,
|
| 827 |
+
"19": 0.0,
|
| 828 |
+
"20": 0.0
|
| 829 |
+
},
|
| 830 |
+
"pass@128": {
|
| 831 |
+
"11": 0.499,
|
| 832 |
+
"12": 0.459,
|
| 833 |
+
"13": 0.287,
|
| 834 |
+
"14": 0.052,
|
| 835 |
+
"15": 0.004,
|
| 836 |
+
"16": 0.001,
|
| 837 |
+
"17": 0.0,
|
| 838 |
+
"18": 0.0,
|
| 839 |
+
"19": 0.0,
|
| 840 |
+
"20": 0.0
|
| 841 |
+
}
|
| 842 |
+
},
|
| 843 |
+
"total_pass_at_k": {
|
| 844 |
+
"pass@1": 0.0621,
|
| 845 |
+
"pass@2": 0.0813,
|
| 846 |
+
"pass@4": 0.0925,
|
| 847 |
+
"pass@8": 0.1027,
|
| 848 |
+
"pass@16": 0.1117,
|
| 849 |
+
"pass@32": 0.1175,
|
| 850 |
+
"pass@64": 0.1233,
|
| 851 |
+
"pass@128": 0.1302
|
| 852 |
+
}
|
| 853 |
+
},
|
| 854 |
+
"ks": [
|
| 855 |
+
1,
|
| 856 |
+
2,
|
| 857 |
+
4,
|
| 858 |
+
8,
|
| 859 |
+
16,
|
| 860 |
+
32,
|
| 861 |
+
64,
|
| 862 |
+
128
|
| 863 |
+
],
|
| 864 |
+
"prompt_counts": {
|
| 865 |
+
"per_template": {
|
| 866 |
+
"crazy_zootopia": {
|
| 867 |
+
"per_op": {
|
| 868 |
+
"11": 353,
|
| 869 |
+
"12": 354,
|
| 870 |
+
"13": 319,
|
| 871 |
+
"14": 321,
|
| 872 |
+
"15": 346,
|
| 873 |
+
"16": 310,
|
| 874 |
+
"17": 346,
|
| 875 |
+
"18": 350,
|
| 876 |
+
"19": 333,
|
| 877 |
+
"20": 333
|
| 878 |
+
},
|
| 879 |
+
"total": 3365
|
| 880 |
+
},
|
| 881 |
+
"movie_festival_awards": {
|
| 882 |
+
"per_op": {
|
| 883 |
+
"11": 315,
|
| 884 |
+
"12": 327,
|
| 885 |
+
"13": 324,
|
| 886 |
+
"14": 337,
|
| 887 |
+
"15": 324,
|
| 888 |
+
"16": 339,
|
| 889 |
+
"17": 332,
|
| 890 |
+
"18": 310,
|
| 891 |
+
"19": 331,
|
| 892 |
+
"20": 333
|
| 893 |
+
},
|
| 894 |
+
"total": 3272
|
| 895 |
+
},
|
| 896 |
+
"teachers_in_school": {
|
| 897 |
+
"per_op": {
|
| 898 |
+
"11": 332,
|
| 899 |
+
"12": 319,
|
| 900 |
+
"13": 357,
|
| 901 |
+
"14": 342,
|
| 902 |
+
"15": 330,
|
| 903 |
+
"16": 351,
|
| 904 |
+
"17": 322,
|
| 905 |
+
"18": 340,
|
| 906 |
+
"19": 336,
|
| 907 |
+
"20": 334
|
| 908 |
+
},
|
| 909 |
+
"total": 3363
|
| 910 |
+
}
|
| 911 |
+
},
|
| 912 |
+
"total": {
|
| 913 |
+
"per_op": {
|
| 914 |
+
"11": 1000,
|
| 915 |
+
"12": 1000,
|
| 916 |
+
"13": 1000,
|
| 917 |
+
"14": 1000,
|
| 918 |
+
"15": 1000,
|
| 919 |
+
"16": 1000,
|
| 920 |
+
"17": 1000,
|
| 921 |
+
"18": 1000,
|
| 922 |
+
"19": 1000,
|
| 923 |
+
"20": 1000
|
| 924 |
+
},
|
| 925 |
+
"total": 10000
|
| 926 |
+
}
|
| 927 |
+
}
|
| 928 |
+
},
|
| 929 |
+
"pretrain_050302_ckpt18586_id_generations.jsonl.graph_results.jsonl": {
|
| 930 |
+
"per_template": {
|
| 931 |
+
"crazy_zootopia": {
|
| 932 |
+
"per_op_pass_at_k": {
|
| 933 |
+
"2": {
|
| 934 |
+
"pass@1": 0.9688473520249221,
|
| 935 |
+
"pass@2": 0.9719626168224299,
|
| 936 |
+
"pass@4": 0.9750778816199377,
|
| 937 |
+
"pass@8": 0.9813084112149533,
|
| 938 |
+
"pass@16": 0.9844236760124611,
|
| 939 |
+
"pass@32": 0.9844236760124611,
|
| 940 |
+
"pass@64": 0.9844236760124611,
|
| 941 |
+
"pass@128": 0.9937694704049844
|
| 942 |
+
},
|
| 943 |
+
"3": {
|
| 944 |
+
"pass@1": 0.9418960244648318,
|
| 945 |
+
"pass@2": 0.9663608562691132,
|
| 946 |
+
"pass@4": 0.9724770642201835,
|
| 947 |
+
"pass@8": 0.9755351681957186,
|
| 948 |
+
"pass@16": 0.9755351681957186,
|
| 949 |
+
"pass@32": 0.981651376146789,
|
| 950 |
+
"pass@64": 0.9847094801223242,
|
| 951 |
+
"pass@128": 0.9877675840978594
|
| 952 |
+
},
|
| 953 |
+
"4": {
|
| 954 |
+
"pass@1": 0.65625,
|
| 955 |
+
"pass@2": 0.675,
|
| 956 |
+
"pass@4": 0.696875,
|
| 957 |
+
"pass@8": 0.7125,
|
| 958 |
+
"pass@16": 0.725,
|
| 959 |
+
"pass@32": 0.725,
|
| 960 |
+
"pass@64": 0.728125,
|
| 961 |
+
"pass@128": 0.73125
|
| 962 |
+
},
|
| 963 |
+
"5": {
|
| 964 |
+
"pass@1": 0.5523809523809524,
|
| 965 |
+
"pass@2": 0.5841269841269842,
|
| 966 |
+
"pass@4": 0.6031746031746031,
|
| 967 |
+
"pass@8": 0.6253968253968254,
|
| 968 |
+
"pass@16": 0.638095238095238,
|
| 969 |
+
"pass@32": 0.6412698412698413,
|
| 970 |
+
"pass@64": 0.6476190476190476,
|
| 971 |
+
"pass@128": 0.6507936507936508
|
| 972 |
+
},
|
| 973 |
+
"6": {
|
| 974 |
+
"pass@1": 0.5119760479041916,
|
| 975 |
+
"pass@2": 0.5359281437125748,
|
| 976 |
+
"pass@4": 0.5688622754491018,
|
| 977 |
+
"pass@8": 0.5958083832335329,
|
| 978 |
+
"pass@16": 0.6107784431137725,
|
| 979 |
+
"pass@32": 0.6317365269461078,
|
| 980 |
+
"pass@64": 0.6437125748502994,
|
| 981 |
+
"pass@128": 0.6526946107784432
|
| 982 |
+
},
|
| 983 |
+
"7": {
|
| 984 |
+
"pass@1": 0.48520710059171596,
|
| 985 |
+
"pass@2": 0.5059171597633136,
|
| 986 |
+
"pass@4": 0.5355029585798816,
|
| 987 |
+
"pass@8": 0.5650887573964497,
|
| 988 |
+
"pass@16": 0.5710059171597633,
|
| 989 |
+
"pass@32": 0.5828402366863905,
|
| 990 |
+
"pass@64": 0.5887573964497042,
|
| 991 |
+
"pass@128": 0.6005917159763313
|
| 992 |
+
},
|
| 993 |
+
"8": {
|
| 994 |
+
"pass@1": 0.4198717948717949,
|
| 995 |
+
"pass@2": 0.47115384615384615,
|
| 996 |
+
"pass@4": 0.5,
|
| 997 |
+
"pass@8": 0.5352564102564102,
|
| 998 |
+
"pass@16": 0.5576923076923077,
|
| 999 |
+
"pass@32": 0.5673076923076923,
|
| 1000 |
+
"pass@64": 0.5769230769230769,
|
| 1001 |
+
"pass@128": 0.5897435897435898
|
| 1002 |
+
},
|
| 1003 |
+
"9": {
|
| 1004 |
+
"pass@1": 0.4140845070422535,
|
| 1005 |
+
"pass@2": 0.4563380281690141,
|
| 1006 |
+
"pass@4": 0.48450704225352115,
|
| 1007 |
+
"pass@8": 0.5126760563380282,
|
| 1008 |
+
"pass@16": 0.5352112676056338,
|
| 1009 |
+
"pass@32": 0.571830985915493,
|
| 1010 |
+
"pass@64": 0.5887323943661972,
|
| 1011 |
+
"pass@128": 0.6084507042253521
|
| 1012 |
+
},
|
| 1013 |
+
"10": {
|
| 1014 |
+
"pass@1": 0.41002949852507375,
|
| 1015 |
+
"pass@2": 0.44542772861356933,
|
| 1016 |
+
"pass@4": 0.471976401179941,
|
| 1017 |
+
"pass@8": 0.5014749262536873,
|
| 1018 |
+
"pass@16": 0.5191740412979351,
|
| 1019 |
+
"pass@32": 0.5309734513274337,
|
| 1020 |
+
"pass@64": 0.5368731563421829,
|
| 1021 |
+
"pass@128": 0.5427728613569321
|
| 1022 |
+
}
|
| 1023 |
+
},
|
| 1024 |
+
"per_op_pass_at_columns": {
|
| 1025 |
+
"pass@1": {
|
| 1026 |
+
"2": 0.9688473520249221,
|
| 1027 |
+
"3": 0.9418960244648318,
|
| 1028 |
+
"4": 0.65625,
|
| 1029 |
+
"5": 0.5523809523809524,
|
| 1030 |
+
"6": 0.5119760479041916,
|
| 1031 |
+
"7": 0.48520710059171596,
|
| 1032 |
+
"8": 0.4198717948717949,
|
| 1033 |
+
"9": 0.4140845070422535,
|
| 1034 |
+
"10": 0.41002949852507375
|
| 1035 |
+
},
|
| 1036 |
+
"pass@2": {
|
| 1037 |
+
"2": 0.9719626168224299,
|
| 1038 |
+
"3": 0.9663608562691132,
|
| 1039 |
+
"4": 0.675,
|
| 1040 |
+
"5": 0.5841269841269842,
|
| 1041 |
+
"6": 0.5359281437125748,
|
| 1042 |
+
"7": 0.5059171597633136,
|
| 1043 |
+
"8": 0.47115384615384615,
|
| 1044 |
+
"9": 0.4563380281690141,
|
| 1045 |
+
"10": 0.44542772861356933
|
| 1046 |
+
},
|
| 1047 |
+
"pass@4": {
|
| 1048 |
+
"2": 0.9750778816199377,
|
| 1049 |
+
"3": 0.9724770642201835,
|
| 1050 |
+
"4": 0.696875,
|
| 1051 |
+
"5": 0.6031746031746031,
|
| 1052 |
+
"6": 0.5688622754491018,
|
| 1053 |
+
"7": 0.5355029585798816,
|
| 1054 |
+
"8": 0.5,
|
| 1055 |
+
"9": 0.48450704225352115,
|
| 1056 |
+
"10": 0.471976401179941
|
| 1057 |
+
},
|
| 1058 |
+
"pass@8": {
|
| 1059 |
+
"2": 0.9813084112149533,
|
| 1060 |
+
"3": 0.9755351681957186,
|
| 1061 |
+
"4": 0.7125,
|
| 1062 |
+
"5": 0.6253968253968254,
|
| 1063 |
+
"6": 0.5958083832335329,
|
| 1064 |
+
"7": 0.5650887573964497,
|
| 1065 |
+
"8": 0.5352564102564102,
|
| 1066 |
+
"9": 0.5126760563380282,
|
| 1067 |
+
"10": 0.5014749262536873
|
| 1068 |
+
},
|
| 1069 |
+
"pass@16": {
|
| 1070 |
+
"2": 0.9844236760124611,
|
| 1071 |
+
"3": 0.9755351681957186,
|
| 1072 |
+
"4": 0.725,
|
| 1073 |
+
"5": 0.638095238095238,
|
| 1074 |
+
"6": 0.6107784431137725,
|
| 1075 |
+
"7": 0.5710059171597633,
|
| 1076 |
+
"8": 0.5576923076923077,
|
| 1077 |
+
"9": 0.5352112676056338,
|
| 1078 |
+
"10": 0.5191740412979351
|
| 1079 |
+
},
|
| 1080 |
+
"pass@32": {
|
| 1081 |
+
"2": 0.9844236760124611,
|
| 1082 |
+
"3": 0.981651376146789,
|
| 1083 |
+
"4": 0.725,
|
| 1084 |
+
"5": 0.6412698412698413,
|
| 1085 |
+
"6": 0.6317365269461078,
|
| 1086 |
+
"7": 0.5828402366863905,
|
| 1087 |
+
"8": 0.5673076923076923,
|
| 1088 |
+
"9": 0.571830985915493,
|
| 1089 |
+
"10": 0.5309734513274337
|
| 1090 |
+
},
|
| 1091 |
+
"pass@64": {
|
| 1092 |
+
"2": 0.9844236760124611,
|
| 1093 |
+
"3": 0.9847094801223242,
|
| 1094 |
+
"4": 0.728125,
|
| 1095 |
+
"5": 0.6476190476190476,
|
| 1096 |
+
"6": 0.6437125748502994,
|
| 1097 |
+
"7": 0.5887573964497042,
|
| 1098 |
+
"8": 0.5769230769230769,
|
| 1099 |
+
"9": 0.5887323943661972,
|
| 1100 |
+
"10": 0.5368731563421829
|
| 1101 |
+
},
|
| 1102 |
+
"pass@128": {
|
| 1103 |
+
"2": 0.9937694704049844,
|
| 1104 |
+
"3": 0.9877675840978594,
|
| 1105 |
+
"4": 0.73125,
|
| 1106 |
+
"5": 0.6507936507936508,
|
| 1107 |
+
"6": 0.6526946107784432,
|
| 1108 |
+
"7": 0.6005917159763313,
|
| 1109 |
+
"8": 0.5897435897435898,
|
| 1110 |
+
"9": 0.6084507042253521,
|
| 1111 |
+
"10": 0.5427728613569321
|
| 1112 |
+
}
|
| 1113 |
+
},
|
| 1114 |
+
"total_pass_at_k": {
|
| 1115 |
+
"pass@1": 0.5927051671732523,
|
| 1116 |
+
"pass@2": 0.6207362377575144,
|
| 1117 |
+
"pass@4": 0.6426882809861534,
|
| 1118 |
+
"pass@8": 0.6646403242147924,
|
| 1119 |
+
"pass@16": 0.6771361026680176,
|
| 1120 |
+
"pass@32": 0.6886187098953056,
|
| 1121 |
+
"pass@64": 0.6957109084768659,
|
| 1122 |
+
"pass@128": 0.7044917257683215
|
| 1123 |
+
}
|
| 1124 |
+
},
|
| 1125 |
+
"movie_festival_awards": {
|
| 1126 |
+
"per_op_pass_at_k": {
|
| 1127 |
+
"2": {
|
| 1128 |
+
"pass@1": 0.9542857142857143,
|
| 1129 |
+
"pass@2": 0.9714285714285714,
|
| 1130 |
+
"pass@4": 0.9857142857142858,
|
| 1131 |
+
"pass@8": 0.9885714285714285,
|
| 1132 |
+
"pass@16": 0.9942857142857143,
|
| 1133 |
+
"pass@32": 0.9942857142857143,
|
| 1134 |
+
"pass@64": 0.9942857142857143,
|
| 1135 |
+
"pass@128": 1.0
|
| 1136 |
+
},
|
| 1137 |
+
"3": {
|
| 1138 |
+
"pass@1": 0.9387755102040817,
|
| 1139 |
+
"pass@2": 0.9591836734693877,
|
| 1140 |
+
"pass@4": 0.967930029154519,
|
| 1141 |
+
"pass@8": 0.9737609329446064,
|
| 1142 |
+
"pass@16": 0.9795918367346939,
|
| 1143 |
+
"pass@32": 0.9795918367346939,
|
| 1144 |
+
"pass@64": 0.9795918367346939,
|
| 1145 |
+
"pass@128": 0.9825072886297376
|
| 1146 |
+
},
|
| 1147 |
+
"4": {
|
| 1148 |
+
"pass@1": 0.631578947368421,
|
| 1149 |
+
"pass@2": 0.6783625730994152,
|
| 1150 |
+
"pass@4": 0.7105263157894737,
|
| 1151 |
+
"pass@8": 0.7251461988304093,
|
| 1152 |
+
"pass@16": 0.7456140350877193,
|
| 1153 |
+
"pass@32": 0.7514619883040936,
|
| 1154 |
+
"pass@64": 0.7719298245614035,
|
| 1155 |
+
"pass@128": 0.7923976608187134
|
| 1156 |
+
},
|
| 1157 |
+
"5": {
|
| 1158 |
+
"pass@1": 0.5323529411764706,
|
| 1159 |
+
"pass@2": 0.5647058823529412,
|
| 1160 |
+
"pass@4": 0.5794117647058824,
|
| 1161 |
+
"pass@8": 0.6,
|
| 1162 |
+
"pass@16": 0.6147058823529412,
|
| 1163 |
+
"pass@32": 0.6352941176470588,
|
| 1164 |
+
"pass@64": 0.65,
|
| 1165 |
+
"pass@128": 0.6529411764705882
|
| 1166 |
+
},
|
| 1167 |
+
"6": {
|
| 1168 |
+
"pass@1": 0.49842271293375395,
|
| 1169 |
+
"pass@2": 0.5205047318611987,
|
| 1170 |
+
"pass@4": 0.5457413249211357,
|
| 1171 |
+
"pass@8": 0.5520504731861199,
|
| 1172 |
+
"pass@16": 0.5772870662460567,
|
| 1173 |
+
"pass@32": 0.5899053627760252,
|
| 1174 |
+
"pass@64": 0.6088328075709779,
|
| 1175 |
+
"pass@128": 0.6309148264984227
|
| 1176 |
+
},
|
| 1177 |
+
"7": {
|
| 1178 |
+
"pass@1": 0.43670886075949367,
|
| 1179 |
+
"pass@2": 0.4588607594936709,
|
| 1180 |
+
"pass@4": 0.4873417721518987,
|
| 1181 |
+
"pass@8": 0.5189873417721519,
|
| 1182 |
+
"pass@16": 0.5348101265822784,
|
| 1183 |
+
"pass@32": 0.5569620253164557,
|
| 1184 |
+
"pass@64": 0.560126582278481,
|
| 1185 |
+
"pass@128": 0.5727848101265823
|
| 1186 |
+
},
|
| 1187 |
+
"8": {
|
| 1188 |
+
"pass@1": 0.45045045045045046,
|
| 1189 |
+
"pass@2": 0.47147147147147145,
|
| 1190 |
+
"pass@4": 0.4954954954954955,
|
| 1191 |
+
"pass@8": 0.5195195195195195,
|
| 1192 |
+
"pass@16": 0.5375375375375375,
|
| 1193 |
+
"pass@32": 0.5765765765765766,
|
| 1194 |
+
"pass@64": 0.5945945945945946,
|
| 1195 |
+
"pass@128": 0.6216216216216216
|
| 1196 |
+
},
|
| 1197 |
+
"9": {
|
| 1198 |
+
"pass@1": 0.3890675241157556,
|
| 1199 |
+
"pass@2": 0.45016077170418006,
|
| 1200 |
+
"pass@4": 0.5112540192926045,
|
| 1201 |
+
"pass@8": 0.5273311897106109,
|
| 1202 |
+
"pass@16": 0.5466237942122186,
|
| 1203 |
+
"pass@32": 0.5562700964630225,
|
| 1204 |
+
"pass@64": 0.5659163987138264,
|
| 1205 |
+
"pass@128": 0.5819935691318328
|
| 1206 |
+
},
|
| 1207 |
+
"10": {
|
| 1208 |
+
"pass@1": 0.3582089552238806,
|
| 1209 |
+
"pass@2": 0.4059701492537313,
|
| 1210 |
+
"pass@4": 0.43582089552238806,
|
| 1211 |
+
"pass@8": 0.4597014925373134,
|
| 1212 |
+
"pass@16": 0.4746268656716418,
|
| 1213 |
+
"pass@32": 0.48656716417910445,
|
| 1214 |
+
"pass@64": 0.5014925373134328,
|
| 1215 |
+
"pass@128": 0.5194029850746269
|
| 1216 |
+
}
|
| 1217 |
+
},
|
| 1218 |
+
"per_op_pass_at_columns": {
|
| 1219 |
+
"pass@1": {
|
| 1220 |
+
"2": 0.9542857142857143,
|
| 1221 |
+
"3": 0.9387755102040817,
|
| 1222 |
+
"4": 0.631578947368421,
|
| 1223 |
+
"5": 0.5323529411764706,
|
| 1224 |
+
"6": 0.49842271293375395,
|
| 1225 |
+
"7": 0.43670886075949367,
|
| 1226 |
+
"8": 0.45045045045045046,
|
| 1227 |
+
"9": 0.3890675241157556,
|
| 1228 |
+
"10": 0.3582089552238806
|
| 1229 |
+
},
|
| 1230 |
+
"pass@2": {
|
| 1231 |
+
"2": 0.9714285714285714,
|
| 1232 |
+
"3": 0.9591836734693877,
|
| 1233 |
+
"4": 0.6783625730994152,
|
| 1234 |
+
"5": 0.5647058823529412,
|
| 1235 |
+
"6": 0.5205047318611987,
|
| 1236 |
+
"7": 0.4588607594936709,
|
| 1237 |
+
"8": 0.47147147147147145,
|
| 1238 |
+
"9": 0.45016077170418006,
|
| 1239 |
+
"10": 0.4059701492537313
|
| 1240 |
+
},
|
| 1241 |
+
"pass@4": {
|
| 1242 |
+
"2": 0.9857142857142858,
|
| 1243 |
+
"3": 0.967930029154519,
|
| 1244 |
+
"4": 0.7105263157894737,
|
| 1245 |
+
"5": 0.5794117647058824,
|
| 1246 |
+
"6": 0.5457413249211357,
|
| 1247 |
+
"7": 0.4873417721518987,
|
| 1248 |
+
"8": 0.4954954954954955,
|
| 1249 |
+
"9": 0.5112540192926045,
|
| 1250 |
+
"10": 0.43582089552238806
|
| 1251 |
+
},
|
| 1252 |
+
"pass@8": {
|
| 1253 |
+
"2": 0.9885714285714285,
|
| 1254 |
+
"3": 0.9737609329446064,
|
| 1255 |
+
"4": 0.7251461988304093,
|
| 1256 |
+
"5": 0.6,
|
| 1257 |
+
"6": 0.5520504731861199,
|
| 1258 |
+
"7": 0.5189873417721519,
|
| 1259 |
+
"8": 0.5195195195195195,
|
| 1260 |
+
"9": 0.5273311897106109,
|
| 1261 |
+
"10": 0.4597014925373134
|
| 1262 |
+
},
|
| 1263 |
+
"pass@16": {
|
| 1264 |
+
"2": 0.9942857142857143,
|
| 1265 |
+
"3": 0.9795918367346939,
|
| 1266 |
+
"4": 0.7456140350877193,
|
| 1267 |
+
"5": 0.6147058823529412,
|
| 1268 |
+
"6": 0.5772870662460567,
|
| 1269 |
+
"7": 0.5348101265822784,
|
| 1270 |
+
"8": 0.5375375375375375,
|
| 1271 |
+
"9": 0.5466237942122186,
|
| 1272 |
+
"10": 0.4746268656716418
|
| 1273 |
+
},
|
| 1274 |
+
"pass@32": {
|
| 1275 |
+
"2": 0.9942857142857143,
|
| 1276 |
+
"3": 0.9795918367346939,
|
| 1277 |
+
"4": 0.7514619883040936,
|
| 1278 |
+
"5": 0.6352941176470588,
|
| 1279 |
+
"6": 0.5899053627760252,
|
| 1280 |
+
"7": 0.5569620253164557,
|
| 1281 |
+
"8": 0.5765765765765766,
|
| 1282 |
+
"9": 0.5562700964630225,
|
| 1283 |
+
"10": 0.48656716417910445
|
| 1284 |
+
},
|
| 1285 |
+
"pass@64": {
|
| 1286 |
+
"2": 0.9942857142857143,
|
| 1287 |
+
"3": 0.9795918367346939,
|
| 1288 |
+
"4": 0.7719298245614035,
|
| 1289 |
+
"5": 0.65,
|
| 1290 |
+
"6": 0.6088328075709779,
|
| 1291 |
+
"7": 0.560126582278481,
|
| 1292 |
+
"8": 0.5945945945945946,
|
| 1293 |
+
"9": 0.5659163987138264,
|
| 1294 |
+
"10": 0.5014925373134328
|
| 1295 |
+
},
|
| 1296 |
+
"pass@128": {
|
| 1297 |
+
"2": 1.0,
|
| 1298 |
+
"3": 0.9825072886297376,
|
| 1299 |
+
"4": 0.7923976608187134,
|
| 1300 |
+
"5": 0.6529411764705882,
|
| 1301 |
+
"6": 0.6309148264984227,
|
| 1302 |
+
"7": 0.5727848101265823,
|
| 1303 |
+
"8": 0.6216216216216216,
|
| 1304 |
+
"9": 0.5819935691318328,
|
| 1305 |
+
"10": 0.5194029850746269
|
| 1306 |
+
}
|
| 1307 |
+
},
|
| 1308 |
+
"total_pass_at_k": {
|
| 1309 |
+
"pass@1": 0.5825242718446602,
|
| 1310 |
+
"pass@2": 0.6146635420154001,
|
| 1311 |
+
"pass@4": 0.6407766990291263,
|
| 1312 |
+
"pass@8": 0.6568463341144961,
|
| 1313 |
+
"pass@16": 0.672246401071309,
|
| 1314 |
+
"pass@32": 0.6856377636424507,
|
| 1315 |
+
"pass@64": 0.6966856377636425,
|
| 1316 |
+
"pass@128": 0.7107465684633412
|
| 1317 |
+
}
|
| 1318 |
+
},
|
| 1319 |
+
"teachers_in_school": {
|
| 1320 |
+
"per_op_pass_at_k": {
|
| 1321 |
+
"2": {
|
| 1322 |
+
"pass@1": 0.9696048632218845,
|
| 1323 |
+
"pass@2": 0.9787234042553191,
|
| 1324 |
+
"pass@4": 0.9817629179331308,
|
| 1325 |
+
"pass@8": 0.9878419452887538,
|
| 1326 |
+
"pass@16": 0.9908814589665653,
|
| 1327 |
+
"pass@32": 0.993920972644377,
|
| 1328 |
+
"pass@64": 0.993920972644377,
|
| 1329 |
+
"pass@128": 0.993920972644377
|
| 1330 |
+
},
|
| 1331 |
+
"3": {
|
| 1332 |
+
"pass@1": 0.9454545454545454,
|
| 1333 |
+
"pass@2": 0.9515151515151515,
|
| 1334 |
+
"pass@4": 0.9575757575757575,
|
| 1335 |
+
"pass@8": 0.9606060606060606,
|
| 1336 |
+
"pass@16": 0.9696969696969697,
|
| 1337 |
+
"pass@32": 0.9757575757575757,
|
| 1338 |
+
"pass@64": 0.9787878787878788,
|
| 1339 |
+
"pass@128": 0.9818181818181818
|
| 1340 |
+
},
|
| 1341 |
+
"4": {
|
| 1342 |
+
"pass@1": 0.636094674556213,
|
| 1343 |
+
"pass@2": 0.6627218934911243,
|
| 1344 |
+
"pass@4": 0.6982248520710059,
|
| 1345 |
+
"pass@8": 0.7071005917159763,
|
| 1346 |
+
"pass@16": 0.7159763313609467,
|
| 1347 |
+
"pass@32": 0.7337278106508875,
|
| 1348 |
+
"pass@64": 0.742603550295858,
|
| 1349 |
+
"pass@128": 0.7514792899408284
|
| 1350 |
+
},
|
| 1351 |
+
"5": {
|
| 1352 |
+
"pass@1": 0.5623188405797102,
|
| 1353 |
+
"pass@2": 0.6057971014492753,
|
| 1354 |
+
"pass@4": 0.6144927536231884,
|
| 1355 |
+
"pass@8": 0.6260869565217392,
|
| 1356 |
+
"pass@16": 0.6434782608695652,
|
| 1357 |
+
"pass@32": 0.6550724637681159,
|
| 1358 |
+
"pass@64": 0.663768115942029,
|
| 1359 |
+
"pass@128": 0.6666666666666666
|
| 1360 |
+
},
|
| 1361 |
+
"6": {
|
| 1362 |
+
"pass@1": 0.46418338108882523,
|
| 1363 |
+
"pass@2": 0.4871060171919771,
|
| 1364 |
+
"pass@4": 0.5214899713467048,
|
| 1365 |
+
"pass@8": 0.5415472779369628,
|
| 1366 |
+
"pass@16": 0.5530085959885387,
|
| 1367 |
+
"pass@32": 0.5587392550143266,
|
| 1368 |
+
"pass@64": 0.5673352435530086,
|
| 1369 |
+
"pass@128": 0.5759312320916905
|
| 1370 |
+
},
|
| 1371 |
+
"7": {
|
| 1372 |
+
"pass@1": 0.4653179190751445,
|
| 1373 |
+
"pass@2": 0.5115606936416185,
|
| 1374 |
+
"pass@4": 0.5289017341040463,
|
| 1375 |
+
"pass@8": 0.5404624277456648,
|
| 1376 |
+
"pass@16": 0.5578034682080925,
|
| 1377 |
+
"pass@32": 0.5635838150289018,
|
| 1378 |
+
"pass@64": 0.5722543352601156,
|
| 1379 |
+
"pass@128": 0.5924855491329479
|
| 1380 |
+
},
|
| 1381 |
+
"8": {
|
| 1382 |
+
"pass@1": 0.4,
|
| 1383 |
+
"pass@2": 0.4422535211267606,
|
| 1384 |
+
"pass@4": 0.4788732394366197,
|
| 1385 |
+
"pass@8": 0.49859154929577465,
|
| 1386 |
+
"pass@16": 0.5014084507042254,
|
| 1387 |
+
"pass@32": 0.5098591549295775,
|
| 1388 |
+
"pass@64": 0.532394366197183,
|
| 1389 |
+
"pass@128": 0.5408450704225352
|
| 1390 |
+
},
|
| 1391 |
+
"9": {
|
| 1392 |
+
"pass@1": 0.38922155688622756,
|
| 1393 |
+
"pass@2": 0.437125748502994,
|
| 1394 |
+
"pass@4": 0.46407185628742514,
|
| 1395 |
+
"pass@8": 0.4820359281437126,
|
| 1396 |
+
"pass@16": 0.5,
|
| 1397 |
+
"pass@32": 0.5089820359281437,
|
| 1398 |
+
"pass@64": 0.5179640718562875,
|
| 1399 |
+
"pass@128": 0.5299401197604791
|
| 1400 |
+
},
|
| 1401 |
+
"10": {
|
| 1402 |
+
"pass@1": 0.4294478527607362,
|
| 1403 |
+
"pass@2": 0.46319018404907975,
|
| 1404 |
+
"pass@4": 0.4938650306748466,
|
| 1405 |
+
"pass@8": 0.5030674846625767,
|
| 1406 |
+
"pass@16": 0.5245398773006135,
|
| 1407 |
+
"pass@32": 0.5398773006134969,
|
| 1408 |
+
"pass@64": 0.549079754601227,
|
| 1409 |
+
"pass@128": 0.5613496932515337
|
| 1410 |
+
}
|
| 1411 |
+
},
|
| 1412 |
+
"per_op_pass_at_columns": {
|
| 1413 |
+
"pass@1": {
|
| 1414 |
+
"2": 0.9696048632218845,
|
| 1415 |
+
"3": 0.9454545454545454,
|
| 1416 |
+
"4": 0.636094674556213,
|
| 1417 |
+
"5": 0.5623188405797102,
|
| 1418 |
+
"6": 0.46418338108882523,
|
| 1419 |
+
"7": 0.4653179190751445,
|
| 1420 |
+
"8": 0.4,
|
| 1421 |
+
"9": 0.38922155688622756,
|
| 1422 |
+
"10": 0.4294478527607362
|
| 1423 |
+
},
|
| 1424 |
+
"pass@2": {
|
| 1425 |
+
"2": 0.9787234042553191,
|
| 1426 |
+
"3": 0.9515151515151515,
|
| 1427 |
+
"4": 0.6627218934911243,
|
| 1428 |
+
"5": 0.6057971014492753,
|
| 1429 |
+
"6": 0.4871060171919771,
|
| 1430 |
+
"7": 0.5115606936416185,
|
| 1431 |
+
"8": 0.4422535211267606,
|
| 1432 |
+
"9": 0.437125748502994,
|
| 1433 |
+
"10": 0.46319018404907975
|
| 1434 |
+
},
|
| 1435 |
+
"pass@4": {
|
| 1436 |
+
"2": 0.9817629179331308,
|
| 1437 |
+
"3": 0.9575757575757575,
|
| 1438 |
+
"4": 0.6982248520710059,
|
| 1439 |
+
"5": 0.6144927536231884,
|
| 1440 |
+
"6": 0.5214899713467048,
|
| 1441 |
+
"7": 0.5289017341040463,
|
| 1442 |
+
"8": 0.4788732394366197,
|
| 1443 |
+
"9": 0.46407185628742514,
|
| 1444 |
+
"10": 0.4938650306748466
|
| 1445 |
+
},
|
| 1446 |
+
"pass@8": {
|
| 1447 |
+
"2": 0.9878419452887538,
|
| 1448 |
+
"3": 0.9606060606060606,
|
| 1449 |
+
"4": 0.7071005917159763,
|
| 1450 |
+
"5": 0.6260869565217392,
|
| 1451 |
+
"6": 0.5415472779369628,
|
| 1452 |
+
"7": 0.5404624277456648,
|
| 1453 |
+
"8": 0.49859154929577465,
|
| 1454 |
+
"9": 0.4820359281437126,
|
| 1455 |
+
"10": 0.5030674846625767
|
| 1456 |
+
},
|
| 1457 |
+
"pass@16": {
|
| 1458 |
+
"2": 0.9908814589665653,
|
| 1459 |
+
"3": 0.9696969696969697,
|
| 1460 |
+
"4": 0.7159763313609467,
|
| 1461 |
+
"5": 0.6434782608695652,
|
| 1462 |
+
"6": 0.5530085959885387,
|
| 1463 |
+
"7": 0.5578034682080925,
|
| 1464 |
+
"8": 0.5014084507042254,
|
| 1465 |
+
"9": 0.5,
|
| 1466 |
+
"10": 0.5245398773006135
|
| 1467 |
+
},
|
| 1468 |
+
"pass@32": {
|
| 1469 |
+
"2": 0.993920972644377,
|
| 1470 |
+
"3": 0.9757575757575757,
|
| 1471 |
+
"4": 0.7337278106508875,
|
| 1472 |
+
"5": 0.6550724637681159,
|
| 1473 |
+
"6": 0.5587392550143266,
|
| 1474 |
+
"7": 0.5635838150289018,
|
| 1475 |
+
"8": 0.5098591549295775,
|
| 1476 |
+
"9": 0.5089820359281437,
|
| 1477 |
+
"10": 0.5398773006134969
|
| 1478 |
+
},
|
| 1479 |
+
"pass@64": {
|
| 1480 |
+
"2": 0.993920972644377,
|
| 1481 |
+
"3": 0.9787878787878788,
|
| 1482 |
+
"4": 0.742603550295858,
|
| 1483 |
+
"5": 0.663768115942029,
|
| 1484 |
+
"6": 0.5673352435530086,
|
| 1485 |
+
"7": 0.5722543352601156,
|
| 1486 |
+
"8": 0.532394366197183,
|
| 1487 |
+
"9": 0.5179640718562875,
|
| 1488 |
+
"10": 0.549079754601227
|
| 1489 |
+
},
|
| 1490 |
+
"pass@128": {
|
| 1491 |
+
"2": 0.993920972644377,
|
| 1492 |
+
"3": 0.9818181818181818,
|
| 1493 |
+
"4": 0.7514792899408284,
|
| 1494 |
+
"5": 0.6666666666666666,
|
| 1495 |
+
"6": 0.5759312320916905,
|
| 1496 |
+
"7": 0.5924855491329479,
|
| 1497 |
+
"8": 0.5408450704225352,
|
| 1498 |
+
"9": 0.5299401197604791,
|
| 1499 |
+
"10": 0.5613496932515337
|
| 1500 |
+
}
|
| 1501 |
+
},
|
| 1502 |
+
"total_pass_at_k": {
|
| 1503 |
+
"pass@1": 0.5815858453473133,
|
| 1504 |
+
"pass@2": 0.6127129750982963,
|
| 1505 |
+
"pass@4": 0.6349934469200524,
|
| 1506 |
+
"pass@8": 0.6471166448230669,
|
| 1507 |
+
"pass@16": 0.6592398427260813,
|
| 1508 |
+
"pass@32": 0.6684141546526867,
|
| 1509 |
+
"pass@64": 0.6772608125819135,
|
| 1510 |
+
"pass@128": 0.6857798165137615
|
| 1511 |
+
}
|
| 1512 |
+
}
|
| 1513 |
+
},
|
| 1514 |
+
"total": {
|
| 1515 |
+
"per_op_pass_at_k": {
|
| 1516 |
+
"2": {
|
| 1517 |
+
"pass@1": 0.964,
|
| 1518 |
+
"pass@2": 0.974,
|
| 1519 |
+
"pass@4": 0.981,
|
| 1520 |
+
"pass@8": 0.986,
|
| 1521 |
+
"pass@16": 0.99,
|
| 1522 |
+
"pass@32": 0.991,
|
| 1523 |
+
"pass@64": 0.991,
|
| 1524 |
+
"pass@128": 0.996
|
| 1525 |
+
},
|
| 1526 |
+
"3": {
|
| 1527 |
+
"pass@1": 0.942,
|
| 1528 |
+
"pass@2": 0.959,
|
| 1529 |
+
"pass@4": 0.966,
|
| 1530 |
+
"pass@8": 0.97,
|
| 1531 |
+
"pass@16": 0.975,
|
| 1532 |
+
"pass@32": 0.979,
|
| 1533 |
+
"pass@64": 0.981,
|
| 1534 |
+
"pass@128": 0.984
|
| 1535 |
+
},
|
| 1536 |
+
"4": {
|
| 1537 |
+
"pass@1": 0.641,
|
| 1538 |
+
"pass@2": 0.672,
|
| 1539 |
+
"pass@4": 0.702,
|
| 1540 |
+
"pass@8": 0.715,
|
| 1541 |
+
"pass@16": 0.729,
|
| 1542 |
+
"pass@32": 0.737,
|
| 1543 |
+
"pass@64": 0.748,
|
| 1544 |
+
"pass@128": 0.759
|
| 1545 |
+
},
|
| 1546 |
+
"5": {
|
| 1547 |
+
"pass@1": 0.549,
|
| 1548 |
+
"pass@2": 0.585,
|
| 1549 |
+
"pass@4": 0.599,
|
| 1550 |
+
"pass@8": 0.617,
|
| 1551 |
+
"pass@16": 0.632,
|
| 1552 |
+
"pass@32": 0.644,
|
| 1553 |
+
"pass@64": 0.654,
|
| 1554 |
+
"pass@128": 0.657
|
| 1555 |
+
},
|
| 1556 |
+
"6": {
|
| 1557 |
+
"pass@1": 0.491,
|
| 1558 |
+
"pass@2": 0.514,
|
| 1559 |
+
"pass@4": 0.545,
|
| 1560 |
+
"pass@8": 0.563,
|
| 1561 |
+
"pass@16": 0.58,
|
| 1562 |
+
"pass@32": 0.593,
|
| 1563 |
+
"pass@64": 0.606,
|
| 1564 |
+
"pass@128": 0.619
|
| 1565 |
+
},
|
| 1566 |
+
"7": {
|
| 1567 |
+
"pass@1": 0.463,
|
| 1568 |
+
"pass@2": 0.493,
|
| 1569 |
+
"pass@4": 0.518,
|
| 1570 |
+
"pass@8": 0.542,
|
| 1571 |
+
"pass@16": 0.555,
|
| 1572 |
+
"pass@32": 0.568,
|
| 1573 |
+
"pass@64": 0.574,
|
| 1574 |
+
"pass@128": 0.589
|
| 1575 |
+
},
|
| 1576 |
+
"8": {
|
| 1577 |
+
"pass@1": 0.423,
|
| 1578 |
+
"pass@2": 0.461,
|
| 1579 |
+
"pass@4": 0.491,
|
| 1580 |
+
"pass@8": 0.517,
|
| 1581 |
+
"pass@16": 0.531,
|
| 1582 |
+
"pass@32": 0.55,
|
| 1583 |
+
"pass@64": 0.567,
|
| 1584 |
+
"pass@128": 0.583
|
| 1585 |
+
},
|
| 1586 |
+
"9": {
|
| 1587 |
+
"pass@1": 0.398,
|
| 1588 |
+
"pass@2": 0.448,
|
| 1589 |
+
"pass@4": 0.486,
|
| 1590 |
+
"pass@8": 0.507,
|
| 1591 |
+
"pass@16": 0.527,
|
| 1592 |
+
"pass@32": 0.546,
|
| 1593 |
+
"pass@64": 0.558,
|
| 1594 |
+
"pass@128": 0.574
|
| 1595 |
+
},
|
| 1596 |
+
"10": {
|
| 1597 |
+
"pass@1": 0.399,
|
| 1598 |
+
"pass@2": 0.438,
|
| 1599 |
+
"pass@4": 0.467,
|
| 1600 |
+
"pass@8": 0.488,
|
| 1601 |
+
"pass@16": 0.506,
|
| 1602 |
+
"pass@32": 0.519,
|
| 1603 |
+
"pass@64": 0.529,
|
| 1604 |
+
"pass@128": 0.541
|
| 1605 |
+
}
|
| 1606 |
+
},
|
| 1607 |
+
"per_op_pass_at_columns": {
|
| 1608 |
+
"pass@1": {
|
| 1609 |
+
"2": 0.964,
|
| 1610 |
+
"3": 0.942,
|
| 1611 |
+
"4": 0.641,
|
| 1612 |
+
"5": 0.549,
|
| 1613 |
+
"6": 0.491,
|
| 1614 |
+
"7": 0.463,
|
| 1615 |
+
"8": 0.423,
|
| 1616 |
+
"9": 0.398,
|
| 1617 |
+
"10": 0.399
|
| 1618 |
+
},
|
| 1619 |
+
"pass@2": {
|
| 1620 |
+
"2": 0.974,
|
| 1621 |
+
"3": 0.959,
|
| 1622 |
+
"4": 0.672,
|
| 1623 |
+
"5": 0.585,
|
| 1624 |
+
"6": 0.514,
|
| 1625 |
+
"7": 0.493,
|
| 1626 |
+
"8": 0.461,
|
| 1627 |
+
"9": 0.448,
|
| 1628 |
+
"10": 0.438
|
| 1629 |
+
},
|
| 1630 |
+
"pass@4": {
|
| 1631 |
+
"2": 0.981,
|
| 1632 |
+
"3": 0.966,
|
| 1633 |
+
"4": 0.702,
|
| 1634 |
+
"5": 0.599,
|
| 1635 |
+
"6": 0.545,
|
| 1636 |
+
"7": 0.518,
|
| 1637 |
+
"8": 0.491,
|
| 1638 |
+
"9": 0.486,
|
| 1639 |
+
"10": 0.467
|
| 1640 |
+
},
|
| 1641 |
+
"pass@8": {
|
| 1642 |
+
"2": 0.986,
|
| 1643 |
+
"3": 0.97,
|
| 1644 |
+
"4": 0.715,
|
| 1645 |
+
"5": 0.617,
|
| 1646 |
+
"6": 0.563,
|
| 1647 |
+
"7": 0.542,
|
| 1648 |
+
"8": 0.517,
|
| 1649 |
+
"9": 0.507,
|
| 1650 |
+
"10": 0.488
|
| 1651 |
+
},
|
| 1652 |
+
"pass@16": {
|
| 1653 |
+
"2": 0.99,
|
| 1654 |
+
"3": 0.975,
|
| 1655 |
+
"4": 0.729,
|
| 1656 |
+
"5": 0.632,
|
| 1657 |
+
"6": 0.58,
|
| 1658 |
+
"7": 0.555,
|
| 1659 |
+
"8": 0.531,
|
| 1660 |
+
"9": 0.527,
|
| 1661 |
+
"10": 0.506
|
| 1662 |
+
},
|
| 1663 |
+
"pass@32": {
|
| 1664 |
+
"2": 0.991,
|
| 1665 |
+
"3": 0.979,
|
| 1666 |
+
"4": 0.737,
|
| 1667 |
+
"5": 0.644,
|
| 1668 |
+
"6": 0.593,
|
| 1669 |
+
"7": 0.568,
|
| 1670 |
+
"8": 0.55,
|
| 1671 |
+
"9": 0.546,
|
| 1672 |
+
"10": 0.519
|
| 1673 |
+
},
|
| 1674 |
+
"pass@64": {
|
| 1675 |
+
"2": 0.991,
|
| 1676 |
+
"3": 0.981,
|
| 1677 |
+
"4": 0.748,
|
| 1678 |
+
"5": 0.654,
|
| 1679 |
+
"6": 0.606,
|
| 1680 |
+
"7": 0.574,
|
| 1681 |
+
"8": 0.567,
|
| 1682 |
+
"9": 0.558,
|
| 1683 |
+
"10": 0.529
|
| 1684 |
+
},
|
| 1685 |
+
"pass@128": {
|
| 1686 |
+
"2": 0.996,
|
| 1687 |
+
"3": 0.984,
|
| 1688 |
+
"4": 0.759,
|
| 1689 |
+
"5": 0.657,
|
| 1690 |
+
"6": 0.619,
|
| 1691 |
+
"7": 0.589,
|
| 1692 |
+
"8": 0.583,
|
| 1693 |
+
"9": 0.574,
|
| 1694 |
+
"10": 0.541
|
| 1695 |
+
}
|
| 1696 |
+
},
|
| 1697 |
+
"total_pass_at_k": {
|
| 1698 |
+
"pass@1": 0.5855555555555556,
|
| 1699 |
+
"pass@2": 0.616,
|
| 1700 |
+
"pass@4": 0.6394444444444445,
|
| 1701 |
+
"pass@8": 0.6561111111111111,
|
| 1702 |
+
"pass@16": 0.6694444444444444,
|
| 1703 |
+
"pass@32": 0.6807777777777778,
|
| 1704 |
+
"pass@64": 0.6897777777777778,
|
| 1705 |
+
"pass@128": 0.7002222222222222
|
| 1706 |
+
}
|
| 1707 |
+
},
|
| 1708 |
+
"ks": [
|
| 1709 |
+
1,
|
| 1710 |
+
2,
|
| 1711 |
+
4,
|
| 1712 |
+
8,
|
| 1713 |
+
16,
|
| 1714 |
+
32,
|
| 1715 |
+
64,
|
| 1716 |
+
128
|
| 1717 |
+
],
|
| 1718 |
+
"prompt_counts": {
|
| 1719 |
+
"per_template": {
|
| 1720 |
+
"crazy_zootopia": {
|
| 1721 |
+
"per_op": {
|
| 1722 |
+
"2": 321,
|
| 1723 |
+
"3": 327,
|
| 1724 |
+
"4": 320,
|
| 1725 |
+
"5": 315,
|
| 1726 |
+
"6": 334,
|
| 1727 |
+
"7": 338,
|
| 1728 |
+
"8": 312,
|
| 1729 |
+
"9": 355,
|
| 1730 |
+
"10": 339
|
| 1731 |
+
},
|
| 1732 |
+
"total": 2961
|
| 1733 |
+
},
|
| 1734 |
+
"movie_festival_awards": {
|
| 1735 |
+
"per_op": {
|
| 1736 |
+
"2": 350,
|
| 1737 |
+
"3": 343,
|
| 1738 |
+
"4": 342,
|
| 1739 |
+
"5": 340,
|
| 1740 |
+
"6": 317,
|
| 1741 |
+
"7": 316,
|
| 1742 |
+
"8": 333,
|
| 1743 |
+
"9": 311,
|
| 1744 |
+
"10": 335
|
| 1745 |
+
},
|
| 1746 |
+
"total": 2987
|
| 1747 |
+
},
|
| 1748 |
+
"teachers_in_school": {
|
| 1749 |
+
"per_op": {
|
| 1750 |
+
"2": 329,
|
| 1751 |
+
"3": 330,
|
| 1752 |
+
"4": 338,
|
| 1753 |
+
"5": 345,
|
| 1754 |
+
"6": 349,
|
| 1755 |
+
"7": 346,
|
| 1756 |
+
"8": 355,
|
| 1757 |
+
"9": 334,
|
| 1758 |
+
"10": 326
|
| 1759 |
+
},
|
| 1760 |
+
"total": 3052
|
| 1761 |
+
}
|
| 1762 |
+
},
|
| 1763 |
+
"total": {
|
| 1764 |
+
"per_op": {
|
| 1765 |
+
"2": 1000,
|
| 1766 |
+
"3": 1000,
|
| 1767 |
+
"4": 1000,
|
| 1768 |
+
"5": 1000,
|
| 1769 |
+
"6": 1000,
|
| 1770 |
+
"7": 1000,
|
| 1771 |
+
"8": 1000,
|
| 1772 |
+
"9": 1000,
|
| 1773 |
+
"10": 1000
|
| 1774 |
+
},
|
| 1775 |
+
"total": 9000
|
| 1776 |
+
}
|
| 1777 |
+
}
|
| 1778 |
+
}
|
| 1779 |
+
}
|
| 1780 |
+
}
|