ZachW commited on
Commit
792fa95
·
verified ·
1 Parent(s): 7942bf1

Upload extrapolation artifact: 050302 RL OP15-20 step200 score report

Browse files
050302/evals/rl050302_op15_20_step200_merged_hf/graph_results/rl050302_op15_20_step200_mergedhf_paper_eval_r79_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79/gold_graphs", "generated_path": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79", "results_dir": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79/graph_results", "per_file": [{"file": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79/rl050302_op15_20_step200_merged_hf_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 675101, "value_mismatch": 456305, "dependency_mismatch": 234298, "answer_mismatch": 322716, "extra_nodes": 77190, "missing_nodes": 55194, "perfect_with_extra": 7199, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 223602, "value_mismatch": 147938, "dependency_mismatch": 76065, "answer_mismatch": 106076, "extra_nodes": 26563, "perfect_with_extra": 2549, "missing_nodes": 18503}, "teachers_in_school": {"total": 390656, "dependency_mismatch": 78203, "perfect": 228985, "value_mismatch": 155281, "answer_mismatch": 108111, "missing_nodes": 16796, "extra_nodes": 22881, "perfect_with_extra": 1591}, "movie_festival_awards": {"total": 382336, "perfect": 222514, "value_mismatch": 153086, "dependency_mismatch": 80030, "answer_mismatch": 108529, "extra_nodes": 27746, "missing_nodes": 19895, "perfect_with_extra": 3059}}, "results_path": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79/graph_results/rl050302_op15_20_step200_merged_hf_id_generations.jsonl.graph_results.jsonl"}, {"file": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79/rl050302_op15_20_step200_merged_hf_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 145951, "value_mismatch": 1106943, "dependency_mismatch": 1067855, "answer_mismatch": 906497, "extra_nodes": 145397, "missing_nodes": 766500, "perfect_with_extra": 310, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "perfect": 50185, "value_mismatch": 371332, "dependency_mismatch": 358886, "answer_mismatch": 303536, "extra_nodes": 49792, "missing_nodes": 252260, "perfect_with_extra": 137}, "teachers_in_school": {"total": 430464, "perfect": 51174, "value_mismatch": 371053, "dependency_mismatch": 356299, "answer_mismatch": 302893, "extra_nodes": 43501, "missing_nodes": 253506, "perfect_with_extra": 33}, "movie_festival_awards": {"total": 418816, "perfect": 44592, "value_mismatch": 364558, "dependency_mismatch": 352670, "answer_mismatch": 300068, "extra_nodes": 52104, "perfect_with_extra": 140, "missing_nodes": 260734}}, "results_path": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79/graph_results/rl050302_op15_20_step200_merged_hf_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 821052, "value_mismatch": 1563248, "dependency_mismatch": 1302153, "answer_mismatch": 1229213, "extra_nodes": 222587, "missing_nodes": 821694, "perfect_with_extra": 7509, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "/mnt/hdfs/output/work/rl050302_op15_20_step200_mergedhf_paper_eval_r79/graph_results/rl050302_op15_20_step200_mergedhf_paper_eval_r79_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 273787, "value_mismatch": 519270, "dependency_mismatch": 434951, "answer_mismatch": 409612, "extra_nodes": 76355, "perfect_with_extra": 2686, "missing_nodes": 270763}, "teachers_in_school": {"total": 821120, "dependency_mismatch": 434502, "perfect": 280159, "value_mismatch": 526334, "answer_mismatch": 411004, "missing_nodes": 270302, "extra_nodes": 66382, "perfect_with_extra": 1624}, "movie_festival_awards": {"total": 801152, "perfect": 267106, "value_mismatch": 517644, "dependency_mismatch": 432700, "answer_mismatch": 408597, "extra_nodes": 79850, "missing_nodes": 280629, "perfect_with_extra": 3199}}}}