ZachW commited on
Commit
193f942
·
verified ·
1 Parent(s): 2bd12cb

Upload extrapolation artifact: 050302 RL OP11-14 step200 score report

Browse files
050302/evals/rl050302_op11_14_step200_merged_hf/graph_results/rl050302_op11_14_step200_mergedhf_paper_eval_r77_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77/gold_graphs", "generated_path": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77", "results_dir": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77/graph_results", "per_file": [{"file": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77/rl050302_op11_14_step200_merged_hf_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 705100, "value_mismatch": 403368, "dependency_mismatch": 217751, "answer_mismatch": 280554, "extra_nodes": 114229, "missing_nodes": 31907, "perfect_with_extra": 20435, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 233666, "dependency_mismatch": 71950, "value_mismatch": 130475, "answer_mismatch": 90910, "extra_nodes": 39074, "missing_nodes": 10390, "perfect_with_extra": 6967}, "teachers_in_school": {"total": 390656, "perfect": 240232, "dependency_mismatch": 70117, "value_mismatch": 136784, "answer_mismatch": 94329, "extra_nodes": 32639, "missing_nodes": 9533, "perfect_with_extra": 4183}, "movie_festival_awards": {"total": 382336, "perfect": 231202, "dependency_mismatch": 75684, "value_mismatch": 136109, "answer_mismatch": 95315, "extra_nodes": 42516, "missing_nodes": 11984, "perfect_with_extra": 9285}}, "results_path": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77/graph_results/rl050302_op11_14_step200_merged_hf_id_generations.jsonl.graph_results.jsonl"}, {"file": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77/rl050302_op11_14_step200_merged_hf_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 198563, "value_mismatch": 1050099, "dependency_mismatch": 1017759, "answer_mismatch": 834455, "extra_nodes": 84421, "missing_nodes": 657328, "perfect_with_extra": 275, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "value_mismatch": 352012, "dependency_mismatch": 342973, "answer_mismatch": 279929, "extra_nodes": 29497, "missing_nodes": 222499, "perfect": 67551, "perfect_with_extra": 134}, "teachers_in_school": {"total": 430464, "perfect": 68650, "dependency_mismatch": 338666, "value_mismatch": 352119, "answer_mismatch": 280871, "missing_nodes": 217958, "extra_nodes": 27406, "perfect_with_extra": 71}, "movie_festival_awards": {"total": 418816, "perfect": 62362, "dependency_mismatch": 336120, "value_mismatch": 345968, "answer_mismatch": 273655, "extra_nodes": 27518, "missing_nodes": 216871, "perfect_with_extra": 70}}, "results_path": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77/graph_results/rl050302_op11_14_step200_merged_hf_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 903663, "value_mismatch": 1453467, "dependency_mismatch": 1235510, "answer_mismatch": 1115009, "extra_nodes": 198650, "missing_nodes": 689235, "perfect_with_extra": 20710, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "/mnt/hdfs/output/work/rl050302_op11_14_step200_mergedhf_paper_eval_r77/graph_results/rl050302_op11_14_step200_mergedhf_paper_eval_r77_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 301217, "dependency_mismatch": 414923, "value_mismatch": 482487, "answer_mismatch": 370839, "extra_nodes": 68571, "missing_nodes": 232889, "perfect_with_extra": 7101}, "teachers_in_school": {"total": 821120, "perfect": 308882, "dependency_mismatch": 408783, "value_mismatch": 488903, "answer_mismatch": 375200, "extra_nodes": 60045, "missing_nodes": 227491, "perfect_with_extra": 4254}, "movie_festival_awards": {"total": 801152, "perfect": 293564, "dependency_mismatch": 411804, "value_mismatch": 482077, "answer_mismatch": 368970, "extra_nodes": 70034, "missing_nodes": 228855, "perfect_with_extra": 9355}}}}