Upload extrapolation artifact: 050302 RL OP13-20 step200 score report

050302/evals/rl050302_op13_20_step200_merged_hf/graph_results/rl050302_op13_20_step200_mergedhf_paper_eval_r78_score_report.jsonl

@@ -0,0 +1 @@
+{"gold_dir": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78/gold_graphs", "generated_path": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78", "results_dir": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78/graph_results", "per_file": [{"file": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78/rl050302_op13_20_step200_merged_hf_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 672940, "value_mismatch": 454693, "dependency_mismatch": 231045, "answer_mismatch": 334427, "extra_nodes": 97031, "missing_nodes": 50135, "perfect_with_extra": 13425, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 223250, "value_mismatch": 147333, "dependency_mismatch": 75473, "answer_mismatch": 108291, "extra_nodes": 33856, "missing_nodes": 15891, "perfect_with_extra": 5099}, "teachers_in_school": {"total": 390656, "perfect": 227466, "dependency_mismatch": 75702, "value_mismatch": 155724, "answer_mismatch": 113639, "extra_nodes": 27789, "missing_nodes": 15152, "perfect_with_extra": 2227}, "movie_festival_awards": {"total": 382336, "perfect": 222224, "dependency_mismatch": 79870, "value_mismatch": 151636, "answer_mismatch": 112497, "extra_nodes": 35386, "missing_nodes": 19092, "perfect_with_extra": 6099}}, "results_path": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78/graph_results/rl050302_op13_20_step200_merged_hf_id_generations.jsonl.graph_results.jsonl"}, {"file": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78/rl050302_op13_20_step200_merged_hf_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 203037, "value_mismatch": 1042220, "dependency_mismatch": 999537, "answer_mismatch": 840251, "extra_nodes": 106921, "missing_nodes": 581480, "perfect_with_extra": 510, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "value_mismatch": 349870, "dependency_mismatch": 335915, "answer_mismatch": 281295, "extra_nodes": 37672, "perfect": 69129, "missing_nodes": 194576, "perfect_with_extra": 137}, "teachers_in_school": {"total": 430464, "perfect": 70691, "value_mismatch": 348361, "answer_mismatch": 280940, "dependency_mismatch": 331619, "extra_nodes": 34463, "missing_nodes": 193923, "perfect_with_extra": 107}, "movie_festival_awards": {"total": 418816, "perfect": 63217, "value_mismatch": 343989, "dependency_mismatch": 332003, "answer_mismatch": 278016, "extra_nodes": 34786, "missing_nodes": 192981, "perfect_with_extra": 266}}, "results_path": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78/graph_results/rl050302_op13_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": 875977, "value_mismatch": 1496913, "dependency_mismatch": 1230582, "answer_mismatch": 1174678, "extra_nodes": 203952, "missing_nodes": 631615, "perfect_with_extra": 13935, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "/mnt/hdfs/output/work/rl050302_op13_20_step200_mergedhf_paper_eval_r78/graph_results/rl050302_op13_20_step200_mergedhf_paper_eval_r78_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 292379, "value_mismatch": 497203, "dependency_mismatch": 411388, "answer_mismatch": 389586, "extra_nodes": 71528, "missing_nodes": 210467, "perfect_with_extra": 5236}, "teachers_in_school": {"total": 821120, "perfect": 298157, "dependency_mismatch": 407321, "value_mismatch": 504085, "answer_mismatch": 394579, "extra_nodes": 62252, "missing_nodes": 209075, "perfect_with_extra": 2334}, "movie_festival_awards": {"total": 801152, "perfect": 285441, "dependency_mismatch": 411873, "value_mismatch": 495625, "answer_mismatch": 390513, "extra_nodes": 70172, "missing_nodes": 212073, "perfect_with_extra": 6365}}}}