ZachW commited on
Commit
7d62058
·
verified ·
1 Parent(s): acacd48

Upload extrapolation artifact: 050302 OPD Ref-KL step20 score report

Browse files
050302/evals/opd_refkl_sweep/step20/graph_results/opd050302_refkl_s020_mergedhf_paper_eval_r81_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81/gold_graphs", "generated_path": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81", "results_dir": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81/graph_results", "per_file": [{"file": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81/opd050302_refkl_s020_merged_hf_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 689373, "value_mismatch": 438878, "dependency_mismatch": 223813, "answer_mismatch": 325323, "extra_nodes": 84251, "missing_nodes": 51420, "perfect_with_extra": 9946, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 228735, "value_mismatch": 142044, "dependency_mismatch": 72722, "answer_mismatch": 105452, "extra_nodes": 29082, "missing_nodes": 16604, "perfect_with_extra": 3682}, "teachers_in_school": {"total": 390656, "perfect": 232781, "dependency_mismatch": 73858, "value_mismatch": 150521, "answer_mismatch": 110711, "extra_nodes": 24491, "missing_nodes": 15418, "perfect_with_extra": 1833}, "movie_festival_awards": {"total": 382336, "perfect": 227857, "value_mismatch": 146313, "dependency_mismatch": 77233, "answer_mismatch": 109160, "extra_nodes": 30678, "missing_nodes": 19398, "perfect_with_extra": 4431}}, "results_path": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81/graph_results/opd050302_refkl_s020_merged_hf_id_generations.jsonl.graph_results.jsonl"}, {"file": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81/opd050302_refkl_s020_merged_hf_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 181248, "value_mismatch": 1066370, "dependency_mismatch": 1024643, "answer_mismatch": 867858, "extra_nodes": 118471, "missing_nodes": 612298, "perfect_with_extra": 484, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "value_mismatch": 358419, "dependency_mismatch": 344783, "answer_mismatch": 290901, "extra_nodes": 42327, "perfect": 61385, "missing_nodes": 204462, "perfect_with_extra": 150}, "teachers_in_school": {"total": 430464, "perfect": 63289, "dependency_mismatch": 340010, "value_mismatch": 356408, "answer_mismatch": 289792, "missing_nodes": 204535, "extra_nodes": 37757, "perfect_with_extra": 95}, "movie_festival_awards": {"total": 418816, "perfect": 56574, "value_mismatch": 351543, "dependency_mismatch": 339850, "answer_mismatch": 287165, "extra_nodes": 38387, "missing_nodes": 203301, "perfect_with_extra": 239}}, "results_path": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81/graph_results/opd050302_refkl_s020_merged_hf_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 870621, "value_mismatch": 1505248, "dependency_mismatch": 1248456, "answer_mismatch": 1193181, "extra_nodes": 202722, "missing_nodes": 663718, "perfect_with_extra": 10430, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "/mnt/hdfs/output/work/opd050302_refkl_s020_mergedhf_paper_eval_r81/graph_results/opd050302_refkl_s020_mergedhf_paper_eval_r81_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 290120, "value_mismatch": 500463, "dependency_mismatch": 417505, "answer_mismatch": 396353, "extra_nodes": 71409, "missing_nodes": 221066, "perfect_with_extra": 3832}, "teachers_in_school": {"total": 821120, "perfect": 296070, "dependency_mismatch": 413868, "value_mismatch": 506929, "answer_mismatch": 400503, "extra_nodes": 62248, "missing_nodes": 219953, "perfect_with_extra": 1928}, "movie_festival_awards": {"total": 801152, "perfect": 284431, "value_mismatch": 497856, "dependency_mismatch": 417083, "answer_mismatch": 396325, "extra_nodes": 69065, "missing_nodes": 222699, "perfect_with_extra": 4670}}}}