DatPySci commited on
Commit
d0a4b48
·
verified ·
1 Parent(s): 0906202

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +40 -0
  2. Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs/0.999zoo_op2-20+0.001teacher_op2_score_report.jsonl +1 -0
  3. Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs/results.json +910 -0
  4. Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/hf_model_metrics.json +1077 -0
  5. Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/hf_model_ood_generations.jsonl +3 -0
  6. Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/summary.csv +2 -0
  7. Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/summary.json +245 -0
  8. Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs/0.99zoo_op2-20+0.01teacher_op2_score_report.jsonl +1 -0
  9. Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs/results.json +910 -0
  10. Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/hf_model_ood_generations.jsonl +3 -0
  11. Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/summary.csv +2 -0
  12. Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/summary.json +245 -0
  13. Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs/0.9zoo_op2-20+0.1teacher_op2_score_report.jsonl +1 -0
  14. Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs/results.json +910 -0
  15. Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_id_generations.jsonl +3 -0
  16. Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_metrics.json +1077 -0
  17. Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_ood_generations.jsonl +3 -0
  18. Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/summary.csv +2 -0
  19. Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/summary.json +245 -0
  20. Qwen3-100M-ep4/composition/checkpoint-85276_id_generations.jsonl +3 -0
  21. Qwen3-100M-ep4/composition/checkpoint-85276_metrics.json +1897 -0
  22. Qwen3-100M-ep4/composition/checkpoint-85276_ood_generations.jsonl +3 -0
  23. Qwen3-100M-ep4/composition/graphs/checkpoint-85276_ood_generations.jsonl.graph_results.jsonl +3 -0
  24. Qwen3-100M-ep4/composition/graphs/composition_score_report.jsonl +1 -0
  25. Qwen3-100M-ep4/composition/graphs/results.json +1780 -0
  26. Qwen3-100M-ep4/composition/summary.csv +2 -0
  27. Qwen3-100M-ep4/composition/summary.json +645 -0
  28. Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_id_generations.jsonl +3 -0
  29. Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_metrics.json +1897 -0
  30. Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_ood_generations.jsonl +3 -0
  31. Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl +3 -0
  32. Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl +3 -0
  33. Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/composition_score_report.jsonl +1 -0
  34. Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/results.json +1780 -0
  35. Qwen3-100M-midtrain-diff_ar-block16/composition/summary.csv +2 -0
  36. Qwen3-100M-midtrain-diff_ar-block16/composition/summary.json +645 -0
  37. Qwen3-100M-midtrain-diff_ar-block4/composition/checkpoint-38646_id_generations.jsonl +3 -0
  38. Qwen3-100M-midtrain-diff_ar-block4/composition/checkpoint-38646_metrics.json +1897 -0
  39. Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl +3 -0
  40. Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl +3 -0
  41. Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/composition_score_report.jsonl +1 -0
  42. Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/results.json +1780 -0
  43. Qwen3-100M-midtrain-diff_ar-block4/composition/summary.csv +2 -0
  44. Qwen3-100M-midtrain-diff_ar-block4/composition/summary.json +645 -0
  45. Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_id_generations.jsonl +3 -0
  46. Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_metrics.json +1897 -0
  47. Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_ood_generations.jsonl +3 -0
  48. Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_id_generations.jsonl.graph_results.jsonl +3 -0
  49. Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_ood_generations.jsonl.graph_results.jsonl +3 -0
  50. Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/composition_score_report.jsonl +1 -0
.gitattributes CHANGED
@@ -300,3 +300,43 @@ SDAR-100M-ep4-block4-op7-10/composition/autoregressive/hf_model_id_generations.j
300
  SDAR-100M-ep4-block4-op7-10/composition/autoregressive/hf_model_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
301
  SDAR-100M-ep4-block4-op9-12/composition/autoregressive/hf_model_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
302
  Qwen3-100M-ep4/composition/graphs/checkpoint-85276_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
300
  SDAR-100M-ep4-block4-op7-10/composition/autoregressive/hf_model_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
301
  SDAR-100M-ep4-block4-op9-12/composition/autoregressive/hf_model_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
302
  Qwen3-100M-ep4/composition/graphs/checkpoint-85276_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
303
+ Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
304
+ Qwen3-100M-ep4/composition/graphs/checkpoint-85276_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
305
+ Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
306
+ Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
307
+ SDAR-100M-ep4-block8/composition/autoregressive/checkpoint-86183_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
308
+ Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
309
+ Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/hf_model_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
310
+ Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
311
+ Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
312
+ Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
313
+ SDAR-100M-midtrain-ar_diff-block8/composition/autoregressive/graphs/checkpoint-39008_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
314
+ SDAR-100M-midtrain-ar_diff-block8/composition/autoregressive/graphs/checkpoint-39008_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
315
+ Qwen3-100M-ep4/composition/checkpoint-85276_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
316
+ Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/hf_model_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
317
+ SDAR-100M-midtrain-ar_diff-block16/composition/autoregressive/graphs/checkpoint-39470_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
318
+ Qwen3-100M-midtrain-diff_ar-block4/composition/checkpoint-38646_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
319
+ Qwen3-100M-ep4/composition/checkpoint-85276_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
320
+ Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
321
+ SDAR-100M-midtrain-ar_diff-block16/composition/autoregressive/graphs/checkpoint-39470_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
322
+ Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
323
+ Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
324
+ SDAR-100M-midtrain-ar_diff-block_curriculum-1_8/composition/autoregressive/graphs/checkpoint-39008_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
325
+ SDAR-100M-midtrain-ar_diff-block_curriculum-1_8/composition/autoregressive/graphs/checkpoint-39008_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
326
+ SDAR-100M-midtrain-ar_diff-block_curriculum-2_16/composition/autoregressive/graphs/checkpoint-39470_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
327
+ SDAR-100M-midtrain-ar_diff-block_curriculum-2_16/composition/autoregressive/graphs/checkpoint-39470_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
328
+ SDAR-100M-midtrain-ar_diff-block8/composition/autoregressive/checkpoint-39008_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
329
+ Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
330
+ SDAR-100M-midtrain-ar_diff-block8/composition/autoregressive/checkpoint-39008_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
331
+ SDAR-100M-midtrain-ar_diff-block16/composition/autoregressive/checkpoint-39470_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
332
+ SDAR-100M-midtrain-ar_diff-block_curriculum_8_4_2_1/composition/autoregressive/checkpoint-39008_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
333
+ SDAR-100M-midtrain-ar_diff-block_curriculum_16_8_4_2/composition/autoregressive/checkpoint-39470_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
334
+ SDAR-100M-midtrain-ar_diff-block_curriculum-2_16/composition/autoregressive/checkpoint-39470_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
335
+ SDAR-100M-midtrain-ar_diff-block_curriculum_16_8_4_2/composition/autoregressive/checkpoint-39470_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
336
+ SDAR-100M-midtrain-ar_diff-block_curriculum_8_4_2_1/composition/autoregressive/checkpoint-39008_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
337
+ SDAR-100M-midtrain-ar_diff-block_curriculum-1_8/composition/autoregressive/checkpoint-39008_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
338
+ SDAR-100M-midtrain-ar_diff-block_curriculum-2_16/composition/autoregressive/checkpoint-39470_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
339
+ Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
340
+ SDAR-100M-ep1-block4/composition/low_confidence_static/block8/graphs/checkpoint-21414_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
341
+ SDAR-100M-ep1-block4/composition/autoregressive/graphs/checkpoint-21414_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
342
+ SDAR-100M-ep1-block4/composition/low_confidence_static/block4/graphs/checkpoint-21414_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs/0.999zoo_op2-20+0.001teacher_op2_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/context/op-difficulty-10B/graphs", "generated_path": "results/Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2", "results_dir": "results/Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs", "per_file": [{"file": "results/Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/hf_model_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 73614, "value_mismatch": 536991, "dependency_mismatch": 698222, "answer_mismatch": 744241, "extra_nodes": 627017, "missing_nodes": 1077262, "perfect_with_extra": 9, "unused_gold_entries": 10000, "template_stats": {"teachers_in_school": {"total": 1152000, "value_mismatch": 536991, "dependency_mismatch": 698222, "answer_mismatch": 744241, "missing_nodes": 1077262, "extra_nodes": 627017, "perfect": 73614, "perfect_with_extra": 9}}, "results_path": "results/Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs/hf_model_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/hf_model_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 959844, "dependency_mismatch": 1020173, "answer_mismatch": 1093236, "extra_nodes": 890642, "missing_nodes": 1280000, "perfect_with_extra": 0, "unused_gold_entries": 9000, "template_stats": {"teachers_in_school": {"total": 1280000, "value_mismatch": 959844, "dependency_mismatch": 1020173, "answer_mismatch": 1093236, "extra_nodes": 890642, "missing_nodes": 1280000}}, "results_path": "results/Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs/hf_model_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 73614, "value_mismatch": 1496835, "dependency_mismatch": 1718395, "answer_mismatch": 1837477, "extra_nodes": 1517659, "missing_nodes": 2357262, "perfect_with_extra": 9, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs/0.999zoo_op2-20+0.001teacher_op2_score_report.jsonl", "template_stats": {"teachers_in_school": {"total": 2432000, "value_mismatch": 1496835, "dependency_mismatch": 1718395, "answer_mismatch": 1837477, "missing_nodes": 2357262, "extra_nodes": 1517659, "perfect": 73614, "perfect_with_extra": 9}}}}
Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/graphs/results.json ADDED
@@ -0,0 +1,910 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "hf_model_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "teachers_in_school": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 0.577,
9
+ "pass@2": 0.635,
10
+ "pass@4": 0.701,
11
+ "pass@8": 0.753,
12
+ "pass@16": 0.807,
13
+ "pass@32": 0.835,
14
+ "pass@64": 0.863,
15
+ "pass@128": 0.884
16
+ },
17
+ "3": {
18
+ "pass@1": 0.0,
19
+ "pass@2": 0.0,
20
+ "pass@4": 0.0,
21
+ "pass@8": 0.0,
22
+ "pass@16": 0.0,
23
+ "pass@32": 0.001,
24
+ "pass@64": 0.001,
25
+ "pass@128": 0.001
26
+ },
27
+ "4": {
28
+ "pass@1": 0.0,
29
+ "pass@2": 0.0,
30
+ "pass@4": 0.0,
31
+ "pass@8": 0.0,
32
+ "pass@16": 0.0,
33
+ "pass@32": 0.0,
34
+ "pass@64": 0.0,
35
+ "pass@128": 0.0
36
+ },
37
+ "5": {
38
+ "pass@1": 0.0,
39
+ "pass@2": 0.0,
40
+ "pass@4": 0.0,
41
+ "pass@8": 0.0,
42
+ "pass@16": 0.0,
43
+ "pass@32": 0.0,
44
+ "pass@64": 0.0,
45
+ "pass@128": 0.0
46
+ },
47
+ "6": {
48
+ "pass@1": 0.0,
49
+ "pass@2": 0.0,
50
+ "pass@4": 0.0,
51
+ "pass@8": 0.0,
52
+ "pass@16": 0.0,
53
+ "pass@32": 0.0,
54
+ "pass@64": 0.0,
55
+ "pass@128": 0.0
56
+ },
57
+ "7": {
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
+ "8": {
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
+ "9": {
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
+ "10": {
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
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 0.577,
101
+ "3": 0.0,
102
+ "4": 0.0,
103
+ "5": 0.0,
104
+ "6": 0.0,
105
+ "7": 0.0,
106
+ "8": 0.0,
107
+ "9": 0.0,
108
+ "10": 0.0
109
+ },
110
+ "pass@2": {
111
+ "2": 0.635,
112
+ "3": 0.0,
113
+ "4": 0.0,
114
+ "5": 0.0,
115
+ "6": 0.0,
116
+ "7": 0.0,
117
+ "8": 0.0,
118
+ "9": 0.0,
119
+ "10": 0.0
120
+ },
121
+ "pass@4": {
122
+ "2": 0.701,
123
+ "3": 0.0,
124
+ "4": 0.0,
125
+ "5": 0.0,
126
+ "6": 0.0,
127
+ "7": 0.0,
128
+ "8": 0.0,
129
+ "9": 0.0,
130
+ "10": 0.0
131
+ },
132
+ "pass@8": {
133
+ "2": 0.753,
134
+ "3": 0.0,
135
+ "4": 0.0,
136
+ "5": 0.0,
137
+ "6": 0.0,
138
+ "7": 0.0,
139
+ "8": 0.0,
140
+ "9": 0.0,
141
+ "10": 0.0
142
+ },
143
+ "pass@16": {
144
+ "2": 0.807,
145
+ "3": 0.0,
146
+ "4": 0.0,
147
+ "5": 0.0,
148
+ "6": 0.0,
149
+ "7": 0.0,
150
+ "8": 0.0,
151
+ "9": 0.0,
152
+ "10": 0.0
153
+ },
154
+ "pass@32": {
155
+ "2": 0.835,
156
+ "3": 0.001,
157
+ "4": 0.0,
158
+ "5": 0.0,
159
+ "6": 0.0,
160
+ "7": 0.0,
161
+ "8": 0.0,
162
+ "9": 0.0,
163
+ "10": 0.0
164
+ },
165
+ "pass@64": {
166
+ "2": 0.863,
167
+ "3": 0.001,
168
+ "4": 0.0,
169
+ "5": 0.0,
170
+ "6": 0.0,
171
+ "7": 0.0,
172
+ "8": 0.0,
173
+ "9": 0.0,
174
+ "10": 0.0
175
+ },
176
+ "pass@128": {
177
+ "2": 0.884,
178
+ "3": 0.001,
179
+ "4": 0.0,
180
+ "5": 0.0,
181
+ "6": 0.0,
182
+ "7": 0.0,
183
+ "8": 0.0,
184
+ "9": 0.0,
185
+ "10": 0.0
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.0641111111111111,
190
+ "pass@2": 0.07055555555555555,
191
+ "pass@4": 0.07788888888888888,
192
+ "pass@8": 0.08366666666666667,
193
+ "pass@16": 0.08966666666666667,
194
+ "pass@32": 0.09288888888888888,
195
+ "pass@64": 0.096,
196
+ "pass@128": 0.09833333333333333
197
+ }
198
+ }
199
+ },
200
+ "total": {
201
+ "per_op_pass_at_k": {
202
+ "2": {
203
+ "pass@1": 0.577,
204
+ "pass@2": 0.635,
205
+ "pass@4": 0.701,
206
+ "pass@8": 0.753,
207
+ "pass@16": 0.807,
208
+ "pass@32": 0.835,
209
+ "pass@64": 0.863,
210
+ "pass@128": 0.884
211
+ },
212
+ "3": {
213
+ "pass@1": 0.0,
214
+ "pass@2": 0.0,
215
+ "pass@4": 0.0,
216
+ "pass@8": 0.0,
217
+ "pass@16": 0.0,
218
+ "pass@32": 0.001,
219
+ "pass@64": 0.001,
220
+ "pass@128": 0.001
221
+ },
222
+ "4": {
223
+ "pass@1": 0.0,
224
+ "pass@2": 0.0,
225
+ "pass@4": 0.0,
226
+ "pass@8": 0.0,
227
+ "pass@16": 0.0,
228
+ "pass@32": 0.0,
229
+ "pass@64": 0.0,
230
+ "pass@128": 0.0
231
+ },
232
+ "5": {
233
+ "pass@1": 0.0,
234
+ "pass@2": 0.0,
235
+ "pass@4": 0.0,
236
+ "pass@8": 0.0,
237
+ "pass@16": 0.0,
238
+ "pass@32": 0.0,
239
+ "pass@64": 0.0,
240
+ "pass@128": 0.0
241
+ },
242
+ "6": {
243
+ "pass@1": 0.0,
244
+ "pass@2": 0.0,
245
+ "pass@4": 0.0,
246
+ "pass@8": 0.0,
247
+ "pass@16": 0.0,
248
+ "pass@32": 0.0,
249
+ "pass@64": 0.0,
250
+ "pass@128": 0.0
251
+ },
252
+ "7": {
253
+ "pass@1": 0.0,
254
+ "pass@2": 0.0,
255
+ "pass@4": 0.0,
256
+ "pass@8": 0.0,
257
+ "pass@16": 0.0,
258
+ "pass@32": 0.0,
259
+ "pass@64": 0.0,
260
+ "pass@128": 0.0
261
+ },
262
+ "8": {
263
+ "pass@1": 0.0,
264
+ "pass@2": 0.0,
265
+ "pass@4": 0.0,
266
+ "pass@8": 0.0,
267
+ "pass@16": 0.0,
268
+ "pass@32": 0.0,
269
+ "pass@64": 0.0,
270
+ "pass@128": 0.0
271
+ },
272
+ "9": {
273
+ "pass@1": 0.0,
274
+ "pass@2": 0.0,
275
+ "pass@4": 0.0,
276
+ "pass@8": 0.0,
277
+ "pass@16": 0.0,
278
+ "pass@32": 0.0,
279
+ "pass@64": 0.0,
280
+ "pass@128": 0.0
281
+ },
282
+ "10": {
283
+ "pass@1": 0.0,
284
+ "pass@2": 0.0,
285
+ "pass@4": 0.0,
286
+ "pass@8": 0.0,
287
+ "pass@16": 0.0,
288
+ "pass@32": 0.0,
289
+ "pass@64": 0.0,
290
+ "pass@128": 0.0
291
+ }
292
+ },
293
+ "per_op_pass_at_columns": {
294
+ "pass@1": {
295
+ "2": 0.577,
296
+ "3": 0.0,
297
+ "4": 0.0,
298
+ "5": 0.0,
299
+ "6": 0.0,
300
+ "7": 0.0,
301
+ "8": 0.0,
302
+ "9": 0.0,
303
+ "10": 0.0
304
+ },
305
+ "pass@2": {
306
+ "2": 0.635,
307
+ "3": 0.0,
308
+ "4": 0.0,
309
+ "5": 0.0,
310
+ "6": 0.0,
311
+ "7": 0.0,
312
+ "8": 0.0,
313
+ "9": 0.0,
314
+ "10": 0.0
315
+ },
316
+ "pass@4": {
317
+ "2": 0.701,
318
+ "3": 0.0,
319
+ "4": 0.0,
320
+ "5": 0.0,
321
+ "6": 0.0,
322
+ "7": 0.0,
323
+ "8": 0.0,
324
+ "9": 0.0,
325
+ "10": 0.0
326
+ },
327
+ "pass@8": {
328
+ "2": 0.753,
329
+ "3": 0.0,
330
+ "4": 0.0,
331
+ "5": 0.0,
332
+ "6": 0.0,
333
+ "7": 0.0,
334
+ "8": 0.0,
335
+ "9": 0.0,
336
+ "10": 0.0
337
+ },
338
+ "pass@16": {
339
+ "2": 0.807,
340
+ "3": 0.0,
341
+ "4": 0.0,
342
+ "5": 0.0,
343
+ "6": 0.0,
344
+ "7": 0.0,
345
+ "8": 0.0,
346
+ "9": 0.0,
347
+ "10": 0.0
348
+ },
349
+ "pass@32": {
350
+ "2": 0.835,
351
+ "3": 0.001,
352
+ "4": 0.0,
353
+ "5": 0.0,
354
+ "6": 0.0,
355
+ "7": 0.0,
356
+ "8": 0.0,
357
+ "9": 0.0,
358
+ "10": 0.0
359
+ },
360
+ "pass@64": {
361
+ "2": 0.863,
362
+ "3": 0.001,
363
+ "4": 0.0,
364
+ "5": 0.0,
365
+ "6": 0.0,
366
+ "7": 0.0,
367
+ "8": 0.0,
368
+ "9": 0.0,
369
+ "10": 0.0
370
+ },
371
+ "pass@128": {
372
+ "2": 0.884,
373
+ "3": 0.001,
374
+ "4": 0.0,
375
+ "5": 0.0,
376
+ "6": 0.0,
377
+ "7": 0.0,
378
+ "8": 0.0,
379
+ "9": 0.0,
380
+ "10": 0.0
381
+ }
382
+ },
383
+ "total_pass_at_k": {
384
+ "pass@1": 0.0641111111111111,
385
+ "pass@2": 0.07055555555555555,
386
+ "pass@4": 0.07788888888888888,
387
+ "pass@8": 0.08366666666666667,
388
+ "pass@16": 0.08966666666666667,
389
+ "pass@32": 0.09288888888888888,
390
+ "pass@64": 0.096,
391
+ "pass@128": 0.09833333333333333
392
+ }
393
+ },
394
+ "ks": [
395
+ 1,
396
+ 2,
397
+ 4,
398
+ 8,
399
+ 16,
400
+ 32,
401
+ 64,
402
+ 128
403
+ ],
404
+ "prompt_counts": {
405
+ "per_template": {
406
+ "teachers_in_school": {
407
+ "per_op": {
408
+ "2": 1000,
409
+ "3": 1000,
410
+ "4": 1000,
411
+ "5": 1000,
412
+ "6": 1000,
413
+ "7": 1000,
414
+ "8": 1000,
415
+ "9": 1000,
416
+ "10": 1000
417
+ },
418
+ "total": 9000
419
+ }
420
+ },
421
+ "total": {
422
+ "per_op": {
423
+ "2": 1000,
424
+ "3": 1000,
425
+ "4": 1000,
426
+ "5": 1000,
427
+ "6": 1000,
428
+ "7": 1000,
429
+ "8": 1000,
430
+ "9": 1000,
431
+ "10": 1000
432
+ },
433
+ "total": 9000
434
+ }
435
+ }
436
+ },
437
+ "hf_model_ood_generations.jsonl.graph_results.jsonl": {
438
+ "per_template": {
439
+ "teachers_in_school": {
440
+ "per_op_pass_at_k": {
441
+ "11": {
442
+ "pass@1": 0.0,
443
+ "pass@2": 0.0,
444
+ "pass@4": 0.0,
445
+ "pass@8": 0.0,
446
+ "pass@16": 0.0,
447
+ "pass@32": 0.0,
448
+ "pass@64": 0.0,
449
+ "pass@128": 0.0
450
+ },
451
+ "12": {
452
+ "pass@1": 0.0,
453
+ "pass@2": 0.0,
454
+ "pass@4": 0.0,
455
+ "pass@8": 0.0,
456
+ "pass@16": 0.0,
457
+ "pass@32": 0.0,
458
+ "pass@64": 0.0,
459
+ "pass@128": 0.0
460
+ },
461
+ "13": {
462
+ "pass@1": 0.0,
463
+ "pass@2": 0.0,
464
+ "pass@4": 0.0,
465
+ "pass@8": 0.0,
466
+ "pass@16": 0.0,
467
+ "pass@32": 0.0,
468
+ "pass@64": 0.0,
469
+ "pass@128": 0.0
470
+ },
471
+ "14": {
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": 0.0
480
+ },
481
+ "15": {
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": 0.0
490
+ },
491
+ "16": {
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
+ "17": {
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
+ "18": {
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
+ "19": {
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
+ "20": {
532
+ "pass@1": 0.0,
533
+ "pass@2": 0.0,
534
+ "pass@4": 0.0,
535
+ "pass@8": 0.0,
536
+ "pass@16": 0.0,
537
+ "pass@32": 0.0,
538
+ "pass@64": 0.0,
539
+ "pass@128": 0.0
540
+ }
541
+ },
542
+ "per_op_pass_at_columns": {
543
+ "pass@1": {
544
+ "11": 0.0,
545
+ "12": 0.0,
546
+ "13": 0.0,
547
+ "14": 0.0,
548
+ "15": 0.0,
549
+ "16": 0.0,
550
+ "17": 0.0,
551
+ "18": 0.0,
552
+ "19": 0.0,
553
+ "20": 0.0
554
+ },
555
+ "pass@2": {
556
+ "11": 0.0,
557
+ "12": 0.0,
558
+ "13": 0.0,
559
+ "14": 0.0,
560
+ "15": 0.0,
561
+ "16": 0.0,
562
+ "17": 0.0,
563
+ "18": 0.0,
564
+ "19": 0.0,
565
+ "20": 0.0
566
+ },
567
+ "pass@4": {
568
+ "11": 0.0,
569
+ "12": 0.0,
570
+ "13": 0.0,
571
+ "14": 0.0,
572
+ "15": 0.0,
573
+ "16": 0.0,
574
+ "17": 0.0,
575
+ "18": 0.0,
576
+ "19": 0.0,
577
+ "20": 0.0
578
+ },
579
+ "pass@8": {
580
+ "11": 0.0,
581
+ "12": 0.0,
582
+ "13": 0.0,
583
+ "14": 0.0,
584
+ "15": 0.0,
585
+ "16": 0.0,
586
+ "17": 0.0,
587
+ "18": 0.0,
588
+ "19": 0.0,
589
+ "20": 0.0
590
+ },
591
+ "pass@16": {
592
+ "11": 0.0,
593
+ "12": 0.0,
594
+ "13": 0.0,
595
+ "14": 0.0,
596
+ "15": 0.0,
597
+ "16": 0.0,
598
+ "17": 0.0,
599
+ "18": 0.0,
600
+ "19": 0.0,
601
+ "20": 0.0
602
+ },
603
+ "pass@32": {
604
+ "11": 0.0,
605
+ "12": 0.0,
606
+ "13": 0.0,
607
+ "14": 0.0,
608
+ "15": 0.0,
609
+ "16": 0.0,
610
+ "17": 0.0,
611
+ "18": 0.0,
612
+ "19": 0.0,
613
+ "20": 0.0
614
+ },
615
+ "pass@64": {
616
+ "11": 0.0,
617
+ "12": 0.0,
618
+ "13": 0.0,
619
+ "14": 0.0,
620
+ "15": 0.0,
621
+ "16": 0.0,
622
+ "17": 0.0,
623
+ "18": 0.0,
624
+ "19": 0.0,
625
+ "20": 0.0
626
+ },
627
+ "pass@128": {
628
+ "11": 0.0,
629
+ "12": 0.0,
630
+ "13": 0.0,
631
+ "14": 0.0,
632
+ "15": 0.0,
633
+ "16": 0.0,
634
+ "17": 0.0,
635
+ "18": 0.0,
636
+ "19": 0.0,
637
+ "20": 0.0
638
+ }
639
+ },
640
+ "total_pass_at_k": {
641
+ "pass@1": 0.0,
642
+ "pass@2": 0.0,
643
+ "pass@4": 0.0,
644
+ "pass@8": 0.0,
645
+ "pass@16": 0.0,
646
+ "pass@32": 0.0,
647
+ "pass@64": 0.0,
648
+ "pass@128": 0.0
649
+ }
650
+ }
651
+ },
652
+ "total": {
653
+ "per_op_pass_at_k": {
654
+ "11": {
655
+ "pass@1": 0.0,
656
+ "pass@2": 0.0,
657
+ "pass@4": 0.0,
658
+ "pass@8": 0.0,
659
+ "pass@16": 0.0,
660
+ "pass@32": 0.0,
661
+ "pass@64": 0.0,
662
+ "pass@128": 0.0
663
+ },
664
+ "12": {
665
+ "pass@1": 0.0,
666
+ "pass@2": 0.0,
667
+ "pass@4": 0.0,
668
+ "pass@8": 0.0,
669
+ "pass@16": 0.0,
670
+ "pass@32": 0.0,
671
+ "pass@64": 0.0,
672
+ "pass@128": 0.0
673
+ },
674
+ "13": {
675
+ "pass@1": 0.0,
676
+ "pass@2": 0.0,
677
+ "pass@4": 0.0,
678
+ "pass@8": 0.0,
679
+ "pass@16": 0.0,
680
+ "pass@32": 0.0,
681
+ "pass@64": 0.0,
682
+ "pass@128": 0.0
683
+ },
684
+ "14": {
685
+ "pass@1": 0.0,
686
+ "pass@2": 0.0,
687
+ "pass@4": 0.0,
688
+ "pass@8": 0.0,
689
+ "pass@16": 0.0,
690
+ "pass@32": 0.0,
691
+ "pass@64": 0.0,
692
+ "pass@128": 0.0
693
+ },
694
+ "15": {
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": 0.0
703
+ },
704
+ "16": {
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
+ "17": {
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
+ "18": {
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
+ "19": {
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
+ "20": {
745
+ "pass@1": 0.0,
746
+ "pass@2": 0.0,
747
+ "pass@4": 0.0,
748
+ "pass@8": 0.0,
749
+ "pass@16": 0.0,
750
+ "pass@32": 0.0,
751
+ "pass@64": 0.0,
752
+ "pass@128": 0.0
753
+ }
754
+ },
755
+ "per_op_pass_at_columns": {
756
+ "pass@1": {
757
+ "11": 0.0,
758
+ "12": 0.0,
759
+ "13": 0.0,
760
+ "14": 0.0,
761
+ "15": 0.0,
762
+ "16": 0.0,
763
+ "17": 0.0,
764
+ "18": 0.0,
765
+ "19": 0.0,
766
+ "20": 0.0
767
+ },
768
+ "pass@2": {
769
+ "11": 0.0,
770
+ "12": 0.0,
771
+ "13": 0.0,
772
+ "14": 0.0,
773
+ "15": 0.0,
774
+ "16": 0.0,
775
+ "17": 0.0,
776
+ "18": 0.0,
777
+ "19": 0.0,
778
+ "20": 0.0
779
+ },
780
+ "pass@4": {
781
+ "11": 0.0,
782
+ "12": 0.0,
783
+ "13": 0.0,
784
+ "14": 0.0,
785
+ "15": 0.0,
786
+ "16": 0.0,
787
+ "17": 0.0,
788
+ "18": 0.0,
789
+ "19": 0.0,
790
+ "20": 0.0
791
+ },
792
+ "pass@8": {
793
+ "11": 0.0,
794
+ "12": 0.0,
795
+ "13": 0.0,
796
+ "14": 0.0,
797
+ "15": 0.0,
798
+ "16": 0.0,
799
+ "17": 0.0,
800
+ "18": 0.0,
801
+ "19": 0.0,
802
+ "20": 0.0
803
+ },
804
+ "pass@16": {
805
+ "11": 0.0,
806
+ "12": 0.0,
807
+ "13": 0.0,
808
+ "14": 0.0,
809
+ "15": 0.0,
810
+ "16": 0.0,
811
+ "17": 0.0,
812
+ "18": 0.0,
813
+ "19": 0.0,
814
+ "20": 0.0
815
+ },
816
+ "pass@32": {
817
+ "11": 0.0,
818
+ "12": 0.0,
819
+ "13": 0.0,
820
+ "14": 0.0,
821
+ "15": 0.0,
822
+ "16": 0.0,
823
+ "17": 0.0,
824
+ "18": 0.0,
825
+ "19": 0.0,
826
+ "20": 0.0
827
+ },
828
+ "pass@64": {
829
+ "11": 0.0,
830
+ "12": 0.0,
831
+ "13": 0.0,
832
+ "14": 0.0,
833
+ "15": 0.0,
834
+ "16": 0.0,
835
+ "17": 0.0,
836
+ "18": 0.0,
837
+ "19": 0.0,
838
+ "20": 0.0
839
+ },
840
+ "pass@128": {
841
+ "11": 0.0,
842
+ "12": 0.0,
843
+ "13": 0.0,
844
+ "14": 0.0,
845
+ "15": 0.0,
846
+ "16": 0.0,
847
+ "17": 0.0,
848
+ "18": 0.0,
849
+ "19": 0.0,
850
+ "20": 0.0
851
+ }
852
+ },
853
+ "total_pass_at_k": {
854
+ "pass@1": 0.0,
855
+ "pass@2": 0.0,
856
+ "pass@4": 0.0,
857
+ "pass@8": 0.0,
858
+ "pass@16": 0.0,
859
+ "pass@32": 0.0,
860
+ "pass@64": 0.0,
861
+ "pass@128": 0.0
862
+ }
863
+ },
864
+ "ks": [
865
+ 1,
866
+ 2,
867
+ 4,
868
+ 8,
869
+ 16,
870
+ 32,
871
+ 64,
872
+ 128
873
+ ],
874
+ "prompt_counts": {
875
+ "per_template": {
876
+ "teachers_in_school": {
877
+ "per_op": {
878
+ "11": 1000,
879
+ "12": 1000,
880
+ "13": 1000,
881
+ "14": 1000,
882
+ "15": 1000,
883
+ "16": 1000,
884
+ "17": 1000,
885
+ "18": 1000,
886
+ "19": 1000,
887
+ "20": 1000
888
+ },
889
+ "total": 10000
890
+ }
891
+ },
892
+ "total": {
893
+ "per_op": {
894
+ "11": 1000,
895
+ "12": 1000,
896
+ "13": 1000,
897
+ "14": 1000,
898
+ "15": 1000,
899
+ "16": 1000,
900
+ "17": 1000,
901
+ "18": 1000,
902
+ "19": 1000,
903
+ "20": 1000
904
+ },
905
+ "total": 10000
906
+ }
907
+ }
908
+ }
909
+ }
910
+ }
Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/hf_model_metrics.json ADDED
@@ -0,0 +1,1077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "hf_model",
3
+ "id": {
4
+ "answer_accuracy": 0.35395746527777777,
5
+ "avg_response_len": 143.9383420138889,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.35395746527777777,
11
+ "pass@2": 0.36394313210848733,
12
+ "pass@4": 0.3721463061179857,
13
+ "pass@8": 0.38002626115669125,
14
+ "pass@16": 0.3881806229770293,
15
+ "pass@32": 0.3970353048170402,
16
+ "pass@64": 0.40672349924466805,
17
+ "pass@128": 0.41733333333333333
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.179671875,
22
+ "pass@2": 0.1866203248031496,
23
+ "pass@4": 0.19349498397075368,
24
+ "pass@8": 0.20171124100488724,
25
+ "pass@16": 0.21184839720232201,
26
+ "pass@32": 0.22407444095023307,
27
+ "pass@64": 0.23828823396176474,
28
+ "pass@128": 0.255
29
+ },
30
+ "2": {
31
+ "pass@1": 0.9675390625,
32
+ "pass@2": 0.9754135088582678,
33
+ "pass@4": 0.9807076276715406,
34
+ "pass@8": 0.9842055326995033,
35
+ "pass@16": 0.9866531838082899,
36
+ "pass@32": 0.9888710784240634,
37
+ "pass@64": 0.991123358518923,
38
+ "pass@128": 0.993
39
+ },
40
+ "3": {
41
+ "pass@1": 0.7970390625,
42
+ "pass@2": 0.8376731053149615,
43
+ "pass@4": 0.8661379510686164,
44
+ "pass@8": 0.8884730983835463,
45
+ "pass@16": 0.9065882701957276,
46
+ "pass@32": 0.9221857999677552,
47
+ "pass@64": 0.9361523489727314,
48
+ "pass@128": 0.949
49
+ },
50
+ "4": {
51
+ "pass@1": 0.2107890625,
52
+ "pass@2": 0.21529441437007876,
53
+ "pass@4": 0.21916330239970003,
54
+ "pass@8": 0.22346821216105478,
55
+ "pass@16": 0.22872197474530756,
56
+ "pass@32": 0.23562179093658991,
57
+ "pass@64": 0.24510618631947784,
58
+ "pass@128": 0.258
59
+ },
60
+ "5": {
61
+ "pass@1": 0.2116171875,
62
+ "pass@2": 0.21723412893700783,
63
+ "pass@4": 0.22284044347581547,
64
+ "pass@8": 0.22918635588080552,
65
+ "pass@16": 0.23692081774417614,
66
+ "pass@32": 0.24659684355460448,
67
+ "pass@64": 0.25860912185373264,
68
+ "pass@128": 0.272
69
+ },
70
+ "6": {
71
+ "pass@1": 0.2580546875,
72
+ "pass@2": 0.262111343503937,
73
+ "pass@4": 0.26583126621672293,
74
+ "pass@8": 0.269561781409488,
75
+ "pass@16": 0.2735911486266416,
76
+ "pass@32": 0.2786441597934989,
77
+ "pass@64": 0.2852150182516317,
78
+ "pass@128": 0.293
79
+ },
80
+ "7": {
81
+ "pass@1": 0.195703125,
82
+ "pass@2": 0.2011721210629921,
83
+ "pass@4": 0.20649363198350204,
84
+ "pass@8": 0.212816902115117,
85
+ "pass@16": 0.22024960690112913,
86
+ "pass@32": 0.2283513294970211,
87
+ "pass@64": 0.23693507099206224,
88
+ "pass@128": 0.247
89
+ },
90
+ "8": {
91
+ "pass@1": 0.18925,
92
+ "pass@2": 0.19675135334645666,
93
+ "pass@4": 0.20417071484814395,
94
+ "pass@8": 0.21275267862195865,
95
+ "pass@16": 0.22278762964396398,
96
+ "pass@32": 0.23415911788441254,
97
+ "pass@64": 0.2463119989893093,
98
+ "pass@128": 0.258
99
+ },
100
+ "9": {
101
+ "pass@1": 0.175953125,
102
+ "pass@2": 0.18321788877952747,
103
+ "pass@4": 0.1904768334270717,
104
+ "pass@8": 0.19806054813384352,
105
+ "pass@16": 0.20626457792569045,
106
+ "pass@32": 0.21481318234518765,
107
+ "pass@64": 0.22277015534238243,
108
+ "pass@128": 0.231
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.179671875,
113
+ "2": 0.9675390625,
114
+ "3": 0.7970390625,
115
+ "4": 0.2107890625,
116
+ "5": 0.2116171875,
117
+ "6": 0.2580546875,
118
+ "7": 0.195703125,
119
+ "8": 0.18925,
120
+ "9": 0.175953125
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 167.241765625,
124
+ "2": 111.679328125,
125
+ "3": 128.0244453125,
126
+ "4": 125.2879921875,
127
+ "5": 135.821828125,
128
+ "6": 152.88628125,
129
+ "7": 142.7650703125,
130
+ "8": 163.613359375,
131
+ "9": 168.1250078125
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 167.241765625,
136
+ "2": 111.679328125,
137
+ "3": 128.0244453125,
138
+ "4": 125.2879921875,
139
+ "5": 135.821828125,
140
+ "6": 152.88628125,
141
+ "7": 142.7650703125,
142
+ "8": 163.613359375,
143
+ "9": 168.1250078125
144
+ },
145
+ "per_op_loss": {},
146
+ "per_template": {
147
+ "crazy_zootopia": {
148
+ "count": 0,
149
+ "correct": 0,
150
+ "answer_accuracy": 0.0,
151
+ "avg_response_len": 0.0,
152
+ "resp_tokens_sum": 0,
153
+ "pass_at_k": {},
154
+ "per_op_pass_at_k": {}
155
+ },
156
+ "teachers_in_school": {
157
+ "count": 1152000,
158
+ "correct": 407759,
159
+ "answer_accuracy": 0.35395746527777777,
160
+ "avg_response_len": 143.9383420138889,
161
+ "resp_tokens_sum": 165816970,
162
+ "pass_at_k": {
163
+ "pass@1": 0.35395746527777777,
164
+ "pass@2": 0.36394313210848733,
165
+ "pass@4": 0.3721463061179857,
166
+ "pass@8": 0.38002626115669125,
167
+ "pass@16": 0.3881806229770293,
168
+ "pass@32": 0.3970353048170402,
169
+ "pass@64": 0.40672349924466805,
170
+ "pass@128": 0.41733333333333333
171
+ },
172
+ "per_op_pass_at_k": {
173
+ "10": {
174
+ "pass@1": 0.179671875,
175
+ "pass@2": 0.1866203248031496,
176
+ "pass@4": 0.19349498397075368,
177
+ "pass@8": 0.20171124100488724,
178
+ "pass@16": 0.21184839720232201,
179
+ "pass@32": 0.22407444095023307,
180
+ "pass@64": 0.23828823396176474,
181
+ "pass@128": 0.255
182
+ },
183
+ "2": {
184
+ "pass@1": 0.9675390625,
185
+ "pass@2": 0.9754135088582678,
186
+ "pass@4": 0.9807076276715406,
187
+ "pass@8": 0.9842055326995033,
188
+ "pass@16": 0.9866531838082899,
189
+ "pass@32": 0.9888710784240634,
190
+ "pass@64": 0.991123358518923,
191
+ "pass@128": 0.993
192
+ },
193
+ "3": {
194
+ "pass@1": 0.7970390625,
195
+ "pass@2": 0.8376731053149615,
196
+ "pass@4": 0.8661379510686164,
197
+ "pass@8": 0.8884730983835463,
198
+ "pass@16": 0.9065882701957276,
199
+ "pass@32": 0.9221857999677552,
200
+ "pass@64": 0.9361523489727314,
201
+ "pass@128": 0.949
202
+ },
203
+ "4": {
204
+ "pass@1": 0.2107890625,
205
+ "pass@2": 0.21529441437007876,
206
+ "pass@4": 0.21916330239970003,
207
+ "pass@8": 0.22346821216105478,
208
+ "pass@16": 0.22872197474530756,
209
+ "pass@32": 0.23562179093658991,
210
+ "pass@64": 0.24510618631947784,
211
+ "pass@128": 0.258
212
+ },
213
+ "5": {
214
+ "pass@1": 0.2116171875,
215
+ "pass@2": 0.21723412893700783,
216
+ "pass@4": 0.22284044347581547,
217
+ "pass@8": 0.22918635588080552,
218
+ "pass@16": 0.23692081774417614,
219
+ "pass@32": 0.24659684355460448,
220
+ "pass@64": 0.25860912185373264,
221
+ "pass@128": 0.272
222
+ },
223
+ "6": {
224
+ "pass@1": 0.2580546875,
225
+ "pass@2": 0.262111343503937,
226
+ "pass@4": 0.26583126621672293,
227
+ "pass@8": 0.269561781409488,
228
+ "pass@16": 0.2735911486266416,
229
+ "pass@32": 0.2786441597934989,
230
+ "pass@64": 0.2852150182516317,
231
+ "pass@128": 0.293
232
+ },
233
+ "7": {
234
+ "pass@1": 0.195703125,
235
+ "pass@2": 0.2011721210629921,
236
+ "pass@4": 0.20649363198350204,
237
+ "pass@8": 0.212816902115117,
238
+ "pass@16": 0.22024960690112913,
239
+ "pass@32": 0.2283513294970211,
240
+ "pass@64": 0.23693507099206224,
241
+ "pass@128": 0.247
242
+ },
243
+ "8": {
244
+ "pass@1": 0.18925,
245
+ "pass@2": 0.19675135334645666,
246
+ "pass@4": 0.20417071484814395,
247
+ "pass@8": 0.21275267862195865,
248
+ "pass@16": 0.22278762964396398,
249
+ "pass@32": 0.23415911788441254,
250
+ "pass@64": 0.2463119989893093,
251
+ "pass@128": 0.258
252
+ },
253
+ "9": {
254
+ "pass@1": 0.175953125,
255
+ "pass@2": 0.18321788877952747,
256
+ "pass@4": 0.1904768334270717,
257
+ "pass@8": 0.19806054813384352,
258
+ "pass@16": 0.20626457792569045,
259
+ "pass@32": 0.21481318234518765,
260
+ "pass@64": 0.22277015534238243,
261
+ "pass@128": 0.231
262
+ }
263
+ }
264
+ },
265
+ "movie_festival_awards": {
266
+ "count": 0,
267
+ "correct": 0,
268
+ "answer_accuracy": 0.0,
269
+ "avg_response_len": 0.0,
270
+ "resp_tokens_sum": 0,
271
+ "pass_at_k": {},
272
+ "per_op_pass_at_k": {}
273
+ }
274
+ }
275
+ },
276
+ "ood": {
277
+ "answer_accuracy": 0.14591171875,
278
+ "avg_response_len": 202.49695546875,
279
+ "avg_loss": 0.0,
280
+ "count": 1280000,
281
+ "validation_metrics": {},
282
+ "pass_at_k": {
283
+ "pass@1": 0.14591171875,
284
+ "pass@2": 0.1588627337598429,
285
+ "pass@4": 0.16978443717660308,
286
+ "pass@8": 0.17994934512615257,
287
+ "pass@16": 0.1899462114350564,
288
+ "pass@32": 0.20014317351317526,
289
+ "pass@64": 0.2107443148217583,
290
+ "pass@128": 0.2222
291
+ },
292
+ "per_op_pass_at_k": {
293
+ "11": {
294
+ "pass@1": 0.1763515625,
295
+ "pass@2": 0.1854534940944882,
296
+ "pass@4": 0.1933735462129733,
297
+ "pass@8": 0.20147957136226124,
298
+ "pass@16": 0.21037463664286407,
299
+ "pass@32": 0.22037157099835816,
300
+ "pass@64": 0.23143147890828927,
301
+ "pass@128": 0.243
302
+ },
303
+ "12": {
304
+ "pass@1": 0.1750078125,
305
+ "pass@2": 0.18632972440944887,
306
+ "pass@4": 0.19674250149981243,
307
+ "pass@8": 0.2075677772984937,
308
+ "pass@16": 0.21899942949146833,
309
+ "pass@32": 0.23008881738333872,
310
+ "pass@64": 0.24004304392698875,
311
+ "pass@128": 0.249
312
+ },
313
+ "13": {
314
+ "pass@1": 0.14003125,
315
+ "pass@2": 0.15481865157480312,
316
+ "pass@4": 0.16692630361829766,
317
+ "pass@8": 0.17772499892830299,
318
+ "pass@16": 0.1882665689521189,
319
+ "pass@32": 0.19883793436883665,
320
+ "pass@64": 0.20967385171136876,
321
+ "pass@128": 0.221
322
+ },
323
+ "14": {
324
+ "pass@1": 0.1436328125,
325
+ "pass@2": 0.15869389763779526,
326
+ "pass@4": 0.17226924925009368,
327
+ "pass@8": 0.1845543174527869,
328
+ "pass@16": 0.19568671047542624,
329
+ "pass@32": 0.2065402438692653,
330
+ "pass@64": 0.21755881523205667,
331
+ "pass@128": 0.229
332
+ },
333
+ "15": {
334
+ "pass@1": 0.1338828125,
335
+ "pass@2": 0.14767212106299207,
336
+ "pass@4": 0.1592121984439444,
337
+ "pass@8": 0.1693664968394039,
338
+ "pass@16": 0.1790848548813016,
339
+ "pass@32": 0.1888553870136373,
340
+ "pass@64": 0.19929553877537814,
341
+ "pass@128": 0.211
342
+ },
343
+ "16": {
344
+ "pass@1": 0.155671875,
345
+ "pass@2": 0.16875172244094488,
346
+ "pass@4": 0.17969398078365192,
347
+ "pass@8": 0.1898988485117523,
348
+ "pass@16": 0.1991953499621563,
349
+ "pass@32": 0.20812386294309929,
350
+ "pass@64": 0.21791788802494516,
351
+ "pass@128": 0.23
352
+ },
353
+ "17": {
354
+ "pass@1": 0.14675,
355
+ "pass@2": 0.16014972933070862,
356
+ "pass@4": 0.16990317519685033,
357
+ "pass@8": 0.17901342366976633,
358
+ "pass@16": 0.1890970246223302,
359
+ "pass@32": 0.2009162762964177,
360
+ "pass@64": 0.21379618773979528,
361
+ "pass@128": 0.227
362
+ },
363
+ "18": {
364
+ "pass@1": 0.123859375,
365
+ "pass@2": 0.13845374015748027,
366
+ "pass@4": 0.15128099362579675,
367
+ "pass@8": 0.1636793233057228,
368
+ "pass@16": 0.17590328285323045,
369
+ "pass@32": 0.18769288846945548,
370
+ "pass@64": 0.19939121996448883,
371
+ "pass@128": 0.213
372
+ },
373
+ "19": {
374
+ "pass@1": 0.1425859375,
375
+ "pass@2": 0.1542038631889764,
376
+ "pass@4": 0.16308084739407575,
377
+ "pass@8": 0.17024050661671622,
378
+ "pass@16": 0.17678480815036582,
379
+ "pass@32": 0.18411748530607766,
380
+ "pass@64": 0.19279372965274186,
381
+ "pass@128": 0.203
382
+ },
383
+ "20": {
384
+ "pass@1": 0.12134375,
385
+ "pass@2": 0.13410039370078738,
386
+ "pass@4": 0.1453615757405324,
387
+ "pass@8": 0.1559681872763174,
388
+ "pass@16": 0.1660694483193041,
389
+ "pass@32": 0.17588726848327202,
390
+ "pass@64": 0.1855413942815293,
391
+ "pass@128": 0.196
392
+ }
393
+ },
394
+ "per_op_accuracy": {
395
+ "11": 0.1763515625,
396
+ "12": 0.1750078125,
397
+ "13": 0.14003125,
398
+ "14": 0.1436328125,
399
+ "15": 0.1338828125,
400
+ "16": 0.155671875,
401
+ "17": 0.14675,
402
+ "18": 0.123859375,
403
+ "19": 0.1425859375,
404
+ "20": 0.12134375
405
+ },
406
+ "per_op_avg_response_len": {
407
+ "11": 175.3768046875,
408
+ "12": 176.2021953125,
409
+ "13": 176.847875,
410
+ "14": 195.620578125,
411
+ "15": 203.4362421875,
412
+ "16": 206.30290625,
413
+ "17": 220.5351796875,
414
+ "18": 222.7138984375,
415
+ "19": 220.836265625,
416
+ "20": 227.097609375
417
+ },
418
+ "per_op_avg_loss": {},
419
+ "per_op_length": {
420
+ "11": 175.3768046875,
421
+ "12": 176.2021953125,
422
+ "13": 176.847875,
423
+ "14": 195.620578125,
424
+ "15": 203.4362421875,
425
+ "16": 206.30290625,
426
+ "17": 220.5351796875,
427
+ "18": 222.7138984375,
428
+ "19": 220.836265625,
429
+ "20": 227.097609375
430
+ },
431
+ "per_op_loss": {},
432
+ "per_template": {
433
+ "crazy_zootopia": {
434
+ "count": 0,
435
+ "correct": 0,
436
+ "answer_accuracy": 0.0,
437
+ "avg_response_len": 0.0,
438
+ "resp_tokens_sum": 0,
439
+ "pass_at_k": {},
440
+ "per_op_pass_at_k": {}
441
+ },
442
+ "teachers_in_school": {
443
+ "count": 1280000,
444
+ "correct": 186767,
445
+ "answer_accuracy": 0.14591171875,
446
+ "avg_response_len": 202.49695546875,
447
+ "resp_tokens_sum": 259196103,
448
+ "pass_at_k": {
449
+ "pass@1": 0.14591171875,
450
+ "pass@2": 0.1588627337598429,
451
+ "pass@4": 0.16978443717660308,
452
+ "pass@8": 0.17994934512615257,
453
+ "pass@16": 0.1899462114350564,
454
+ "pass@32": 0.20014317351317526,
455
+ "pass@64": 0.2107443148217583,
456
+ "pass@128": 0.2222
457
+ },
458
+ "per_op_pass_at_k": {
459
+ "11": {
460
+ "pass@1": 0.1763515625,
461
+ "pass@2": 0.1854534940944882,
462
+ "pass@4": 0.1933735462129733,
463
+ "pass@8": 0.20147957136226124,
464
+ "pass@16": 0.21037463664286407,
465
+ "pass@32": 0.22037157099835816,
466
+ "pass@64": 0.23143147890828927,
467
+ "pass@128": 0.243
468
+ },
469
+ "12": {
470
+ "pass@1": 0.1750078125,
471
+ "pass@2": 0.18632972440944887,
472
+ "pass@4": 0.19674250149981243,
473
+ "pass@8": 0.2075677772984937,
474
+ "pass@16": 0.21899942949146833,
475
+ "pass@32": 0.23008881738333872,
476
+ "pass@64": 0.24004304392698875,
477
+ "pass@128": 0.249
478
+ },
479
+ "13": {
480
+ "pass@1": 0.14003125,
481
+ "pass@2": 0.15481865157480312,
482
+ "pass@4": 0.16692630361829766,
483
+ "pass@8": 0.17772499892830299,
484
+ "pass@16": 0.1882665689521189,
485
+ "pass@32": 0.19883793436883665,
486
+ "pass@64": 0.20967385171136876,
487
+ "pass@128": 0.221
488
+ },
489
+ "14": {
490
+ "pass@1": 0.1436328125,
491
+ "pass@2": 0.15869389763779526,
492
+ "pass@4": 0.17226924925009368,
493
+ "pass@8": 0.1845543174527869,
494
+ "pass@16": 0.19568671047542624,
495
+ "pass@32": 0.2065402438692653,
496
+ "pass@64": 0.21755881523205667,
497
+ "pass@128": 0.229
498
+ },
499
+ "15": {
500
+ "pass@1": 0.1338828125,
501
+ "pass@2": 0.14767212106299207,
502
+ "pass@4": 0.1592121984439444,
503
+ "pass@8": 0.1693664968394039,
504
+ "pass@16": 0.1790848548813016,
505
+ "pass@32": 0.1888553870136373,
506
+ "pass@64": 0.19929553877537814,
507
+ "pass@128": 0.211
508
+ },
509
+ "16": {
510
+ "pass@1": 0.155671875,
511
+ "pass@2": 0.16875172244094488,
512
+ "pass@4": 0.17969398078365192,
513
+ "pass@8": 0.1898988485117523,
514
+ "pass@16": 0.1991953499621563,
515
+ "pass@32": 0.20812386294309929,
516
+ "pass@64": 0.21791788802494516,
517
+ "pass@128": 0.23
518
+ },
519
+ "17": {
520
+ "pass@1": 0.14675,
521
+ "pass@2": 0.16014972933070862,
522
+ "pass@4": 0.16990317519685033,
523
+ "pass@8": 0.17901342366976633,
524
+ "pass@16": 0.1890970246223302,
525
+ "pass@32": 0.2009162762964177,
526
+ "pass@64": 0.21379618773979528,
527
+ "pass@128": 0.227
528
+ },
529
+ "18": {
530
+ "pass@1": 0.123859375,
531
+ "pass@2": 0.13845374015748027,
532
+ "pass@4": 0.15128099362579675,
533
+ "pass@8": 0.1636793233057228,
534
+ "pass@16": 0.17590328285323045,
535
+ "pass@32": 0.18769288846945548,
536
+ "pass@64": 0.19939121996448883,
537
+ "pass@128": 0.213
538
+ },
539
+ "19": {
540
+ "pass@1": 0.1425859375,
541
+ "pass@2": 0.1542038631889764,
542
+ "pass@4": 0.16308084739407575,
543
+ "pass@8": 0.17024050661671622,
544
+ "pass@16": 0.17678480815036582,
545
+ "pass@32": 0.18411748530607766,
546
+ "pass@64": 0.19279372965274186,
547
+ "pass@128": 0.203
548
+ },
549
+ "20": {
550
+ "pass@1": 0.12134375,
551
+ "pass@2": 0.13410039370078738,
552
+ "pass@4": 0.1453615757405324,
553
+ "pass@8": 0.1559681872763174,
554
+ "pass@16": 0.1660694483193041,
555
+ "pass@32": 0.17588726848327202,
556
+ "pass@64": 0.1855413942815293,
557
+ "pass@128": 0.196
558
+ }
559
+ }
560
+ },
561
+ "movie_festival_awards": {
562
+ "count": 0,
563
+ "correct": 0,
564
+ "answer_accuracy": 0.0,
565
+ "avg_response_len": 0.0,
566
+ "resp_tokens_sum": 0,
567
+ "pass_at_k": {},
568
+ "per_op_pass_at_k": {}
569
+ }
570
+ }
571
+ },
572
+ "total": {
573
+ "answer_accuracy": 0.24445970394736843,
574
+ "avg_loss": 0.0,
575
+ "count": 2432000,
576
+ "validation_metrics": {
577
+ "id": {},
578
+ "ood": {}
579
+ },
580
+ "pass_at_k": {
581
+ "pass@1": 0.24445970394736843,
582
+ "pass@2": 0.2560060803460411,
583
+ "pass@4": 0.2656400593067308,
584
+ "pass@8": 0.2747226211406185,
585
+ "pass@16": 0.2838467221654667,
586
+ "pass@32": 0.2934078672886908,
587
+ "pass@64": 0.30357656007471606,
588
+ "pass@128": 0.31463157894736843
589
+ },
590
+ "per_op_pass_at_k": {
591
+ "10": {
592
+ "pass@1": 0.179671875,
593
+ "pass@2": 0.1866203248031496,
594
+ "pass@4": 0.19349498397075368,
595
+ "pass@8": 0.20171124100488724,
596
+ "pass@16": 0.21184839720232201,
597
+ "pass@32": 0.22407444095023307,
598
+ "pass@64": 0.23828823396176474,
599
+ "pass@128": 0.255
600
+ },
601
+ "2": {
602
+ "pass@1": 0.9675390625,
603
+ "pass@2": 0.9754135088582678,
604
+ "pass@4": 0.9807076276715406,
605
+ "pass@8": 0.9842055326995033,
606
+ "pass@16": 0.9866531838082899,
607
+ "pass@32": 0.9888710784240634,
608
+ "pass@64": 0.991123358518923,
609
+ "pass@128": 0.993
610
+ },
611
+ "3": {
612
+ "pass@1": 0.7970390625,
613
+ "pass@2": 0.8376731053149615,
614
+ "pass@4": 0.8661379510686164,
615
+ "pass@8": 0.8884730983835463,
616
+ "pass@16": 0.9065882701957276,
617
+ "pass@32": 0.9221857999677552,
618
+ "pass@64": 0.9361523489727314,
619
+ "pass@128": 0.949
620
+ },
621
+ "4": {
622
+ "pass@1": 0.2107890625,
623
+ "pass@2": 0.21529441437007876,
624
+ "pass@4": 0.21916330239970003,
625
+ "pass@8": 0.22346821216105478,
626
+ "pass@16": 0.22872197474530756,
627
+ "pass@32": 0.23562179093658991,
628
+ "pass@64": 0.24510618631947784,
629
+ "pass@128": 0.258
630
+ },
631
+ "5": {
632
+ "pass@1": 0.2116171875,
633
+ "pass@2": 0.21723412893700783,
634
+ "pass@4": 0.22284044347581547,
635
+ "pass@8": 0.22918635588080552,
636
+ "pass@16": 0.23692081774417614,
637
+ "pass@32": 0.24659684355460448,
638
+ "pass@64": 0.25860912185373264,
639
+ "pass@128": 0.272
640
+ },
641
+ "6": {
642
+ "pass@1": 0.2580546875,
643
+ "pass@2": 0.262111343503937,
644
+ "pass@4": 0.26583126621672293,
645
+ "pass@8": 0.269561781409488,
646
+ "pass@16": 0.2735911486266416,
647
+ "pass@32": 0.2786441597934989,
648
+ "pass@64": 0.2852150182516317,
649
+ "pass@128": 0.293
650
+ },
651
+ "7": {
652
+ "pass@1": 0.195703125,
653
+ "pass@2": 0.2011721210629921,
654
+ "pass@4": 0.20649363198350204,
655
+ "pass@8": 0.212816902115117,
656
+ "pass@16": 0.22024960690112913,
657
+ "pass@32": 0.2283513294970211,
658
+ "pass@64": 0.23693507099206224,
659
+ "pass@128": 0.247
660
+ },
661
+ "8": {
662
+ "pass@1": 0.18925,
663
+ "pass@2": 0.19675135334645666,
664
+ "pass@4": 0.20417071484814395,
665
+ "pass@8": 0.21275267862195865,
666
+ "pass@16": 0.22278762964396398,
667
+ "pass@32": 0.23415911788441254,
668
+ "pass@64": 0.2463119989893093,
669
+ "pass@128": 0.258
670
+ },
671
+ "9": {
672
+ "pass@1": 0.175953125,
673
+ "pass@2": 0.18321788877952747,
674
+ "pass@4": 0.1904768334270717,
675
+ "pass@8": 0.19806054813384352,
676
+ "pass@16": 0.20626457792569045,
677
+ "pass@32": 0.21481318234518765,
678
+ "pass@64": 0.22277015534238243,
679
+ "pass@128": 0.231
680
+ },
681
+ "11": {
682
+ "pass@1": 0.1763515625,
683
+ "pass@2": 0.1854534940944882,
684
+ "pass@4": 0.1933735462129733,
685
+ "pass@8": 0.20147957136226124,
686
+ "pass@16": 0.21037463664286407,
687
+ "pass@32": 0.22037157099835816,
688
+ "pass@64": 0.23143147890828927,
689
+ "pass@128": 0.243
690
+ },
691
+ "12": {
692
+ "pass@1": 0.1750078125,
693
+ "pass@2": 0.18632972440944887,
694
+ "pass@4": 0.19674250149981243,
695
+ "pass@8": 0.2075677772984937,
696
+ "pass@16": 0.21899942949146833,
697
+ "pass@32": 0.23008881738333872,
698
+ "pass@64": 0.24004304392698875,
699
+ "pass@128": 0.249
700
+ },
701
+ "13": {
702
+ "pass@1": 0.14003125,
703
+ "pass@2": 0.15481865157480312,
704
+ "pass@4": 0.16692630361829766,
705
+ "pass@8": 0.17772499892830299,
706
+ "pass@16": 0.1882665689521189,
707
+ "pass@32": 0.19883793436883665,
708
+ "pass@64": 0.20967385171136876,
709
+ "pass@128": 0.221
710
+ },
711
+ "14": {
712
+ "pass@1": 0.1436328125,
713
+ "pass@2": 0.15869389763779526,
714
+ "pass@4": 0.17226924925009368,
715
+ "pass@8": 0.1845543174527869,
716
+ "pass@16": 0.19568671047542624,
717
+ "pass@32": 0.2065402438692653,
718
+ "pass@64": 0.21755881523205667,
719
+ "pass@128": 0.229
720
+ },
721
+ "15": {
722
+ "pass@1": 0.1338828125,
723
+ "pass@2": 0.14767212106299207,
724
+ "pass@4": 0.1592121984439444,
725
+ "pass@8": 0.1693664968394039,
726
+ "pass@16": 0.1790848548813016,
727
+ "pass@32": 0.1888553870136373,
728
+ "pass@64": 0.19929553877537814,
729
+ "pass@128": 0.211
730
+ },
731
+ "16": {
732
+ "pass@1": 0.155671875,
733
+ "pass@2": 0.16875172244094488,
734
+ "pass@4": 0.17969398078365192,
735
+ "pass@8": 0.1898988485117523,
736
+ "pass@16": 0.1991953499621563,
737
+ "pass@32": 0.20812386294309929,
738
+ "pass@64": 0.21791788802494516,
739
+ "pass@128": 0.23
740
+ },
741
+ "17": {
742
+ "pass@1": 0.14675,
743
+ "pass@2": 0.16014972933070862,
744
+ "pass@4": 0.16990317519685033,
745
+ "pass@8": 0.17901342366976633,
746
+ "pass@16": 0.1890970246223302,
747
+ "pass@32": 0.2009162762964177,
748
+ "pass@64": 0.21379618773979528,
749
+ "pass@128": 0.227
750
+ },
751
+ "18": {
752
+ "pass@1": 0.123859375,
753
+ "pass@2": 0.13845374015748027,
754
+ "pass@4": 0.15128099362579675,
755
+ "pass@8": 0.1636793233057228,
756
+ "pass@16": 0.17590328285323045,
757
+ "pass@32": 0.18769288846945548,
758
+ "pass@64": 0.19939121996448883,
759
+ "pass@128": 0.213
760
+ },
761
+ "19": {
762
+ "pass@1": 0.1425859375,
763
+ "pass@2": 0.1542038631889764,
764
+ "pass@4": 0.16308084739407575,
765
+ "pass@8": 0.17024050661671622,
766
+ "pass@16": 0.17678480815036582,
767
+ "pass@32": 0.18411748530607766,
768
+ "pass@64": 0.19279372965274186,
769
+ "pass@128": 0.203
770
+ },
771
+ "20": {
772
+ "pass@1": 0.12134375,
773
+ "pass@2": 0.13410039370078738,
774
+ "pass@4": 0.1453615757405324,
775
+ "pass@8": 0.1559681872763174,
776
+ "pass@16": 0.1660694483193041,
777
+ "pass@32": 0.17588726848327202,
778
+ "pass@64": 0.1855413942815293,
779
+ "pass@128": 0.196
780
+ }
781
+ },
782
+ "per_op_accuracy": {
783
+ "10": 0.179671875,
784
+ "2": 0.9675390625,
785
+ "3": 0.7970390625,
786
+ "4": 0.2107890625,
787
+ "5": 0.2116171875,
788
+ "6": 0.2580546875,
789
+ "7": 0.195703125,
790
+ "8": 0.18925,
791
+ "9": 0.175953125,
792
+ "11": 0.1763515625,
793
+ "12": 0.1750078125,
794
+ "13": 0.14003125,
795
+ "14": 0.1436328125,
796
+ "15": 0.1338828125,
797
+ "16": 0.155671875,
798
+ "17": 0.14675,
799
+ "18": 0.123859375,
800
+ "19": 0.1425859375,
801
+ "20": 0.12134375
802
+ },
803
+ "per_op_avg_response_len": {
804
+ "10": 167.241765625,
805
+ "2": 111.679328125,
806
+ "3": 128.0244453125,
807
+ "4": 125.2879921875,
808
+ "5": 135.821828125,
809
+ "6": 152.88628125,
810
+ "7": 142.7650703125,
811
+ "8": 163.613359375,
812
+ "9": 168.1250078125,
813
+ "11": 175.3768046875,
814
+ "12": 176.2021953125,
815
+ "13": 176.847875,
816
+ "14": 195.620578125,
817
+ "15": 203.4362421875,
818
+ "16": 206.30290625,
819
+ "17": 220.5351796875,
820
+ "18": 222.7138984375,
821
+ "19": 220.836265625,
822
+ "20": 227.097609375
823
+ },
824
+ "per_op_avg_loss": {},
825
+ "per_op_length": {
826
+ "10": 167.241765625,
827
+ "2": 111.679328125,
828
+ "3": 128.0244453125,
829
+ "4": 125.2879921875,
830
+ "5": 135.821828125,
831
+ "6": 152.88628125,
832
+ "7": 142.7650703125,
833
+ "8": 163.613359375,
834
+ "9": 168.1250078125,
835
+ "11": 175.3768046875,
836
+ "12": 176.2021953125,
837
+ "13": 176.847875,
838
+ "14": 195.620578125,
839
+ "15": 203.4362421875,
840
+ "16": 206.30290625,
841
+ "17": 220.5351796875,
842
+ "18": 222.7138984375,
843
+ "19": 220.836265625,
844
+ "20": 227.097609375
845
+ },
846
+ "per_op_loss": {},
847
+ "per_template": {
848
+ "crazy_zootopia": {
849
+ "count": 0,
850
+ "correct": 0,
851
+ "answer_accuracy": 0.0,
852
+ "avg_response_len": 0.0,
853
+ "resp_tokens_sum": 0,
854
+ "pass_at_k": {},
855
+ "per_op_pass_at_k": {}
856
+ },
857
+ "teachers_in_school": {
858
+ "count": 2432000,
859
+ "correct": 594526,
860
+ "answer_accuracy": 0.24445970394736843,
861
+ "avg_response_len": 174.7586648848684,
862
+ "resp_tokens_sum": 425013073,
863
+ "pass_at_k": {
864
+ "pass@1": 0.24445970394736843,
865
+ "pass@2": 0.2560060803460411,
866
+ "pass@4": 0.2656400593067308,
867
+ "pass@8": 0.2747226211406185,
868
+ "pass@16": 0.2838467221654667,
869
+ "pass@32": 0.2934078672886908,
870
+ "pass@64": 0.30357656007471606,
871
+ "pass@128": 0.31463157894736843
872
+ },
873
+ "per_op_pass_at_k": {
874
+ "10": {
875
+ "pass@1": 0.179671875,
876
+ "pass@2": 0.1866203248031496,
877
+ "pass@4": 0.19349498397075368,
878
+ "pass@8": 0.20171124100488724,
879
+ "pass@16": 0.21184839720232201,
880
+ "pass@32": 0.22407444095023307,
881
+ "pass@64": 0.23828823396176474,
882
+ "pass@128": 0.255
883
+ },
884
+ "2": {
885
+ "pass@1": 0.9675390625,
886
+ "pass@2": 0.9754135088582678,
887
+ "pass@4": 0.9807076276715406,
888
+ "pass@8": 0.9842055326995033,
889
+ "pass@16": 0.9866531838082899,
890
+ "pass@32": 0.9888710784240634,
891
+ "pass@64": 0.991123358518923,
892
+ "pass@128": 0.993
893
+ },
894
+ "3": {
895
+ "pass@1": 0.7970390625,
896
+ "pass@2": 0.8376731053149615,
897
+ "pass@4": 0.8661379510686164,
898
+ "pass@8": 0.8884730983835463,
899
+ "pass@16": 0.9065882701957276,
900
+ "pass@32": 0.9221857999677552,
901
+ "pass@64": 0.9361523489727314,
902
+ "pass@128": 0.949
903
+ },
904
+ "4": {
905
+ "pass@1": 0.2107890625,
906
+ "pass@2": 0.21529441437007876,
907
+ "pass@4": 0.21916330239970003,
908
+ "pass@8": 0.22346821216105478,
909
+ "pass@16": 0.22872197474530756,
910
+ "pass@32": 0.23562179093658991,
911
+ "pass@64": 0.24510618631947784,
912
+ "pass@128": 0.258
913
+ },
914
+ "5": {
915
+ "pass@1": 0.2116171875,
916
+ "pass@2": 0.21723412893700783,
917
+ "pass@4": 0.22284044347581547,
918
+ "pass@8": 0.22918635588080552,
919
+ "pass@16": 0.23692081774417614,
920
+ "pass@32": 0.24659684355460448,
921
+ "pass@64": 0.25860912185373264,
922
+ "pass@128": 0.272
923
+ },
924
+ "6": {
925
+ "pass@1": 0.2580546875,
926
+ "pass@2": 0.262111343503937,
927
+ "pass@4": 0.26583126621672293,
928
+ "pass@8": 0.269561781409488,
929
+ "pass@16": 0.2735911486266416,
930
+ "pass@32": 0.2786441597934989,
931
+ "pass@64": 0.2852150182516317,
932
+ "pass@128": 0.293
933
+ },
934
+ "7": {
935
+ "pass@1": 0.195703125,
936
+ "pass@2": 0.2011721210629921,
937
+ "pass@4": 0.20649363198350204,
938
+ "pass@8": 0.212816902115117,
939
+ "pass@16": 0.22024960690112913,
940
+ "pass@32": 0.2283513294970211,
941
+ "pass@64": 0.23693507099206224,
942
+ "pass@128": 0.247
943
+ },
944
+ "8": {
945
+ "pass@1": 0.18925,
946
+ "pass@2": 0.19675135334645666,
947
+ "pass@4": 0.20417071484814395,
948
+ "pass@8": 0.21275267862195865,
949
+ "pass@16": 0.22278762964396398,
950
+ "pass@32": 0.23415911788441254,
951
+ "pass@64": 0.2463119989893093,
952
+ "pass@128": 0.258
953
+ },
954
+ "9": {
955
+ "pass@1": 0.175953125,
956
+ "pass@2": 0.18321788877952747,
957
+ "pass@4": 0.1904768334270717,
958
+ "pass@8": 0.19806054813384352,
959
+ "pass@16": 0.20626457792569045,
960
+ "pass@32": 0.21481318234518765,
961
+ "pass@64": 0.22277015534238243,
962
+ "pass@128": 0.231
963
+ },
964
+ "11": {
965
+ "pass@1": 0.1763515625,
966
+ "pass@2": 0.1854534940944882,
967
+ "pass@4": 0.1933735462129733,
968
+ "pass@8": 0.20147957136226124,
969
+ "pass@16": 0.21037463664286407,
970
+ "pass@32": 0.22037157099835816,
971
+ "pass@64": 0.23143147890828927,
972
+ "pass@128": 0.243
973
+ },
974
+ "12": {
975
+ "pass@1": 0.1750078125,
976
+ "pass@2": 0.18632972440944887,
977
+ "pass@4": 0.19674250149981243,
978
+ "pass@8": 0.2075677772984937,
979
+ "pass@16": 0.21899942949146833,
980
+ "pass@32": 0.23008881738333872,
981
+ "pass@64": 0.24004304392698875,
982
+ "pass@128": 0.249
983
+ },
984
+ "13": {
985
+ "pass@1": 0.14003125,
986
+ "pass@2": 0.15481865157480312,
987
+ "pass@4": 0.16692630361829766,
988
+ "pass@8": 0.17772499892830299,
989
+ "pass@16": 0.1882665689521189,
990
+ "pass@32": 0.19883793436883665,
991
+ "pass@64": 0.20967385171136876,
992
+ "pass@128": 0.221
993
+ },
994
+ "14": {
995
+ "pass@1": 0.1436328125,
996
+ "pass@2": 0.15869389763779526,
997
+ "pass@4": 0.17226924925009368,
998
+ "pass@8": 0.1845543174527869,
999
+ "pass@16": 0.19568671047542624,
1000
+ "pass@32": 0.2065402438692653,
1001
+ "pass@64": 0.21755881523205667,
1002
+ "pass@128": 0.229
1003
+ },
1004
+ "15": {
1005
+ "pass@1": 0.1338828125,
1006
+ "pass@2": 0.14767212106299207,
1007
+ "pass@4": 0.1592121984439444,
1008
+ "pass@8": 0.1693664968394039,
1009
+ "pass@16": 0.1790848548813016,
1010
+ "pass@32": 0.1888553870136373,
1011
+ "pass@64": 0.19929553877537814,
1012
+ "pass@128": 0.211
1013
+ },
1014
+ "16": {
1015
+ "pass@1": 0.155671875,
1016
+ "pass@2": 0.16875172244094488,
1017
+ "pass@4": 0.17969398078365192,
1018
+ "pass@8": 0.1898988485117523,
1019
+ "pass@16": 0.1991953499621563,
1020
+ "pass@32": 0.20812386294309929,
1021
+ "pass@64": 0.21791788802494516,
1022
+ "pass@128": 0.23
1023
+ },
1024
+ "17": {
1025
+ "pass@1": 0.14675,
1026
+ "pass@2": 0.16014972933070862,
1027
+ "pass@4": 0.16990317519685033,
1028
+ "pass@8": 0.17901342366976633,
1029
+ "pass@16": 0.1890970246223302,
1030
+ "pass@32": 0.2009162762964177,
1031
+ "pass@64": 0.21379618773979528,
1032
+ "pass@128": 0.227
1033
+ },
1034
+ "18": {
1035
+ "pass@1": 0.123859375,
1036
+ "pass@2": 0.13845374015748027,
1037
+ "pass@4": 0.15128099362579675,
1038
+ "pass@8": 0.1636793233057228,
1039
+ "pass@16": 0.17590328285323045,
1040
+ "pass@32": 0.18769288846945548,
1041
+ "pass@64": 0.19939121996448883,
1042
+ "pass@128": 0.213
1043
+ },
1044
+ "19": {
1045
+ "pass@1": 0.1425859375,
1046
+ "pass@2": 0.1542038631889764,
1047
+ "pass@4": 0.16308084739407575,
1048
+ "pass@8": 0.17024050661671622,
1049
+ "pass@16": 0.17678480815036582,
1050
+ "pass@32": 0.18411748530607766,
1051
+ "pass@64": 0.19279372965274186,
1052
+ "pass@128": 0.203
1053
+ },
1054
+ "20": {
1055
+ "pass@1": 0.12134375,
1056
+ "pass@2": 0.13410039370078738,
1057
+ "pass@4": 0.1453615757405324,
1058
+ "pass@8": 0.1559681872763174,
1059
+ "pass@16": 0.1660694483193041,
1060
+ "pass@32": 0.17588726848327202,
1061
+ "pass@64": 0.1855413942815293,
1062
+ "pass@128": 0.196
1063
+ }
1064
+ }
1065
+ },
1066
+ "movie_festival_awards": {
1067
+ "count": 0,
1068
+ "correct": 0,
1069
+ "answer_accuracy": 0.0,
1070
+ "avg_response_len": 0.0,
1071
+ "resp_tokens_sum": 0,
1072
+ "pass_at_k": {},
1073
+ "per_op_pass_at_k": {}
1074
+ }
1075
+ }
1076
+ }
1077
+ }
Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/hf_model_ood_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ef5b332824c945db1d9c25f006be194f9d3c2058bf85b03074d3b4d412bb39
3
+ size 2223008342
Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/summary.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint,id_acc,ood_acc,total_acc,id_avg_loss,ood_avg_loss,total_avg_loss,id_avg_resp_len,ood_avg_resp_len,count_id,count_ood,count_total
2
+ hf_model,0.35395746527777777,0.14591171875,0.24445970394736843,0.0,0.0,0.0,143.9383420138889,202.49695546875,1152000,1280000,2432000
Qwen3-100M-RL/context/0.999zoo_op2-20+0.001teacher_op2/summary.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "hf_model",
4
+ "id_acc": 0.35395746527777777,
5
+ "ood_acc": 0.14591171875,
6
+ "total_acc": 0.24445970394736843,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 143.9383420138889,
11
+ "ood_avg_resp_len": 202.49695546875,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 0,
18
+ "correct": 0,
19
+ "answer_accuracy": 0.0,
20
+ "avg_response_len": 0.0,
21
+ "resp_tokens_sum": 0,
22
+ "pass_at_k": {},
23
+ "per_op_pass_at_k": {}
24
+ },
25
+ "teachers_in_school": {
26
+ "count": 2432000,
27
+ "correct": 594526,
28
+ "answer_accuracy": 0.24445970394736843,
29
+ "avg_response_len": 174.7586648848684,
30
+ "resp_tokens_sum": 425013073,
31
+ "pass_at_k": {
32
+ "pass@1": 0.24445970394736843,
33
+ "pass@2": 0.2560060803460411,
34
+ "pass@4": 0.2656400593067308,
35
+ "pass@8": 0.2747226211406185,
36
+ "pass@16": 0.2838467221654667,
37
+ "pass@32": 0.2934078672886908,
38
+ "pass@64": 0.30357656007471606,
39
+ "pass@128": 0.31463157894736843
40
+ },
41
+ "per_op_pass_at_k": {
42
+ "10": {
43
+ "pass@1": 0.179671875,
44
+ "pass@2": 0.1866203248031496,
45
+ "pass@4": 0.19349498397075368,
46
+ "pass@8": 0.20171124100488724,
47
+ "pass@16": 0.21184839720232201,
48
+ "pass@32": 0.22407444095023307,
49
+ "pass@64": 0.23828823396176474,
50
+ "pass@128": 0.255
51
+ },
52
+ "2": {
53
+ "pass@1": 0.9675390625,
54
+ "pass@2": 0.9754135088582678,
55
+ "pass@4": 0.9807076276715406,
56
+ "pass@8": 0.9842055326995033,
57
+ "pass@16": 0.9866531838082899,
58
+ "pass@32": 0.9888710784240634,
59
+ "pass@64": 0.991123358518923,
60
+ "pass@128": 0.993
61
+ },
62
+ "3": {
63
+ "pass@1": 0.7970390625,
64
+ "pass@2": 0.8376731053149615,
65
+ "pass@4": 0.8661379510686164,
66
+ "pass@8": 0.8884730983835463,
67
+ "pass@16": 0.9065882701957276,
68
+ "pass@32": 0.9221857999677552,
69
+ "pass@64": 0.9361523489727314,
70
+ "pass@128": 0.949
71
+ },
72
+ "4": {
73
+ "pass@1": 0.2107890625,
74
+ "pass@2": 0.21529441437007876,
75
+ "pass@4": 0.21916330239970003,
76
+ "pass@8": 0.22346821216105478,
77
+ "pass@16": 0.22872197474530756,
78
+ "pass@32": 0.23562179093658991,
79
+ "pass@64": 0.24510618631947784,
80
+ "pass@128": 0.258
81
+ },
82
+ "5": {
83
+ "pass@1": 0.2116171875,
84
+ "pass@2": 0.21723412893700783,
85
+ "pass@4": 0.22284044347581547,
86
+ "pass@8": 0.22918635588080552,
87
+ "pass@16": 0.23692081774417614,
88
+ "pass@32": 0.24659684355460448,
89
+ "pass@64": 0.25860912185373264,
90
+ "pass@128": 0.272
91
+ },
92
+ "6": {
93
+ "pass@1": 0.2580546875,
94
+ "pass@2": 0.262111343503937,
95
+ "pass@4": 0.26583126621672293,
96
+ "pass@8": 0.269561781409488,
97
+ "pass@16": 0.2735911486266416,
98
+ "pass@32": 0.2786441597934989,
99
+ "pass@64": 0.2852150182516317,
100
+ "pass@128": 0.293
101
+ },
102
+ "7": {
103
+ "pass@1": 0.195703125,
104
+ "pass@2": 0.2011721210629921,
105
+ "pass@4": 0.20649363198350204,
106
+ "pass@8": 0.212816902115117,
107
+ "pass@16": 0.22024960690112913,
108
+ "pass@32": 0.2283513294970211,
109
+ "pass@64": 0.23693507099206224,
110
+ "pass@128": 0.247
111
+ },
112
+ "8": {
113
+ "pass@1": 0.18925,
114
+ "pass@2": 0.19675135334645666,
115
+ "pass@4": 0.20417071484814395,
116
+ "pass@8": 0.21275267862195865,
117
+ "pass@16": 0.22278762964396398,
118
+ "pass@32": 0.23415911788441254,
119
+ "pass@64": 0.2463119989893093,
120
+ "pass@128": 0.258
121
+ },
122
+ "9": {
123
+ "pass@1": 0.175953125,
124
+ "pass@2": 0.18321788877952747,
125
+ "pass@4": 0.1904768334270717,
126
+ "pass@8": 0.19806054813384352,
127
+ "pass@16": 0.20626457792569045,
128
+ "pass@32": 0.21481318234518765,
129
+ "pass@64": 0.22277015534238243,
130
+ "pass@128": 0.231
131
+ },
132
+ "11": {
133
+ "pass@1": 0.1763515625,
134
+ "pass@2": 0.1854534940944882,
135
+ "pass@4": 0.1933735462129733,
136
+ "pass@8": 0.20147957136226124,
137
+ "pass@16": 0.21037463664286407,
138
+ "pass@32": 0.22037157099835816,
139
+ "pass@64": 0.23143147890828927,
140
+ "pass@128": 0.243
141
+ },
142
+ "12": {
143
+ "pass@1": 0.1750078125,
144
+ "pass@2": 0.18632972440944887,
145
+ "pass@4": 0.19674250149981243,
146
+ "pass@8": 0.2075677772984937,
147
+ "pass@16": 0.21899942949146833,
148
+ "pass@32": 0.23008881738333872,
149
+ "pass@64": 0.24004304392698875,
150
+ "pass@128": 0.249
151
+ },
152
+ "13": {
153
+ "pass@1": 0.14003125,
154
+ "pass@2": 0.15481865157480312,
155
+ "pass@4": 0.16692630361829766,
156
+ "pass@8": 0.17772499892830299,
157
+ "pass@16": 0.1882665689521189,
158
+ "pass@32": 0.19883793436883665,
159
+ "pass@64": 0.20967385171136876,
160
+ "pass@128": 0.221
161
+ },
162
+ "14": {
163
+ "pass@1": 0.1436328125,
164
+ "pass@2": 0.15869389763779526,
165
+ "pass@4": 0.17226924925009368,
166
+ "pass@8": 0.1845543174527869,
167
+ "pass@16": 0.19568671047542624,
168
+ "pass@32": 0.2065402438692653,
169
+ "pass@64": 0.21755881523205667,
170
+ "pass@128": 0.229
171
+ },
172
+ "15": {
173
+ "pass@1": 0.1338828125,
174
+ "pass@2": 0.14767212106299207,
175
+ "pass@4": 0.1592121984439444,
176
+ "pass@8": 0.1693664968394039,
177
+ "pass@16": 0.1790848548813016,
178
+ "pass@32": 0.1888553870136373,
179
+ "pass@64": 0.19929553877537814,
180
+ "pass@128": 0.211
181
+ },
182
+ "16": {
183
+ "pass@1": 0.155671875,
184
+ "pass@2": 0.16875172244094488,
185
+ "pass@4": 0.17969398078365192,
186
+ "pass@8": 0.1898988485117523,
187
+ "pass@16": 0.1991953499621563,
188
+ "pass@32": 0.20812386294309929,
189
+ "pass@64": 0.21791788802494516,
190
+ "pass@128": 0.23
191
+ },
192
+ "17": {
193
+ "pass@1": 0.14675,
194
+ "pass@2": 0.16014972933070862,
195
+ "pass@4": 0.16990317519685033,
196
+ "pass@8": 0.17901342366976633,
197
+ "pass@16": 0.1890970246223302,
198
+ "pass@32": 0.2009162762964177,
199
+ "pass@64": 0.21379618773979528,
200
+ "pass@128": 0.227
201
+ },
202
+ "18": {
203
+ "pass@1": 0.123859375,
204
+ "pass@2": 0.13845374015748027,
205
+ "pass@4": 0.15128099362579675,
206
+ "pass@8": 0.1636793233057228,
207
+ "pass@16": 0.17590328285323045,
208
+ "pass@32": 0.18769288846945548,
209
+ "pass@64": 0.19939121996448883,
210
+ "pass@128": 0.213
211
+ },
212
+ "19": {
213
+ "pass@1": 0.1425859375,
214
+ "pass@2": 0.1542038631889764,
215
+ "pass@4": 0.16308084739407575,
216
+ "pass@8": 0.17024050661671622,
217
+ "pass@16": 0.17678480815036582,
218
+ "pass@32": 0.18411748530607766,
219
+ "pass@64": 0.19279372965274186,
220
+ "pass@128": 0.203
221
+ },
222
+ "20": {
223
+ "pass@1": 0.12134375,
224
+ "pass@2": 0.13410039370078738,
225
+ "pass@4": 0.1453615757405324,
226
+ "pass@8": 0.1559681872763174,
227
+ "pass@16": 0.1660694483193041,
228
+ "pass@32": 0.17588726848327202,
229
+ "pass@64": 0.1855413942815293,
230
+ "pass@128": 0.196
231
+ }
232
+ }
233
+ },
234
+ "movie_festival_awards": {
235
+ "count": 0,
236
+ "correct": 0,
237
+ "answer_accuracy": 0.0,
238
+ "avg_response_len": 0.0,
239
+ "resp_tokens_sum": 0,
240
+ "pass_at_k": {},
241
+ "per_op_pass_at_k": {}
242
+ }
243
+ }
244
+ }
245
+ ]
Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs/0.99zoo_op2-20+0.01teacher_op2_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/context/op-difficulty-10B/graphs", "generated_path": "results/Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2", "results_dir": "results/Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs", "per_file": [{"file": "results/Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/hf_model_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 0, "dependency_mismatch": 0, "answer_mismatch": 9541, "extra_nodes": 1152000, "missing_nodes": 1152000, "perfect_with_extra": 0, "unused_gold_entries": 10000, "template_stats": {"teachers_in_school": {"total": 1152000, "extra_nodes": 1152000, "missing_nodes": 1152000, "answer_mismatch": 9541}}, "results_path": "results/Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs/hf_model_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/hf_model_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 0, "dependency_mismatch": 0, "answer_mismatch": 121879, "extra_nodes": 1279999, "missing_nodes": 1280000, "perfect_with_extra": 0, "unused_gold_entries": 9000, "template_stats": {"teachers_in_school": {"total": 1280000, "extra_nodes": 1279999, "missing_nodes": 1280000, "answer_mismatch": 121879}}, "results_path": "results/Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs/hf_model_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 0, "dependency_mismatch": 0, "answer_mismatch": 131420, "extra_nodes": 2431999, "missing_nodes": 2432000, "perfect_with_extra": 0, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs/0.99zoo_op2-20+0.01teacher_op2_score_report.jsonl", "template_stats": {"teachers_in_school": {"total": 2432000, "extra_nodes": 2431999, "missing_nodes": 2432000, "answer_mismatch": 131420}}}}
Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/graphs/results.json ADDED
@@ -0,0 +1,910 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "hf_model_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "teachers_in_school": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 0.0,
9
+ "pass@2": 0.0,
10
+ "pass@4": 0.0,
11
+ "pass@8": 0.0,
12
+ "pass@16": 0.0,
13
+ "pass@32": 0.0,
14
+ "pass@64": 0.0,
15
+ "pass@128": 0.0
16
+ },
17
+ "3": {
18
+ "pass@1": 0.0,
19
+ "pass@2": 0.0,
20
+ "pass@4": 0.0,
21
+ "pass@8": 0.0,
22
+ "pass@16": 0.0,
23
+ "pass@32": 0.0,
24
+ "pass@64": 0.0,
25
+ "pass@128": 0.0
26
+ },
27
+ "4": {
28
+ "pass@1": 0.0,
29
+ "pass@2": 0.0,
30
+ "pass@4": 0.0,
31
+ "pass@8": 0.0,
32
+ "pass@16": 0.0,
33
+ "pass@32": 0.0,
34
+ "pass@64": 0.0,
35
+ "pass@128": 0.0
36
+ },
37
+ "5": {
38
+ "pass@1": 0.0,
39
+ "pass@2": 0.0,
40
+ "pass@4": 0.0,
41
+ "pass@8": 0.0,
42
+ "pass@16": 0.0,
43
+ "pass@32": 0.0,
44
+ "pass@64": 0.0,
45
+ "pass@128": 0.0
46
+ },
47
+ "6": {
48
+ "pass@1": 0.0,
49
+ "pass@2": 0.0,
50
+ "pass@4": 0.0,
51
+ "pass@8": 0.0,
52
+ "pass@16": 0.0,
53
+ "pass@32": 0.0,
54
+ "pass@64": 0.0,
55
+ "pass@128": 0.0
56
+ },
57
+ "7": {
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
+ "8": {
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
+ "9": {
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
+ "10": {
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
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 0.0,
101
+ "3": 0.0,
102
+ "4": 0.0,
103
+ "5": 0.0,
104
+ "6": 0.0,
105
+ "7": 0.0,
106
+ "8": 0.0,
107
+ "9": 0.0,
108
+ "10": 0.0
109
+ },
110
+ "pass@2": {
111
+ "2": 0.0,
112
+ "3": 0.0,
113
+ "4": 0.0,
114
+ "5": 0.0,
115
+ "6": 0.0,
116
+ "7": 0.0,
117
+ "8": 0.0,
118
+ "9": 0.0,
119
+ "10": 0.0
120
+ },
121
+ "pass@4": {
122
+ "2": 0.0,
123
+ "3": 0.0,
124
+ "4": 0.0,
125
+ "5": 0.0,
126
+ "6": 0.0,
127
+ "7": 0.0,
128
+ "8": 0.0,
129
+ "9": 0.0,
130
+ "10": 0.0
131
+ },
132
+ "pass@8": {
133
+ "2": 0.0,
134
+ "3": 0.0,
135
+ "4": 0.0,
136
+ "5": 0.0,
137
+ "6": 0.0,
138
+ "7": 0.0,
139
+ "8": 0.0,
140
+ "9": 0.0,
141
+ "10": 0.0
142
+ },
143
+ "pass@16": {
144
+ "2": 0.0,
145
+ "3": 0.0,
146
+ "4": 0.0,
147
+ "5": 0.0,
148
+ "6": 0.0,
149
+ "7": 0.0,
150
+ "8": 0.0,
151
+ "9": 0.0,
152
+ "10": 0.0
153
+ },
154
+ "pass@32": {
155
+ "2": 0.0,
156
+ "3": 0.0,
157
+ "4": 0.0,
158
+ "5": 0.0,
159
+ "6": 0.0,
160
+ "7": 0.0,
161
+ "8": 0.0,
162
+ "9": 0.0,
163
+ "10": 0.0
164
+ },
165
+ "pass@64": {
166
+ "2": 0.0,
167
+ "3": 0.0,
168
+ "4": 0.0,
169
+ "5": 0.0,
170
+ "6": 0.0,
171
+ "7": 0.0,
172
+ "8": 0.0,
173
+ "9": 0.0,
174
+ "10": 0.0
175
+ },
176
+ "pass@128": {
177
+ "2": 0.0,
178
+ "3": 0.0,
179
+ "4": 0.0,
180
+ "5": 0.0,
181
+ "6": 0.0,
182
+ "7": 0.0,
183
+ "8": 0.0,
184
+ "9": 0.0,
185
+ "10": 0.0
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.0,
190
+ "pass@2": 0.0,
191
+ "pass@4": 0.0,
192
+ "pass@8": 0.0,
193
+ "pass@16": 0.0,
194
+ "pass@32": 0.0,
195
+ "pass@64": 0.0,
196
+ "pass@128": 0.0
197
+ }
198
+ }
199
+ },
200
+ "total": {
201
+ "per_op_pass_at_k": {
202
+ "2": {
203
+ "pass@1": 0.0,
204
+ "pass@2": 0.0,
205
+ "pass@4": 0.0,
206
+ "pass@8": 0.0,
207
+ "pass@16": 0.0,
208
+ "pass@32": 0.0,
209
+ "pass@64": 0.0,
210
+ "pass@128": 0.0
211
+ },
212
+ "3": {
213
+ "pass@1": 0.0,
214
+ "pass@2": 0.0,
215
+ "pass@4": 0.0,
216
+ "pass@8": 0.0,
217
+ "pass@16": 0.0,
218
+ "pass@32": 0.0,
219
+ "pass@64": 0.0,
220
+ "pass@128": 0.0
221
+ },
222
+ "4": {
223
+ "pass@1": 0.0,
224
+ "pass@2": 0.0,
225
+ "pass@4": 0.0,
226
+ "pass@8": 0.0,
227
+ "pass@16": 0.0,
228
+ "pass@32": 0.0,
229
+ "pass@64": 0.0,
230
+ "pass@128": 0.0
231
+ },
232
+ "5": {
233
+ "pass@1": 0.0,
234
+ "pass@2": 0.0,
235
+ "pass@4": 0.0,
236
+ "pass@8": 0.0,
237
+ "pass@16": 0.0,
238
+ "pass@32": 0.0,
239
+ "pass@64": 0.0,
240
+ "pass@128": 0.0
241
+ },
242
+ "6": {
243
+ "pass@1": 0.0,
244
+ "pass@2": 0.0,
245
+ "pass@4": 0.0,
246
+ "pass@8": 0.0,
247
+ "pass@16": 0.0,
248
+ "pass@32": 0.0,
249
+ "pass@64": 0.0,
250
+ "pass@128": 0.0
251
+ },
252
+ "7": {
253
+ "pass@1": 0.0,
254
+ "pass@2": 0.0,
255
+ "pass@4": 0.0,
256
+ "pass@8": 0.0,
257
+ "pass@16": 0.0,
258
+ "pass@32": 0.0,
259
+ "pass@64": 0.0,
260
+ "pass@128": 0.0
261
+ },
262
+ "8": {
263
+ "pass@1": 0.0,
264
+ "pass@2": 0.0,
265
+ "pass@4": 0.0,
266
+ "pass@8": 0.0,
267
+ "pass@16": 0.0,
268
+ "pass@32": 0.0,
269
+ "pass@64": 0.0,
270
+ "pass@128": 0.0
271
+ },
272
+ "9": {
273
+ "pass@1": 0.0,
274
+ "pass@2": 0.0,
275
+ "pass@4": 0.0,
276
+ "pass@8": 0.0,
277
+ "pass@16": 0.0,
278
+ "pass@32": 0.0,
279
+ "pass@64": 0.0,
280
+ "pass@128": 0.0
281
+ },
282
+ "10": {
283
+ "pass@1": 0.0,
284
+ "pass@2": 0.0,
285
+ "pass@4": 0.0,
286
+ "pass@8": 0.0,
287
+ "pass@16": 0.0,
288
+ "pass@32": 0.0,
289
+ "pass@64": 0.0,
290
+ "pass@128": 0.0
291
+ }
292
+ },
293
+ "per_op_pass_at_columns": {
294
+ "pass@1": {
295
+ "2": 0.0,
296
+ "3": 0.0,
297
+ "4": 0.0,
298
+ "5": 0.0,
299
+ "6": 0.0,
300
+ "7": 0.0,
301
+ "8": 0.0,
302
+ "9": 0.0,
303
+ "10": 0.0
304
+ },
305
+ "pass@2": {
306
+ "2": 0.0,
307
+ "3": 0.0,
308
+ "4": 0.0,
309
+ "5": 0.0,
310
+ "6": 0.0,
311
+ "7": 0.0,
312
+ "8": 0.0,
313
+ "9": 0.0,
314
+ "10": 0.0
315
+ },
316
+ "pass@4": {
317
+ "2": 0.0,
318
+ "3": 0.0,
319
+ "4": 0.0,
320
+ "5": 0.0,
321
+ "6": 0.0,
322
+ "7": 0.0,
323
+ "8": 0.0,
324
+ "9": 0.0,
325
+ "10": 0.0
326
+ },
327
+ "pass@8": {
328
+ "2": 0.0,
329
+ "3": 0.0,
330
+ "4": 0.0,
331
+ "5": 0.0,
332
+ "6": 0.0,
333
+ "7": 0.0,
334
+ "8": 0.0,
335
+ "9": 0.0,
336
+ "10": 0.0
337
+ },
338
+ "pass@16": {
339
+ "2": 0.0,
340
+ "3": 0.0,
341
+ "4": 0.0,
342
+ "5": 0.0,
343
+ "6": 0.0,
344
+ "7": 0.0,
345
+ "8": 0.0,
346
+ "9": 0.0,
347
+ "10": 0.0
348
+ },
349
+ "pass@32": {
350
+ "2": 0.0,
351
+ "3": 0.0,
352
+ "4": 0.0,
353
+ "5": 0.0,
354
+ "6": 0.0,
355
+ "7": 0.0,
356
+ "8": 0.0,
357
+ "9": 0.0,
358
+ "10": 0.0
359
+ },
360
+ "pass@64": {
361
+ "2": 0.0,
362
+ "3": 0.0,
363
+ "4": 0.0,
364
+ "5": 0.0,
365
+ "6": 0.0,
366
+ "7": 0.0,
367
+ "8": 0.0,
368
+ "9": 0.0,
369
+ "10": 0.0
370
+ },
371
+ "pass@128": {
372
+ "2": 0.0,
373
+ "3": 0.0,
374
+ "4": 0.0,
375
+ "5": 0.0,
376
+ "6": 0.0,
377
+ "7": 0.0,
378
+ "8": 0.0,
379
+ "9": 0.0,
380
+ "10": 0.0
381
+ }
382
+ },
383
+ "total_pass_at_k": {
384
+ "pass@1": 0.0,
385
+ "pass@2": 0.0,
386
+ "pass@4": 0.0,
387
+ "pass@8": 0.0,
388
+ "pass@16": 0.0,
389
+ "pass@32": 0.0,
390
+ "pass@64": 0.0,
391
+ "pass@128": 0.0
392
+ }
393
+ },
394
+ "ks": [
395
+ 1,
396
+ 2,
397
+ 4,
398
+ 8,
399
+ 16,
400
+ 32,
401
+ 64,
402
+ 128
403
+ ],
404
+ "prompt_counts": {
405
+ "per_template": {
406
+ "teachers_in_school": {
407
+ "per_op": {
408
+ "2": 1000,
409
+ "3": 1000,
410
+ "4": 1000,
411
+ "5": 1000,
412
+ "6": 1000,
413
+ "7": 1000,
414
+ "8": 1000,
415
+ "9": 1000,
416
+ "10": 1000
417
+ },
418
+ "total": 9000
419
+ }
420
+ },
421
+ "total": {
422
+ "per_op": {
423
+ "2": 1000,
424
+ "3": 1000,
425
+ "4": 1000,
426
+ "5": 1000,
427
+ "6": 1000,
428
+ "7": 1000,
429
+ "8": 1000,
430
+ "9": 1000,
431
+ "10": 1000
432
+ },
433
+ "total": 9000
434
+ }
435
+ }
436
+ },
437
+ "hf_model_ood_generations.jsonl.graph_results.jsonl": {
438
+ "per_template": {
439
+ "teachers_in_school": {
440
+ "per_op_pass_at_k": {
441
+ "11": {
442
+ "pass@1": 0.0,
443
+ "pass@2": 0.0,
444
+ "pass@4": 0.0,
445
+ "pass@8": 0.0,
446
+ "pass@16": 0.0,
447
+ "pass@32": 0.0,
448
+ "pass@64": 0.0,
449
+ "pass@128": 0.0
450
+ },
451
+ "12": {
452
+ "pass@1": 0.0,
453
+ "pass@2": 0.0,
454
+ "pass@4": 0.0,
455
+ "pass@8": 0.0,
456
+ "pass@16": 0.0,
457
+ "pass@32": 0.0,
458
+ "pass@64": 0.0,
459
+ "pass@128": 0.0
460
+ },
461
+ "13": {
462
+ "pass@1": 0.0,
463
+ "pass@2": 0.0,
464
+ "pass@4": 0.0,
465
+ "pass@8": 0.0,
466
+ "pass@16": 0.0,
467
+ "pass@32": 0.0,
468
+ "pass@64": 0.0,
469
+ "pass@128": 0.0
470
+ },
471
+ "14": {
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": 0.0
480
+ },
481
+ "15": {
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": 0.0
490
+ },
491
+ "16": {
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
+ "17": {
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
+ "18": {
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
+ "19": {
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
+ "20": {
532
+ "pass@1": 0.0,
533
+ "pass@2": 0.0,
534
+ "pass@4": 0.0,
535
+ "pass@8": 0.0,
536
+ "pass@16": 0.0,
537
+ "pass@32": 0.0,
538
+ "pass@64": 0.0,
539
+ "pass@128": 0.0
540
+ }
541
+ },
542
+ "per_op_pass_at_columns": {
543
+ "pass@1": {
544
+ "11": 0.0,
545
+ "12": 0.0,
546
+ "13": 0.0,
547
+ "14": 0.0,
548
+ "15": 0.0,
549
+ "16": 0.0,
550
+ "17": 0.0,
551
+ "18": 0.0,
552
+ "19": 0.0,
553
+ "20": 0.0
554
+ },
555
+ "pass@2": {
556
+ "11": 0.0,
557
+ "12": 0.0,
558
+ "13": 0.0,
559
+ "14": 0.0,
560
+ "15": 0.0,
561
+ "16": 0.0,
562
+ "17": 0.0,
563
+ "18": 0.0,
564
+ "19": 0.0,
565
+ "20": 0.0
566
+ },
567
+ "pass@4": {
568
+ "11": 0.0,
569
+ "12": 0.0,
570
+ "13": 0.0,
571
+ "14": 0.0,
572
+ "15": 0.0,
573
+ "16": 0.0,
574
+ "17": 0.0,
575
+ "18": 0.0,
576
+ "19": 0.0,
577
+ "20": 0.0
578
+ },
579
+ "pass@8": {
580
+ "11": 0.0,
581
+ "12": 0.0,
582
+ "13": 0.0,
583
+ "14": 0.0,
584
+ "15": 0.0,
585
+ "16": 0.0,
586
+ "17": 0.0,
587
+ "18": 0.0,
588
+ "19": 0.0,
589
+ "20": 0.0
590
+ },
591
+ "pass@16": {
592
+ "11": 0.0,
593
+ "12": 0.0,
594
+ "13": 0.0,
595
+ "14": 0.0,
596
+ "15": 0.0,
597
+ "16": 0.0,
598
+ "17": 0.0,
599
+ "18": 0.0,
600
+ "19": 0.0,
601
+ "20": 0.0
602
+ },
603
+ "pass@32": {
604
+ "11": 0.0,
605
+ "12": 0.0,
606
+ "13": 0.0,
607
+ "14": 0.0,
608
+ "15": 0.0,
609
+ "16": 0.0,
610
+ "17": 0.0,
611
+ "18": 0.0,
612
+ "19": 0.0,
613
+ "20": 0.0
614
+ },
615
+ "pass@64": {
616
+ "11": 0.0,
617
+ "12": 0.0,
618
+ "13": 0.0,
619
+ "14": 0.0,
620
+ "15": 0.0,
621
+ "16": 0.0,
622
+ "17": 0.0,
623
+ "18": 0.0,
624
+ "19": 0.0,
625
+ "20": 0.0
626
+ },
627
+ "pass@128": {
628
+ "11": 0.0,
629
+ "12": 0.0,
630
+ "13": 0.0,
631
+ "14": 0.0,
632
+ "15": 0.0,
633
+ "16": 0.0,
634
+ "17": 0.0,
635
+ "18": 0.0,
636
+ "19": 0.0,
637
+ "20": 0.0
638
+ }
639
+ },
640
+ "total_pass_at_k": {
641
+ "pass@1": 0.0,
642
+ "pass@2": 0.0,
643
+ "pass@4": 0.0,
644
+ "pass@8": 0.0,
645
+ "pass@16": 0.0,
646
+ "pass@32": 0.0,
647
+ "pass@64": 0.0,
648
+ "pass@128": 0.0
649
+ }
650
+ }
651
+ },
652
+ "total": {
653
+ "per_op_pass_at_k": {
654
+ "11": {
655
+ "pass@1": 0.0,
656
+ "pass@2": 0.0,
657
+ "pass@4": 0.0,
658
+ "pass@8": 0.0,
659
+ "pass@16": 0.0,
660
+ "pass@32": 0.0,
661
+ "pass@64": 0.0,
662
+ "pass@128": 0.0
663
+ },
664
+ "12": {
665
+ "pass@1": 0.0,
666
+ "pass@2": 0.0,
667
+ "pass@4": 0.0,
668
+ "pass@8": 0.0,
669
+ "pass@16": 0.0,
670
+ "pass@32": 0.0,
671
+ "pass@64": 0.0,
672
+ "pass@128": 0.0
673
+ },
674
+ "13": {
675
+ "pass@1": 0.0,
676
+ "pass@2": 0.0,
677
+ "pass@4": 0.0,
678
+ "pass@8": 0.0,
679
+ "pass@16": 0.0,
680
+ "pass@32": 0.0,
681
+ "pass@64": 0.0,
682
+ "pass@128": 0.0
683
+ },
684
+ "14": {
685
+ "pass@1": 0.0,
686
+ "pass@2": 0.0,
687
+ "pass@4": 0.0,
688
+ "pass@8": 0.0,
689
+ "pass@16": 0.0,
690
+ "pass@32": 0.0,
691
+ "pass@64": 0.0,
692
+ "pass@128": 0.0
693
+ },
694
+ "15": {
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": 0.0
703
+ },
704
+ "16": {
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
+ "17": {
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
+ "18": {
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
+ "19": {
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
+ "20": {
745
+ "pass@1": 0.0,
746
+ "pass@2": 0.0,
747
+ "pass@4": 0.0,
748
+ "pass@8": 0.0,
749
+ "pass@16": 0.0,
750
+ "pass@32": 0.0,
751
+ "pass@64": 0.0,
752
+ "pass@128": 0.0
753
+ }
754
+ },
755
+ "per_op_pass_at_columns": {
756
+ "pass@1": {
757
+ "11": 0.0,
758
+ "12": 0.0,
759
+ "13": 0.0,
760
+ "14": 0.0,
761
+ "15": 0.0,
762
+ "16": 0.0,
763
+ "17": 0.0,
764
+ "18": 0.0,
765
+ "19": 0.0,
766
+ "20": 0.0
767
+ },
768
+ "pass@2": {
769
+ "11": 0.0,
770
+ "12": 0.0,
771
+ "13": 0.0,
772
+ "14": 0.0,
773
+ "15": 0.0,
774
+ "16": 0.0,
775
+ "17": 0.0,
776
+ "18": 0.0,
777
+ "19": 0.0,
778
+ "20": 0.0
779
+ },
780
+ "pass@4": {
781
+ "11": 0.0,
782
+ "12": 0.0,
783
+ "13": 0.0,
784
+ "14": 0.0,
785
+ "15": 0.0,
786
+ "16": 0.0,
787
+ "17": 0.0,
788
+ "18": 0.0,
789
+ "19": 0.0,
790
+ "20": 0.0
791
+ },
792
+ "pass@8": {
793
+ "11": 0.0,
794
+ "12": 0.0,
795
+ "13": 0.0,
796
+ "14": 0.0,
797
+ "15": 0.0,
798
+ "16": 0.0,
799
+ "17": 0.0,
800
+ "18": 0.0,
801
+ "19": 0.0,
802
+ "20": 0.0
803
+ },
804
+ "pass@16": {
805
+ "11": 0.0,
806
+ "12": 0.0,
807
+ "13": 0.0,
808
+ "14": 0.0,
809
+ "15": 0.0,
810
+ "16": 0.0,
811
+ "17": 0.0,
812
+ "18": 0.0,
813
+ "19": 0.0,
814
+ "20": 0.0
815
+ },
816
+ "pass@32": {
817
+ "11": 0.0,
818
+ "12": 0.0,
819
+ "13": 0.0,
820
+ "14": 0.0,
821
+ "15": 0.0,
822
+ "16": 0.0,
823
+ "17": 0.0,
824
+ "18": 0.0,
825
+ "19": 0.0,
826
+ "20": 0.0
827
+ },
828
+ "pass@64": {
829
+ "11": 0.0,
830
+ "12": 0.0,
831
+ "13": 0.0,
832
+ "14": 0.0,
833
+ "15": 0.0,
834
+ "16": 0.0,
835
+ "17": 0.0,
836
+ "18": 0.0,
837
+ "19": 0.0,
838
+ "20": 0.0
839
+ },
840
+ "pass@128": {
841
+ "11": 0.0,
842
+ "12": 0.0,
843
+ "13": 0.0,
844
+ "14": 0.0,
845
+ "15": 0.0,
846
+ "16": 0.0,
847
+ "17": 0.0,
848
+ "18": 0.0,
849
+ "19": 0.0,
850
+ "20": 0.0
851
+ }
852
+ },
853
+ "total_pass_at_k": {
854
+ "pass@1": 0.0,
855
+ "pass@2": 0.0,
856
+ "pass@4": 0.0,
857
+ "pass@8": 0.0,
858
+ "pass@16": 0.0,
859
+ "pass@32": 0.0,
860
+ "pass@64": 0.0,
861
+ "pass@128": 0.0
862
+ }
863
+ },
864
+ "ks": [
865
+ 1,
866
+ 2,
867
+ 4,
868
+ 8,
869
+ 16,
870
+ 32,
871
+ 64,
872
+ 128
873
+ ],
874
+ "prompt_counts": {
875
+ "per_template": {
876
+ "teachers_in_school": {
877
+ "per_op": {
878
+ "11": 1000,
879
+ "12": 1000,
880
+ "13": 1000,
881
+ "14": 1000,
882
+ "15": 1000,
883
+ "16": 1000,
884
+ "17": 1000,
885
+ "18": 1000,
886
+ "19": 1000,
887
+ "20": 1000
888
+ },
889
+ "total": 10000
890
+ }
891
+ },
892
+ "total": {
893
+ "per_op": {
894
+ "11": 1000,
895
+ "12": 1000,
896
+ "13": 1000,
897
+ "14": 1000,
898
+ "15": 1000,
899
+ "16": 1000,
900
+ "17": 1000,
901
+ "18": 1000,
902
+ "19": 1000,
903
+ "20": 1000
904
+ },
905
+ "total": 10000
906
+ }
907
+ }
908
+ }
909
+ }
910
+ }
Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/hf_model_ood_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968c7292d5ffa390a250d1268de665f37a960ee75282d094d9edc38122cbc9b8
3
+ size 2616730794
Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/summary.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint,id_acc,ood_acc,total_acc,id_avg_loss,ood_avg_loss,total_avg_loss,id_avg_resp_len,ood_avg_resp_len,count_id,count_ood,count_total
2
+ hf_model,0.9917178819444444,0.90478203125,0.9459621710526316,0.0,0.0,0.0,180.0242638888889,346.5120359375,1152000,1280000,2432000
Qwen3-100M-RL/context/0.99zoo_op2-20+0.01teacher_op2/summary.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "hf_model",
4
+ "id_acc": 0.9917178819444444,
5
+ "ood_acc": 0.90478203125,
6
+ "total_acc": 0.9459621710526316,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 180.0242638888889,
11
+ "ood_avg_resp_len": 346.5120359375,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 0,
18
+ "correct": 0,
19
+ "answer_accuracy": 0.0,
20
+ "avg_response_len": 0.0,
21
+ "resp_tokens_sum": 0,
22
+ "pass_at_k": {},
23
+ "per_op_pass_at_k": {}
24
+ },
25
+ "teachers_in_school": {
26
+ "count": 2432000,
27
+ "correct": 2300580,
28
+ "answer_accuracy": 0.9459621710526316,
29
+ "avg_response_len": 267.64940707236843,
30
+ "resp_tokens_sum": 650923358,
31
+ "pass_at_k": {
32
+ "pass@1": 0.9459621710526316,
33
+ "pass@2": 0.965499624430164,
34
+ "pass@4": 0.9754853252816995,
35
+ "pass@8": 0.9815746569203379,
36
+ "pass@16": 0.9856429402662464,
37
+ "pass@32": 0.9886553766902775,
38
+ "pass@64": 0.9910604803835107,
39
+ "pass@128": 0.9930526315789474
40
+ },
41
+ "per_op_pass_at_k": {
42
+ "10": {
43
+ "pass@1": 0.9699453125,
44
+ "pass@2": 0.9797700541338586,
45
+ "pass@4": 0.9846088579865014,
46
+ "pass@8": 0.9883971297589192,
47
+ "pass@16": 0.991548693276063,
48
+ "pass@32": 0.9939062487742031,
49
+ "pass@64": 0.9956849154464417,
50
+ "pass@128": 0.997
51
+ },
52
+ "2": {
53
+ "pass@1": 1.0,
54
+ "pass@2": 1.0,
55
+ "pass@4": 1.0,
56
+ "pass@8": 1.0,
57
+ "pass@16": 1.0,
58
+ "pass@32": 1.0,
59
+ "pass@64": 1.0,
60
+ "pass@128": 1.0
61
+ },
62
+ "3": {
63
+ "pass@1": 0.99759375,
64
+ "pass@2": 0.9991465305118111,
65
+ "pass@4": 0.9998152384701912,
66
+ "pass@8": 0.9999862821828273,
67
+ "pass@16": 0.9999999227084759,
68
+ "pass@32": 0.9999999999993933,
69
+ "pass@64": 1.0,
70
+ "pass@128": 1.0
71
+ },
72
+ "4": {
73
+ "pass@1": 0.99834375,
74
+ "pass@2": 0.9994431594488189,
75
+ "pass@4": 0.9998681761342333,
76
+ "pass@8": 0.9999880140745279,
77
+ "pass@16": 0.9999999083912323,
78
+ "pass@32": 0.999999999998944,
79
+ "pass@64": 1.0,
80
+ "pass@128": 1.0
81
+ },
82
+ "5": {
83
+ "pass@1": 0.9933515625,
84
+ "pass@2": 0.9955663139763777,
85
+ "pass@4": 0.9974079118860144,
86
+ "pass@8": 0.9986958248958838,
87
+ "pass@16": 0.9994353865491737,
88
+ "pass@32": 0.9998235513802302,
89
+ "pass@64": 0.9999861740539754,
90
+ "pass@128": 1.0
91
+ },
92
+ "6": {
93
+ "pass@1": 0.995625,
94
+ "pass@2": 0.99801156496063,
95
+ "pass@4": 0.9991621754780652,
96
+ "pass@8": 0.9997905041568963,
97
+ "pass@16": 0.9999826485802666,
98
+ "pass@32": 0.999999900717592,
99
+ "pass@64": 0.9999999999999175,
100
+ "pass@128": 1.0
101
+ },
102
+ "7": {
103
+ "pass@1": 0.991,
104
+ "pass@2": 0.9933371062992128,
105
+ "pass@4": 0.9947224583802023,
106
+ "pass@8": 0.9958695873510292,
107
+ "pass@16": 0.9966041585170369,
108
+ "pass@32": 0.9969280491355603,
109
+ "pass@64": 0.9969985543119962,
110
+ "pass@128": 0.997
111
+ },
112
+ "8": {
113
+ "pass@1": 0.9948046875,
114
+ "pass@2": 0.99785125492126,
115
+ "pass@4": 0.998795172384702,
116
+ "pass@8": 0.9994316174246192,
117
+ "pass@16": 0.9998579688324685,
118
+ "pass@32": 0.9999931255781963,
119
+ "pass@64": 0.9999999975930302,
120
+ "pass@128": 1.0
121
+ },
122
+ "9": {
123
+ "pass@1": 0.984796875,
124
+ "pass@2": 0.9912790354330716,
125
+ "pass@4": 0.9942763324896889,
126
+ "pass@8": 0.996222904016301,
127
+ "pass@16": 0.9974501804727003,
128
+ "pass@32": 0.9981885625139278,
129
+ "pass@64": 0.998723119840615,
130
+ "pass@128": 0.999
131
+ },
132
+ "11": {
133
+ "pass@1": 0.9512578125,
134
+ "pass@2": 0.9658013041338588,
135
+ "pass@4": 0.9731058290213717,
136
+ "pass@8": 0.9777503786832513,
137
+ "pass@16": 0.9812478554053372,
138
+ "pass@32": 0.9844936593333612,
139
+ "pass@64": 0.9875782128535292,
140
+ "pass@128": 0.99
141
+ },
142
+ "12": {
143
+ "pass@1": 0.9279609375,
144
+ "pass@2": 0.9452753444881897,
145
+ "pass@4": 0.9557707446569181,
146
+ "pass@8": 0.9629128336731604,
147
+ "pass@16": 0.9684001319561727,
148
+ "pass@32": 0.9734901999432878,
149
+ "pass@64": 0.9785937143414183,
150
+ "pass@128": 0.984
151
+ },
152
+ "13": {
153
+ "pass@1": 0.9148515625,
154
+ "pass@2": 0.9373233267716538,
155
+ "pass@4": 0.9503126651668536,
156
+ "pass@8": 0.9590150667585761,
157
+ "pass@16": 0.9658224358162538,
158
+ "pass@32": 0.9720045806193894,
159
+ "pass@64": 0.9776870791192475,
160
+ "pass@128": 0.983
161
+ },
162
+ "14": {
163
+ "pass@1": 0.9195390625,
164
+ "pass@2": 0.9461455462598434,
165
+ "pass@4": 0.9610489086989125,
166
+ "pass@8": 0.9705652801128191,
167
+ "pass@16": 0.976617495691548,
168
+ "pass@32": 0.9807539224865852,
169
+ "pass@64": 0.9838434201680727,
170
+ "pass@128": 0.986
171
+ },
172
+ "15": {
173
+ "pass@1": 0.9212421875,
174
+ "pass@2": 0.9496477608267725,
175
+ "pass@4": 0.9639471972253464,
176
+ "pass@8": 0.9731272495996897,
177
+ "pass@16": 0.9795135593649998,
178
+ "pass@32": 0.9843676266202894,
179
+ "pass@64": 0.9887092071015339,
180
+ "pass@128": 0.993
181
+ },
182
+ "16": {
183
+ "pass@1": 0.9186484375,
184
+ "pass@2": 0.9507684547244115,
185
+ "pass@4": 0.9659008573303339,
186
+ "pass@8": 0.974618462414321,
187
+ "pass@16": 0.9800429740397889,
188
+ "pass@32": 0.9841030640501913,
189
+ "pass@64": 0.9876616774077218,
190
+ "pass@128": 0.99
191
+ },
192
+ "17": {
193
+ "pass@1": 0.9137890625,
194
+ "pass@2": 0.9511459153543321,
195
+ "pass@4": 0.9683324656917881,
196
+ "pass@8": 0.9782519917436393,
197
+ "pass@16": 0.9845447476466959,
198
+ "pass@32": 0.9884888034847372,
199
+ "pass@64": 0.9909003607208057,
200
+ "pass@128": 0.993
201
+ },
202
+ "18": {
203
+ "pass@1": 0.8819921875,
204
+ "pass@2": 0.9288923474409468,
205
+ "pass@4": 0.9518024659730036,
206
+ "pass@8": 0.9643686704288694,
207
+ "pass@16": 0.9725036453284903,
208
+ "pass@32": 0.9785188430691222,
209
+ "pass@64": 0.9827390755534815,
210
+ "pass@128": 0.985
211
+ },
212
+ "19": {
213
+ "pass@1": 0.8668359375,
214
+ "pass@2": 0.9196662155511819,
215
+ "pass@4": 0.9460197001312345,
216
+ "pass@8": 0.9618559891779669,
217
+ "pass@16": 0.9724486989570319,
218
+ "pass@32": 0.9796740074314165,
219
+ "pass@64": 0.9850677359090562,
220
+ "pass@128": 0.99
221
+ },
222
+ "20": {
223
+ "pass@1": 0.831703125,
224
+ "pass@2": 0.8954216289370094,
225
+ "pass@4": 0.9293240232470946,
226
+ "pass@8": 0.9490706950329557,
227
+ "pass@16": 0.9611954535250025,
228
+ "pass@32": 0.9697180119787673,
229
+ "pass@64": 0.9759758828658656,
230
+ "pass@128": 0.981
231
+ }
232
+ }
233
+ },
234
+ "movie_festival_awards": {
235
+ "count": 0,
236
+ "correct": 0,
237
+ "answer_accuracy": 0.0,
238
+ "avg_response_len": 0.0,
239
+ "resp_tokens_sum": 0,
240
+ "pass_at_k": {},
241
+ "per_op_pass_at_k": {}
242
+ }
243
+ }
244
+ }
245
+ ]
Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs/0.9zoo_op2-20+0.1teacher_op2_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/context/op-difficulty-10B/graphs", "generated_path": "results/Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2", "results_dir": "results/Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs", "per_file": [{"file": "results/Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 2173, "dependency_mismatch": 933959, "answer_mismatch": 8758, "extra_nodes": 1151956, "missing_nodes": 1152000, "perfect_with_extra": 0, "unused_gold_entries": 10000, "template_stats": {"teachers_in_school": {"total": 1152000, "dependency_mismatch": 933959, "extra_nodes": 1151956, "missing_nodes": 1152000, "answer_mismatch": 8758, "value_mismatch": 2173}}, "results_path": "results/Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs/hf_model_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 46724, "dependency_mismatch": 1062723, "answer_mismatch": 111672, "extra_nodes": 1279965, "missing_nodes": 1280000, "perfect_with_extra": 0, "unused_gold_entries": 9000, "template_stats": {"teachers_in_school": {"total": 1280000, "dependency_mismatch": 1062723, "answer_mismatch": 111672, "extra_nodes": 1279965, "missing_nodes": 1280000, "value_mismatch": 46724}}, "results_path": "results/Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs/hf_model_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 48897, "dependency_mismatch": 1996682, "answer_mismatch": 120430, "extra_nodes": 2431921, "missing_nodes": 2432000, "perfect_with_extra": 0, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs/0.9zoo_op2-20+0.1teacher_op2_score_report.jsonl", "template_stats": {"teachers_in_school": {"total": 2432000, "dependency_mismatch": 1996682, "extra_nodes": 2431921, "missing_nodes": 2432000, "answer_mismatch": 120430, "value_mismatch": 48897}}}}
Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/graphs/results.json ADDED
@@ -0,0 +1,910 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "hf_model_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "teachers_in_school": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 0.0,
9
+ "pass@2": 0.0,
10
+ "pass@4": 0.0,
11
+ "pass@8": 0.0,
12
+ "pass@16": 0.0,
13
+ "pass@32": 0.0,
14
+ "pass@64": 0.0,
15
+ "pass@128": 0.0
16
+ },
17
+ "3": {
18
+ "pass@1": 0.0,
19
+ "pass@2": 0.0,
20
+ "pass@4": 0.0,
21
+ "pass@8": 0.0,
22
+ "pass@16": 0.0,
23
+ "pass@32": 0.0,
24
+ "pass@64": 0.0,
25
+ "pass@128": 0.0
26
+ },
27
+ "4": {
28
+ "pass@1": 0.0,
29
+ "pass@2": 0.0,
30
+ "pass@4": 0.0,
31
+ "pass@8": 0.0,
32
+ "pass@16": 0.0,
33
+ "pass@32": 0.0,
34
+ "pass@64": 0.0,
35
+ "pass@128": 0.0
36
+ },
37
+ "5": {
38
+ "pass@1": 0.0,
39
+ "pass@2": 0.0,
40
+ "pass@4": 0.0,
41
+ "pass@8": 0.0,
42
+ "pass@16": 0.0,
43
+ "pass@32": 0.0,
44
+ "pass@64": 0.0,
45
+ "pass@128": 0.0
46
+ },
47
+ "6": {
48
+ "pass@1": 0.0,
49
+ "pass@2": 0.0,
50
+ "pass@4": 0.0,
51
+ "pass@8": 0.0,
52
+ "pass@16": 0.0,
53
+ "pass@32": 0.0,
54
+ "pass@64": 0.0,
55
+ "pass@128": 0.0
56
+ },
57
+ "7": {
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
+ "8": {
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
+ "9": {
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
+ "10": {
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
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 0.0,
101
+ "3": 0.0,
102
+ "4": 0.0,
103
+ "5": 0.0,
104
+ "6": 0.0,
105
+ "7": 0.0,
106
+ "8": 0.0,
107
+ "9": 0.0,
108
+ "10": 0.0
109
+ },
110
+ "pass@2": {
111
+ "2": 0.0,
112
+ "3": 0.0,
113
+ "4": 0.0,
114
+ "5": 0.0,
115
+ "6": 0.0,
116
+ "7": 0.0,
117
+ "8": 0.0,
118
+ "9": 0.0,
119
+ "10": 0.0
120
+ },
121
+ "pass@4": {
122
+ "2": 0.0,
123
+ "3": 0.0,
124
+ "4": 0.0,
125
+ "5": 0.0,
126
+ "6": 0.0,
127
+ "7": 0.0,
128
+ "8": 0.0,
129
+ "9": 0.0,
130
+ "10": 0.0
131
+ },
132
+ "pass@8": {
133
+ "2": 0.0,
134
+ "3": 0.0,
135
+ "4": 0.0,
136
+ "5": 0.0,
137
+ "6": 0.0,
138
+ "7": 0.0,
139
+ "8": 0.0,
140
+ "9": 0.0,
141
+ "10": 0.0
142
+ },
143
+ "pass@16": {
144
+ "2": 0.0,
145
+ "3": 0.0,
146
+ "4": 0.0,
147
+ "5": 0.0,
148
+ "6": 0.0,
149
+ "7": 0.0,
150
+ "8": 0.0,
151
+ "9": 0.0,
152
+ "10": 0.0
153
+ },
154
+ "pass@32": {
155
+ "2": 0.0,
156
+ "3": 0.0,
157
+ "4": 0.0,
158
+ "5": 0.0,
159
+ "6": 0.0,
160
+ "7": 0.0,
161
+ "8": 0.0,
162
+ "9": 0.0,
163
+ "10": 0.0
164
+ },
165
+ "pass@64": {
166
+ "2": 0.0,
167
+ "3": 0.0,
168
+ "4": 0.0,
169
+ "5": 0.0,
170
+ "6": 0.0,
171
+ "7": 0.0,
172
+ "8": 0.0,
173
+ "9": 0.0,
174
+ "10": 0.0
175
+ },
176
+ "pass@128": {
177
+ "2": 0.0,
178
+ "3": 0.0,
179
+ "4": 0.0,
180
+ "5": 0.0,
181
+ "6": 0.0,
182
+ "7": 0.0,
183
+ "8": 0.0,
184
+ "9": 0.0,
185
+ "10": 0.0
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.0,
190
+ "pass@2": 0.0,
191
+ "pass@4": 0.0,
192
+ "pass@8": 0.0,
193
+ "pass@16": 0.0,
194
+ "pass@32": 0.0,
195
+ "pass@64": 0.0,
196
+ "pass@128": 0.0
197
+ }
198
+ }
199
+ },
200
+ "total": {
201
+ "per_op_pass_at_k": {
202
+ "2": {
203
+ "pass@1": 0.0,
204
+ "pass@2": 0.0,
205
+ "pass@4": 0.0,
206
+ "pass@8": 0.0,
207
+ "pass@16": 0.0,
208
+ "pass@32": 0.0,
209
+ "pass@64": 0.0,
210
+ "pass@128": 0.0
211
+ },
212
+ "3": {
213
+ "pass@1": 0.0,
214
+ "pass@2": 0.0,
215
+ "pass@4": 0.0,
216
+ "pass@8": 0.0,
217
+ "pass@16": 0.0,
218
+ "pass@32": 0.0,
219
+ "pass@64": 0.0,
220
+ "pass@128": 0.0
221
+ },
222
+ "4": {
223
+ "pass@1": 0.0,
224
+ "pass@2": 0.0,
225
+ "pass@4": 0.0,
226
+ "pass@8": 0.0,
227
+ "pass@16": 0.0,
228
+ "pass@32": 0.0,
229
+ "pass@64": 0.0,
230
+ "pass@128": 0.0
231
+ },
232
+ "5": {
233
+ "pass@1": 0.0,
234
+ "pass@2": 0.0,
235
+ "pass@4": 0.0,
236
+ "pass@8": 0.0,
237
+ "pass@16": 0.0,
238
+ "pass@32": 0.0,
239
+ "pass@64": 0.0,
240
+ "pass@128": 0.0
241
+ },
242
+ "6": {
243
+ "pass@1": 0.0,
244
+ "pass@2": 0.0,
245
+ "pass@4": 0.0,
246
+ "pass@8": 0.0,
247
+ "pass@16": 0.0,
248
+ "pass@32": 0.0,
249
+ "pass@64": 0.0,
250
+ "pass@128": 0.0
251
+ },
252
+ "7": {
253
+ "pass@1": 0.0,
254
+ "pass@2": 0.0,
255
+ "pass@4": 0.0,
256
+ "pass@8": 0.0,
257
+ "pass@16": 0.0,
258
+ "pass@32": 0.0,
259
+ "pass@64": 0.0,
260
+ "pass@128": 0.0
261
+ },
262
+ "8": {
263
+ "pass@1": 0.0,
264
+ "pass@2": 0.0,
265
+ "pass@4": 0.0,
266
+ "pass@8": 0.0,
267
+ "pass@16": 0.0,
268
+ "pass@32": 0.0,
269
+ "pass@64": 0.0,
270
+ "pass@128": 0.0
271
+ },
272
+ "9": {
273
+ "pass@1": 0.0,
274
+ "pass@2": 0.0,
275
+ "pass@4": 0.0,
276
+ "pass@8": 0.0,
277
+ "pass@16": 0.0,
278
+ "pass@32": 0.0,
279
+ "pass@64": 0.0,
280
+ "pass@128": 0.0
281
+ },
282
+ "10": {
283
+ "pass@1": 0.0,
284
+ "pass@2": 0.0,
285
+ "pass@4": 0.0,
286
+ "pass@8": 0.0,
287
+ "pass@16": 0.0,
288
+ "pass@32": 0.0,
289
+ "pass@64": 0.0,
290
+ "pass@128": 0.0
291
+ }
292
+ },
293
+ "per_op_pass_at_columns": {
294
+ "pass@1": {
295
+ "2": 0.0,
296
+ "3": 0.0,
297
+ "4": 0.0,
298
+ "5": 0.0,
299
+ "6": 0.0,
300
+ "7": 0.0,
301
+ "8": 0.0,
302
+ "9": 0.0,
303
+ "10": 0.0
304
+ },
305
+ "pass@2": {
306
+ "2": 0.0,
307
+ "3": 0.0,
308
+ "4": 0.0,
309
+ "5": 0.0,
310
+ "6": 0.0,
311
+ "7": 0.0,
312
+ "8": 0.0,
313
+ "9": 0.0,
314
+ "10": 0.0
315
+ },
316
+ "pass@4": {
317
+ "2": 0.0,
318
+ "3": 0.0,
319
+ "4": 0.0,
320
+ "5": 0.0,
321
+ "6": 0.0,
322
+ "7": 0.0,
323
+ "8": 0.0,
324
+ "9": 0.0,
325
+ "10": 0.0
326
+ },
327
+ "pass@8": {
328
+ "2": 0.0,
329
+ "3": 0.0,
330
+ "4": 0.0,
331
+ "5": 0.0,
332
+ "6": 0.0,
333
+ "7": 0.0,
334
+ "8": 0.0,
335
+ "9": 0.0,
336
+ "10": 0.0
337
+ },
338
+ "pass@16": {
339
+ "2": 0.0,
340
+ "3": 0.0,
341
+ "4": 0.0,
342
+ "5": 0.0,
343
+ "6": 0.0,
344
+ "7": 0.0,
345
+ "8": 0.0,
346
+ "9": 0.0,
347
+ "10": 0.0
348
+ },
349
+ "pass@32": {
350
+ "2": 0.0,
351
+ "3": 0.0,
352
+ "4": 0.0,
353
+ "5": 0.0,
354
+ "6": 0.0,
355
+ "7": 0.0,
356
+ "8": 0.0,
357
+ "9": 0.0,
358
+ "10": 0.0
359
+ },
360
+ "pass@64": {
361
+ "2": 0.0,
362
+ "3": 0.0,
363
+ "4": 0.0,
364
+ "5": 0.0,
365
+ "6": 0.0,
366
+ "7": 0.0,
367
+ "8": 0.0,
368
+ "9": 0.0,
369
+ "10": 0.0
370
+ },
371
+ "pass@128": {
372
+ "2": 0.0,
373
+ "3": 0.0,
374
+ "4": 0.0,
375
+ "5": 0.0,
376
+ "6": 0.0,
377
+ "7": 0.0,
378
+ "8": 0.0,
379
+ "9": 0.0,
380
+ "10": 0.0
381
+ }
382
+ },
383
+ "total_pass_at_k": {
384
+ "pass@1": 0.0,
385
+ "pass@2": 0.0,
386
+ "pass@4": 0.0,
387
+ "pass@8": 0.0,
388
+ "pass@16": 0.0,
389
+ "pass@32": 0.0,
390
+ "pass@64": 0.0,
391
+ "pass@128": 0.0
392
+ }
393
+ },
394
+ "ks": [
395
+ 1,
396
+ 2,
397
+ 4,
398
+ 8,
399
+ 16,
400
+ 32,
401
+ 64,
402
+ 128
403
+ ],
404
+ "prompt_counts": {
405
+ "per_template": {
406
+ "teachers_in_school": {
407
+ "per_op": {
408
+ "2": 1000,
409
+ "3": 1000,
410
+ "4": 1000,
411
+ "5": 1000,
412
+ "6": 1000,
413
+ "7": 1000,
414
+ "8": 1000,
415
+ "9": 1000,
416
+ "10": 1000
417
+ },
418
+ "total": 9000
419
+ }
420
+ },
421
+ "total": {
422
+ "per_op": {
423
+ "2": 1000,
424
+ "3": 1000,
425
+ "4": 1000,
426
+ "5": 1000,
427
+ "6": 1000,
428
+ "7": 1000,
429
+ "8": 1000,
430
+ "9": 1000,
431
+ "10": 1000
432
+ },
433
+ "total": 9000
434
+ }
435
+ }
436
+ },
437
+ "hf_model_ood_generations.jsonl.graph_results.jsonl": {
438
+ "per_template": {
439
+ "teachers_in_school": {
440
+ "per_op_pass_at_k": {
441
+ "11": {
442
+ "pass@1": 0.0,
443
+ "pass@2": 0.0,
444
+ "pass@4": 0.0,
445
+ "pass@8": 0.0,
446
+ "pass@16": 0.0,
447
+ "pass@32": 0.0,
448
+ "pass@64": 0.0,
449
+ "pass@128": 0.0
450
+ },
451
+ "12": {
452
+ "pass@1": 0.0,
453
+ "pass@2": 0.0,
454
+ "pass@4": 0.0,
455
+ "pass@8": 0.0,
456
+ "pass@16": 0.0,
457
+ "pass@32": 0.0,
458
+ "pass@64": 0.0,
459
+ "pass@128": 0.0
460
+ },
461
+ "13": {
462
+ "pass@1": 0.0,
463
+ "pass@2": 0.0,
464
+ "pass@4": 0.0,
465
+ "pass@8": 0.0,
466
+ "pass@16": 0.0,
467
+ "pass@32": 0.0,
468
+ "pass@64": 0.0,
469
+ "pass@128": 0.0
470
+ },
471
+ "14": {
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": 0.0
480
+ },
481
+ "15": {
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": 0.0
490
+ },
491
+ "16": {
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
+ "17": {
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
+ "18": {
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
+ "19": {
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
+ "20": {
532
+ "pass@1": 0.0,
533
+ "pass@2": 0.0,
534
+ "pass@4": 0.0,
535
+ "pass@8": 0.0,
536
+ "pass@16": 0.0,
537
+ "pass@32": 0.0,
538
+ "pass@64": 0.0,
539
+ "pass@128": 0.0
540
+ }
541
+ },
542
+ "per_op_pass_at_columns": {
543
+ "pass@1": {
544
+ "11": 0.0,
545
+ "12": 0.0,
546
+ "13": 0.0,
547
+ "14": 0.0,
548
+ "15": 0.0,
549
+ "16": 0.0,
550
+ "17": 0.0,
551
+ "18": 0.0,
552
+ "19": 0.0,
553
+ "20": 0.0
554
+ },
555
+ "pass@2": {
556
+ "11": 0.0,
557
+ "12": 0.0,
558
+ "13": 0.0,
559
+ "14": 0.0,
560
+ "15": 0.0,
561
+ "16": 0.0,
562
+ "17": 0.0,
563
+ "18": 0.0,
564
+ "19": 0.0,
565
+ "20": 0.0
566
+ },
567
+ "pass@4": {
568
+ "11": 0.0,
569
+ "12": 0.0,
570
+ "13": 0.0,
571
+ "14": 0.0,
572
+ "15": 0.0,
573
+ "16": 0.0,
574
+ "17": 0.0,
575
+ "18": 0.0,
576
+ "19": 0.0,
577
+ "20": 0.0
578
+ },
579
+ "pass@8": {
580
+ "11": 0.0,
581
+ "12": 0.0,
582
+ "13": 0.0,
583
+ "14": 0.0,
584
+ "15": 0.0,
585
+ "16": 0.0,
586
+ "17": 0.0,
587
+ "18": 0.0,
588
+ "19": 0.0,
589
+ "20": 0.0
590
+ },
591
+ "pass@16": {
592
+ "11": 0.0,
593
+ "12": 0.0,
594
+ "13": 0.0,
595
+ "14": 0.0,
596
+ "15": 0.0,
597
+ "16": 0.0,
598
+ "17": 0.0,
599
+ "18": 0.0,
600
+ "19": 0.0,
601
+ "20": 0.0
602
+ },
603
+ "pass@32": {
604
+ "11": 0.0,
605
+ "12": 0.0,
606
+ "13": 0.0,
607
+ "14": 0.0,
608
+ "15": 0.0,
609
+ "16": 0.0,
610
+ "17": 0.0,
611
+ "18": 0.0,
612
+ "19": 0.0,
613
+ "20": 0.0
614
+ },
615
+ "pass@64": {
616
+ "11": 0.0,
617
+ "12": 0.0,
618
+ "13": 0.0,
619
+ "14": 0.0,
620
+ "15": 0.0,
621
+ "16": 0.0,
622
+ "17": 0.0,
623
+ "18": 0.0,
624
+ "19": 0.0,
625
+ "20": 0.0
626
+ },
627
+ "pass@128": {
628
+ "11": 0.0,
629
+ "12": 0.0,
630
+ "13": 0.0,
631
+ "14": 0.0,
632
+ "15": 0.0,
633
+ "16": 0.0,
634
+ "17": 0.0,
635
+ "18": 0.0,
636
+ "19": 0.0,
637
+ "20": 0.0
638
+ }
639
+ },
640
+ "total_pass_at_k": {
641
+ "pass@1": 0.0,
642
+ "pass@2": 0.0,
643
+ "pass@4": 0.0,
644
+ "pass@8": 0.0,
645
+ "pass@16": 0.0,
646
+ "pass@32": 0.0,
647
+ "pass@64": 0.0,
648
+ "pass@128": 0.0
649
+ }
650
+ }
651
+ },
652
+ "total": {
653
+ "per_op_pass_at_k": {
654
+ "11": {
655
+ "pass@1": 0.0,
656
+ "pass@2": 0.0,
657
+ "pass@4": 0.0,
658
+ "pass@8": 0.0,
659
+ "pass@16": 0.0,
660
+ "pass@32": 0.0,
661
+ "pass@64": 0.0,
662
+ "pass@128": 0.0
663
+ },
664
+ "12": {
665
+ "pass@1": 0.0,
666
+ "pass@2": 0.0,
667
+ "pass@4": 0.0,
668
+ "pass@8": 0.0,
669
+ "pass@16": 0.0,
670
+ "pass@32": 0.0,
671
+ "pass@64": 0.0,
672
+ "pass@128": 0.0
673
+ },
674
+ "13": {
675
+ "pass@1": 0.0,
676
+ "pass@2": 0.0,
677
+ "pass@4": 0.0,
678
+ "pass@8": 0.0,
679
+ "pass@16": 0.0,
680
+ "pass@32": 0.0,
681
+ "pass@64": 0.0,
682
+ "pass@128": 0.0
683
+ },
684
+ "14": {
685
+ "pass@1": 0.0,
686
+ "pass@2": 0.0,
687
+ "pass@4": 0.0,
688
+ "pass@8": 0.0,
689
+ "pass@16": 0.0,
690
+ "pass@32": 0.0,
691
+ "pass@64": 0.0,
692
+ "pass@128": 0.0
693
+ },
694
+ "15": {
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": 0.0
703
+ },
704
+ "16": {
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
+ "17": {
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
+ "18": {
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
+ "19": {
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
+ "20": {
745
+ "pass@1": 0.0,
746
+ "pass@2": 0.0,
747
+ "pass@4": 0.0,
748
+ "pass@8": 0.0,
749
+ "pass@16": 0.0,
750
+ "pass@32": 0.0,
751
+ "pass@64": 0.0,
752
+ "pass@128": 0.0
753
+ }
754
+ },
755
+ "per_op_pass_at_columns": {
756
+ "pass@1": {
757
+ "11": 0.0,
758
+ "12": 0.0,
759
+ "13": 0.0,
760
+ "14": 0.0,
761
+ "15": 0.0,
762
+ "16": 0.0,
763
+ "17": 0.0,
764
+ "18": 0.0,
765
+ "19": 0.0,
766
+ "20": 0.0
767
+ },
768
+ "pass@2": {
769
+ "11": 0.0,
770
+ "12": 0.0,
771
+ "13": 0.0,
772
+ "14": 0.0,
773
+ "15": 0.0,
774
+ "16": 0.0,
775
+ "17": 0.0,
776
+ "18": 0.0,
777
+ "19": 0.0,
778
+ "20": 0.0
779
+ },
780
+ "pass@4": {
781
+ "11": 0.0,
782
+ "12": 0.0,
783
+ "13": 0.0,
784
+ "14": 0.0,
785
+ "15": 0.0,
786
+ "16": 0.0,
787
+ "17": 0.0,
788
+ "18": 0.0,
789
+ "19": 0.0,
790
+ "20": 0.0
791
+ },
792
+ "pass@8": {
793
+ "11": 0.0,
794
+ "12": 0.0,
795
+ "13": 0.0,
796
+ "14": 0.0,
797
+ "15": 0.0,
798
+ "16": 0.0,
799
+ "17": 0.0,
800
+ "18": 0.0,
801
+ "19": 0.0,
802
+ "20": 0.0
803
+ },
804
+ "pass@16": {
805
+ "11": 0.0,
806
+ "12": 0.0,
807
+ "13": 0.0,
808
+ "14": 0.0,
809
+ "15": 0.0,
810
+ "16": 0.0,
811
+ "17": 0.0,
812
+ "18": 0.0,
813
+ "19": 0.0,
814
+ "20": 0.0
815
+ },
816
+ "pass@32": {
817
+ "11": 0.0,
818
+ "12": 0.0,
819
+ "13": 0.0,
820
+ "14": 0.0,
821
+ "15": 0.0,
822
+ "16": 0.0,
823
+ "17": 0.0,
824
+ "18": 0.0,
825
+ "19": 0.0,
826
+ "20": 0.0
827
+ },
828
+ "pass@64": {
829
+ "11": 0.0,
830
+ "12": 0.0,
831
+ "13": 0.0,
832
+ "14": 0.0,
833
+ "15": 0.0,
834
+ "16": 0.0,
835
+ "17": 0.0,
836
+ "18": 0.0,
837
+ "19": 0.0,
838
+ "20": 0.0
839
+ },
840
+ "pass@128": {
841
+ "11": 0.0,
842
+ "12": 0.0,
843
+ "13": 0.0,
844
+ "14": 0.0,
845
+ "15": 0.0,
846
+ "16": 0.0,
847
+ "17": 0.0,
848
+ "18": 0.0,
849
+ "19": 0.0,
850
+ "20": 0.0
851
+ }
852
+ },
853
+ "total_pass_at_k": {
854
+ "pass@1": 0.0,
855
+ "pass@2": 0.0,
856
+ "pass@4": 0.0,
857
+ "pass@8": 0.0,
858
+ "pass@16": 0.0,
859
+ "pass@32": 0.0,
860
+ "pass@64": 0.0,
861
+ "pass@128": 0.0
862
+ }
863
+ },
864
+ "ks": [
865
+ 1,
866
+ 2,
867
+ 4,
868
+ 8,
869
+ 16,
870
+ 32,
871
+ 64,
872
+ 128
873
+ ],
874
+ "prompt_counts": {
875
+ "per_template": {
876
+ "teachers_in_school": {
877
+ "per_op": {
878
+ "11": 1000,
879
+ "12": 1000,
880
+ "13": 1000,
881
+ "14": 1000,
882
+ "15": 1000,
883
+ "16": 1000,
884
+ "17": 1000,
885
+ "18": 1000,
886
+ "19": 1000,
887
+ "20": 1000
888
+ },
889
+ "total": 10000
890
+ }
891
+ },
892
+ "total": {
893
+ "per_op": {
894
+ "11": 1000,
895
+ "12": 1000,
896
+ "13": 1000,
897
+ "14": 1000,
898
+ "15": 1000,
899
+ "16": 1000,
900
+ "17": 1000,
901
+ "18": 1000,
902
+ "19": 1000,
903
+ "20": 1000
904
+ },
905
+ "total": 10000
906
+ }
907
+ }
908
+ }
909
+ }
910
+ }
Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_id_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb59d98db815792924ef404ed5ac8271c437ee058e414b57938353dcb1adef5d
3
+ size 1674664484
Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_metrics.json ADDED
@@ -0,0 +1,1077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "hf_model",
3
+ "id": {
4
+ "answer_accuracy": 0.9923975694444445,
5
+ "avg_response_len": 176.4994105902778,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.9923975694444445,
11
+ "pass@2": 0.9957820018591392,
12
+ "pass@4": 0.9971995788963887,
13
+ "pass@8": 0.9979632664900273,
14
+ "pass@16": 0.9984037349725341,
15
+ "pass@32": 0.9987061615186326,
16
+ "pass@64": 0.9988642449684446,
17
+ "pass@128": 0.9988888888888889
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.9722734375,
22
+ "pass@2": 0.982090920275591,
23
+ "pass@4": 0.9870395954255715,
24
+ "pass@8": 0.9898463912960546,
25
+ "pass@16": 0.9913574932933285,
26
+ "pass@32": 0.9924062358073099,
27
+ "pass@64": 0.9929435009525102,
28
+ "pass@128": 0.993
29
+ },
30
+ "2": {
31
+ "pass@1": 1.0,
32
+ "pass@2": 1.0,
33
+ "pass@4": 1.0,
34
+ "pass@8": 1.0,
35
+ "pass@16": 1.0,
36
+ "pass@32": 1.0,
37
+ "pass@64": 1.0,
38
+ "pass@128": 1.0
39
+ },
40
+ "3": {
41
+ "pass@1": 0.99696875,
42
+ "pass@2": 0.9987176427165356,
43
+ "pass@4": 0.999073522215973,
44
+ "pass@8": 0.9991772006158419,
45
+ "pass@16": 0.9993323490768988,
46
+ "pass@32": 0.9995814585676791,
47
+ "pass@64": 0.9998779527559055,
48
+ "pass@128": 1.0
49
+ },
50
+ "4": {
51
+ "pass@1": 0.998421875,
52
+ "pass@2": 0.999459153543307,
53
+ "pass@4": 0.9998440072178476,
54
+ "pass@8": 0.999979701409027,
55
+ "pass@16": 0.9999997111918157,
56
+ "pass@32": 0.9999999999851739,
57
+ "pass@64": 1.0,
58
+ "pass@128": 1.0
59
+ },
60
+ "5": {
61
+ "pass@1": 0.9941015625,
62
+ "pass@2": 0.9965524114173228,
63
+ "pass@4": 0.9978783887326584,
64
+ "pass@8": 0.9987054335254999,
65
+ "pass@16": 0.9993742678247356,
66
+ "pass@32": 0.9998140401510567,
67
+ "pass@64": 0.9999861487158879,
68
+ "pass@128": 1.0
69
+ },
70
+ "6": {
71
+ "pass@1": 0.99475,
72
+ "pass@2": 0.9969265501968505,
73
+ "pass@4": 0.9980495649606299,
74
+ "pass@8": 0.9987365127580474,
75
+ "pass@16": 0.9989781223272445,
76
+ "pass@32": 0.9989999037739257,
77
+ "pass@64": 0.9989999999999666,
78
+ "pass@128": 0.999
79
+ },
80
+ "7": {
81
+ "pass@1": 0.9951015625,
82
+ "pass@2": 0.9976016240157483,
83
+ "pass@4": 0.9984762033183351,
84
+ "pass@8": 0.9988805544747335,
85
+ "pass@16": 0.9989943223963219,
86
+ "pass@32": 0.9989999945303923,
87
+ "pass@64": 0.999,
88
+ "pass@128": 0.999
89
+ },
90
+ "8": {
91
+ "pass@1": 0.992984375,
92
+ "pass@2": 0.9974980314960634,
93
+ "pass@4": 0.9988455806149232,
94
+ "pass@8": 0.9992881325051802,
95
+ "pass@16": 0.9995580380881292,
96
+ "pass@32": 0.999829071592898,
97
+ "pass@64": 0.9999861763011332,
98
+ "pass@128": 1.0
99
+ },
100
+ "9": {
101
+ "pass@1": 0.9869765625,
102
+ "pass@2": 0.9931916830708665,
103
+ "pass@4": 0.995589347581552,
104
+ "pass@8": 0.9970554718258637,
105
+ "pass@16": 0.9980393105543356,
106
+ "pass@32": 0.9987247492592555,
107
+ "pass@64": 0.998984425990599,
108
+ "pass@128": 0.999
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.9722734375,
113
+ "2": 1.0,
114
+ "3": 0.99696875,
115
+ "4": 0.998421875,
116
+ "5": 0.9941015625,
117
+ "6": 0.99475,
118
+ "7": 0.9951015625,
119
+ "8": 0.992984375,
120
+ "9": 0.9869765625
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 245.9643203125,
124
+ "2": 103.040046875,
125
+ "3": 121.6964375,
126
+ "4": 141.7835859375,
127
+ "5": 164.8098203125,
128
+ "6": 175.4171015625,
129
+ "7": 190.5570234375,
130
+ "8": 213.8619296875,
131
+ "9": 231.3644296875
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 245.9643203125,
136
+ "2": 103.040046875,
137
+ "3": 121.6964375,
138
+ "4": 141.7835859375,
139
+ "5": 164.8098203125,
140
+ "6": 175.4171015625,
141
+ "7": 190.5570234375,
142
+ "8": 213.8619296875,
143
+ "9": 231.3644296875
144
+ },
145
+ "per_op_loss": {},
146
+ "per_template": {
147
+ "crazy_zootopia": {
148
+ "count": 0,
149
+ "correct": 0,
150
+ "answer_accuracy": 0.0,
151
+ "avg_response_len": 0.0,
152
+ "resp_tokens_sum": 0,
153
+ "pass_at_k": {},
154
+ "per_op_pass_at_k": {}
155
+ },
156
+ "teachers_in_school": {
157
+ "count": 1152000,
158
+ "correct": 1143242,
159
+ "answer_accuracy": 0.9923975694444445,
160
+ "avg_response_len": 176.4994105902778,
161
+ "resp_tokens_sum": 203327321,
162
+ "pass_at_k": {
163
+ "pass@1": 0.9923975694444445,
164
+ "pass@2": 0.9957820018591392,
165
+ "pass@4": 0.9971995788963887,
166
+ "pass@8": 0.9979632664900273,
167
+ "pass@16": 0.9984037349725341,
168
+ "pass@32": 0.9987061615186326,
169
+ "pass@64": 0.9988642449684446,
170
+ "pass@128": 0.9988888888888889
171
+ },
172
+ "per_op_pass_at_k": {
173
+ "10": {
174
+ "pass@1": 0.9722734375,
175
+ "pass@2": 0.982090920275591,
176
+ "pass@4": 0.9870395954255715,
177
+ "pass@8": 0.9898463912960546,
178
+ "pass@16": 0.9913574932933285,
179
+ "pass@32": 0.9924062358073099,
180
+ "pass@64": 0.9929435009525102,
181
+ "pass@128": 0.993
182
+ },
183
+ "2": {
184
+ "pass@1": 1.0,
185
+ "pass@2": 1.0,
186
+ "pass@4": 1.0,
187
+ "pass@8": 1.0,
188
+ "pass@16": 1.0,
189
+ "pass@32": 1.0,
190
+ "pass@64": 1.0,
191
+ "pass@128": 1.0
192
+ },
193
+ "3": {
194
+ "pass@1": 0.99696875,
195
+ "pass@2": 0.9987176427165356,
196
+ "pass@4": 0.999073522215973,
197
+ "pass@8": 0.9991772006158419,
198
+ "pass@16": 0.9993323490768988,
199
+ "pass@32": 0.9995814585676791,
200
+ "pass@64": 0.9998779527559055,
201
+ "pass@128": 1.0
202
+ },
203
+ "4": {
204
+ "pass@1": 0.998421875,
205
+ "pass@2": 0.999459153543307,
206
+ "pass@4": 0.9998440072178476,
207
+ "pass@8": 0.999979701409027,
208
+ "pass@16": 0.9999997111918157,
209
+ "pass@32": 0.9999999999851739,
210
+ "pass@64": 1.0,
211
+ "pass@128": 1.0
212
+ },
213
+ "5": {
214
+ "pass@1": 0.9941015625,
215
+ "pass@2": 0.9965524114173228,
216
+ "pass@4": 0.9978783887326584,
217
+ "pass@8": 0.9987054335254999,
218
+ "pass@16": 0.9993742678247356,
219
+ "pass@32": 0.9998140401510567,
220
+ "pass@64": 0.9999861487158879,
221
+ "pass@128": 1.0
222
+ },
223
+ "6": {
224
+ "pass@1": 0.99475,
225
+ "pass@2": 0.9969265501968505,
226
+ "pass@4": 0.9980495649606299,
227
+ "pass@8": 0.9987365127580474,
228
+ "pass@16": 0.9989781223272445,
229
+ "pass@32": 0.9989999037739257,
230
+ "pass@64": 0.9989999999999666,
231
+ "pass@128": 0.999
232
+ },
233
+ "7": {
234
+ "pass@1": 0.9951015625,
235
+ "pass@2": 0.9976016240157483,
236
+ "pass@4": 0.9984762033183351,
237
+ "pass@8": 0.9988805544747335,
238
+ "pass@16": 0.9989943223963219,
239
+ "pass@32": 0.9989999945303923,
240
+ "pass@64": 0.999,
241
+ "pass@128": 0.999
242
+ },
243
+ "8": {
244
+ "pass@1": 0.992984375,
245
+ "pass@2": 0.9974980314960634,
246
+ "pass@4": 0.9988455806149232,
247
+ "pass@8": 0.9992881325051802,
248
+ "pass@16": 0.9995580380881292,
249
+ "pass@32": 0.999829071592898,
250
+ "pass@64": 0.9999861763011332,
251
+ "pass@128": 1.0
252
+ },
253
+ "9": {
254
+ "pass@1": 0.9869765625,
255
+ "pass@2": 0.9931916830708665,
256
+ "pass@4": 0.995589347581552,
257
+ "pass@8": 0.9970554718258637,
258
+ "pass@16": 0.9980393105543356,
259
+ "pass@32": 0.9987247492592555,
260
+ "pass@64": 0.998984425990599,
261
+ "pass@128": 0.999
262
+ }
263
+ }
264
+ },
265
+ "movie_festival_awards": {
266
+ "count": 0,
267
+ "correct": 0,
268
+ "answer_accuracy": 0.0,
269
+ "avg_response_len": 0.0,
270
+ "resp_tokens_sum": 0,
271
+ "pass_at_k": {},
272
+ "per_op_pass_at_k": {}
273
+ }
274
+ }
275
+ },
276
+ "ood": {
277
+ "answer_accuracy": 0.91275625,
278
+ "avg_response_len": 339.53681640625,
279
+ "avg_loss": 0.0,
280
+ "count": 1280000,
281
+ "validation_metrics": {},
282
+ "pass_at_k": {
283
+ "pass@1": 0.91275625,
284
+ "pass@2": 0.9458462967519363,
285
+ "pass@4": 0.9624475184758139,
286
+ "pass@8": 0.9726641426761587,
287
+ "pass@16": 0.9796753897332539,
288
+ "pass@32": 0.9849077514114102,
289
+ "pass@64": 0.988984272764239,
290
+ "pass@128": 0.9919
291
+ },
292
+ "per_op_pass_at_k": {
293
+ "11": {
294
+ "pass@1": 0.9569375,
295
+ "pass@2": 0.9694979084645677,
296
+ "pass@4": 0.9755786563554552,
297
+ "pass@8": 0.9795771285286979,
298
+ "pass@16": 0.9828716597217099,
299
+ "pass@32": 0.9858994698672985,
300
+ "pass@64": 0.9886172988906358,
301
+ "pass@128": 0.991
302
+ },
303
+ "12": {
304
+ "pass@1": 0.9321875,
305
+ "pass@2": 0.9527299458661426,
306
+ "pass@4": 0.964783362579677,
307
+ "pass@8": 0.9725947365272651,
308
+ "pass@16": 0.9780288578767546,
309
+ "pass@32": 0.9822927738860049,
310
+ "pass@64": 0.9860262163530781,
311
+ "pass@128": 0.989
312
+ },
313
+ "13": {
314
+ "pass@1": 0.9148515625,
315
+ "pass@2": 0.9376562500000003,
316
+ "pass@4": 0.9520333217097862,
317
+ "pass@8": 0.9627994330286813,
318
+ "pass@16": 0.9713319331348897,
319
+ "pass@32": 0.9782062595316485,
320
+ "pass@64": 0.9837086690994824,
321
+ "pass@128": 0.988
322
+ },
323
+ "14": {
324
+ "pass@1": 0.92659375,
325
+ "pass@2": 0.9529224901574813,
326
+ "pass@4": 0.9665270294338203,
327
+ "pass@8": 0.9751033296649382,
328
+ "pass@16": 0.9814160863652701,
329
+ "pass@32": 0.9866717919871326,
330
+ "pass@64": 0.99098669283729,
331
+ "pass@128": 0.993
332
+ },
333
+ "15": {
334
+ "pass@1": 0.9321484375,
335
+ "pass@2": 0.9586374261811037,
336
+ "pass@4": 0.9716738764529432,
337
+ "pass@8": 0.980257322244576,
338
+ "pass@16": 0.9860876075856799,
339
+ "pass@32": 0.9905182347017089,
340
+ "pass@64": 0.9941053539635863,
341
+ "pass@128": 0.997
342
+ },
343
+ "16": {
344
+ "pass@1": 0.919421875,
345
+ "pass@2": 0.9510446604330718,
346
+ "pass@4": 0.9672112351893514,
347
+ "pass@8": 0.9771642191649528,
348
+ "pass@16": 0.9837104050806683,
349
+ "pass@32": 0.9884127699664014,
350
+ "pass@64": 0.9923083437843704,
351
+ "pass@128": 0.995
352
+ },
353
+ "17": {
354
+ "pass@1": 0.917234375,
355
+ "pass@2": 0.9551825787401591,
356
+ "pass@4": 0.9728983112110978,
357
+ "pass@8": 0.9831834738064922,
358
+ "pass@16": 0.989503100920689,
359
+ "pass@32": 0.9936977352294757,
360
+ "pass@64": 0.9968179233919849,
361
+ "pass@128": 0.999
362
+ },
363
+ "18": {
364
+ "pass@1": 0.8954921875,
365
+ "pass@2": 0.9377255167322847,
366
+ "pass@4": 0.9575529777840263,
367
+ "pass@8": 0.9690916457538964,
368
+ "pass@16": 0.9765775044869797,
369
+ "pass@32": 0.9819170635269723,
370
+ "pass@64": 0.9859361791907656,
371
+ "pass@128": 0.989
372
+ },
373
+ "19": {
374
+ "pass@1": 0.875109375,
375
+ "pass@2": 0.9267666092519707,
376
+ "pass@4": 0.9520276386389189,
377
+ "pass@8": 0.9663416476690758,
378
+ "pass@16": 0.975462333146504,
379
+ "pass@32": 0.981573341392933,
380
+ "pass@64": 0.9858043859763082,
381
+ "pass@128": 0.989
382
+ },
383
+ "20": {
384
+ "pass@1": 0.8575859375,
385
+ "pass@2": 0.9162995816929158,
386
+ "pass@4": 0.944188775403074,
387
+ "pass@8": 0.9605284903730037,
388
+ "pass@16": 0.9717644090133872,
389
+ "pass@32": 0.9798880740245233,
390
+ "pass@64": 0.9855316641548822,
391
+ "pass@128": 0.989
392
+ }
393
+ },
394
+ "per_op_accuracy": {
395
+ "11": 0.9569375,
396
+ "12": 0.9321875,
397
+ "13": 0.9148515625,
398
+ "14": 0.92659375,
399
+ "15": 0.9321484375,
400
+ "16": 0.919421875,
401
+ "17": 0.917234375,
402
+ "18": 0.8954921875,
403
+ "19": 0.875109375,
404
+ "20": 0.8575859375
405
+ },
406
+ "per_op_avg_response_len": {
407
+ "11": 266.557984375,
408
+ "12": 278.4357265625,
409
+ "13": 288.8397265625,
410
+ "14": 317.2391484375,
411
+ "15": 331.4378515625,
412
+ "16": 357.8768828125,
413
+ "17": 368.6404765625,
414
+ "18": 382.5142890625,
415
+ "19": 393.4576171875,
416
+ "20": 410.3684609375
417
+ },
418
+ "per_op_avg_loss": {},
419
+ "per_op_length": {
420
+ "11": 266.557984375,
421
+ "12": 278.4357265625,
422
+ "13": 288.8397265625,
423
+ "14": 317.2391484375,
424
+ "15": 331.4378515625,
425
+ "16": 357.8768828125,
426
+ "17": 368.6404765625,
427
+ "18": 382.5142890625,
428
+ "19": 393.4576171875,
429
+ "20": 410.3684609375
430
+ },
431
+ "per_op_loss": {},
432
+ "per_template": {
433
+ "crazy_zootopia": {
434
+ "count": 0,
435
+ "correct": 0,
436
+ "answer_accuracy": 0.0,
437
+ "avg_response_len": 0.0,
438
+ "resp_tokens_sum": 0,
439
+ "pass_at_k": {},
440
+ "per_op_pass_at_k": {}
441
+ },
442
+ "teachers_in_school": {
443
+ "count": 1280000,
444
+ "correct": 1168328,
445
+ "answer_accuracy": 0.91275625,
446
+ "avg_response_len": 339.53681640625,
447
+ "resp_tokens_sum": 434607125,
448
+ "pass_at_k": {
449
+ "pass@1": 0.91275625,
450
+ "pass@2": 0.9458462967519363,
451
+ "pass@4": 0.9624475184758139,
452
+ "pass@8": 0.9726641426761587,
453
+ "pass@16": 0.9796753897332539,
454
+ "pass@32": 0.9849077514114102,
455
+ "pass@64": 0.988984272764239,
456
+ "pass@128": 0.9919
457
+ },
458
+ "per_op_pass_at_k": {
459
+ "11": {
460
+ "pass@1": 0.9569375,
461
+ "pass@2": 0.9694979084645677,
462
+ "pass@4": 0.9755786563554552,
463
+ "pass@8": 0.9795771285286979,
464
+ "pass@16": 0.9828716597217099,
465
+ "pass@32": 0.9858994698672985,
466
+ "pass@64": 0.9886172988906358,
467
+ "pass@128": 0.991
468
+ },
469
+ "12": {
470
+ "pass@1": 0.9321875,
471
+ "pass@2": 0.9527299458661426,
472
+ "pass@4": 0.964783362579677,
473
+ "pass@8": 0.9725947365272651,
474
+ "pass@16": 0.9780288578767546,
475
+ "pass@32": 0.9822927738860049,
476
+ "pass@64": 0.9860262163530781,
477
+ "pass@128": 0.989
478
+ },
479
+ "13": {
480
+ "pass@1": 0.9148515625,
481
+ "pass@2": 0.9376562500000003,
482
+ "pass@4": 0.9520333217097862,
483
+ "pass@8": 0.9627994330286813,
484
+ "pass@16": 0.9713319331348897,
485
+ "pass@32": 0.9782062595316485,
486
+ "pass@64": 0.9837086690994824,
487
+ "pass@128": 0.988
488
+ },
489
+ "14": {
490
+ "pass@1": 0.92659375,
491
+ "pass@2": 0.9529224901574813,
492
+ "pass@4": 0.9665270294338203,
493
+ "pass@8": 0.9751033296649382,
494
+ "pass@16": 0.9814160863652701,
495
+ "pass@32": 0.9866717919871326,
496
+ "pass@64": 0.99098669283729,
497
+ "pass@128": 0.993
498
+ },
499
+ "15": {
500
+ "pass@1": 0.9321484375,
501
+ "pass@2": 0.9586374261811037,
502
+ "pass@4": 0.9716738764529432,
503
+ "pass@8": 0.980257322244576,
504
+ "pass@16": 0.9860876075856799,
505
+ "pass@32": 0.9905182347017089,
506
+ "pass@64": 0.9941053539635863,
507
+ "pass@128": 0.997
508
+ },
509
+ "16": {
510
+ "pass@1": 0.919421875,
511
+ "pass@2": 0.9510446604330718,
512
+ "pass@4": 0.9672112351893514,
513
+ "pass@8": 0.9771642191649528,
514
+ "pass@16": 0.9837104050806683,
515
+ "pass@32": 0.9884127699664014,
516
+ "pass@64": 0.9923083437843704,
517
+ "pass@128": 0.995
518
+ },
519
+ "17": {
520
+ "pass@1": 0.917234375,
521
+ "pass@2": 0.9551825787401591,
522
+ "pass@4": 0.9728983112110978,
523
+ "pass@8": 0.9831834738064922,
524
+ "pass@16": 0.989503100920689,
525
+ "pass@32": 0.9936977352294757,
526
+ "pass@64": 0.9968179233919849,
527
+ "pass@128": 0.999
528
+ },
529
+ "18": {
530
+ "pass@1": 0.8954921875,
531
+ "pass@2": 0.9377255167322847,
532
+ "pass@4": 0.9575529777840263,
533
+ "pass@8": 0.9690916457538964,
534
+ "pass@16": 0.9765775044869797,
535
+ "pass@32": 0.9819170635269723,
536
+ "pass@64": 0.9859361791907656,
537
+ "pass@128": 0.989
538
+ },
539
+ "19": {
540
+ "pass@1": 0.875109375,
541
+ "pass@2": 0.9267666092519707,
542
+ "pass@4": 0.9520276386389189,
543
+ "pass@8": 0.9663416476690758,
544
+ "pass@16": 0.975462333146504,
545
+ "pass@32": 0.981573341392933,
546
+ "pass@64": 0.9858043859763082,
547
+ "pass@128": 0.989
548
+ },
549
+ "20": {
550
+ "pass@1": 0.8575859375,
551
+ "pass@2": 0.9162995816929158,
552
+ "pass@4": 0.944188775403074,
553
+ "pass@8": 0.9605284903730037,
554
+ "pass@16": 0.9717644090133872,
555
+ "pass@32": 0.9798880740245233,
556
+ "pass@64": 0.9855316641548822,
557
+ "pass@128": 0.989
558
+ }
559
+ }
560
+ },
561
+ "movie_festival_awards": {
562
+ "count": 0,
563
+ "correct": 0,
564
+ "answer_accuracy": 0.0,
565
+ "avg_response_len": 0.0,
566
+ "resp_tokens_sum": 0,
567
+ "pass_at_k": {},
568
+ "per_op_pass_at_k": {}
569
+ }
570
+ }
571
+ },
572
+ "total": {
573
+ "answer_accuracy": 0.9504810855263158,
574
+ "avg_loss": 0.0,
575
+ "count": 2432000,
576
+ "validation_metrics": {
577
+ "id": {},
578
+ "ood": {}
579
+ },
580
+ "pass_at_k": {
581
+ "pass@1": 0.9504810855263158,
582
+ "pass@2": 0.9695000518027258,
583
+ "pass@4": 0.9789090207802891,
584
+ "pass@8": 0.9846479381669422,
585
+ "pass@16": 0.988546711162386,
586
+ "pass@32": 0.9914438404095707,
587
+ "pass@64": 0.9936642595978096,
588
+ "pass@128": 0.9952105263157894
589
+ },
590
+ "per_op_pass_at_k": {
591
+ "10": {
592
+ "pass@1": 0.9722734375,
593
+ "pass@2": 0.982090920275591,
594
+ "pass@4": 0.9870395954255715,
595
+ "pass@8": 0.9898463912960546,
596
+ "pass@16": 0.9913574932933285,
597
+ "pass@32": 0.9924062358073099,
598
+ "pass@64": 0.9929435009525102,
599
+ "pass@128": 0.993
600
+ },
601
+ "2": {
602
+ "pass@1": 1.0,
603
+ "pass@2": 1.0,
604
+ "pass@4": 1.0,
605
+ "pass@8": 1.0,
606
+ "pass@16": 1.0,
607
+ "pass@32": 1.0,
608
+ "pass@64": 1.0,
609
+ "pass@128": 1.0
610
+ },
611
+ "3": {
612
+ "pass@1": 0.99696875,
613
+ "pass@2": 0.9987176427165356,
614
+ "pass@4": 0.999073522215973,
615
+ "pass@8": 0.9991772006158419,
616
+ "pass@16": 0.9993323490768988,
617
+ "pass@32": 0.9995814585676791,
618
+ "pass@64": 0.9998779527559055,
619
+ "pass@128": 1.0
620
+ },
621
+ "4": {
622
+ "pass@1": 0.998421875,
623
+ "pass@2": 0.999459153543307,
624
+ "pass@4": 0.9998440072178476,
625
+ "pass@8": 0.999979701409027,
626
+ "pass@16": 0.9999997111918157,
627
+ "pass@32": 0.9999999999851739,
628
+ "pass@64": 1.0,
629
+ "pass@128": 1.0
630
+ },
631
+ "5": {
632
+ "pass@1": 0.9941015625,
633
+ "pass@2": 0.9965524114173228,
634
+ "pass@4": 0.9978783887326584,
635
+ "pass@8": 0.9987054335254999,
636
+ "pass@16": 0.9993742678247356,
637
+ "pass@32": 0.9998140401510567,
638
+ "pass@64": 0.9999861487158879,
639
+ "pass@128": 1.0
640
+ },
641
+ "6": {
642
+ "pass@1": 0.99475,
643
+ "pass@2": 0.9969265501968505,
644
+ "pass@4": 0.9980495649606299,
645
+ "pass@8": 0.9987365127580474,
646
+ "pass@16": 0.9989781223272445,
647
+ "pass@32": 0.9989999037739257,
648
+ "pass@64": 0.9989999999999666,
649
+ "pass@128": 0.999
650
+ },
651
+ "7": {
652
+ "pass@1": 0.9951015625,
653
+ "pass@2": 0.9976016240157483,
654
+ "pass@4": 0.9984762033183351,
655
+ "pass@8": 0.9988805544747335,
656
+ "pass@16": 0.9989943223963219,
657
+ "pass@32": 0.9989999945303923,
658
+ "pass@64": 0.999,
659
+ "pass@128": 0.999
660
+ },
661
+ "8": {
662
+ "pass@1": 0.992984375,
663
+ "pass@2": 0.9974980314960634,
664
+ "pass@4": 0.9988455806149232,
665
+ "pass@8": 0.9992881325051802,
666
+ "pass@16": 0.9995580380881292,
667
+ "pass@32": 0.999829071592898,
668
+ "pass@64": 0.9999861763011332,
669
+ "pass@128": 1.0
670
+ },
671
+ "9": {
672
+ "pass@1": 0.9869765625,
673
+ "pass@2": 0.9931916830708665,
674
+ "pass@4": 0.995589347581552,
675
+ "pass@8": 0.9970554718258637,
676
+ "pass@16": 0.9980393105543356,
677
+ "pass@32": 0.9987247492592555,
678
+ "pass@64": 0.998984425990599,
679
+ "pass@128": 0.999
680
+ },
681
+ "11": {
682
+ "pass@1": 0.9569375,
683
+ "pass@2": 0.9694979084645677,
684
+ "pass@4": 0.9755786563554552,
685
+ "pass@8": 0.9795771285286979,
686
+ "pass@16": 0.9828716597217099,
687
+ "pass@32": 0.9858994698672985,
688
+ "pass@64": 0.9886172988906358,
689
+ "pass@128": 0.991
690
+ },
691
+ "12": {
692
+ "pass@1": 0.9321875,
693
+ "pass@2": 0.9527299458661426,
694
+ "pass@4": 0.964783362579677,
695
+ "pass@8": 0.9725947365272651,
696
+ "pass@16": 0.9780288578767546,
697
+ "pass@32": 0.9822927738860049,
698
+ "pass@64": 0.9860262163530781,
699
+ "pass@128": 0.989
700
+ },
701
+ "13": {
702
+ "pass@1": 0.9148515625,
703
+ "pass@2": 0.9376562500000003,
704
+ "pass@4": 0.9520333217097862,
705
+ "pass@8": 0.9627994330286813,
706
+ "pass@16": 0.9713319331348897,
707
+ "pass@32": 0.9782062595316485,
708
+ "pass@64": 0.9837086690994824,
709
+ "pass@128": 0.988
710
+ },
711
+ "14": {
712
+ "pass@1": 0.92659375,
713
+ "pass@2": 0.9529224901574813,
714
+ "pass@4": 0.9665270294338203,
715
+ "pass@8": 0.9751033296649382,
716
+ "pass@16": 0.9814160863652701,
717
+ "pass@32": 0.9866717919871326,
718
+ "pass@64": 0.99098669283729,
719
+ "pass@128": 0.993
720
+ },
721
+ "15": {
722
+ "pass@1": 0.9321484375,
723
+ "pass@2": 0.9586374261811037,
724
+ "pass@4": 0.9716738764529432,
725
+ "pass@8": 0.980257322244576,
726
+ "pass@16": 0.9860876075856799,
727
+ "pass@32": 0.9905182347017089,
728
+ "pass@64": 0.9941053539635863,
729
+ "pass@128": 0.997
730
+ },
731
+ "16": {
732
+ "pass@1": 0.919421875,
733
+ "pass@2": 0.9510446604330718,
734
+ "pass@4": 0.9672112351893514,
735
+ "pass@8": 0.9771642191649528,
736
+ "pass@16": 0.9837104050806683,
737
+ "pass@32": 0.9884127699664014,
738
+ "pass@64": 0.9923083437843704,
739
+ "pass@128": 0.995
740
+ },
741
+ "17": {
742
+ "pass@1": 0.917234375,
743
+ "pass@2": 0.9551825787401591,
744
+ "pass@4": 0.9728983112110978,
745
+ "pass@8": 0.9831834738064922,
746
+ "pass@16": 0.989503100920689,
747
+ "pass@32": 0.9936977352294757,
748
+ "pass@64": 0.9968179233919849,
749
+ "pass@128": 0.999
750
+ },
751
+ "18": {
752
+ "pass@1": 0.8954921875,
753
+ "pass@2": 0.9377255167322847,
754
+ "pass@4": 0.9575529777840263,
755
+ "pass@8": 0.9690916457538964,
756
+ "pass@16": 0.9765775044869797,
757
+ "pass@32": 0.9819170635269723,
758
+ "pass@64": 0.9859361791907656,
759
+ "pass@128": 0.989
760
+ },
761
+ "19": {
762
+ "pass@1": 0.875109375,
763
+ "pass@2": 0.9267666092519707,
764
+ "pass@4": 0.9520276386389189,
765
+ "pass@8": 0.9663416476690758,
766
+ "pass@16": 0.975462333146504,
767
+ "pass@32": 0.981573341392933,
768
+ "pass@64": 0.9858043859763082,
769
+ "pass@128": 0.989
770
+ },
771
+ "20": {
772
+ "pass@1": 0.8575859375,
773
+ "pass@2": 0.9162995816929158,
774
+ "pass@4": 0.944188775403074,
775
+ "pass@8": 0.9605284903730037,
776
+ "pass@16": 0.9717644090133872,
777
+ "pass@32": 0.9798880740245233,
778
+ "pass@64": 0.9855316641548822,
779
+ "pass@128": 0.989
780
+ }
781
+ },
782
+ "per_op_accuracy": {
783
+ "10": 0.9722734375,
784
+ "2": 1.0,
785
+ "3": 0.99696875,
786
+ "4": 0.998421875,
787
+ "5": 0.9941015625,
788
+ "6": 0.99475,
789
+ "7": 0.9951015625,
790
+ "8": 0.992984375,
791
+ "9": 0.9869765625,
792
+ "11": 0.9569375,
793
+ "12": 0.9321875,
794
+ "13": 0.9148515625,
795
+ "14": 0.92659375,
796
+ "15": 0.9321484375,
797
+ "16": 0.919421875,
798
+ "17": 0.917234375,
799
+ "18": 0.8954921875,
800
+ "19": 0.875109375,
801
+ "20": 0.8575859375
802
+ },
803
+ "per_op_avg_response_len": {
804
+ "10": 245.9643203125,
805
+ "2": 103.040046875,
806
+ "3": 121.6964375,
807
+ "4": 141.7835859375,
808
+ "5": 164.8098203125,
809
+ "6": 175.4171015625,
810
+ "7": 190.5570234375,
811
+ "8": 213.8619296875,
812
+ "9": 231.3644296875,
813
+ "11": 266.557984375,
814
+ "12": 278.4357265625,
815
+ "13": 288.8397265625,
816
+ "14": 317.2391484375,
817
+ "15": 331.4378515625,
818
+ "16": 357.8768828125,
819
+ "17": 368.6404765625,
820
+ "18": 382.5142890625,
821
+ "19": 393.4576171875,
822
+ "20": 410.3684609375
823
+ },
824
+ "per_op_avg_loss": {},
825
+ "per_op_length": {
826
+ "10": 245.9643203125,
827
+ "2": 103.040046875,
828
+ "3": 121.6964375,
829
+ "4": 141.7835859375,
830
+ "5": 164.8098203125,
831
+ "6": 175.4171015625,
832
+ "7": 190.5570234375,
833
+ "8": 213.8619296875,
834
+ "9": 231.3644296875,
835
+ "11": 266.557984375,
836
+ "12": 278.4357265625,
837
+ "13": 288.8397265625,
838
+ "14": 317.2391484375,
839
+ "15": 331.4378515625,
840
+ "16": 357.8768828125,
841
+ "17": 368.6404765625,
842
+ "18": 382.5142890625,
843
+ "19": 393.4576171875,
844
+ "20": 410.3684609375
845
+ },
846
+ "per_op_loss": {},
847
+ "per_template": {
848
+ "crazy_zootopia": {
849
+ "count": 0,
850
+ "correct": 0,
851
+ "answer_accuracy": 0.0,
852
+ "avg_response_len": 0.0,
853
+ "resp_tokens_sum": 0,
854
+ "pass_at_k": {},
855
+ "per_op_pass_at_k": {}
856
+ },
857
+ "teachers_in_school": {
858
+ "count": 2432000,
859
+ "correct": 2311570,
860
+ "answer_accuracy": 0.9504810855263158,
861
+ "avg_response_len": 262.30857154605263,
862
+ "resp_tokens_sum": 637934446,
863
+ "pass_at_k": {
864
+ "pass@1": 0.9504810855263158,
865
+ "pass@2": 0.9695000518027258,
866
+ "pass@4": 0.9789090207802891,
867
+ "pass@8": 0.9846479381669422,
868
+ "pass@16": 0.988546711162386,
869
+ "pass@32": 0.9914438404095707,
870
+ "pass@64": 0.9936642595978096,
871
+ "pass@128": 0.9952105263157894
872
+ },
873
+ "per_op_pass_at_k": {
874
+ "10": {
875
+ "pass@1": 0.9722734375,
876
+ "pass@2": 0.982090920275591,
877
+ "pass@4": 0.9870395954255715,
878
+ "pass@8": 0.9898463912960546,
879
+ "pass@16": 0.9913574932933285,
880
+ "pass@32": 0.9924062358073099,
881
+ "pass@64": 0.9929435009525102,
882
+ "pass@128": 0.993
883
+ },
884
+ "2": {
885
+ "pass@1": 1.0,
886
+ "pass@2": 1.0,
887
+ "pass@4": 1.0,
888
+ "pass@8": 1.0,
889
+ "pass@16": 1.0,
890
+ "pass@32": 1.0,
891
+ "pass@64": 1.0,
892
+ "pass@128": 1.0
893
+ },
894
+ "3": {
895
+ "pass@1": 0.99696875,
896
+ "pass@2": 0.9987176427165356,
897
+ "pass@4": 0.999073522215973,
898
+ "pass@8": 0.9991772006158419,
899
+ "pass@16": 0.9993323490768988,
900
+ "pass@32": 0.9995814585676791,
901
+ "pass@64": 0.9998779527559055,
902
+ "pass@128": 1.0
903
+ },
904
+ "4": {
905
+ "pass@1": 0.998421875,
906
+ "pass@2": 0.999459153543307,
907
+ "pass@4": 0.9998440072178476,
908
+ "pass@8": 0.999979701409027,
909
+ "pass@16": 0.9999997111918157,
910
+ "pass@32": 0.9999999999851739,
911
+ "pass@64": 1.0,
912
+ "pass@128": 1.0
913
+ },
914
+ "5": {
915
+ "pass@1": 0.9941015625,
916
+ "pass@2": 0.9965524114173228,
917
+ "pass@4": 0.9978783887326584,
918
+ "pass@8": 0.9987054335254999,
919
+ "pass@16": 0.9993742678247356,
920
+ "pass@32": 0.9998140401510567,
921
+ "pass@64": 0.9999861487158879,
922
+ "pass@128": 1.0
923
+ },
924
+ "6": {
925
+ "pass@1": 0.99475,
926
+ "pass@2": 0.9969265501968505,
927
+ "pass@4": 0.9980495649606299,
928
+ "pass@8": 0.9987365127580474,
929
+ "pass@16": 0.9989781223272445,
930
+ "pass@32": 0.9989999037739257,
931
+ "pass@64": 0.9989999999999666,
932
+ "pass@128": 0.999
933
+ },
934
+ "7": {
935
+ "pass@1": 0.9951015625,
936
+ "pass@2": 0.9976016240157483,
937
+ "pass@4": 0.9984762033183351,
938
+ "pass@8": 0.9988805544747335,
939
+ "pass@16": 0.9989943223963219,
940
+ "pass@32": 0.9989999945303923,
941
+ "pass@64": 0.999,
942
+ "pass@128": 0.999
943
+ },
944
+ "8": {
945
+ "pass@1": 0.992984375,
946
+ "pass@2": 0.9974980314960634,
947
+ "pass@4": 0.9988455806149232,
948
+ "pass@8": 0.9992881325051802,
949
+ "pass@16": 0.9995580380881292,
950
+ "pass@32": 0.999829071592898,
951
+ "pass@64": 0.9999861763011332,
952
+ "pass@128": 1.0
953
+ },
954
+ "9": {
955
+ "pass@1": 0.9869765625,
956
+ "pass@2": 0.9931916830708665,
957
+ "pass@4": 0.995589347581552,
958
+ "pass@8": 0.9970554718258637,
959
+ "pass@16": 0.9980393105543356,
960
+ "pass@32": 0.9987247492592555,
961
+ "pass@64": 0.998984425990599,
962
+ "pass@128": 0.999
963
+ },
964
+ "11": {
965
+ "pass@1": 0.9569375,
966
+ "pass@2": 0.9694979084645677,
967
+ "pass@4": 0.9755786563554552,
968
+ "pass@8": 0.9795771285286979,
969
+ "pass@16": 0.9828716597217099,
970
+ "pass@32": 0.9858994698672985,
971
+ "pass@64": 0.9886172988906358,
972
+ "pass@128": 0.991
973
+ },
974
+ "12": {
975
+ "pass@1": 0.9321875,
976
+ "pass@2": 0.9527299458661426,
977
+ "pass@4": 0.964783362579677,
978
+ "pass@8": 0.9725947365272651,
979
+ "pass@16": 0.9780288578767546,
980
+ "pass@32": 0.9822927738860049,
981
+ "pass@64": 0.9860262163530781,
982
+ "pass@128": 0.989
983
+ },
984
+ "13": {
985
+ "pass@1": 0.9148515625,
986
+ "pass@2": 0.9376562500000003,
987
+ "pass@4": 0.9520333217097862,
988
+ "pass@8": 0.9627994330286813,
989
+ "pass@16": 0.9713319331348897,
990
+ "pass@32": 0.9782062595316485,
991
+ "pass@64": 0.9837086690994824,
992
+ "pass@128": 0.988
993
+ },
994
+ "14": {
995
+ "pass@1": 0.92659375,
996
+ "pass@2": 0.9529224901574813,
997
+ "pass@4": 0.9665270294338203,
998
+ "pass@8": 0.9751033296649382,
999
+ "pass@16": 0.9814160863652701,
1000
+ "pass@32": 0.9866717919871326,
1001
+ "pass@64": 0.99098669283729,
1002
+ "pass@128": 0.993
1003
+ },
1004
+ "15": {
1005
+ "pass@1": 0.9321484375,
1006
+ "pass@2": 0.9586374261811037,
1007
+ "pass@4": 0.9716738764529432,
1008
+ "pass@8": 0.980257322244576,
1009
+ "pass@16": 0.9860876075856799,
1010
+ "pass@32": 0.9905182347017089,
1011
+ "pass@64": 0.9941053539635863,
1012
+ "pass@128": 0.997
1013
+ },
1014
+ "16": {
1015
+ "pass@1": 0.919421875,
1016
+ "pass@2": 0.9510446604330718,
1017
+ "pass@4": 0.9672112351893514,
1018
+ "pass@8": 0.9771642191649528,
1019
+ "pass@16": 0.9837104050806683,
1020
+ "pass@32": 0.9884127699664014,
1021
+ "pass@64": 0.9923083437843704,
1022
+ "pass@128": 0.995
1023
+ },
1024
+ "17": {
1025
+ "pass@1": 0.917234375,
1026
+ "pass@2": 0.9551825787401591,
1027
+ "pass@4": 0.9728983112110978,
1028
+ "pass@8": 0.9831834738064922,
1029
+ "pass@16": 0.989503100920689,
1030
+ "pass@32": 0.9936977352294757,
1031
+ "pass@64": 0.9968179233919849,
1032
+ "pass@128": 0.999
1033
+ },
1034
+ "18": {
1035
+ "pass@1": 0.8954921875,
1036
+ "pass@2": 0.9377255167322847,
1037
+ "pass@4": 0.9575529777840263,
1038
+ "pass@8": 0.9690916457538964,
1039
+ "pass@16": 0.9765775044869797,
1040
+ "pass@32": 0.9819170635269723,
1041
+ "pass@64": 0.9859361791907656,
1042
+ "pass@128": 0.989
1043
+ },
1044
+ "19": {
1045
+ "pass@1": 0.875109375,
1046
+ "pass@2": 0.9267666092519707,
1047
+ "pass@4": 0.9520276386389189,
1048
+ "pass@8": 0.9663416476690758,
1049
+ "pass@16": 0.975462333146504,
1050
+ "pass@32": 0.981573341392933,
1051
+ "pass@64": 0.9858043859763082,
1052
+ "pass@128": 0.989
1053
+ },
1054
+ "20": {
1055
+ "pass@1": 0.8575859375,
1056
+ "pass@2": 0.9162995816929158,
1057
+ "pass@4": 0.944188775403074,
1058
+ "pass@8": 0.9605284903730037,
1059
+ "pass@16": 0.9717644090133872,
1060
+ "pass@32": 0.9798880740245233,
1061
+ "pass@64": 0.9855316641548822,
1062
+ "pass@128": 0.989
1063
+ }
1064
+ }
1065
+ },
1066
+ "movie_festival_awards": {
1067
+ "count": 0,
1068
+ "correct": 0,
1069
+ "answer_accuracy": 0.0,
1070
+ "avg_response_len": 0.0,
1071
+ "resp_tokens_sum": 0,
1072
+ "pass_at_k": {},
1073
+ "per_op_pass_at_k": {}
1074
+ }
1075
+ }
1076
+ }
1077
+ }
Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/hf_model_ood_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf1178ba74866a661cdbd18ff34a89792dd569d167d8962551e823a762f7bd5
3
+ size 2618033145
Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/summary.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint,id_acc,ood_acc,total_acc,id_avg_loss,ood_avg_loss,total_avg_loss,id_avg_resp_len,ood_avg_resp_len,count_id,count_ood,count_total
2
+ hf_model,0.9923975694444445,0.91275625,0.9504810855263158,0.0,0.0,0.0,176.4994105902778,339.53681640625,1152000,1280000,2432000
Qwen3-100M-RL/context/0.9zoo_op2-20+0.1teacher_op2/summary.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "hf_model",
4
+ "id_acc": 0.9923975694444445,
5
+ "ood_acc": 0.91275625,
6
+ "total_acc": 0.9504810855263158,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 176.4994105902778,
11
+ "ood_avg_resp_len": 339.53681640625,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 0,
18
+ "correct": 0,
19
+ "answer_accuracy": 0.0,
20
+ "avg_response_len": 0.0,
21
+ "resp_tokens_sum": 0,
22
+ "pass_at_k": {},
23
+ "per_op_pass_at_k": {}
24
+ },
25
+ "teachers_in_school": {
26
+ "count": 2432000,
27
+ "correct": 2311570,
28
+ "answer_accuracy": 0.9504810855263158,
29
+ "avg_response_len": 262.30857154605263,
30
+ "resp_tokens_sum": 637934446,
31
+ "pass_at_k": {
32
+ "pass@1": 0.9504810855263158,
33
+ "pass@2": 0.9695000518027258,
34
+ "pass@4": 0.9789090207802891,
35
+ "pass@8": 0.9846479381669422,
36
+ "pass@16": 0.988546711162386,
37
+ "pass@32": 0.9914438404095707,
38
+ "pass@64": 0.9936642595978096,
39
+ "pass@128": 0.9952105263157894
40
+ },
41
+ "per_op_pass_at_k": {
42
+ "10": {
43
+ "pass@1": 0.9722734375,
44
+ "pass@2": 0.982090920275591,
45
+ "pass@4": 0.9870395954255715,
46
+ "pass@8": 0.9898463912960546,
47
+ "pass@16": 0.9913574932933285,
48
+ "pass@32": 0.9924062358073099,
49
+ "pass@64": 0.9929435009525102,
50
+ "pass@128": 0.993
51
+ },
52
+ "2": {
53
+ "pass@1": 1.0,
54
+ "pass@2": 1.0,
55
+ "pass@4": 1.0,
56
+ "pass@8": 1.0,
57
+ "pass@16": 1.0,
58
+ "pass@32": 1.0,
59
+ "pass@64": 1.0,
60
+ "pass@128": 1.0
61
+ },
62
+ "3": {
63
+ "pass@1": 0.99696875,
64
+ "pass@2": 0.9987176427165356,
65
+ "pass@4": 0.999073522215973,
66
+ "pass@8": 0.9991772006158419,
67
+ "pass@16": 0.9993323490768988,
68
+ "pass@32": 0.9995814585676791,
69
+ "pass@64": 0.9998779527559055,
70
+ "pass@128": 1.0
71
+ },
72
+ "4": {
73
+ "pass@1": 0.998421875,
74
+ "pass@2": 0.999459153543307,
75
+ "pass@4": 0.9998440072178476,
76
+ "pass@8": 0.999979701409027,
77
+ "pass@16": 0.9999997111918157,
78
+ "pass@32": 0.9999999999851739,
79
+ "pass@64": 1.0,
80
+ "pass@128": 1.0
81
+ },
82
+ "5": {
83
+ "pass@1": 0.9941015625,
84
+ "pass@2": 0.9965524114173228,
85
+ "pass@4": 0.9978783887326584,
86
+ "pass@8": 0.9987054335254999,
87
+ "pass@16": 0.9993742678247356,
88
+ "pass@32": 0.9998140401510567,
89
+ "pass@64": 0.9999861487158879,
90
+ "pass@128": 1.0
91
+ },
92
+ "6": {
93
+ "pass@1": 0.99475,
94
+ "pass@2": 0.9969265501968505,
95
+ "pass@4": 0.9980495649606299,
96
+ "pass@8": 0.9987365127580474,
97
+ "pass@16": 0.9989781223272445,
98
+ "pass@32": 0.9989999037739257,
99
+ "pass@64": 0.9989999999999666,
100
+ "pass@128": 0.999
101
+ },
102
+ "7": {
103
+ "pass@1": 0.9951015625,
104
+ "pass@2": 0.9976016240157483,
105
+ "pass@4": 0.9984762033183351,
106
+ "pass@8": 0.9988805544747335,
107
+ "pass@16": 0.9989943223963219,
108
+ "pass@32": 0.9989999945303923,
109
+ "pass@64": 0.999,
110
+ "pass@128": 0.999
111
+ },
112
+ "8": {
113
+ "pass@1": 0.992984375,
114
+ "pass@2": 0.9974980314960634,
115
+ "pass@4": 0.9988455806149232,
116
+ "pass@8": 0.9992881325051802,
117
+ "pass@16": 0.9995580380881292,
118
+ "pass@32": 0.999829071592898,
119
+ "pass@64": 0.9999861763011332,
120
+ "pass@128": 1.0
121
+ },
122
+ "9": {
123
+ "pass@1": 0.9869765625,
124
+ "pass@2": 0.9931916830708665,
125
+ "pass@4": 0.995589347581552,
126
+ "pass@8": 0.9970554718258637,
127
+ "pass@16": 0.9980393105543356,
128
+ "pass@32": 0.9987247492592555,
129
+ "pass@64": 0.998984425990599,
130
+ "pass@128": 0.999
131
+ },
132
+ "11": {
133
+ "pass@1": 0.9569375,
134
+ "pass@2": 0.9694979084645677,
135
+ "pass@4": 0.9755786563554552,
136
+ "pass@8": 0.9795771285286979,
137
+ "pass@16": 0.9828716597217099,
138
+ "pass@32": 0.9858994698672985,
139
+ "pass@64": 0.9886172988906358,
140
+ "pass@128": 0.991
141
+ },
142
+ "12": {
143
+ "pass@1": 0.9321875,
144
+ "pass@2": 0.9527299458661426,
145
+ "pass@4": 0.964783362579677,
146
+ "pass@8": 0.9725947365272651,
147
+ "pass@16": 0.9780288578767546,
148
+ "pass@32": 0.9822927738860049,
149
+ "pass@64": 0.9860262163530781,
150
+ "pass@128": 0.989
151
+ },
152
+ "13": {
153
+ "pass@1": 0.9148515625,
154
+ "pass@2": 0.9376562500000003,
155
+ "pass@4": 0.9520333217097862,
156
+ "pass@8": 0.9627994330286813,
157
+ "pass@16": 0.9713319331348897,
158
+ "pass@32": 0.9782062595316485,
159
+ "pass@64": 0.9837086690994824,
160
+ "pass@128": 0.988
161
+ },
162
+ "14": {
163
+ "pass@1": 0.92659375,
164
+ "pass@2": 0.9529224901574813,
165
+ "pass@4": 0.9665270294338203,
166
+ "pass@8": 0.9751033296649382,
167
+ "pass@16": 0.9814160863652701,
168
+ "pass@32": 0.9866717919871326,
169
+ "pass@64": 0.99098669283729,
170
+ "pass@128": 0.993
171
+ },
172
+ "15": {
173
+ "pass@1": 0.9321484375,
174
+ "pass@2": 0.9586374261811037,
175
+ "pass@4": 0.9716738764529432,
176
+ "pass@8": 0.980257322244576,
177
+ "pass@16": 0.9860876075856799,
178
+ "pass@32": 0.9905182347017089,
179
+ "pass@64": 0.9941053539635863,
180
+ "pass@128": 0.997
181
+ },
182
+ "16": {
183
+ "pass@1": 0.919421875,
184
+ "pass@2": 0.9510446604330718,
185
+ "pass@4": 0.9672112351893514,
186
+ "pass@8": 0.9771642191649528,
187
+ "pass@16": 0.9837104050806683,
188
+ "pass@32": 0.9884127699664014,
189
+ "pass@64": 0.9923083437843704,
190
+ "pass@128": 0.995
191
+ },
192
+ "17": {
193
+ "pass@1": 0.917234375,
194
+ "pass@2": 0.9551825787401591,
195
+ "pass@4": 0.9728983112110978,
196
+ "pass@8": 0.9831834738064922,
197
+ "pass@16": 0.989503100920689,
198
+ "pass@32": 0.9936977352294757,
199
+ "pass@64": 0.9968179233919849,
200
+ "pass@128": 0.999
201
+ },
202
+ "18": {
203
+ "pass@1": 0.8954921875,
204
+ "pass@2": 0.9377255167322847,
205
+ "pass@4": 0.9575529777840263,
206
+ "pass@8": 0.9690916457538964,
207
+ "pass@16": 0.9765775044869797,
208
+ "pass@32": 0.9819170635269723,
209
+ "pass@64": 0.9859361791907656,
210
+ "pass@128": 0.989
211
+ },
212
+ "19": {
213
+ "pass@1": 0.875109375,
214
+ "pass@2": 0.9267666092519707,
215
+ "pass@4": 0.9520276386389189,
216
+ "pass@8": 0.9663416476690758,
217
+ "pass@16": 0.975462333146504,
218
+ "pass@32": 0.981573341392933,
219
+ "pass@64": 0.9858043859763082,
220
+ "pass@128": 0.989
221
+ },
222
+ "20": {
223
+ "pass@1": 0.8575859375,
224
+ "pass@2": 0.9162995816929158,
225
+ "pass@4": 0.944188775403074,
226
+ "pass@8": 0.9605284903730037,
227
+ "pass@16": 0.9717644090133872,
228
+ "pass@32": 0.9798880740245233,
229
+ "pass@64": 0.9855316641548822,
230
+ "pass@128": 0.989
231
+ }
232
+ }
233
+ },
234
+ "movie_festival_awards": {
235
+ "count": 0,
236
+ "correct": 0,
237
+ "answer_accuracy": 0.0,
238
+ "avg_response_len": 0.0,
239
+ "resp_tokens_sum": 0,
240
+ "pass_at_k": {},
241
+ "per_op_pass_at_k": {}
242
+ }
243
+ }
244
+ }
245
+ ]
Qwen3-100M-ep4/composition/checkpoint-85276_id_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa35f6d2d084c259ecd5f0a8f1e745e8bb7ac8fbd684e1a93afc6cbc6a308b5
3
+ size 1789209154
Qwen3-100M-ep4/composition/checkpoint-85276_metrics.json ADDED
@@ -0,0 +1,1897 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "checkpoint-85276",
3
+ "id": {
4
+ "answer_accuracy": 0.9949305555555555,
5
+ "avg_response_len": 200.0108559027778,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.9949305555555555,
11
+ "pass@2": 0.9962390912073487,
12
+ "pass@4": 0.9971986516685417,
13
+ "pass@8": 0.9977962149213019,
14
+ "pass@16": 0.9981298764933108,
15
+ "pass@32": 0.9983723358418248,
16
+ "pass@64": 0.9986656367264329,
17
+ "pass@128": 0.9991111111111111
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.9624921875,
22
+ "pass@2": 0.9715636072834645,
23
+ "pass@4": 0.9781628562054747,
24
+ "pass@8": 0.9820358637737919,
25
+ "pass@16": 0.984177149756922,
26
+ "pass@32": 0.9859330858922759,
27
+ "pass@64": 0.988238824249548,
28
+ "pass@128": 0.992
29
+ },
30
+ "2": {
31
+ "pass@1": 1.0,
32
+ "pass@2": 1.0,
33
+ "pass@4": 1.0,
34
+ "pass@8": 1.0,
35
+ "pass@16": 1.0,
36
+ "pass@32": 1.0,
37
+ "pass@64": 1.0,
38
+ "pass@128": 1.0
39
+ },
40
+ "3": {
41
+ "pass@1": 1.0,
42
+ "pass@2": 1.0,
43
+ "pass@4": 1.0,
44
+ "pass@8": 1.0,
45
+ "pass@16": 1.0,
46
+ "pass@32": 1.0,
47
+ "pass@64": 1.0,
48
+ "pass@128": 1.0
49
+ },
50
+ "4": {
51
+ "pass@1": 1.0,
52
+ "pass@2": 1.0,
53
+ "pass@4": 1.0,
54
+ "pass@8": 1.0,
55
+ "pass@16": 1.0,
56
+ "pass@32": 1.0,
57
+ "pass@64": 1.0,
58
+ "pass@128": 1.0
59
+ },
60
+ "5": {
61
+ "pass@1": 0.999453125,
62
+ "pass@2": 0.9997881397637796,
63
+ "pass@4": 0.9999573371766028,
64
+ "pass@8": 0.9999984489981919,
65
+ "pass@16": 0.9999999988246276,
66
+ "pass@32": 1.0,
67
+ "pass@64": 1.0,
68
+ "pass@128": 1.0
69
+ },
70
+ "6": {
71
+ "pass@1": 0.9999921875,
72
+ "pass@2": 1.0,
73
+ "pass@4": 1.0,
74
+ "pass@8": 1.0,
75
+ "pass@16": 1.0,
76
+ "pass@32": 1.0,
77
+ "pass@64": 1.0,
78
+ "pass@128": 1.0
79
+ },
80
+ "7": {
81
+ "pass@1": 0.9998984375,
82
+ "pass@2": 0.9999944635826771,
83
+ "pass@4": 0.9999999803149605,
84
+ "pass@8": 0.9999999999999685,
85
+ "pass@16": 1.0,
86
+ "pass@32": 1.0,
87
+ "pass@64": 1.0,
88
+ "pass@128": 1.0
89
+ },
90
+ "8": {
91
+ "pass@1": 0.996578125,
92
+ "pass@2": 0.9977417568897637,
93
+ "pass@4": 0.998505216816648,
94
+ "pass@8": 0.9989649390790856,
95
+ "pass@16": 0.9992179855257273,
96
+ "pass@32": 0.9994388347222112,
97
+ "pass@64": 0.9997519685037116,
98
+ "pass@128": 1.0
99
+ },
100
+ "9": {
101
+ "pass@1": 0.9959609375,
102
+ "pass@2": 0.9970638533464568,
103
+ "pass@4": 0.9981624745031872,
104
+ "pass@8": 0.9991666824406795,
105
+ "pass@16": 0.9997737543325198,
106
+ "pass@32": 0.999979101961939,
107
+ "pass@64": 0.9999999377846387,
108
+ "pass@128": 1.0
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.9624921875,
113
+ "2": 1.0,
114
+ "3": 1.0,
115
+ "4": 1.0,
116
+ "5": 0.999453125,
117
+ "6": 0.9999921875,
118
+ "7": 0.9998984375,
119
+ "8": 0.996578125,
120
+ "9": 0.9959609375
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 281.153859375,
124
+ "2": 115.629984375,
125
+ "3": 144.724578125,
126
+ "4": 159.8816328125,
127
+ "5": 172.73553125,
128
+ "6": 198.9245234375,
129
+ "7": 223.9551328125,
130
+ "8": 243.5811875,
131
+ "9": 259.5112734375
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 281.153859375,
136
+ "2": 115.629984375,
137
+ "3": 144.724578125,
138
+ "4": 159.8816328125,
139
+ "5": 172.73553125,
140
+ "6": 198.9245234375,
141
+ "7": 223.9551328125,
142
+ "8": 243.5811875,
143
+ "9": 259.5112734375
144
+ },
145
+ "per_op_loss": {},
146
+ "per_template": {
147
+ "crazy_zootopia": {
148
+ "count": 379008,
149
+ "correct": 377286,
150
+ "answer_accuracy": 0.9954565602836879,
151
+ "avg_response_len": 190.53283571850727,
152
+ "resp_tokens_sum": 72213469,
153
+ "pass_at_k": {
154
+ "pass@1": 0.9954565602836879,
155
+ "pass@2": 0.9967242292851691,
156
+ "pass@4": 0.9975758479784755,
157
+ "pass@8": 0.9980857085222107,
158
+ "pass@16": 0.9983981190211061,
159
+ "pass@32": 0.9986417677980687,
160
+ "pass@64": 0.9989868076836745,
161
+ "pass@128": 0.999662276258021
162
+ },
163
+ "per_op_pass_at_k": {
164
+ "10": {
165
+ "pass@1": 0.964855272861357,
166
+ "pass@2": 0.9744083600445962,
167
+ "pass@4": 0.980863755415529,
168
+ "pass@8": 0.9845045622809016,
169
+ "pass@16": 0.9864817601267433,
170
+ "pass@32": 0.988192742885706,
171
+ "pass@64": 0.9911504413060571,
172
+ "pass@128": 0.9970501474926253
173
+ },
174
+ "2": {
175
+ "pass@1": 1.0,
176
+ "pass@2": 1.0,
177
+ "pass@4": 1.0,
178
+ "pass@8": 1.0,
179
+ "pass@16": 1.0,
180
+ "pass@32": 1.0,
181
+ "pass@64": 1.0,
182
+ "pass@128": 1.0
183
+ },
184
+ "3": {
185
+ "pass@1": 1.0,
186
+ "pass@2": 1.0,
187
+ "pass@4": 1.0,
188
+ "pass@8": 1.0,
189
+ "pass@16": 1.0,
190
+ "pass@32": 1.0,
191
+ "pass@64": 1.0,
192
+ "pass@128": 1.0
193
+ },
194
+ "4": {
195
+ "pass@1": 1.0,
196
+ "pass@2": 1.0,
197
+ "pass@4": 1.0,
198
+ "pass@8": 1.0,
199
+ "pass@16": 1.0,
200
+ "pass@32": 1.0,
201
+ "pass@64": 1.0,
202
+ "pass@128": 1.0
203
+ },
204
+ "5": {
205
+ "pass@1": 0.9985367063492063,
206
+ "pass@2": 0.99933172415948,
207
+ "pass@4": 0.999864562762988,
208
+ "pass@8": 0.999995076184736,
209
+ "pass@16": 0.999999996268659,
210
+ "pass@32": 1.0,
211
+ "pass@64": 1.0,
212
+ "pass@128": 1.0
213
+ },
214
+ "6": {
215
+ "pass@1": 1.0,
216
+ "pass@2": 1.0,
217
+ "pass@4": 1.0,
218
+ "pass@8": 1.0,
219
+ "pass@16": 1.0,
220
+ "pass@32": 1.0,
221
+ "pass@64": 1.0,
222
+ "pass@128": 1.0
223
+ },
224
+ "7": {
225
+ "pass@1": 0.9997688609467456,
226
+ "pass@2": 0.9999836200670922,
227
+ "pass@4": 0.9999999417602385,
228
+ "pass@8": 0.9999999999999069,
229
+ "pass@16": 1.0,
230
+ "pass@32": 1.0,
231
+ "pass@64": 1.0,
232
+ "pass@128": 1.0
233
+ },
234
+ "8": {
235
+ "pass@1": 0.999824719551282,
236
+ "pass@2": 0.9999976340096912,
237
+ "pass@4": 0.9999999996995569,
238
+ "pass@8": 1.0,
239
+ "pass@16": 1.0,
240
+ "pass@32": 1.0,
241
+ "pass@64": 1.0,
242
+ "pass@128": 1.0
243
+ },
244
+ "9": {
245
+ "pass@1": 0.997337147887324,
246
+ "pass@2": 0.9977261700121991,
247
+ "pass@4": 0.9981745219347582,
248
+ "pass@8": 0.9988346121771267,
249
+ "pass@16": 0.9995479293349335,
250
+ "pass@32": 0.9999462946812021,
251
+ "pass@64": 0.9999998252073432,
252
+ "pass@128": 1.0
253
+ }
254
+ }
255
+ },
256
+ "teachers_in_school": {
257
+ "count": 390656,
258
+ "correct": 388437,
259
+ "answer_accuracy": 0.9943198107798165,
260
+ "avg_response_len": 198.04131256143512,
261
+ "resp_tokens_sum": 77366027,
262
+ "pass_at_k": {
263
+ "pass@1": 0.9943198107798165,
264
+ "pass@2": 0.9955572810781106,
265
+ "pass@4": 0.9964470693825461,
266
+ "pass@8": 0.9969549085780425,
267
+ "pass@16": 0.9971560486666131,
268
+ "pass@32": 0.9972767789698127,
269
+ "pass@64": 0.9974613265083974,
270
+ "pass@128": 0.9977064220183486
271
+ },
272
+ "per_op_pass_at_k": {
273
+ "10": {
274
+ "pass@1": 0.9569833205521472,
275
+ "pass@2": 0.9659142372349164,
276
+ "pass@4": 0.9719421844700393,
277
+ "pass@8": 0.9748675318830776,
278
+ "pass@16": 0.9757861748653367,
279
+ "pass@32": 0.9762266888126843,
280
+ "pass@64": 0.9769938650304216,
281
+ "pass@128": 0.9785276073619632
282
+ },
283
+ "2": {
284
+ "pass@1": 1.0,
285
+ "pass@2": 1.0,
286
+ "pass@4": 1.0,
287
+ "pass@8": 1.0,
288
+ "pass@16": 1.0,
289
+ "pass@32": 1.0,
290
+ "pass@64": 1.0,
291
+ "pass@128": 1.0
292
+ },
293
+ "3": {
294
+ "pass@1": 1.0,
295
+ "pass@2": 1.0,
296
+ "pass@4": 1.0,
297
+ "pass@8": 1.0,
298
+ "pass@16": 1.0,
299
+ "pass@32": 1.0,
300
+ "pass@64": 1.0,
301
+ "pass@128": 1.0
302
+ },
303
+ "4": {
304
+ "pass@1": 1.0,
305
+ "pass@2": 1.0,
306
+ "pass@4": 1.0,
307
+ "pass@8": 1.0,
308
+ "pass@16": 1.0,
309
+ "pass@32": 1.0,
310
+ "pass@64": 1.0,
311
+ "pass@128": 1.0
312
+ },
313
+ "5": {
314
+ "pass@1": 0.9998414855072464,
315
+ "pass@2": 0.9999967904827115,
316
+ "pass@4": 0.9999999997282949,
317
+ "pass@8": 1.0,
318
+ "pass@16": 1.0,
319
+ "pass@32": 1.0,
320
+ "pass@64": 1.0,
321
+ "pass@128": 1.0
322
+ },
323
+ "6": {
324
+ "pass@1": 0.9999776146131805,
325
+ "pass@2": 1.0,
326
+ "pass@4": 1.0,
327
+ "pass@8": 1.0,
328
+ "pass@16": 1.0,
329
+ "pass@32": 1.0,
330
+ "pass@64": 1.0,
331
+ "pass@128": 1.0
332
+ },
333
+ "7": {
334
+ "pass@1": 1.0,
335
+ "pass@2": 1.0,
336
+ "pass@4": 1.0,
337
+ "pass@8": 1.0,
338
+ "pass@16": 1.0,
339
+ "pass@32": 1.0,
340
+ "pass@64": 1.0,
341
+ "pass@128": 1.0
342
+ },
343
+ "8": {
344
+ "pass@1": 0.9948283450704225,
345
+ "pass@2": 0.9955154153266054,
346
+ "pass@4": 0.9962789690901313,
347
+ "pass@8": 0.9971273245981712,
348
+ "pass@16": 0.997797475275284,
349
+ "pass@32": 0.9984192527437615,
350
+ "pass@64": 0.9993013197287653,
351
+ "pass@128": 1.0
352
+ },
353
+ "9": {
354
+ "pass@1": 0.9957662799401198,
355
+ "pass@2": 0.9974428603423076,
356
+ "pass@4": 0.9988750589372435,
357
+ "pass@8": 0.9997585789040461,
358
+ "pass@16": 0.9999876161726882,
359
+ "pass@32": 0.9999999824517899,
360
+ "pass@64": 0.9999999999999998,
361
+ "pass@128": 1.0
362
+ }
363
+ }
364
+ },
365
+ "movie_festival_awards": {
366
+ "count": 382336,
367
+ "correct": 380437,
368
+ "answer_accuracy": 0.9950331645463676,
369
+ "avg_response_len": 211.4187782474054,
370
+ "resp_tokens_sum": 80833010,
371
+ "pass_at_k": {
372
+ "pass@1": 0.9950331645463676,
373
+ "pass@2": 0.9964548229334995,
374
+ "pass@4": 0.9975926760619602,
375
+ "pass@8": 0.9983688551648029,
376
+ "pass@16": 0.9988589881110809,
377
+ "pass@32": 0.9992246463711005,
378
+ "pass@64": 0.9995777785346197,
379
+ "pass@128": 1.0
380
+ },
381
+ "per_op_pass_at_k": {
382
+ "10": {
383
+ "pass@1": 0.9654617537313432,
384
+ "pass@2": 0.974182483253026,
385
+ "pass@4": 0.9814832566638125,
386
+ "pass@8": 0.9865134381095033,
387
+ "pass@16": 0.990010567366735,
388
+ "pass@32": 0.9930920761226464,
389
+ "pass@64": 0.9962352974533647,
390
+ "pass@128": 1.0
391
+ },
392
+ "2": {
393
+ "pass@1": 1.0,
394
+ "pass@2": 1.0,
395
+ "pass@4": 1.0,
396
+ "pass@8": 1.0,
397
+ "pass@16": 1.0,
398
+ "pass@32": 1.0,
399
+ "pass@64": 1.0,
400
+ "pass@128": 1.0
401
+ },
402
+ "3": {
403
+ "pass@1": 1.0,
404
+ "pass@2": 1.0,
405
+ "pass@4": 1.0,
406
+ "pass@8": 1.0,
407
+ "pass@16": 1.0,
408
+ "pass@32": 1.0,
409
+ "pass@64": 1.0,
410
+ "pass@128": 1.0
411
+ },
412
+ "4": {
413
+ "pass@1": 1.0,
414
+ "pass@2": 1.0,
415
+ "pass@4": 1.0,
416
+ "pass@8": 1.0,
417
+ "pass@16": 1.0,
418
+ "pass@32": 1.0,
419
+ "pass@64": 1.0,
420
+ "pass@128": 1.0
421
+ },
422
+ "5": {
423
+ "pass@1": 0.9999080882352941,
424
+ "pass@2": 0.9999992762853173,
425
+ "pass@4": 1.0,
426
+ "pass@8": 1.0,
427
+ "pass@16": 1.0,
428
+ "pass@32": 1.0,
429
+ "pass@64": 1.0,
430
+ "pass@128": 1.0
431
+ },
432
+ "6": {
433
+ "pass@1": 1.0,
434
+ "pass@2": 1.0,
435
+ "pass@4": 1.0,
436
+ "pass@8": 1.0,
437
+ "pass@16": 1.0,
438
+ "pass@32": 1.0,
439
+ "pass@64": 1.0,
440
+ "pass@128": 1.0
441
+ },
442
+ "7": {
443
+ "pass@1": 0.9999258306962026,
444
+ "pass@2": 1.0,
445
+ "pass@4": 1.0,
446
+ "pass@8": 1.0,
447
+ "pass@16": 1.0,
448
+ "pass@32": 1.0,
449
+ "pass@64": 1.0,
450
+ "pass@128": 1.0
451
+ },
452
+ "8": {
453
+ "pass@1": 0.9954016516516516,
454
+ "pass@2": 0.9980015694828687,
455
+ "pass@4": 0.9994780266768457,
456
+ "pass@8": 0.9999541707109151,
457
+ "pass@16": 0.9999996450540588,
458
+ "pass@32": 0.9999999999945218,
459
+ "pass@64": 1.0,
460
+ "pass@128": 1.0
461
+ },
462
+ "9": {
463
+ "pass@1": 0.994599075562701,
464
+ "pass@2": 0.9959007962630074,
465
+ "pass@4": 0.9973834390074231,
466
+ "pass@8": 0.9989100635493507,
467
+ "pass@16": 0.9998018508583297,
468
+ "pass@32": 0.9999941260810753,
469
+ "pass@64": 0.9999999994727716,
470
+ "pass@128": 1.0
471
+ }
472
+ }
473
+ }
474
+ }
475
+ },
476
+ "ood": {
477
+ "answer_accuracy": 0.44683984375,
478
+ "avg_response_len": 327.42891796875,
479
+ "avg_loss": 0.0,
480
+ "count": 1280000,
481
+ "validation_metrics": {},
482
+ "pass_at_k": {
483
+ "pass@1": 0.44683984375,
484
+ "pass@2": 0.5119684670275582,
485
+ "pass@4": 0.569463077690281,
486
+ "pass@8": 0.6178828516789759,
487
+ "pass@16": 0.6568252672877612,
488
+ "pass@32": 0.6882615383682829,
489
+ "pass@64": 0.7149255891967156,
490
+ "pass@128": 0.7386
491
+ },
492
+ "per_op_pass_at_k": {
493
+ "11": {
494
+ "pass@1": 0.96253125,
495
+ "pass@2": 0.972941190944882,
496
+ "pass@4": 0.9790027408136479,
497
+ "pass@8": 0.9831148686678516,
498
+ "pass@16": 0.98574542765598,
499
+ "pass@32": 0.9875692041741516,
500
+ "pass@64": 0.9892254753754837,
501
+ "pass@128": 0.991
502
+ },
503
+ "12": {
504
+ "pass@1": 0.876703125,
505
+ "pass@2": 0.9067059547244101,
506
+ "pass@4": 0.9224254388826393,
507
+ "pass@8": 0.9343966760611316,
508
+ "pass@16": 0.9450926015777066,
509
+ "pass@32": 0.9542979874178255,
510
+ "pass@64": 0.9614691678418349,
511
+ "pass@128": 0.966
512
+ },
513
+ "13": {
514
+ "pass@1": 0.70778125,
515
+ "pass@2": 0.7821064222440945,
516
+ "pass@4": 0.8326372481252345,
517
+ "pass@8": 0.8670544873404723,
518
+ "pass@16": 0.890846691933782,
519
+ "pass@32": 0.9088359604915771,
520
+ "pass@64": 0.9236104944347704,
521
+ "pass@128": 0.936
522
+ },
523
+ "14": {
524
+ "pass@1": 0.5578828125,
525
+ "pass@2": 0.6460127952755912,
526
+ "pass@4": 0.714011713348332,
527
+ "pass@8": 0.7653732918196041,
528
+ "pass@16": 0.803843338086645,
529
+ "pass@32": 0.8336969542236903,
530
+ "pass@64": 0.856039598782845,
531
+ "pass@128": 0.872
532
+ },
533
+ "15": {
534
+ "pass@1": 0.38559375,
535
+ "pass@2": 0.4773902559055116,
536
+ "pass@4": 0.5553634880014996,
537
+ "pass@8": 0.6194323066082491,
538
+ "pass@16": 0.6699661651256025,
539
+ "pass@32": 0.7098046818744348,
540
+ "pass@64": 0.7443967566005082,
541
+ "pass@128": 0.777
542
+ },
543
+ "16": {
544
+ "pass@1": 0.23978125,
545
+ "pass@2": 0.3170354330708663,
546
+ "pass@4": 0.3916617366891629,
547
+ "pass@8": 0.4572465077324236,
548
+ "pass@16": 0.5126771573643457,
549
+ "pass@32": 0.5610609835923893,
550
+ "pass@64": 0.6070904239009969,
551
+ "pass@128": 0.651
552
+ },
553
+ "17": {
554
+ "pass@1": 0.2129765625,
555
+ "pass@2": 0.2896716289370081,
556
+ "pass@4": 0.3657562349081365,
557
+ "pass@8": 0.4328031981342337,
558
+ "pass@16": 0.48777685207242233,
559
+ "pass@32": 0.5337343412962802,
560
+ "pass@64": 0.5753223230388924,
561
+ "pass@128": 0.614
562
+ },
563
+ "18": {
564
+ "pass@1": 0.193296875,
565
+ "pass@2": 0.2601900836614175,
566
+ "pass@4": 0.3277885975815519,
567
+ "pass@8": 0.3916256997651364,
568
+ "pass@16": 0.4472835877005817,
569
+ "pass@32": 0.49205269327981904,
570
+ "pass@64": 0.5271340188878637,
571
+ "pass@128": 0.556
572
+ },
573
+ "19": {
574
+ "pass@1": 0.1764375,
575
+ "pass@2": 0.24655782480314958,
576
+ "pass@4": 0.3155220647731533,
577
+ "pass@8": 0.3751407394764381,
578
+ "pass@16": 0.4233042476747667,
579
+ "pass@32": 0.46136250070818885,
580
+ "pass@64": 0.4921356285231653,
581
+ "pass@128": 0.521
582
+ },
583
+ "20": {
584
+ "pass@1": 0.1554140625,
585
+ "pass@2": 0.22107308070866163,
586
+ "pass@4": 0.2904615137795272,
587
+ "pass@8": 0.3526407411842315,
588
+ "pass@16": 0.40171660368563283,
589
+ "pass@32": 0.44020007662447264,
590
+ "pass@64": 0.4728320045807315,
591
+ "pass@128": 0.502
592
+ }
593
+ },
594
+ "per_op_accuracy": {
595
+ "11": 0.96253125,
596
+ "12": 0.876703125,
597
+ "13": 0.70778125,
598
+ "14": 0.5578828125,
599
+ "15": 0.38559375,
600
+ "16": 0.23978125,
601
+ "17": 0.2129765625,
602
+ "18": 0.193296875,
603
+ "19": 0.1764375,
604
+ "20": 0.1554140625
605
+ },
606
+ "per_op_avg_response_len": {
607
+ "11": 299.1838515625,
608
+ "12": 307.2964296875,
609
+ "13": 318.4115390625,
610
+ "14": 333.137890625,
611
+ "15": 335.3022890625,
612
+ "16": 329.080421875,
613
+ "17": 338.9223984375,
614
+ "18": 336.208109375,
615
+ "19": 336.5952578125,
616
+ "20": 340.1509921875
617
+ },
618
+ "per_op_avg_loss": {},
619
+ "per_op_length": {
620
+ "11": 299.1838515625,
621
+ "12": 307.2964296875,
622
+ "13": 318.4115390625,
623
+ "14": 333.137890625,
624
+ "15": 335.3022890625,
625
+ "16": 329.080421875,
626
+ "17": 338.9223984375,
627
+ "18": 336.208109375,
628
+ "19": 336.5952578125,
629
+ "20": 340.1509921875
630
+ },
631
+ "per_op_loss": {},
632
+ "per_template": {
633
+ "crazy_zootopia": {
634
+ "count": 430720,
635
+ "correct": 199569,
636
+ "answer_accuracy": 0.46333813150074293,
637
+ "avg_response_len": 314.1041906575037,
638
+ "resp_tokens_sum": 135290957,
639
+ "pass_at_k": {
640
+ "pass@1": 0.46333813150074293,
641
+ "pass@2": 0.5296728934375414,
642
+ "pass@4": 0.5881637628413112,
643
+ "pass@8": 0.6371085247462108,
644
+ "pass@16": 0.6759604016198593,
645
+ "pass@32": 0.7069346470921534,
646
+ "pass@64": 0.7328271853390599,
647
+ "pass@128": 0.7551263001485884
648
+ },
649
+ "per_op_pass_at_k": {
650
+ "11": {
651
+ "pass@1": 0.9568431303116147,
652
+ "pass@2": 0.966704122147621,
653
+ "pass@4": 0.9737702782725814,
654
+ "pass@8": 0.9797293556840062,
655
+ "pass@16": 0.9839171023985908,
656
+ "pass@32": 0.9864784015256126,
657
+ "pass@64": 0.9885864447521222,
658
+ "pass@128": 0.9915014164305949
659
+ },
660
+ "12": {
661
+ "pass@1": 0.8533501059322034,
662
+ "pass@2": 0.8813041477601309,
663
+ "pass@4": 0.8969065471688916,
664
+ "pass@8": 0.9103012428913164,
665
+ "pass@16": 0.9232330989994582,
666
+ "pass@32": 0.9356599220900689,
667
+ "pass@64": 0.9473396438691338,
668
+ "pass@128": 0.9548022598870056
669
+ },
670
+ "13": {
671
+ "pass@1": 0.760384012539185,
672
+ "pass@2": 0.8294336077308518,
673
+ "pass@4": 0.874541486977137,
674
+ "pass@8": 0.9027689973847379,
675
+ "pass@16": 0.9198466852847369,
676
+ "pass@32": 0.9308948171804944,
677
+ "pass@64": 0.9399058726440269,
678
+ "pass@128": 0.9498432601880877
679
+ },
680
+ "14": {
681
+ "pass@1": 0.6034852024922118,
682
+ "pass@2": 0.6929789259695341,
683
+ "pass@4": 0.7630072742075453,
684
+ "pass@8": 0.8164932601872855,
685
+ "pass@16": 0.8526563967709537,
686
+ "pass@32": 0.8763087593659933,
687
+ "pass@64": 0.8936422032813724,
688
+ "pass@128": 0.9065420560747663
689
+ },
690
+ "15": {
691
+ "pass@1": 0.4252619219653179,
692
+ "pass@2": 0.5253370209594465,
693
+ "pass@4": 0.6099591160209015,
694
+ "pass@8": 0.6784789856366449,
695
+ "pass@16": 0.7314473595873143,
696
+ "pass@32": 0.7713284427298922,
697
+ "pass@64": 0.8031345386516523,
698
+ "pass@128": 0.8294797687861272
699
+ },
700
+ "16": {
701
+ "pass@1": 0.26829637096774195,
702
+ "pass@2": 0.3590876619253239,
703
+ "pass@4": 0.44438377874136703,
704
+ "pass@8": 0.5160205150620084,
705
+ "pass@16": 0.572072708861716,
706
+ "pass@32": 0.6173416875891375,
707
+ "pass@64": 0.6591309169128403,
708
+ "pass@128": 0.6967741935483871
709
+ },
710
+ "17": {
711
+ "pass@1": 0.210305274566474,
712
+ "pass@2": 0.2880021534067633,
713
+ "pass@4": 0.36638274885075767,
714
+ "pass@8": 0.4354115772958514,
715
+ "pass@16": 0.4924820483803051,
716
+ "pass@32": 0.5414044485040482,
717
+ "pass@64": 0.5843553236837202,
718
+ "pass@128": 0.6242774566473989
719
+ },
720
+ "18": {
721
+ "pass@1": 0.19066964285714286,
722
+ "pass@2": 0.2540649606299211,
723
+ "pass@4": 0.3153792696448659,
724
+ "pass@8": 0.3744374956178368,
725
+ "pass@16": 0.4304686242139373,
726
+ "pass@32": 0.4799023237679476,
727
+ "pass@64": 0.5191885486106175,
728
+ "pass@128": 0.5485714285714286
729
+ },
730
+ "19": {
731
+ "pass@1": 0.17203922672672672,
732
+ "pass@2": 0.2452760339079237,
733
+ "pass@4": 0.31713847114831356,
734
+ "pass@8": 0.3807029920118585,
735
+ "pass@16": 0.43294372077217796,
736
+ "pass@32": 0.47306262676523364,
737
+ "pass@64": 0.5035309613007347,
738
+ "pass@128": 0.5315315315315315
739
+ },
740
+ "20": {
741
+ "pass@1": 0.16786317567567569,
742
+ "pass@2": 0.23649646201319421,
743
+ "pass@4": 0.3076818460755471,
744
+ "pass@8": 0.3678730399252492,
745
+ "pass@16": 0.41342134802722214,
746
+ "pass@32": 0.450621229184501,
747
+ "pass@64": 0.48393762875113866,
748
+ "pass@128": 0.5135135135135135
749
+ }
750
+ }
751
+ },
752
+ "teachers_in_school": {
753
+ "count": 430464,
754
+ "correct": 189989,
755
+ "answer_accuracy": 0.4413586269699673,
756
+ "avg_response_len": 322.06403787540887,
757
+ "resp_tokens_sum": 138636974,
758
+ "pass_at_k": {
759
+ "pass@1": 0.4413586269699673,
760
+ "pass@2": 0.5069858329762768,
761
+ "pass@4": 0.5649965586928776,
762
+ "pass@8": 0.6138581833337501,
763
+ "pass@16": 0.6533552733745646,
764
+ "pass@32": 0.6853306195144797,
765
+ "pass@64": 0.7123738268599717,
766
+ "pass@128": 0.736544751709783
767
+ },
768
+ "per_op_pass_at_k": {
769
+ "11": {
770
+ "pass@1": 0.9643731174698795,
771
+ "pass@2": 0.9750883455080163,
772
+ "pass@4": 0.9803072865138847,
773
+ "pass@8": 0.9823661486047269,
774
+ "pass@16": 0.9832962407555205,
775
+ "pass@32": 0.9844320989052803,
776
+ "pass@64": 0.9860781709515227,
777
+ "pass@128": 0.9879518072289156
778
+ },
779
+ "12": {
780
+ "pass@1": 0.8863636363636364,
781
+ "pass@2": 0.9133642287660749,
782
+ "pass@4": 0.9258904760729354,
783
+ "pass@8": 0.9354300779654707,
784
+ "pass@16": 0.945221377305145,
785
+ "pass@32": 0.9540520042583904,
786
+ "pass@64": 0.9598380142135106,
787
+ "pass@128": 0.9623824451410659
788
+ },
789
+ "13": {
790
+ "pass@1": 0.6867997198879552,
791
+ "pass@2": 0.7681042397273864,
792
+ "pass@4": 0.824483724986057,
793
+ "pass@8": 0.8627893286369971,
794
+ "pass@16": 0.8897924787212615,
795
+ "pass@32": 0.9118141519741789,
796
+ "pass@64": 0.9305813041850224,
797
+ "pass@128": 0.9439775910364145
798
+ },
799
+ "14": {
800
+ "pass@1": 0.5445906432748538,
801
+ "pass@2": 0.6282847970483952,
802
+ "pass@4": 0.6919824232497251,
803
+ "pass@8": 0.7401227434606403,
804
+ "pass@16": 0.7772650766591268,
805
+ "pass@32": 0.8067142511689581,
806
+ "pass@64": 0.8289431092869494,
807
+ "pass@128": 0.8450292397660819
808
+ },
809
+ "15": {
810
+ "pass@1": 0.3677556818181818,
811
+ "pass@2": 0.4612525351944643,
812
+ "pass@4": 0.5395015228210107,
813
+ "pass@8": 0.6038984673310392,
814
+ "pass@16": 0.6548475782041733,
815
+ "pass@32": 0.695211253240757,
816
+ "pass@64": 0.7307349783554408,
817
+ "pass@128": 0.7636363636363637
818
+ },
819
+ "16": {
820
+ "pass@1": 0.23595530626780628,
821
+ "pass@2": 0.30808173217129914,
822
+ "pass@4": 0.37879288913672104,
823
+ "pass@8": 0.44199327843430775,
824
+ "pass@16": 0.49717687261406224,
825
+ "pass@32": 0.5475518095537767,
826
+ "pass@64": 0.5956511172414417,
827
+ "pass@128": 0.6410256410256411
828
+ },
829
+ "17": {
830
+ "pass@1": 0.23090547360248448,
831
+ "pass@2": 0.31294512948109743,
832
+ "pass@4": 0.3923752244478753,
833
+ "pass@8": 0.4620048777355182,
834
+ "pass@16": 0.5184937076070995,
835
+ "pass@32": 0.5641996443460395,
836
+ "pass@64": 0.6058905683329744,
837
+ "pass@128": 0.6490683229813664
838
+ },
839
+ "18": {
840
+ "pass@1": 0.19181985294117648,
841
+ "pass@2": 0.2639264416396479,
842
+ "pass@4": 0.3402037715873749,
843
+ "pass@8": 0.41292313703410055,
844
+ "pass@16": 0.4755867515992984,
845
+ "pass@32": 0.5242663505584598,
846
+ "pass@64": 0.5607374408176437,
847
+ "pass@128": 0.5911764705882353
848
+ },
849
+ "19": {
850
+ "pass@1": 0.17740885416666666,
851
+ "pass@2": 0.24643025578833894,
852
+ "pass@4": 0.3146818307867766,
853
+ "pass@8": 0.37225657621985075,
854
+ "pass@16": 0.4180985090398595,
855
+ "pass@32": 0.4553241566350863,
856
+ "pass@64": 0.48681976016382017,
857
+ "pass@128": 0.5178571428571429
858
+ },
859
+ "20": {
860
+ "pass@1": 0.1394320733532934,
861
+ "pass@2": 0.2010787725729644,
862
+ "pass@4": 0.26803790703183067,
863
+ "pass@8": 0.32950827537338695,
864
+ "pass@16": 0.37733200724855503,
865
+ "pass@32": 0.4121459313058152,
866
+ "pass@64": 0.43980782684006975,
867
+ "pass@128": 0.46407185628742514
868
+ }
869
+ }
870
+ },
871
+ "movie_festival_awards": {
872
+ "count": 418816,
873
+ "correct": 182397,
874
+ "answer_accuracy": 0.4355062843826406,
875
+ "avg_response_len": 346.6464604981663,
876
+ "resp_tokens_sum": 145181084,
877
+ "pass_at_k": {
878
+ "pass@1": 0.4355062843826406,
879
+ "pass@2": 0.49888203776254814,
880
+ "pass@4": 0.5548216039296309,
881
+ "pass@8": 0.6022473289936959,
882
+ "pass@16": 0.6407127558276247,
883
+ "pass@32": 0.6720701169897646,
884
+ "pass@64": 0.6991379075706123,
885
+ "pass@128": 0.7237163814180929
886
+ },
887
+ "per_op_pass_at_k": {
888
+ "11": {
889
+ "pass@1": 0.9669642857142857,
890
+ "pass@2": 0.977667635295588,
891
+ "pass@4": 0.9834914713041819,
892
+ "pass@8": 0.987697919919454,
893
+ "pass@16": 0.9903756780268099,
894
+ "pass@32": 0.9920980050763724,
895
+ "pass@64": 0.9932587543558059,
896
+ "pass@128": 0.9936507936507937
897
+ },
898
+ "12": {
899
+ "pass@1": 0.8925602064220184,
900
+ "pass@2": 0.927709778106865,
901
+ "pass@4": 0.9466711294115757,
902
+ "pass@8": 0.9594735205095442,
903
+ "pass@16": 0.968631391961948,
904
+ "pass@32": 0.9747149407936225,
905
+ "pass@64": 0.9783565974863963,
906
+ "pass@128": 0.981651376146789
907
+ },
908
+ "13": {
909
+ "pass@1": 0.6791087962962963,
910
+ "pass@2": 0.7509379252940609,
911
+ "pass@4": 0.8003636541960031,
912
+ "pass@8": 0.836590700158435,
913
+ "pass@16": 0.8634558161248805,
914
+ "pass@32": 0.8838359924574606,
915
+ "pass@64": 0.8998857884792347,
916
+ "pass@128": 0.9135802469135802
917
+ },
918
+ "14": {
919
+ "pass@1": 0.5279349035608308,
920
+ "pass@2": 0.6192675354564355,
921
+ "pass@4": 0.6896984853896232,
922
+ "pass@8": 0.7423055698396044,
923
+ "pass@16": 0.7843204109962838,
924
+ "pass@32": 0.8204913013870107,
925
+ "pass@64": 0.8477207957073809,
926
+ "pass@128": 0.8664688427299704
927
+ },
928
+ "15": {
929
+ "pass@1": 0.36140046296296297,
930
+ "pass@2": 0.4426244137017595,
931
+ "pass@4": 0.5132164547139938,
932
+ "pass@8": 0.5721977881442194,
933
+ "pass@16": 0.6197088824105395,
934
+ "pass@32": 0.658967059013711,
935
+ "pass@64": 0.6955853807708048,
936
+ "pass@128": 0.7345679012345679
937
+ },
938
+ "16": {
939
+ "pass@1": 0.21766685103244837,
940
+ "pass@2": 0.2878512385896452,
941
+ "pass@4": 0.35677422180634516,
942
+ "pass@8": 0.4192935319550409,
943
+ "pass@16": 0.4744116086421201,
944
+ "pass@32": 0.5235822279834264,
945
+ "pass@64": 0.5713460103429768,
946
+ "pass@128": 0.6194690265486725
947
+ },
948
+ "17": {
949
+ "pass@1": 0.19837161144578314,
950
+ "pass@2": 0.26883901254624787,
951
+ "pass@4": 0.33928608895650064,
952
+ "pass@8": 0.40176271614166426,
953
+ "pass@16": 0.4530815948293738,
954
+ "pass@32": 0.49619312239293656,
955
+ "pass@64": 0.536260897714176,
956
+ "pass@128": 0.5692771084337349
957
+ },
958
+ "18": {
959
+ "pass@1": 0.19788306451612903,
960
+ "pass@2": 0.2630076041402083,
961
+ "pass@4": 0.3281824866649735,
962
+ "pass@8": 0.38767325712032175,
963
+ "pass@16": 0.4352260441352987,
964
+ "pass@32": 0.47043974442309966,
965
+ "pass@64": 0.4992493451488665,
966
+ "pass@128": 0.5258064516129032
967
+ },
968
+ "19": {
969
+ "pass@1": 0.17987632175226587,
970
+ "pass@2": 0.247976856697671,
971
+ "pass@4": 0.3147488179347673,
972
+ "pass@8": 0.37247260884174876,
973
+ "pass@16": 0.41889090519709676,
974
+ "pass@32": 0.45572123675521775,
975
+ "pass@64": 0.4860676102567291,
976
+ "pass@128": 0.513595166163142
977
+ },
978
+ "20": {
979
+ "pass@1": 0.15899493243243243,
980
+ "pass@2": 0.2257040505071999,
981
+ "pass@4": 0.29573212638960666,
982
+ "pass@8": 0.3606103751183562,
983
+ "pass@16": 0.41446968279744983,
984
+ "pass@32": 0.457917316065741,
985
+ "pass@64": 0.49484972985591286,
986
+ "pass@128": 0.5285285285285285
987
+ }
988
+ }
989
+ }
990
+ }
991
+ },
992
+ "total": {
993
+ "answer_accuracy": 0.7064617598684211,
994
+ "avg_loss": 0.0,
995
+ "count": 2432000,
996
+ "validation_metrics": {
997
+ "id": {},
998
+ "ood": {}
999
+ },
1000
+ "pass_at_k": {
1001
+ "pass@1": 0.7064617598684211,
1002
+ "pass@2": 0.7413598153232354,
1003
+ "pass@4": 0.7720746653641805,
1004
+ "pass@8": 0.7978418132148272,
1005
+ "pass@16": 0.8184958716482886,
1006
+ "pass@32": 0.835156126645237,
1007
+ "pass@64": 0.8493287696055289,
1008
+ "pass@128": 0.862
1009
+ },
1010
+ "per_op_pass_at_k": {
1011
+ "10": {
1012
+ "pass@1": 0.9624921875,
1013
+ "pass@2": 0.9715636072834645,
1014
+ "pass@4": 0.9781628562054747,
1015
+ "pass@8": 0.9820358637737919,
1016
+ "pass@16": 0.984177149756922,
1017
+ "pass@32": 0.9859330858922759,
1018
+ "pass@64": 0.988238824249548,
1019
+ "pass@128": 0.992
1020
+ },
1021
+ "2": {
1022
+ "pass@1": 1.0,
1023
+ "pass@2": 1.0,
1024
+ "pass@4": 1.0,
1025
+ "pass@8": 1.0,
1026
+ "pass@16": 1.0,
1027
+ "pass@32": 1.0,
1028
+ "pass@64": 1.0,
1029
+ "pass@128": 1.0
1030
+ },
1031
+ "3": {
1032
+ "pass@1": 1.0,
1033
+ "pass@2": 1.0,
1034
+ "pass@4": 1.0,
1035
+ "pass@8": 1.0,
1036
+ "pass@16": 1.0,
1037
+ "pass@32": 1.0,
1038
+ "pass@64": 1.0,
1039
+ "pass@128": 1.0
1040
+ },
1041
+ "4": {
1042
+ "pass@1": 1.0,
1043
+ "pass@2": 1.0,
1044
+ "pass@4": 1.0,
1045
+ "pass@8": 1.0,
1046
+ "pass@16": 1.0,
1047
+ "pass@32": 1.0,
1048
+ "pass@64": 1.0,
1049
+ "pass@128": 1.0
1050
+ },
1051
+ "5": {
1052
+ "pass@1": 0.999453125,
1053
+ "pass@2": 0.9997881397637796,
1054
+ "pass@4": 0.9999573371766028,
1055
+ "pass@8": 0.9999984489981919,
1056
+ "pass@16": 0.9999999988246276,
1057
+ "pass@32": 1.0,
1058
+ "pass@64": 1.0,
1059
+ "pass@128": 1.0
1060
+ },
1061
+ "6": {
1062
+ "pass@1": 0.9999921875,
1063
+ "pass@2": 1.0,
1064
+ "pass@4": 1.0,
1065
+ "pass@8": 1.0,
1066
+ "pass@16": 1.0,
1067
+ "pass@32": 1.0,
1068
+ "pass@64": 1.0,
1069
+ "pass@128": 1.0
1070
+ },
1071
+ "7": {
1072
+ "pass@1": 0.9998984375,
1073
+ "pass@2": 0.9999944635826771,
1074
+ "pass@4": 0.9999999803149605,
1075
+ "pass@8": 0.9999999999999685,
1076
+ "pass@16": 1.0,
1077
+ "pass@32": 1.0,
1078
+ "pass@64": 1.0,
1079
+ "pass@128": 1.0
1080
+ },
1081
+ "8": {
1082
+ "pass@1": 0.996578125,
1083
+ "pass@2": 0.9977417568897637,
1084
+ "pass@4": 0.998505216816648,
1085
+ "pass@8": 0.9989649390790856,
1086
+ "pass@16": 0.9992179855257273,
1087
+ "pass@32": 0.9994388347222112,
1088
+ "pass@64": 0.9997519685037116,
1089
+ "pass@128": 1.0
1090
+ },
1091
+ "9": {
1092
+ "pass@1": 0.9959609375,
1093
+ "pass@2": 0.9970638533464568,
1094
+ "pass@4": 0.9981624745031872,
1095
+ "pass@8": 0.9991666824406795,
1096
+ "pass@16": 0.9997737543325198,
1097
+ "pass@32": 0.999979101961939,
1098
+ "pass@64": 0.9999999377846387,
1099
+ "pass@128": 1.0
1100
+ },
1101
+ "11": {
1102
+ "pass@1": 0.96253125,
1103
+ "pass@2": 0.972941190944882,
1104
+ "pass@4": 0.9790027408136479,
1105
+ "pass@8": 0.9831148686678516,
1106
+ "pass@16": 0.98574542765598,
1107
+ "pass@32": 0.9875692041741516,
1108
+ "pass@64": 0.9892254753754837,
1109
+ "pass@128": 0.991
1110
+ },
1111
+ "12": {
1112
+ "pass@1": 0.876703125,
1113
+ "pass@2": 0.9067059547244101,
1114
+ "pass@4": 0.9224254388826393,
1115
+ "pass@8": 0.9343966760611316,
1116
+ "pass@16": 0.9450926015777066,
1117
+ "pass@32": 0.9542979874178255,
1118
+ "pass@64": 0.9614691678418349,
1119
+ "pass@128": 0.966
1120
+ },
1121
+ "13": {
1122
+ "pass@1": 0.70778125,
1123
+ "pass@2": 0.7821064222440945,
1124
+ "pass@4": 0.8326372481252345,
1125
+ "pass@8": 0.8670544873404723,
1126
+ "pass@16": 0.890846691933782,
1127
+ "pass@32": 0.9088359604915771,
1128
+ "pass@64": 0.9236104944347704,
1129
+ "pass@128": 0.936
1130
+ },
1131
+ "14": {
1132
+ "pass@1": 0.5578828125,
1133
+ "pass@2": 0.6460127952755912,
1134
+ "pass@4": 0.714011713348332,
1135
+ "pass@8": 0.7653732918196041,
1136
+ "pass@16": 0.803843338086645,
1137
+ "pass@32": 0.8336969542236903,
1138
+ "pass@64": 0.856039598782845,
1139
+ "pass@128": 0.872
1140
+ },
1141
+ "15": {
1142
+ "pass@1": 0.38559375,
1143
+ "pass@2": 0.4773902559055116,
1144
+ "pass@4": 0.5553634880014996,
1145
+ "pass@8": 0.6194323066082491,
1146
+ "pass@16": 0.6699661651256025,
1147
+ "pass@32": 0.7098046818744348,
1148
+ "pass@64": 0.7443967566005082,
1149
+ "pass@128": 0.777
1150
+ },
1151
+ "16": {
1152
+ "pass@1": 0.23978125,
1153
+ "pass@2": 0.3170354330708663,
1154
+ "pass@4": 0.3916617366891629,
1155
+ "pass@8": 0.4572465077324236,
1156
+ "pass@16": 0.5126771573643457,
1157
+ "pass@32": 0.5610609835923893,
1158
+ "pass@64": 0.6070904239009969,
1159
+ "pass@128": 0.651
1160
+ },
1161
+ "17": {
1162
+ "pass@1": 0.2129765625,
1163
+ "pass@2": 0.2896716289370081,
1164
+ "pass@4": 0.3657562349081365,
1165
+ "pass@8": 0.4328031981342337,
1166
+ "pass@16": 0.48777685207242233,
1167
+ "pass@32": 0.5337343412962802,
1168
+ "pass@64": 0.5753223230388924,
1169
+ "pass@128": 0.614
1170
+ },
1171
+ "18": {
1172
+ "pass@1": 0.193296875,
1173
+ "pass@2": 0.2601900836614175,
1174
+ "pass@4": 0.3277885975815519,
1175
+ "pass@8": 0.3916256997651364,
1176
+ "pass@16": 0.4472835877005817,
1177
+ "pass@32": 0.49205269327981904,
1178
+ "pass@64": 0.5271340188878637,
1179
+ "pass@128": 0.556
1180
+ },
1181
+ "19": {
1182
+ "pass@1": 0.1764375,
1183
+ "pass@2": 0.24655782480314958,
1184
+ "pass@4": 0.3155220647731533,
1185
+ "pass@8": 0.3751407394764381,
1186
+ "pass@16": 0.4233042476747667,
1187
+ "pass@32": 0.46136250070818885,
1188
+ "pass@64": 0.4921356285231653,
1189
+ "pass@128": 0.521
1190
+ },
1191
+ "20": {
1192
+ "pass@1": 0.1554140625,
1193
+ "pass@2": 0.22107308070866163,
1194
+ "pass@4": 0.2904615137795272,
1195
+ "pass@8": 0.3526407411842315,
1196
+ "pass@16": 0.40171660368563283,
1197
+ "pass@32": 0.44020007662447264,
1198
+ "pass@64": 0.4728320045807315,
1199
+ "pass@128": 0.502
1200
+ }
1201
+ },
1202
+ "per_op_accuracy": {
1203
+ "10": 0.9624921875,
1204
+ "2": 1.0,
1205
+ "3": 1.0,
1206
+ "4": 1.0,
1207
+ "5": 0.999453125,
1208
+ "6": 0.9999921875,
1209
+ "7": 0.9998984375,
1210
+ "8": 0.996578125,
1211
+ "9": 0.9959609375,
1212
+ "11": 0.96253125,
1213
+ "12": 0.876703125,
1214
+ "13": 0.70778125,
1215
+ "14": 0.5578828125,
1216
+ "15": 0.38559375,
1217
+ "16": 0.23978125,
1218
+ "17": 0.2129765625,
1219
+ "18": 0.193296875,
1220
+ "19": 0.1764375,
1221
+ "20": 0.1554140625
1222
+ },
1223
+ "per_op_avg_response_len": {
1224
+ "10": 281.153859375,
1225
+ "2": 115.629984375,
1226
+ "3": 144.724578125,
1227
+ "4": 159.8816328125,
1228
+ "5": 172.73553125,
1229
+ "6": 198.9245234375,
1230
+ "7": 223.9551328125,
1231
+ "8": 243.5811875,
1232
+ "9": 259.5112734375,
1233
+ "11": 299.1838515625,
1234
+ "12": 307.2964296875,
1235
+ "13": 318.4115390625,
1236
+ "14": 333.137890625,
1237
+ "15": 335.3022890625,
1238
+ "16": 329.080421875,
1239
+ "17": 338.9223984375,
1240
+ "18": 336.208109375,
1241
+ "19": 336.5952578125,
1242
+ "20": 340.1509921875
1243
+ },
1244
+ "per_op_avg_loss": {},
1245
+ "per_op_length": {
1246
+ "10": 281.153859375,
1247
+ "2": 115.629984375,
1248
+ "3": 144.724578125,
1249
+ "4": 159.8816328125,
1250
+ "5": 172.73553125,
1251
+ "6": 198.9245234375,
1252
+ "7": 223.9551328125,
1253
+ "8": 243.5811875,
1254
+ "9": 259.5112734375,
1255
+ "11": 299.1838515625,
1256
+ "12": 307.2964296875,
1257
+ "13": 318.4115390625,
1258
+ "14": 333.137890625,
1259
+ "15": 335.3022890625,
1260
+ "16": 329.080421875,
1261
+ "17": 338.9223984375,
1262
+ "18": 336.208109375,
1263
+ "19": 336.5952578125,
1264
+ "20": 340.1509921875
1265
+ },
1266
+ "per_op_loss": {},
1267
+ "per_template": {
1268
+ "crazy_zootopia": {
1269
+ "count": 809728,
1270
+ "correct": 576855,
1271
+ "answer_accuracy": 0.7124058943250079,
1272
+ "avg_response_len": 256.26435790784063,
1273
+ "resp_tokens_sum": 207504426,
1274
+ "pass_at_k": {
1275
+ "pass@1": 0.7124058943250079,
1276
+ "pass@2": 0.7482848133624225,
1277
+ "pass@4": 0.7797965772724061,
1278
+ "pass@8": 0.8060704977403156,
1279
+ "pass@16": 0.8268832725059063,
1280
+ "pass@32": 0.8434735001446694,
1281
+ "pass@64": 0.8574080645300883,
1282
+ "pass@128": 0.8695858362314258
1283
+ },
1284
+ "per_op_pass_at_k": {
1285
+ "10": {
1286
+ "pass@1": 0.964855272861357,
1287
+ "pass@2": 0.9744083600445962,
1288
+ "pass@4": 0.980863755415529,
1289
+ "pass@8": 0.9845045622809016,
1290
+ "pass@16": 0.9864817601267433,
1291
+ "pass@32": 0.988192742885706,
1292
+ "pass@64": 0.9911504413060571,
1293
+ "pass@128": 0.9970501474926253
1294
+ },
1295
+ "2": {
1296
+ "pass@1": 1.0,
1297
+ "pass@2": 1.0,
1298
+ "pass@4": 1.0,
1299
+ "pass@8": 1.0,
1300
+ "pass@16": 1.0,
1301
+ "pass@32": 1.0,
1302
+ "pass@64": 1.0,
1303
+ "pass@128": 1.0
1304
+ },
1305
+ "3": {
1306
+ "pass@1": 1.0,
1307
+ "pass@2": 1.0,
1308
+ "pass@4": 1.0,
1309
+ "pass@8": 1.0,
1310
+ "pass@16": 1.0,
1311
+ "pass@32": 1.0,
1312
+ "pass@64": 1.0,
1313
+ "pass@128": 1.0
1314
+ },
1315
+ "4": {
1316
+ "pass@1": 1.0,
1317
+ "pass@2": 1.0,
1318
+ "pass@4": 1.0,
1319
+ "pass@8": 1.0,
1320
+ "pass@16": 1.0,
1321
+ "pass@32": 1.0,
1322
+ "pass@64": 1.0,
1323
+ "pass@128": 1.0
1324
+ },
1325
+ "5": {
1326
+ "pass@1": 0.9985367063492063,
1327
+ "pass@2": 0.99933172415948,
1328
+ "pass@4": 0.999864562762988,
1329
+ "pass@8": 0.999995076184736,
1330
+ "pass@16": 0.999999996268659,
1331
+ "pass@32": 1.0,
1332
+ "pass@64": 1.0,
1333
+ "pass@128": 1.0
1334
+ },
1335
+ "6": {
1336
+ "pass@1": 1.0,
1337
+ "pass@2": 1.0,
1338
+ "pass@4": 1.0,
1339
+ "pass@8": 1.0,
1340
+ "pass@16": 1.0,
1341
+ "pass@32": 1.0,
1342
+ "pass@64": 1.0,
1343
+ "pass@128": 1.0
1344
+ },
1345
+ "7": {
1346
+ "pass@1": 0.9997688609467456,
1347
+ "pass@2": 0.9999836200670922,
1348
+ "pass@4": 0.9999999417602385,
1349
+ "pass@8": 0.9999999999999069,
1350
+ "pass@16": 1.0,
1351
+ "pass@32": 1.0,
1352
+ "pass@64": 1.0,
1353
+ "pass@128": 1.0
1354
+ },
1355
+ "8": {
1356
+ "pass@1": 0.999824719551282,
1357
+ "pass@2": 0.9999976340096912,
1358
+ "pass@4": 0.9999999996995569,
1359
+ "pass@8": 1.0,
1360
+ "pass@16": 1.0,
1361
+ "pass@32": 1.0,
1362
+ "pass@64": 1.0,
1363
+ "pass@128": 1.0
1364
+ },
1365
+ "9": {
1366
+ "pass@1": 0.997337147887324,
1367
+ "pass@2": 0.9977261700121991,
1368
+ "pass@4": 0.9981745219347582,
1369
+ "pass@8": 0.9988346121771267,
1370
+ "pass@16": 0.9995479293349335,
1371
+ "pass@32": 0.9999462946812021,
1372
+ "pass@64": 0.9999998252073432,
1373
+ "pass@128": 1.0
1374
+ },
1375
+ "11": {
1376
+ "pass@1": 0.9568431303116147,
1377
+ "pass@2": 0.966704122147621,
1378
+ "pass@4": 0.9737702782725814,
1379
+ "pass@8": 0.9797293556840062,
1380
+ "pass@16": 0.9839171023985908,
1381
+ "pass@32": 0.9864784015256126,
1382
+ "pass@64": 0.9885864447521222,
1383
+ "pass@128": 0.9915014164305949
1384
+ },
1385
+ "12": {
1386
+ "pass@1": 0.8533501059322034,
1387
+ "pass@2": 0.8813041477601309,
1388
+ "pass@4": 0.8969065471688916,
1389
+ "pass@8": 0.9103012428913164,
1390
+ "pass@16": 0.9232330989994582,
1391
+ "pass@32": 0.9356599220900689,
1392
+ "pass@64": 0.9473396438691338,
1393
+ "pass@128": 0.9548022598870056
1394
+ },
1395
+ "13": {
1396
+ "pass@1": 0.760384012539185,
1397
+ "pass@2": 0.8294336077308518,
1398
+ "pass@4": 0.874541486977137,
1399
+ "pass@8": 0.9027689973847379,
1400
+ "pass@16": 0.9198466852847369,
1401
+ "pass@32": 0.9308948171804944,
1402
+ "pass@64": 0.9399058726440269,
1403
+ "pass@128": 0.9498432601880877
1404
+ },
1405
+ "14": {
1406
+ "pass@1": 0.6034852024922118,
1407
+ "pass@2": 0.6929789259695341,
1408
+ "pass@4": 0.7630072742075453,
1409
+ "pass@8": 0.8164932601872855,
1410
+ "pass@16": 0.8526563967709537,
1411
+ "pass@32": 0.8763087593659933,
1412
+ "pass@64": 0.8936422032813724,
1413
+ "pass@128": 0.9065420560747663
1414
+ },
1415
+ "15": {
1416
+ "pass@1": 0.4252619219653179,
1417
+ "pass@2": 0.5253370209594465,
1418
+ "pass@4": 0.6099591160209015,
1419
+ "pass@8": 0.6784789856366449,
1420
+ "pass@16": 0.7314473595873143,
1421
+ "pass@32": 0.7713284427298922,
1422
+ "pass@64": 0.8031345386516523,
1423
+ "pass@128": 0.8294797687861272
1424
+ },
1425
+ "16": {
1426
+ "pass@1": 0.26829637096774195,
1427
+ "pass@2": 0.3590876619253239,
1428
+ "pass@4": 0.44438377874136703,
1429
+ "pass@8": 0.5160205150620084,
1430
+ "pass@16": 0.572072708861716,
1431
+ "pass@32": 0.6173416875891375,
1432
+ "pass@64": 0.6591309169128403,
1433
+ "pass@128": 0.6967741935483871
1434
+ },
1435
+ "17": {
1436
+ "pass@1": 0.210305274566474,
1437
+ "pass@2": 0.2880021534067633,
1438
+ "pass@4": 0.36638274885075767,
1439
+ "pass@8": 0.4354115772958514,
1440
+ "pass@16": 0.4924820483803051,
1441
+ "pass@32": 0.5414044485040482,
1442
+ "pass@64": 0.5843553236837202,
1443
+ "pass@128": 0.6242774566473989
1444
+ },
1445
+ "18": {
1446
+ "pass@1": 0.19066964285714286,
1447
+ "pass@2": 0.2540649606299211,
1448
+ "pass@4": 0.3153792696448659,
1449
+ "pass@8": 0.3744374956178368,
1450
+ "pass@16": 0.4304686242139373,
1451
+ "pass@32": 0.4799023237679476,
1452
+ "pass@64": 0.5191885486106175,
1453
+ "pass@128": 0.5485714285714286
1454
+ },
1455
+ "19": {
1456
+ "pass@1": 0.17203922672672672,
1457
+ "pass@2": 0.2452760339079237,
1458
+ "pass@4": 0.31713847114831356,
1459
+ "pass@8": 0.3807029920118585,
1460
+ "pass@16": 0.43294372077217796,
1461
+ "pass@32": 0.47306262676523364,
1462
+ "pass@64": 0.5035309613007347,
1463
+ "pass@128": 0.5315315315315315
1464
+ },
1465
+ "20": {
1466
+ "pass@1": 0.16786317567567569,
1467
+ "pass@2": 0.23649646201319421,
1468
+ "pass@4": 0.3076818460755471,
1469
+ "pass@8": 0.3678730399252492,
1470
+ "pass@16": 0.41342134802722214,
1471
+ "pass@32": 0.450621229184501,
1472
+ "pass@64": 0.48393762875113866,
1473
+ "pass@128": 0.5135135135135135
1474
+ }
1475
+ }
1476
+ },
1477
+ "teachers_in_school": {
1478
+ "count": 821120,
1479
+ "correct": 578426,
1480
+ "answer_accuracy": 0.704435405300078,
1481
+ "avg_response_len": 263.05899381332813,
1482
+ "resp_tokens_sum": 216003001,
1483
+ "pass_at_k": {
1484
+ "pass@1": 0.704435405300078,
1485
+ "pass@2": 0.7394285546608842,
1486
+ "pass@4": 0.7702634267559836,
1487
+ "pass@8": 0.7961202574484137,
1488
+ "pass@16": 0.8169219087902136,
1489
+ "pass@32": 0.8337421048859038,
1490
+ "pass@64": 0.8480070379164071,
1491
+ "pass@128": 0.8607950116913484
1492
+ },
1493
+ "per_op_pass_at_k": {
1494
+ "10": {
1495
+ "pass@1": 0.9569833205521472,
1496
+ "pass@2": 0.9659142372349164,
1497
+ "pass@4": 0.9719421844700393,
1498
+ "pass@8": 0.9748675318830776,
1499
+ "pass@16": 0.9757861748653367,
1500
+ "pass@32": 0.9762266888126843,
1501
+ "pass@64": 0.9769938650304216,
1502
+ "pass@128": 0.9785276073619632
1503
+ },
1504
+ "2": {
1505
+ "pass@1": 1.0,
1506
+ "pass@2": 1.0,
1507
+ "pass@4": 1.0,
1508
+ "pass@8": 1.0,
1509
+ "pass@16": 1.0,
1510
+ "pass@32": 1.0,
1511
+ "pass@64": 1.0,
1512
+ "pass@128": 1.0
1513
+ },
1514
+ "3": {
1515
+ "pass@1": 1.0,
1516
+ "pass@2": 1.0,
1517
+ "pass@4": 1.0,
1518
+ "pass@8": 1.0,
1519
+ "pass@16": 1.0,
1520
+ "pass@32": 1.0,
1521
+ "pass@64": 1.0,
1522
+ "pass@128": 1.0
1523
+ },
1524
+ "4": {
1525
+ "pass@1": 1.0,
1526
+ "pass@2": 1.0,
1527
+ "pass@4": 1.0,
1528
+ "pass@8": 1.0,
1529
+ "pass@16": 1.0,
1530
+ "pass@32": 1.0,
1531
+ "pass@64": 1.0,
1532
+ "pass@128": 1.0
1533
+ },
1534
+ "5": {
1535
+ "pass@1": 0.9998414855072464,
1536
+ "pass@2": 0.9999967904827115,
1537
+ "pass@4": 0.9999999997282949,
1538
+ "pass@8": 1.0,
1539
+ "pass@16": 1.0,
1540
+ "pass@32": 1.0,
1541
+ "pass@64": 1.0,
1542
+ "pass@128": 1.0
1543
+ },
1544
+ "6": {
1545
+ "pass@1": 0.9999776146131805,
1546
+ "pass@2": 1.0,
1547
+ "pass@4": 1.0,
1548
+ "pass@8": 1.0,
1549
+ "pass@16": 1.0,
1550
+ "pass@32": 1.0,
1551
+ "pass@64": 1.0,
1552
+ "pass@128": 1.0
1553
+ },
1554
+ "7": {
1555
+ "pass@1": 1.0,
1556
+ "pass@2": 1.0,
1557
+ "pass@4": 1.0,
1558
+ "pass@8": 1.0,
1559
+ "pass@16": 1.0,
1560
+ "pass@32": 1.0,
1561
+ "pass@64": 1.0,
1562
+ "pass@128": 1.0
1563
+ },
1564
+ "8": {
1565
+ "pass@1": 0.9948283450704225,
1566
+ "pass@2": 0.9955154153266054,
1567
+ "pass@4": 0.9962789690901313,
1568
+ "pass@8": 0.9971273245981712,
1569
+ "pass@16": 0.997797475275284,
1570
+ "pass@32": 0.9984192527437615,
1571
+ "pass@64": 0.9993013197287653,
1572
+ "pass@128": 1.0
1573
+ },
1574
+ "9": {
1575
+ "pass@1": 0.9957662799401198,
1576
+ "pass@2": 0.9974428603423076,
1577
+ "pass@4": 0.9988750589372435,
1578
+ "pass@8": 0.9997585789040461,
1579
+ "pass@16": 0.9999876161726882,
1580
+ "pass@32": 0.9999999824517899,
1581
+ "pass@64": 0.9999999999999998,
1582
+ "pass@128": 1.0
1583
+ },
1584
+ "11": {
1585
+ "pass@1": 0.9643731174698795,
1586
+ "pass@2": 0.9750883455080163,
1587
+ "pass@4": 0.9803072865138847,
1588
+ "pass@8": 0.9823661486047269,
1589
+ "pass@16": 0.9832962407555205,
1590
+ "pass@32": 0.9844320989052803,
1591
+ "pass@64": 0.9860781709515227,
1592
+ "pass@128": 0.9879518072289156
1593
+ },
1594
+ "12": {
1595
+ "pass@1": 0.8863636363636364,
1596
+ "pass@2": 0.9133642287660749,
1597
+ "pass@4": 0.9258904760729354,
1598
+ "pass@8": 0.9354300779654707,
1599
+ "pass@16": 0.945221377305145,
1600
+ "pass@32": 0.9540520042583904,
1601
+ "pass@64": 0.9598380142135106,
1602
+ "pass@128": 0.9623824451410659
1603
+ },
1604
+ "13": {
1605
+ "pass@1": 0.6867997198879552,
1606
+ "pass@2": 0.7681042397273864,
1607
+ "pass@4": 0.824483724986057,
1608
+ "pass@8": 0.8627893286369971,
1609
+ "pass@16": 0.8897924787212615,
1610
+ "pass@32": 0.9118141519741789,
1611
+ "pass@64": 0.9305813041850224,
1612
+ "pass@128": 0.9439775910364145
1613
+ },
1614
+ "14": {
1615
+ "pass@1": 0.5445906432748538,
1616
+ "pass@2": 0.6282847970483952,
1617
+ "pass@4": 0.6919824232497251,
1618
+ "pass@8": 0.7401227434606403,
1619
+ "pass@16": 0.7772650766591268,
1620
+ "pass@32": 0.8067142511689581,
1621
+ "pass@64": 0.8289431092869494,
1622
+ "pass@128": 0.8450292397660819
1623
+ },
1624
+ "15": {
1625
+ "pass@1": 0.3677556818181818,
1626
+ "pass@2": 0.4612525351944643,
1627
+ "pass@4": 0.5395015228210107,
1628
+ "pass@8": 0.6038984673310392,
1629
+ "pass@16": 0.6548475782041733,
1630
+ "pass@32": 0.695211253240757,
1631
+ "pass@64": 0.7307349783554408,
1632
+ "pass@128": 0.7636363636363637
1633
+ },
1634
+ "16": {
1635
+ "pass@1": 0.23595530626780628,
1636
+ "pass@2": 0.30808173217129914,
1637
+ "pass@4": 0.37879288913672104,
1638
+ "pass@8": 0.44199327843430775,
1639
+ "pass@16": 0.49717687261406224,
1640
+ "pass@32": 0.5475518095537767,
1641
+ "pass@64": 0.5956511172414417,
1642
+ "pass@128": 0.6410256410256411
1643
+ },
1644
+ "17": {
1645
+ "pass@1": 0.23090547360248448,
1646
+ "pass@2": 0.31294512948109743,
1647
+ "pass@4": 0.3923752244478753,
1648
+ "pass@8": 0.4620048777355182,
1649
+ "pass@16": 0.5184937076070995,
1650
+ "pass@32": 0.5641996443460395,
1651
+ "pass@64": 0.6058905683329744,
1652
+ "pass@128": 0.6490683229813664
1653
+ },
1654
+ "18": {
1655
+ "pass@1": 0.19181985294117648,
1656
+ "pass@2": 0.2639264416396479,
1657
+ "pass@4": 0.3402037715873749,
1658
+ "pass@8": 0.41292313703410055,
1659
+ "pass@16": 0.4755867515992984,
1660
+ "pass@32": 0.5242663505584598,
1661
+ "pass@64": 0.5607374408176437,
1662
+ "pass@128": 0.5911764705882353
1663
+ },
1664
+ "19": {
1665
+ "pass@1": 0.17740885416666666,
1666
+ "pass@2": 0.24643025578833894,
1667
+ "pass@4": 0.3146818307867766,
1668
+ "pass@8": 0.37225657621985075,
1669
+ "pass@16": 0.4180985090398595,
1670
+ "pass@32": 0.4553241566350863,
1671
+ "pass@64": 0.48681976016382017,
1672
+ "pass@128": 0.5178571428571429
1673
+ },
1674
+ "20": {
1675
+ "pass@1": 0.1394320733532934,
1676
+ "pass@2": 0.2010787725729644,
1677
+ "pass@4": 0.26803790703183067,
1678
+ "pass@8": 0.32950827537338695,
1679
+ "pass@16": 0.37733200724855503,
1680
+ "pass@32": 0.4121459313058152,
1681
+ "pass@64": 0.43980782684006975,
1682
+ "pass@128": 0.46407185628742514
1683
+ }
1684
+ }
1685
+ },
1686
+ "movie_festival_awards": {
1687
+ "count": 801152,
1688
+ "correct": 562834,
1689
+ "answer_accuracy": 0.7025308555679821,
1690
+ "avg_response_len": 282.1113771169516,
1691
+ "resp_tokens_sum": 226014094,
1692
+ "pass_at_k": {
1693
+ "pass@1": 0.7025308555679821,
1694
+ "pass@2": 0.736340083665345,
1695
+ "pass@4": 0.7661264757077474,
1696
+ "pass@8": 0.791289508043559,
1697
+ "pass@16": 0.8116318796222768,
1698
+ "pass@32": 0.8281989841030529,
1699
+ "pass@64": 0.8425176638526883,
1700
+ "pass@128": 0.8555679821057677
1701
+ },
1702
+ "per_op_pass_at_k": {
1703
+ "10": {
1704
+ "pass@1": 0.9654617537313432,
1705
+ "pass@2": 0.974182483253026,
1706
+ "pass@4": 0.9814832566638125,
1707
+ "pass@8": 0.9865134381095033,
1708
+ "pass@16": 0.990010567366735,
1709
+ "pass@32": 0.9930920761226464,
1710
+ "pass@64": 0.9962352974533647,
1711
+ "pass@128": 1.0
1712
+ },
1713
+ "2": {
1714
+ "pass@1": 1.0,
1715
+ "pass@2": 1.0,
1716
+ "pass@4": 1.0,
1717
+ "pass@8": 1.0,
1718
+ "pass@16": 1.0,
1719
+ "pass@32": 1.0,
1720
+ "pass@64": 1.0,
1721
+ "pass@128": 1.0
1722
+ },
1723
+ "3": {
1724
+ "pass@1": 1.0,
1725
+ "pass@2": 1.0,
1726
+ "pass@4": 1.0,
1727
+ "pass@8": 1.0,
1728
+ "pass@16": 1.0,
1729
+ "pass@32": 1.0,
1730
+ "pass@64": 1.0,
1731
+ "pass@128": 1.0
1732
+ },
1733
+ "4": {
1734
+ "pass@1": 1.0,
1735
+ "pass@2": 1.0,
1736
+ "pass@4": 1.0,
1737
+ "pass@8": 1.0,
1738
+ "pass@16": 1.0,
1739
+ "pass@32": 1.0,
1740
+ "pass@64": 1.0,
1741
+ "pass@128": 1.0
1742
+ },
1743
+ "5": {
1744
+ "pass@1": 0.9999080882352941,
1745
+ "pass@2": 0.9999992762853173,
1746
+ "pass@4": 1.0,
1747
+ "pass@8": 1.0,
1748
+ "pass@16": 1.0,
1749
+ "pass@32": 1.0,
1750
+ "pass@64": 1.0,
1751
+ "pass@128": 1.0
1752
+ },
1753
+ "6": {
1754
+ "pass@1": 1.0,
1755
+ "pass@2": 1.0,
1756
+ "pass@4": 1.0,
1757
+ "pass@8": 1.0,
1758
+ "pass@16": 1.0,
1759
+ "pass@32": 1.0,
1760
+ "pass@64": 1.0,
1761
+ "pass@128": 1.0
1762
+ },
1763
+ "7": {
1764
+ "pass@1": 0.9999258306962026,
1765
+ "pass@2": 1.0,
1766
+ "pass@4": 1.0,
1767
+ "pass@8": 1.0,
1768
+ "pass@16": 1.0,
1769
+ "pass@32": 1.0,
1770
+ "pass@64": 1.0,
1771
+ "pass@128": 1.0
1772
+ },
1773
+ "8": {
1774
+ "pass@1": 0.9954016516516516,
1775
+ "pass@2": 0.9980015694828687,
1776
+ "pass@4": 0.9994780266768457,
1777
+ "pass@8": 0.9999541707109151,
1778
+ "pass@16": 0.9999996450540588,
1779
+ "pass@32": 0.9999999999945218,
1780
+ "pass@64": 1.0,
1781
+ "pass@128": 1.0
1782
+ },
1783
+ "9": {
1784
+ "pass@1": 0.994599075562701,
1785
+ "pass@2": 0.9959007962630074,
1786
+ "pass@4": 0.9973834390074231,
1787
+ "pass@8": 0.9989100635493507,
1788
+ "pass@16": 0.9998018508583297,
1789
+ "pass@32": 0.9999941260810753,
1790
+ "pass@64": 0.9999999994727716,
1791
+ "pass@128": 1.0
1792
+ },
1793
+ "11": {
1794
+ "pass@1": 0.9669642857142857,
1795
+ "pass@2": 0.977667635295588,
1796
+ "pass@4": 0.9834914713041819,
1797
+ "pass@8": 0.987697919919454,
1798
+ "pass@16": 0.9903756780268099,
1799
+ "pass@32": 0.9920980050763724,
1800
+ "pass@64": 0.9932587543558059,
1801
+ "pass@128": 0.9936507936507937
1802
+ },
1803
+ "12": {
1804
+ "pass@1": 0.8925602064220184,
1805
+ "pass@2": 0.927709778106865,
1806
+ "pass@4": 0.9466711294115757,
1807
+ "pass@8": 0.9594735205095442,
1808
+ "pass@16": 0.968631391961948,
1809
+ "pass@32": 0.9747149407936225,
1810
+ "pass@64": 0.9783565974863963,
1811
+ "pass@128": 0.981651376146789
1812
+ },
1813
+ "13": {
1814
+ "pass@1": 0.6791087962962963,
1815
+ "pass@2": 0.7509379252940609,
1816
+ "pass@4": 0.8003636541960031,
1817
+ "pass@8": 0.836590700158435,
1818
+ "pass@16": 0.8634558161248805,
1819
+ "pass@32": 0.8838359924574606,
1820
+ "pass@64": 0.8998857884792347,
1821
+ "pass@128": 0.9135802469135802
1822
+ },
1823
+ "14": {
1824
+ "pass@1": 0.5279349035608308,
1825
+ "pass@2": 0.6192675354564355,
1826
+ "pass@4": 0.6896984853896232,
1827
+ "pass@8": 0.7423055698396044,
1828
+ "pass@16": 0.7843204109962838,
1829
+ "pass@32": 0.8204913013870107,
1830
+ "pass@64": 0.8477207957073809,
1831
+ "pass@128": 0.8664688427299704
1832
+ },
1833
+ "15": {
1834
+ "pass@1": 0.36140046296296297,
1835
+ "pass@2": 0.4426244137017595,
1836
+ "pass@4": 0.5132164547139938,
1837
+ "pass@8": 0.5721977881442194,
1838
+ "pass@16": 0.6197088824105395,
1839
+ "pass@32": 0.658967059013711,
1840
+ "pass@64": 0.6955853807708048,
1841
+ "pass@128": 0.7345679012345679
1842
+ },
1843
+ "16": {
1844
+ "pass@1": 0.21766685103244837,
1845
+ "pass@2": 0.2878512385896452,
1846
+ "pass@4": 0.35677422180634516,
1847
+ "pass@8": 0.4192935319550409,
1848
+ "pass@16": 0.4744116086421201,
1849
+ "pass@32": 0.5235822279834264,
1850
+ "pass@64": 0.5713460103429768,
1851
+ "pass@128": 0.6194690265486725
1852
+ },
1853
+ "17": {
1854
+ "pass@1": 0.19837161144578314,
1855
+ "pass@2": 0.26883901254624787,
1856
+ "pass@4": 0.33928608895650064,
1857
+ "pass@8": 0.40176271614166426,
1858
+ "pass@16": 0.4530815948293738,
1859
+ "pass@32": 0.49619312239293656,
1860
+ "pass@64": 0.536260897714176,
1861
+ "pass@128": 0.5692771084337349
1862
+ },
1863
+ "18": {
1864
+ "pass@1": 0.19788306451612903,
1865
+ "pass@2": 0.2630076041402083,
1866
+ "pass@4": 0.3281824866649735,
1867
+ "pass@8": 0.38767325712032175,
1868
+ "pass@16": 0.4352260441352987,
1869
+ "pass@32": 0.47043974442309966,
1870
+ "pass@64": 0.4992493451488665,
1871
+ "pass@128": 0.5258064516129032
1872
+ },
1873
+ "19": {
1874
+ "pass@1": 0.17987632175226587,
1875
+ "pass@2": 0.247976856697671,
1876
+ "pass@4": 0.3147488179347673,
1877
+ "pass@8": 0.37247260884174876,
1878
+ "pass@16": 0.41889090519709676,
1879
+ "pass@32": 0.45572123675521775,
1880
+ "pass@64": 0.4860676102567291,
1881
+ "pass@128": 0.513595166163142
1882
+ },
1883
+ "20": {
1884
+ "pass@1": 0.15899493243243243,
1885
+ "pass@2": 0.2257040505071999,
1886
+ "pass@4": 0.29573212638960666,
1887
+ "pass@8": 0.3606103751183562,
1888
+ "pass@16": 0.41446968279744983,
1889
+ "pass@32": 0.457917316065741,
1890
+ "pass@64": 0.49484972985591286,
1891
+ "pass@128": 0.5285285285285285
1892
+ }
1893
+ }
1894
+ }
1895
+ }
1896
+ }
1897
+ }
Qwen3-100M-ep4/composition/checkpoint-85276_ood_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2abdb12f6d038b927e060a53ec87dfd2305d556b14c3e117c4aad58035dc74fc
3
+ size 2568335013
Qwen3-100M-ep4/composition/graphs/checkpoint-85276_ood_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0faae406ec3d46534b09ef38089b687062513477f9ef33d60d9610f09b4b1fa
3
+ size 443430559
Qwen3-100M-ep4/composition/graphs/composition_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/composition/op-difficulty-10B/graphs", "generated_path": "results/Qwen3-100M-ep4/composition", "results_dir": "results/Qwen3-100M-ep4/composition/graphs", "per_file": [{"file": "results/Qwen3-100M-ep4/composition/checkpoint-85276_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1026138, "value_mismatch": 6602, "dependency_mismatch": 124380, "answer_mismatch": 5840, "extra_nodes": 8258, "missing_nodes": 8221, "perfect_with_extra": 86, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 338323, "value_mismatch": 2010, "answer_mismatch": 1722, "dependency_mismatch": 40374, "extra_nodes": 2856, "missing_nodes": 2819, "perfect_with_extra": 16}, "teachers_in_school": {"total": 390656, "perfect": 347450, "value_mismatch": 2410, "dependency_mismatch": 42575, "answer_mismatch": 2219, "missing_nodes": 2895, "extra_nodes": 2905, "perfect_with_extra": 8}, "movie_festival_awards": {"total": 382336, "perfect": 340365, "dependency_mismatch": 41431, "value_mismatch": 2182, "answer_mismatch": 1899, "extra_nodes": 2497, "missing_nodes": 2507, "perfect_with_extra": 62}}, "results_path": "results/Qwen3-100M-ep4/composition/graphs/checkpoint-85276_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/Qwen3-100M-ep4/composition/checkpoint-85276_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 258020, "value_mismatch": 824338, "dependency_mismatch": 998879, "answer_mismatch": 708052, "extra_nodes": 67333, "missing_nodes": 765676, "perfect_with_extra": 19, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "value_mismatch": 270906, "dependency_mismatch": 331115, "answer_mismatch": 231155, "perfect": 91646, "extra_nodes": 25775, "missing_nodes": 243669, "perfect_with_extra": 4}, "movie_festival_awards": {"total": 418816, "perfect": 80786, "value_mismatch": 274419, "dependency_mismatch": 330693, "answer_mismatch": 236421, "missing_nodes": 258294, "extra_nodes": 21013, "perfect_with_extra": 15}, "teachers_in_school": {"total": 430464, "perfect": 85588, "value_mismatch": 279013, "answer_mismatch": 240476, "dependency_mismatch": 337071, "extra_nodes": 20545, "missing_nodes": 263713}}, "results_path": "results/Qwen3-100M-ep4/composition/graphs/checkpoint-85276_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1284158, "value_mismatch": 830940, "dependency_mismatch": 1123259, "answer_mismatch": 713892, "extra_nodes": 75591, "missing_nodes": 773897, "perfect_with_extra": 105, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/Qwen3-100M-ep4/composition/graphs/composition_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 429969, "value_mismatch": 272916, "answer_mismatch": 232877, "dependency_mismatch": 371489, "extra_nodes": 28631, "missing_nodes": 246488, "perfect_with_extra": 20}, "teachers_in_school": {"total": 821120, "perfect": 433038, "value_mismatch": 281423, "dependency_mismatch": 379646, "answer_mismatch": 242695, "missing_nodes": 266608, "extra_nodes": 23450, "perfect_with_extra": 8}, "movie_festival_awards": {"total": 801152, "perfect": 421151, "dependency_mismatch": 372124, "value_mismatch": 276601, "answer_mismatch": 238320, "extra_nodes": 23510, "missing_nodes": 260801, "perfect_with_extra": 77}}}}
Qwen3-100M-ep4/composition/graphs/results.json ADDED
@@ -0,0 +1,1780 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "checkpoint-85276_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "crazy_zootopia": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 1.0,
9
+ "pass@2": 1.0,
10
+ "pass@4": 1.0,
11
+ "pass@8": 1.0,
12
+ "pass@16": 1.0,
13
+ "pass@32": 1.0,
14
+ "pass@64": 1.0,
15
+ "pass@128": 1.0
16
+ },
17
+ "3": {
18
+ "pass@1": 1.0,
19
+ "pass@2": 1.0,
20
+ "pass@4": 1.0,
21
+ "pass@8": 1.0,
22
+ "pass@16": 1.0,
23
+ "pass@32": 1.0,
24
+ "pass@64": 1.0,
25
+ "pass@128": 1.0
26
+ },
27
+ "4": {
28
+ "pass@1": 0.99375,
29
+ "pass@2": 0.996875,
30
+ "pass@4": 1.0,
31
+ "pass@8": 1.0,
32
+ "pass@16": 1.0,
33
+ "pass@32": 1.0,
34
+ "pass@64": 1.0,
35
+ "pass@128": 1.0
36
+ },
37
+ "5": {
38
+ "pass@1": 0.9555555555555556,
39
+ "pass@2": 0.9746031746031746,
40
+ "pass@4": 0.9904761904761905,
41
+ "pass@8": 0.9968253968253968,
42
+ "pass@16": 0.9968253968253968,
43
+ "pass@32": 0.9968253968253968,
44
+ "pass@64": 0.9968253968253968,
45
+ "pass@128": 0.9968253968253968
46
+ },
47
+ "6": {
48
+ "pass@1": 0.9640718562874252,
49
+ "pass@2": 0.9850299401197605,
50
+ "pass@4": 1.0,
51
+ "pass@8": 1.0,
52
+ "pass@16": 1.0,
53
+ "pass@32": 1.0,
54
+ "pass@64": 1.0,
55
+ "pass@128": 1.0
56
+ },
57
+ "7": {
58
+ "pass@1": 0.8994082840236687,
59
+ "pass@2": 0.9437869822485208,
60
+ "pass@4": 0.9644970414201184,
61
+ "pass@8": 0.985207100591716,
62
+ "pass@16": 0.9970414201183432,
63
+ "pass@32": 1.0,
64
+ "pass@64": 1.0,
65
+ "pass@128": 1.0
66
+ },
67
+ "8": {
68
+ "pass@1": 0.8301282051282052,
69
+ "pass@2": 0.8910256410256411,
70
+ "pass@4": 0.9391025641025641,
71
+ "pass@8": 0.9743589743589743,
72
+ "pass@16": 0.9903846153846154,
73
+ "pass@32": 1.0,
74
+ "pass@64": 1.0,
75
+ "pass@128": 1.0
76
+ },
77
+ "9": {
78
+ "pass@1": 0.7436619718309859,
79
+ "pass@2": 0.819718309859155,
80
+ "pass@4": 0.9014084507042254,
81
+ "pass@8": 0.9577464788732394,
82
+ "pass@16": 0.9915492957746479,
83
+ "pass@32": 0.9971830985915493,
84
+ "pass@64": 1.0,
85
+ "pass@128": 1.0
86
+ },
87
+ "10": {
88
+ "pass@1": 0.6666666666666666,
89
+ "pass@2": 0.7374631268436578,
90
+ "pass@4": 0.8082595870206489,
91
+ "pass@8": 0.8790560471976401,
92
+ "pass@16": 0.9262536873156342,
93
+ "pass@32": 0.9557522123893806,
94
+ "pass@64": 0.9646017699115044,
95
+ "pass@128": 0.9734513274336283
96
+ }
97
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 1.0,
101
+ "3": 1.0,
102
+ "4": 0.99375,
103
+ "5": 0.9555555555555556,
104
+ "6": 0.9640718562874252,
105
+ "7": 0.8994082840236687,
106
+ "8": 0.8301282051282052,
107
+ "9": 0.7436619718309859,
108
+ "10": 0.6666666666666666
109
+ },
110
+ "pass@2": {
111
+ "2": 1.0,
112
+ "3": 1.0,
113
+ "4": 0.996875,
114
+ "5": 0.9746031746031746,
115
+ "6": 0.9850299401197605,
116
+ "7": 0.9437869822485208,
117
+ "8": 0.8910256410256411,
118
+ "9": 0.819718309859155,
119
+ "10": 0.7374631268436578
120
+ },
121
+ "pass@4": {
122
+ "2": 1.0,
123
+ "3": 1.0,
124
+ "4": 1.0,
125
+ "5": 0.9904761904761905,
126
+ "6": 1.0,
127
+ "7": 0.9644970414201184,
128
+ "8": 0.9391025641025641,
129
+ "9": 0.9014084507042254,
130
+ "10": 0.8082595870206489
131
+ },
132
+ "pass@8": {
133
+ "2": 1.0,
134
+ "3": 1.0,
135
+ "4": 1.0,
136
+ "5": 0.9968253968253968,
137
+ "6": 1.0,
138
+ "7": 0.985207100591716,
139
+ "8": 0.9743589743589743,
140
+ "9": 0.9577464788732394,
141
+ "10": 0.8790560471976401
142
+ },
143
+ "pass@16": {
144
+ "2": 1.0,
145
+ "3": 1.0,
146
+ "4": 1.0,
147
+ "5": 0.9968253968253968,
148
+ "6": 1.0,
149
+ "7": 0.9970414201183432,
150
+ "8": 0.9903846153846154,
151
+ "9": 0.9915492957746479,
152
+ "10": 0.9262536873156342
153
+ },
154
+ "pass@32": {
155
+ "2": 1.0,
156
+ "3": 1.0,
157
+ "4": 1.0,
158
+ "5": 0.9968253968253968,
159
+ "6": 1.0,
160
+ "7": 1.0,
161
+ "8": 1.0,
162
+ "9": 0.9971830985915493,
163
+ "10": 0.9557522123893806
164
+ },
165
+ "pass@64": {
166
+ "2": 1.0,
167
+ "3": 1.0,
168
+ "4": 1.0,
169
+ "5": 0.9968253968253968,
170
+ "6": 1.0,
171
+ "7": 1.0,
172
+ "8": 1.0,
173
+ "9": 1.0,
174
+ "10": 0.9646017699115044
175
+ },
176
+ "pass@128": {
177
+ "2": 1.0,
178
+ "3": 1.0,
179
+ "4": 1.0,
180
+ "5": 0.9968253968253968,
181
+ "6": 1.0,
182
+ "7": 1.0,
183
+ "8": 1.0,
184
+ "9": 1.0,
185
+ "10": 0.9734513274336283
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.8922661263086795,
190
+ "pass@2": 0.9257007767646066,
191
+ "pass@4": 0.9547450185748058,
192
+ "pass@8": 0.9763593380614657,
193
+ "pass@16": 0.9888551165146909,
194
+ "pass@32": 0.994258696386356,
195
+ "pass@64": 0.9956095913542722,
196
+ "pass@128": 0.9966227625802094
197
+ }
198
+ },
199
+ "movie_festival_awards": {
200
+ "per_op_pass_at_k": {
201
+ "2": {
202
+ "pass@1": 1.0,
203
+ "pass@2": 1.0,
204
+ "pass@4": 1.0,
205
+ "pass@8": 1.0,
206
+ "pass@16": 1.0,
207
+ "pass@32": 1.0,
208
+ "pass@64": 1.0,
209
+ "pass@128": 1.0
210
+ },
211
+ "3": {
212
+ "pass@1": 1.0,
213
+ "pass@2": 1.0,
214
+ "pass@4": 1.0,
215
+ "pass@8": 1.0,
216
+ "pass@16": 1.0,
217
+ "pass@32": 1.0,
218
+ "pass@64": 1.0,
219
+ "pass@128": 1.0
220
+ },
221
+ "4": {
222
+ "pass@1": 0.9912280701754386,
223
+ "pass@2": 1.0,
224
+ "pass@4": 1.0,
225
+ "pass@8": 1.0,
226
+ "pass@16": 1.0,
227
+ "pass@32": 1.0,
228
+ "pass@64": 1.0,
229
+ "pass@128": 1.0
230
+ },
231
+ "5": {
232
+ "pass@1": 0.9558823529411765,
233
+ "pass@2": 0.9705882352941176,
234
+ "pass@4": 0.9941176470588236,
235
+ "pass@8": 1.0,
236
+ "pass@16": 1.0,
237
+ "pass@32": 1.0,
238
+ "pass@64": 1.0,
239
+ "pass@128": 1.0
240
+ },
241
+ "6": {
242
+ "pass@1": 0.9684542586750788,
243
+ "pass@2": 0.9747634069400631,
244
+ "pass@4": 0.9873817034700315,
245
+ "pass@8": 0.9936908517350158,
246
+ "pass@16": 1.0,
247
+ "pass@32": 1.0,
248
+ "pass@64": 1.0,
249
+ "pass@128": 1.0
250
+ },
251
+ "7": {
252
+ "pass@1": 0.879746835443038,
253
+ "pass@2": 0.9145569620253164,
254
+ "pass@4": 0.9493670886075949,
255
+ "pass@8": 0.9841772151898734,
256
+ "pass@16": 0.9968354430379747,
257
+ "pass@32": 1.0,
258
+ "pass@64": 1.0,
259
+ "pass@128": 1.0
260
+ },
261
+ "8": {
262
+ "pass@1": 0.8048048048048048,
263
+ "pass@2": 0.8678678678678678,
264
+ "pass@4": 0.93993993993994,
265
+ "pass@8": 0.96996996996997,
266
+ "pass@16": 0.996996996996997,
267
+ "pass@32": 1.0,
268
+ "pass@64": 1.0,
269
+ "pass@128": 1.0
270
+ },
271
+ "9": {
272
+ "pass@1": 0.7620578778135049,
273
+ "pass@2": 0.8392282958199357,
274
+ "pass@4": 0.9003215434083601,
275
+ "pass@8": 0.9453376205787781,
276
+ "pass@16": 0.9678456591639871,
277
+ "pass@32": 0.9935691318327974,
278
+ "pass@64": 1.0,
279
+ "pass@128": 1.0
280
+ },
281
+ "10": {
282
+ "pass@1": 0.608955223880597,
283
+ "pass@2": 0.6746268656716418,
284
+ "pass@4": 0.7671641791044777,
285
+ "pass@8": 0.8567164179104477,
286
+ "pass@16": 0.9074626865671642,
287
+ "pass@32": 0.9432835820895522,
288
+ "pass@64": 0.9641791044776119,
289
+ "pass@128": 0.9671641791044776
290
+ }
291
+ },
292
+ "per_op_pass_at_columns": {
293
+ "pass@1": {
294
+ "2": 1.0,
295
+ "3": 1.0,
296
+ "4": 0.9912280701754386,
297
+ "5": 0.9558823529411765,
298
+ "6": 0.9684542586750788,
299
+ "7": 0.879746835443038,
300
+ "8": 0.8048048048048048,
301
+ "9": 0.7620578778135049,
302
+ "10": 0.608955223880597
303
+ },
304
+ "pass@2": {
305
+ "2": 1.0,
306
+ "3": 1.0,
307
+ "4": 1.0,
308
+ "5": 0.9705882352941176,
309
+ "6": 0.9747634069400631,
310
+ "7": 0.9145569620253164,
311
+ "8": 0.8678678678678678,
312
+ "9": 0.8392282958199357,
313
+ "10": 0.6746268656716418
314
+ },
315
+ "pass@4": {
316
+ "2": 1.0,
317
+ "3": 1.0,
318
+ "4": 1.0,
319
+ "5": 0.9941176470588236,
320
+ "6": 0.9873817034700315,
321
+ "7": 0.9493670886075949,
322
+ "8": 0.93993993993994,
323
+ "9": 0.9003215434083601,
324
+ "10": 0.7671641791044777
325
+ },
326
+ "pass@8": {
327
+ "2": 1.0,
328
+ "3": 1.0,
329
+ "4": 1.0,
330
+ "5": 1.0,
331
+ "6": 0.9936908517350158,
332
+ "7": 0.9841772151898734,
333
+ "8": 0.96996996996997,
334
+ "9": 0.9453376205787781,
335
+ "10": 0.8567164179104477
336
+ },
337
+ "pass@16": {
338
+ "2": 1.0,
339
+ "3": 1.0,
340
+ "4": 1.0,
341
+ "5": 1.0,
342
+ "6": 1.0,
343
+ "7": 0.9968354430379747,
344
+ "8": 0.996996996996997,
345
+ "9": 0.9678456591639871,
346
+ "10": 0.9074626865671642
347
+ },
348
+ "pass@32": {
349
+ "2": 1.0,
350
+ "3": 1.0,
351
+ "4": 1.0,
352
+ "5": 1.0,
353
+ "6": 1.0,
354
+ "7": 1.0,
355
+ "8": 1.0,
356
+ "9": 0.9935691318327974,
357
+ "10": 0.9432835820895522
358
+ },
359
+ "pass@64": {
360
+ "2": 1.0,
361
+ "3": 1.0,
362
+ "4": 1.0,
363
+ "5": 1.0,
364
+ "6": 1.0,
365
+ "7": 1.0,
366
+ "8": 1.0,
367
+ "9": 1.0,
368
+ "10": 0.9641791044776119
369
+ },
370
+ "pass@128": {
371
+ "2": 1.0,
372
+ "3": 1.0,
373
+ "4": 1.0,
374
+ "5": 1.0,
375
+ "6": 1.0,
376
+ "7": 1.0,
377
+ "8": 1.0,
378
+ "9": 1.0,
379
+ "10": 0.9671641791044776
380
+ }
381
+ },
382
+ "total_pass_at_k": {
383
+ "pass@1": 0.8875125544024104,
384
+ "pass@2": 0.916973552058922,
385
+ "pass@4": 0.9494476062939404,
386
+ "pass@8": 0.9725477067291597,
387
+ "pass@16": 0.9856042852360227,
388
+ "pass@32": 0.9929695346501507,
389
+ "pass@64": 0.9959825912286575,
390
+ "pass@128": 0.9963173752929361
391
+ }
392
+ },
393
+ "teachers_in_school": {
394
+ "per_op_pass_at_k": {
395
+ "2": {
396
+ "pass@1": 1.0,
397
+ "pass@2": 1.0,
398
+ "pass@4": 1.0,
399
+ "pass@8": 1.0,
400
+ "pass@16": 1.0,
401
+ "pass@32": 1.0,
402
+ "pass@64": 1.0,
403
+ "pass@128": 1.0
404
+ },
405
+ "3": {
406
+ "pass@1": 1.0,
407
+ "pass@2": 1.0,
408
+ "pass@4": 1.0,
409
+ "pass@8": 1.0,
410
+ "pass@16": 1.0,
411
+ "pass@32": 1.0,
412
+ "pass@64": 1.0,
413
+ "pass@128": 1.0
414
+ },
415
+ "4": {
416
+ "pass@1": 0.9822485207100592,
417
+ "pass@2": 0.985207100591716,
418
+ "pass@4": 0.9970414201183432,
419
+ "pass@8": 1.0,
420
+ "pass@16": 1.0,
421
+ "pass@32": 1.0,
422
+ "pass@64": 1.0,
423
+ "pass@128": 1.0
424
+ },
425
+ "5": {
426
+ "pass@1": 0.9594202898550724,
427
+ "pass@2": 0.9797101449275363,
428
+ "pass@4": 0.991304347826087,
429
+ "pass@8": 1.0,
430
+ "pass@16": 1.0,
431
+ "pass@32": 1.0,
432
+ "pass@64": 1.0,
433
+ "pass@128": 1.0
434
+ },
435
+ "6": {
436
+ "pass@1": 0.9684813753581661,
437
+ "pass@2": 0.9770773638968482,
438
+ "pass@4": 0.9856733524355301,
439
+ "pass@8": 0.997134670487106,
440
+ "pass@16": 1.0,
441
+ "pass@32": 1.0,
442
+ "pass@64": 1.0,
443
+ "pass@128": 1.0
444
+ },
445
+ "7": {
446
+ "pass@1": 0.8728323699421965,
447
+ "pass@2": 0.9132947976878613,
448
+ "pass@4": 0.9566473988439307,
449
+ "pass@8": 0.9913294797687862,
450
+ "pass@16": 0.9971098265895953,
451
+ "pass@32": 1.0,
452
+ "pass@64": 1.0,
453
+ "pass@128": 1.0
454
+ },
455
+ "8": {
456
+ "pass@1": 0.8112676056338028,
457
+ "pass@2": 0.8816901408450705,
458
+ "pass@4": 0.9605633802816902,
459
+ "pass@8": 0.9859154929577465,
460
+ "pass@16": 0.9971830985915493,
461
+ "pass@32": 0.9971830985915493,
462
+ "pass@64": 0.9971830985915493,
463
+ "pass@128": 0.9971830985915493
464
+ },
465
+ "9": {
466
+ "pass@1": 0.7305389221556886,
467
+ "pass@2": 0.7724550898203593,
468
+ "pass@4": 0.8622754491017964,
469
+ "pass@8": 0.9401197604790419,
470
+ "pass@16": 0.9670658682634731,
471
+ "pass@32": 0.9910179640718563,
472
+ "pass@64": 0.9970059880239521,
473
+ "pass@128": 1.0
474
+ },
475
+ "10": {
476
+ "pass@1": 0.6717791411042945,
477
+ "pass@2": 0.7392638036809815,
478
+ "pass@4": 0.8159509202453987,
479
+ "pass@8": 0.8926380368098159,
480
+ "pass@16": 0.9325153374233128,
481
+ "pass@32": 0.9478527607361963,
482
+ "pass@64": 0.9631901840490797,
483
+ "pass@128": 0.9662576687116564
484
+ }
485
+ },
486
+ "per_op_pass_at_columns": {
487
+ "pass@1": {
488
+ "2": 1.0,
489
+ "3": 1.0,
490
+ "4": 0.9822485207100592,
491
+ "5": 0.9594202898550724,
492
+ "6": 0.9684813753581661,
493
+ "7": 0.8728323699421965,
494
+ "8": 0.8112676056338028,
495
+ "9": 0.7305389221556886,
496
+ "10": 0.6717791411042945
497
+ },
498
+ "pass@2": {
499
+ "2": 1.0,
500
+ "3": 1.0,
501
+ "4": 0.985207100591716,
502
+ "5": 0.9797101449275363,
503
+ "6": 0.9770773638968482,
504
+ "7": 0.9132947976878613,
505
+ "8": 0.8816901408450705,
506
+ "9": 0.7724550898203593,
507
+ "10": 0.7392638036809815
508
+ },
509
+ "pass@4": {
510
+ "2": 1.0,
511
+ "3": 1.0,
512
+ "4": 0.9970414201183432,
513
+ "5": 0.991304347826087,
514
+ "6": 0.9856733524355301,
515
+ "7": 0.9566473988439307,
516
+ "8": 0.9605633802816902,
517
+ "9": 0.8622754491017964,
518
+ "10": 0.8159509202453987
519
+ },
520
+ "pass@8": {
521
+ "2": 1.0,
522
+ "3": 1.0,
523
+ "4": 1.0,
524
+ "5": 1.0,
525
+ "6": 0.997134670487106,
526
+ "7": 0.9913294797687862,
527
+ "8": 0.9859154929577465,
528
+ "9": 0.9401197604790419,
529
+ "10": 0.8926380368098159
530
+ },
531
+ "pass@16": {
532
+ "2": 1.0,
533
+ "3": 1.0,
534
+ "4": 1.0,
535
+ "5": 1.0,
536
+ "6": 1.0,
537
+ "7": 0.9971098265895953,
538
+ "8": 0.9971830985915493,
539
+ "9": 0.9670658682634731,
540
+ "10": 0.9325153374233128
541
+ },
542
+ "pass@32": {
543
+ "2": 1.0,
544
+ "3": 1.0,
545
+ "4": 1.0,
546
+ "5": 1.0,
547
+ "6": 1.0,
548
+ "7": 1.0,
549
+ "8": 0.9971830985915493,
550
+ "9": 0.9910179640718563,
551
+ "10": 0.9478527607361963
552
+ },
553
+ "pass@64": {
554
+ "2": 1.0,
555
+ "3": 1.0,
556
+ "4": 1.0,
557
+ "5": 1.0,
558
+ "6": 1.0,
559
+ "7": 1.0,
560
+ "8": 0.9971830985915493,
561
+ "9": 0.9970059880239521,
562
+ "10": 0.9631901840490797
563
+ },
564
+ "pass@128": {
565
+ "2": 1.0,
566
+ "3": 1.0,
567
+ "4": 1.0,
568
+ "5": 1.0,
569
+ "6": 1.0,
570
+ "7": 1.0,
571
+ "8": 0.9971830985915493,
572
+ "9": 1.0,
573
+ "10": 0.9662576687116564
574
+ }
575
+ },
576
+ "total_pass_at_k": {
577
+ "pass@1": 0.8889252948885976,
578
+ "pass@2": 0.9171035386631717,
579
+ "pass@4": 0.9528178243774574,
580
+ "pass@8": 0.9790301441677588,
581
+ "pass@16": 0.9885321100917431,
582
+ "pass@32": 0.9931192660550459,
583
+ "pass@64": 0.9954128440366973,
584
+ "pass@128": 0.9960681520314548
585
+ }
586
+ }
587
+ },
588
+ "total": {
589
+ "per_op_pass_at_k": {
590
+ "2": {
591
+ "pass@1": 1.0,
592
+ "pass@2": 1.0,
593
+ "pass@4": 1.0,
594
+ "pass@8": 1.0,
595
+ "pass@16": 1.0,
596
+ "pass@32": 1.0,
597
+ "pass@64": 1.0,
598
+ "pass@128": 1.0
599
+ },
600
+ "3": {
601
+ "pass@1": 1.0,
602
+ "pass@2": 1.0,
603
+ "pass@4": 1.0,
604
+ "pass@8": 1.0,
605
+ "pass@16": 1.0,
606
+ "pass@32": 1.0,
607
+ "pass@64": 1.0,
608
+ "pass@128": 1.0
609
+ },
610
+ "4": {
611
+ "pass@1": 0.989,
612
+ "pass@2": 0.994,
613
+ "pass@4": 0.999,
614
+ "pass@8": 1.0,
615
+ "pass@16": 1.0,
616
+ "pass@32": 1.0,
617
+ "pass@64": 1.0,
618
+ "pass@128": 1.0
619
+ },
620
+ "5": {
621
+ "pass@1": 0.957,
622
+ "pass@2": 0.975,
623
+ "pass@4": 0.992,
624
+ "pass@8": 0.999,
625
+ "pass@16": 0.999,
626
+ "pass@32": 0.999,
627
+ "pass@64": 0.999,
628
+ "pass@128": 0.999
629
+ },
630
+ "6": {
631
+ "pass@1": 0.967,
632
+ "pass@2": 0.979,
633
+ "pass@4": 0.991,
634
+ "pass@8": 0.997,
635
+ "pass@16": 1.0,
636
+ "pass@32": 1.0,
637
+ "pass@64": 1.0,
638
+ "pass@128": 1.0
639
+ },
640
+ "7": {
641
+ "pass@1": 0.884,
642
+ "pass@2": 0.924,
643
+ "pass@4": 0.957,
644
+ "pass@8": 0.987,
645
+ "pass@16": 0.997,
646
+ "pass@32": 1.0,
647
+ "pass@64": 1.0,
648
+ "pass@128": 1.0
649
+ },
650
+ "8": {
651
+ "pass@1": 0.815,
652
+ "pass@2": 0.88,
653
+ "pass@4": 0.947,
654
+ "pass@8": 0.977,
655
+ "pass@16": 0.995,
656
+ "pass@32": 0.999,
657
+ "pass@64": 0.999,
658
+ "pass@128": 0.999
659
+ },
660
+ "9": {
661
+ "pass@1": 0.745,
662
+ "pass@2": 0.81,
663
+ "pass@4": 0.888,
664
+ "pass@8": 0.948,
665
+ "pass@16": 0.976,
666
+ "pass@32": 0.994,
667
+ "pass@64": 0.999,
668
+ "pass@128": 1.0
669
+ },
670
+ "10": {
671
+ "pass@1": 0.649,
672
+ "pass@2": 0.717,
673
+ "pass@4": 0.797,
674
+ "pass@8": 0.876,
675
+ "pass@16": 0.922,
676
+ "pass@32": 0.949,
677
+ "pass@64": 0.964,
678
+ "pass@128": 0.969
679
+ }
680
+ },
681
+ "per_op_pass_at_columns": {
682
+ "pass@1": {
683
+ "2": 1.0,
684
+ "3": 1.0,
685
+ "4": 0.989,
686
+ "5": 0.957,
687
+ "6": 0.967,
688
+ "7": 0.884,
689
+ "8": 0.815,
690
+ "9": 0.745,
691
+ "10": 0.649
692
+ },
693
+ "pass@2": {
694
+ "2": 1.0,
695
+ "3": 1.0,
696
+ "4": 0.994,
697
+ "5": 0.975,
698
+ "6": 0.979,
699
+ "7": 0.924,
700
+ "8": 0.88,
701
+ "9": 0.81,
702
+ "10": 0.717
703
+ },
704
+ "pass@4": {
705
+ "2": 1.0,
706
+ "3": 1.0,
707
+ "4": 0.999,
708
+ "5": 0.992,
709
+ "6": 0.991,
710
+ "7": 0.957,
711
+ "8": 0.947,
712
+ "9": 0.888,
713
+ "10": 0.797
714
+ },
715
+ "pass@8": {
716
+ "2": 1.0,
717
+ "3": 1.0,
718
+ "4": 1.0,
719
+ "5": 0.999,
720
+ "6": 0.997,
721
+ "7": 0.987,
722
+ "8": 0.977,
723
+ "9": 0.948,
724
+ "10": 0.876
725
+ },
726
+ "pass@16": {
727
+ "2": 1.0,
728
+ "3": 1.0,
729
+ "4": 1.0,
730
+ "5": 0.999,
731
+ "6": 1.0,
732
+ "7": 0.997,
733
+ "8": 0.995,
734
+ "9": 0.976,
735
+ "10": 0.922
736
+ },
737
+ "pass@32": {
738
+ "2": 1.0,
739
+ "3": 1.0,
740
+ "4": 1.0,
741
+ "5": 0.999,
742
+ "6": 1.0,
743
+ "7": 1.0,
744
+ "8": 0.999,
745
+ "9": 0.994,
746
+ "10": 0.949
747
+ },
748
+ "pass@64": {
749
+ "2": 1.0,
750
+ "3": 1.0,
751
+ "4": 1.0,
752
+ "5": 0.999,
753
+ "6": 1.0,
754
+ "7": 1.0,
755
+ "8": 0.999,
756
+ "9": 0.999,
757
+ "10": 0.964
758
+ },
759
+ "pass@128": {
760
+ "2": 1.0,
761
+ "3": 1.0,
762
+ "4": 1.0,
763
+ "5": 0.999,
764
+ "6": 1.0,
765
+ "7": 1.0,
766
+ "8": 0.999,
767
+ "9": 1.0,
768
+ "10": 0.969
769
+ }
770
+ },
771
+ "total_pass_at_k": {
772
+ "pass@1": 0.8895555555555555,
773
+ "pass@2": 0.9198888888888889,
774
+ "pass@4": 0.9523333333333334,
775
+ "pass@8": 0.976,
776
+ "pass@16": 0.9876666666666667,
777
+ "pass@32": 0.9934444444444445,
778
+ "pass@64": 0.9956666666666667,
779
+ "pass@128": 0.9963333333333333
780
+ }
781
+ },
782
+ "ks": [
783
+ 1,
784
+ 2,
785
+ 4,
786
+ 8,
787
+ 16,
788
+ 32,
789
+ 64,
790
+ 128
791
+ ],
792
+ "prompt_counts": {
793
+ "per_template": {
794
+ "crazy_zootopia": {
795
+ "per_op": {
796
+ "2": 321,
797
+ "3": 327,
798
+ "4": 320,
799
+ "5": 315,
800
+ "6": 334,
801
+ "7": 338,
802
+ "8": 312,
803
+ "9": 355,
804
+ "10": 339
805
+ },
806
+ "total": 2961
807
+ },
808
+ "movie_festival_awards": {
809
+ "per_op": {
810
+ "2": 350,
811
+ "3": 343,
812
+ "4": 342,
813
+ "5": 340,
814
+ "6": 317,
815
+ "7": 316,
816
+ "8": 333,
817
+ "9": 311,
818
+ "10": 335
819
+ },
820
+ "total": 2987
821
+ },
822
+ "teachers_in_school": {
823
+ "per_op": {
824
+ "2": 329,
825
+ "3": 330,
826
+ "4": 338,
827
+ "5": 345,
828
+ "6": 349,
829
+ "7": 346,
830
+ "8": 355,
831
+ "9": 334,
832
+ "10": 326
833
+ },
834
+ "total": 3052
835
+ }
836
+ },
837
+ "total": {
838
+ "per_op": {
839
+ "2": 1000,
840
+ "3": 1000,
841
+ "4": 1000,
842
+ "5": 1000,
843
+ "6": 1000,
844
+ "7": 1000,
845
+ "8": 1000,
846
+ "9": 1000,
847
+ "10": 1000
848
+ },
849
+ "total": 9000
850
+ }
851
+ }
852
+ },
853
+ "checkpoint-85276_ood_generations.jsonl.graph_results.jsonl": {
854
+ "per_template": {
855
+ "crazy_zootopia": {
856
+ "per_op_pass_at_k": {
857
+ "11": {
858
+ "pass@1": 0.5835694050991501,
859
+ "pass@2": 0.6458923512747875,
860
+ "pass@4": 0.71671388101983,
861
+ "pass@8": 0.8158640226628895,
862
+ "pass@16": 0.8923512747875354,
863
+ "pass@32": 0.9206798866855525,
864
+ "pass@64": 0.943342776203966,
865
+ "pass@128": 0.9461756373937678
866
+ },
867
+ "12": {
868
+ "pass@1": 0.5790960451977402,
869
+ "pass@2": 0.6497175141242938,
870
+ "pass@4": 0.7033898305084746,
871
+ "pass@8": 0.7598870056497176,
872
+ "pass@16": 0.8107344632768362,
873
+ "pass@32": 0.8361581920903954,
874
+ "pass@64": 0.8502824858757062,
875
+ "pass@128": 0.867231638418079
876
+ },
877
+ "13": {
878
+ "pass@1": 0.4231974921630094,
879
+ "pass@2": 0.48589341692789967,
880
+ "pass@4": 0.5642633228840125,
881
+ "pass@8": 0.6238244514106583,
882
+ "pass@16": 0.6865203761755486,
883
+ "pass@32": 0.7366771159874608,
884
+ "pass@64": 0.774294670846395,
885
+ "pass@128": 0.7962382445141066
886
+ },
887
+ "14": {
888
+ "pass@1": 0.26479750778816197,
889
+ "pass@2": 0.3426791277258567,
890
+ "pass@4": 0.40186915887850466,
891
+ "pass@8": 0.4797507788161994,
892
+ "pass@16": 0.5545171339563862,
893
+ "pass@32": 0.6074766355140186,
894
+ "pass@64": 0.6697819314641744,
895
+ "pass@128": 0.7040498442367601
896
+ },
897
+ "15": {
898
+ "pass@1": 0.15895953757225434,
899
+ "pass@2": 0.1936416184971098,
900
+ "pass@4": 0.23699421965317918,
901
+ "pass@8": 0.2658959537572254,
902
+ "pass@16": 0.33236994219653176,
903
+ "pass@32": 0.3901734104046243,
904
+ "pass@64": 0.45375722543352603,
905
+ "pass@128": 0.49710982658959535
906
+ },
907
+ "16": {
908
+ "pass@1": 0.04838709677419355,
909
+ "pass@2": 0.08387096774193549,
910
+ "pass@4": 0.1064516129032258,
911
+ "pass@8": 0.12903225806451613,
912
+ "pass@16": 0.14838709677419354,
913
+ "pass@32": 0.16451612903225807,
914
+ "pass@64": 0.19032258064516128,
915
+ "pass@128": 0.2129032258064516
916
+ },
917
+ "17": {
918
+ "pass@1": 0.031791907514450865,
919
+ "pass@2": 0.04046242774566474,
920
+ "pass@4": 0.057803468208092484,
921
+ "pass@8": 0.06069364161849711,
922
+ "pass@16": 0.08092485549132948,
923
+ "pass@32": 0.11560693641618497,
924
+ "pass@64": 0.1329479768786127,
925
+ "pass@128": 0.15895953757225434
926
+ },
927
+ "18": {
928
+ "pass@1": 0.008571428571428572,
929
+ "pass@2": 0.011428571428571429,
930
+ "pass@4": 0.014285714285714285,
931
+ "pass@8": 0.02,
932
+ "pass@16": 0.02857142857142857,
933
+ "pass@32": 0.037142857142857144,
934
+ "pass@64": 0.04285714285714286,
935
+ "pass@128": 0.05142857142857143
936
+ },
937
+ "19": {
938
+ "pass@1": 0.003003003003003003,
939
+ "pass@2": 0.009009009009009009,
940
+ "pass@4": 0.009009009009009009,
941
+ "pass@8": 0.012012012012012012,
942
+ "pass@16": 0.012012012012012012,
943
+ "pass@32": 0.015015015015015015,
944
+ "pass@64": 0.018018018018018018,
945
+ "pass@128": 0.018018018018018018
946
+ },
947
+ "20": {
948
+ "pass@1": 0.0,
949
+ "pass@2": 0.0,
950
+ "pass@4": 0.0,
951
+ "pass@8": 0.003003003003003003,
952
+ "pass@16": 0.003003003003003003,
953
+ "pass@32": 0.003003003003003003,
954
+ "pass@64": 0.003003003003003003,
955
+ "pass@128": 0.003003003003003003
956
+ }
957
+ },
958
+ "per_op_pass_at_columns": {
959
+ "pass@1": {
960
+ "11": 0.5835694050991501,
961
+ "12": 0.5790960451977402,
962
+ "13": 0.4231974921630094,
963
+ "14": 0.26479750778816197,
964
+ "15": 0.15895953757225434,
965
+ "16": 0.04838709677419355,
966
+ "17": 0.031791907514450865,
967
+ "18": 0.008571428571428572,
968
+ "19": 0.003003003003003003,
969
+ "20": 0.0
970
+ },
971
+ "pass@2": {
972
+ "11": 0.6458923512747875,
973
+ "12": 0.6497175141242938,
974
+ "13": 0.48589341692789967,
975
+ "14": 0.3426791277258567,
976
+ "15": 0.1936416184971098,
977
+ "16": 0.08387096774193549,
978
+ "17": 0.04046242774566474,
979
+ "18": 0.011428571428571429,
980
+ "19": 0.009009009009009009,
981
+ "20": 0.0
982
+ },
983
+ "pass@4": {
984
+ "11": 0.71671388101983,
985
+ "12": 0.7033898305084746,
986
+ "13": 0.5642633228840125,
987
+ "14": 0.40186915887850466,
988
+ "15": 0.23699421965317918,
989
+ "16": 0.1064516129032258,
990
+ "17": 0.057803468208092484,
991
+ "18": 0.014285714285714285,
992
+ "19": 0.009009009009009009,
993
+ "20": 0.0
994
+ },
995
+ "pass@8": {
996
+ "11": 0.8158640226628895,
997
+ "12": 0.7598870056497176,
998
+ "13": 0.6238244514106583,
999
+ "14": 0.4797507788161994,
1000
+ "15": 0.2658959537572254,
1001
+ "16": 0.12903225806451613,
1002
+ "17": 0.06069364161849711,
1003
+ "18": 0.02,
1004
+ "19": 0.012012012012012012,
1005
+ "20": 0.003003003003003003
1006
+ },
1007
+ "pass@16": {
1008
+ "11": 0.8923512747875354,
1009
+ "12": 0.8107344632768362,
1010
+ "13": 0.6865203761755486,
1011
+ "14": 0.5545171339563862,
1012
+ "15": 0.33236994219653176,
1013
+ "16": 0.14838709677419354,
1014
+ "17": 0.08092485549132948,
1015
+ "18": 0.02857142857142857,
1016
+ "19": 0.012012012012012012,
1017
+ "20": 0.003003003003003003
1018
+ },
1019
+ "pass@32": {
1020
+ "11": 0.9206798866855525,
1021
+ "12": 0.8361581920903954,
1022
+ "13": 0.7366771159874608,
1023
+ "14": 0.6074766355140186,
1024
+ "15": 0.3901734104046243,
1025
+ "16": 0.16451612903225807,
1026
+ "17": 0.11560693641618497,
1027
+ "18": 0.037142857142857144,
1028
+ "19": 0.015015015015015015,
1029
+ "20": 0.003003003003003003
1030
+ },
1031
+ "pass@64": {
1032
+ "11": 0.943342776203966,
1033
+ "12": 0.8502824858757062,
1034
+ "13": 0.774294670846395,
1035
+ "14": 0.6697819314641744,
1036
+ "15": 0.45375722543352603,
1037
+ "16": 0.19032258064516128,
1038
+ "17": 0.1329479768786127,
1039
+ "18": 0.04285714285714286,
1040
+ "19": 0.018018018018018018,
1041
+ "20": 0.003003003003003003
1042
+ },
1043
+ "pass@128": {
1044
+ "11": 0.9461756373937678,
1045
+ "12": 0.867231638418079,
1046
+ "13": 0.7962382445141066,
1047
+ "14": 0.7040498442367601,
1048
+ "15": 0.49710982658959535,
1049
+ "16": 0.2129032258064516,
1050
+ "17": 0.15895953757225434,
1051
+ "18": 0.05142857142857143,
1052
+ "19": 0.018018018018018018,
1053
+ "20": 0.003003003003003003
1054
+ }
1055
+ },
1056
+ "total_pass_at_k": {
1057
+ "pass@1": 0.21277860326894502,
1058
+ "pass@2": 0.2487369985141159,
1059
+ "pass@4": 0.2835066864784547,
1060
+ "pass@8": 0.31946508172362553,
1061
+ "pass@16": 0.3575037147102526,
1062
+ "pass@32": 0.38514115898959883,
1063
+ "pass@64": 0.4101040118870728,
1064
+ "pass@128": 0.4276374442793462
1065
+ }
1066
+ },
1067
+ "movie_festival_awards": {
1068
+ "per_op_pass_at_k": {
1069
+ "11": {
1070
+ "pass@1": 0.5873015873015873,
1071
+ "pass@2": 0.6634920634920635,
1072
+ "pass@4": 0.7555555555555555,
1073
+ "pass@8": 0.8539682539682539,
1074
+ "pass@16": 0.926984126984127,
1075
+ "pass@32": 0.9619047619047619,
1076
+ "pass@64": 0.9714285714285714,
1077
+ "pass@128": 0.9746031746031746
1078
+ },
1079
+ "12": {
1080
+ "pass@1": 0.5902140672782875,
1081
+ "pass@2": 0.6238532110091743,
1082
+ "pass@4": 0.6880733944954128,
1083
+ "pass@8": 0.7706422018348624,
1084
+ "pass@16": 0.8348623853211009,
1085
+ "pass@32": 0.8746177370030581,
1086
+ "pass@64": 0.8868501529051988,
1087
+ "pass@128": 0.8929663608562691
1088
+ },
1089
+ "13": {
1090
+ "pass@1": 0.41358024691358025,
1091
+ "pass@2": 0.4537037037037037,
1092
+ "pass@4": 0.5339506172839507,
1093
+ "pass@8": 0.5925925925925926,
1094
+ "pass@16": 0.6419753086419753,
1095
+ "pass@32": 0.6666666666666666,
1096
+ "pass@64": 0.7006172839506173,
1097
+ "pass@128": 0.7160493827160493
1098
+ },
1099
+ "14": {
1100
+ "pass@1": 0.21364985163204747,
1101
+ "pass@2": 0.2789317507418398,
1102
+ "pass@4": 0.3353115727002967,
1103
+ "pass@8": 0.4035608308605341,
1104
+ "pass@16": 0.4658753709198813,
1105
+ "pass@32": 0.516320474777448,
1106
+ "pass@64": 0.5548961424332344,
1107
+ "pass@128": 0.6320474777448071
1108
+ },
1109
+ "15": {
1110
+ "pass@1": 0.08024691358024691,
1111
+ "pass@2": 0.11728395061728394,
1112
+ "pass@4": 0.15123456790123457,
1113
+ "pass@8": 0.19135802469135801,
1114
+ "pass@16": 0.24074074074074073,
1115
+ "pass@32": 0.2808641975308642,
1116
+ "pass@64": 0.3549382716049383,
1117
+ "pass@128": 0.404320987654321
1118
+ },
1119
+ "16": {
1120
+ "pass@1": 0.038348082595870206,
1121
+ "pass@2": 0.061946902654867256,
1122
+ "pass@4": 0.06489675516224189,
1123
+ "pass@8": 0.07669616519174041,
1124
+ "pass@16": 0.09144542772861357,
1125
+ "pass@32": 0.11504424778761062,
1126
+ "pass@64": 0.13274336283185842,
1127
+ "pass@128": 0.14749262536873156
1128
+ },
1129
+ "17": {
1130
+ "pass@1": 0.02108433734939759,
1131
+ "pass@2": 0.030120481927710843,
1132
+ "pass@4": 0.03614457831325301,
1133
+ "pass@8": 0.045180722891566265,
1134
+ "pass@16": 0.05120481927710843,
1135
+ "pass@32": 0.060240963855421686,
1136
+ "pass@64": 0.06927710843373494,
1137
+ "pass@128": 0.08433734939759036
1138
+ },
1139
+ "18": {
1140
+ "pass@1": 0.012903225806451613,
1141
+ "pass@2": 0.012903225806451613,
1142
+ "pass@4": 0.016129032258064516,
1143
+ "pass@8": 0.025806451612903226,
1144
+ "pass@16": 0.03225806451612903,
1145
+ "pass@32": 0.041935483870967745,
1146
+ "pass@64": 0.04838709677419355,
1147
+ "pass@128": 0.06451612903225806
1148
+ },
1149
+ "19": {
1150
+ "pass@1": 0.0,
1151
+ "pass@2": 0.0,
1152
+ "pass@4": 0.0030211480362537764,
1153
+ "pass@8": 0.006042296072507553,
1154
+ "pass@16": 0.00906344410876133,
1155
+ "pass@32": 0.00906344410876133,
1156
+ "pass@64": 0.00906344410876133,
1157
+ "pass@128": 0.012084592145015106
1158
+ },
1159
+ "20": {
1160
+ "pass@1": 0.003003003003003003,
1161
+ "pass@2": 0.003003003003003003,
1162
+ "pass@4": 0.006006006006006006,
1163
+ "pass@8": 0.009009009009009009,
1164
+ "pass@16": 0.012012012012012012,
1165
+ "pass@32": 0.015015015015015015,
1166
+ "pass@64": 0.015015015015015015,
1167
+ "pass@128": 0.018018018018018018
1168
+ }
1169
+ },
1170
+ "per_op_pass_at_columns": {
1171
+ "pass@1": {
1172
+ "11": 0.5873015873015873,
1173
+ "12": 0.5902140672782875,
1174
+ "13": 0.41358024691358025,
1175
+ "14": 0.21364985163204747,
1176
+ "15": 0.08024691358024691,
1177
+ "16": 0.038348082595870206,
1178
+ "17": 0.02108433734939759,
1179
+ "18": 0.012903225806451613,
1180
+ "19": 0.0,
1181
+ "20": 0.003003003003003003
1182
+ },
1183
+ "pass@2": {
1184
+ "11": 0.6634920634920635,
1185
+ "12": 0.6238532110091743,
1186
+ "13": 0.4537037037037037,
1187
+ "14": 0.2789317507418398,
1188
+ "15": 0.11728395061728394,
1189
+ "16": 0.061946902654867256,
1190
+ "17": 0.030120481927710843,
1191
+ "18": 0.012903225806451613,
1192
+ "19": 0.0,
1193
+ "20": 0.003003003003003003
1194
+ },
1195
+ "pass@4": {
1196
+ "11": 0.7555555555555555,
1197
+ "12": 0.6880733944954128,
1198
+ "13": 0.5339506172839507,
1199
+ "14": 0.3353115727002967,
1200
+ "15": 0.15123456790123457,
1201
+ "16": 0.06489675516224189,
1202
+ "17": 0.03614457831325301,
1203
+ "18": 0.016129032258064516,
1204
+ "19": 0.0030211480362537764,
1205
+ "20": 0.006006006006006006
1206
+ },
1207
+ "pass@8": {
1208
+ "11": 0.8539682539682539,
1209
+ "12": 0.7706422018348624,
1210
+ "13": 0.5925925925925926,
1211
+ "14": 0.4035608308605341,
1212
+ "15": 0.19135802469135801,
1213
+ "16": 0.07669616519174041,
1214
+ "17": 0.045180722891566265,
1215
+ "18": 0.025806451612903226,
1216
+ "19": 0.006042296072507553,
1217
+ "20": 0.009009009009009009
1218
+ },
1219
+ "pass@16": {
1220
+ "11": 0.926984126984127,
1221
+ "12": 0.8348623853211009,
1222
+ "13": 0.6419753086419753,
1223
+ "14": 0.4658753709198813,
1224
+ "15": 0.24074074074074073,
1225
+ "16": 0.09144542772861357,
1226
+ "17": 0.05120481927710843,
1227
+ "18": 0.03225806451612903,
1228
+ "19": 0.00906344410876133,
1229
+ "20": 0.012012012012012012
1230
+ },
1231
+ "pass@32": {
1232
+ "11": 0.9619047619047619,
1233
+ "12": 0.8746177370030581,
1234
+ "13": 0.6666666666666666,
1235
+ "14": 0.516320474777448,
1236
+ "15": 0.2808641975308642,
1237
+ "16": 0.11504424778761062,
1238
+ "17": 0.060240963855421686,
1239
+ "18": 0.041935483870967745,
1240
+ "19": 0.00906344410876133,
1241
+ "20": 0.015015015015015015
1242
+ },
1243
+ "pass@64": {
1244
+ "11": 0.9714285714285714,
1245
+ "12": 0.8868501529051988,
1246
+ "13": 0.7006172839506173,
1247
+ "14": 0.5548961424332344,
1248
+ "15": 0.3549382716049383,
1249
+ "16": 0.13274336283185842,
1250
+ "17": 0.06927710843373494,
1251
+ "18": 0.04838709677419355,
1252
+ "19": 0.00906344410876133,
1253
+ "20": 0.015015015015015015
1254
+ },
1255
+ "pass@128": {
1256
+ "11": 0.9746031746031746,
1257
+ "12": 0.8929663608562691,
1258
+ "13": 0.7160493827160493,
1259
+ "14": 0.6320474777448071,
1260
+ "15": 0.404320987654321,
1261
+ "16": 0.14749262536873156,
1262
+ "17": 0.08433734939759036,
1263
+ "18": 0.06451612903225806,
1264
+ "19": 0.012084592145015106,
1265
+ "20": 0.018018018018018018
1266
+ }
1267
+ },
1268
+ "total_pass_at_k": {
1269
+ "pass@1": 0.19407090464547677,
1270
+ "pass@2": 0.22249388753056235,
1271
+ "pass@4": 0.2567237163814181,
1272
+ "pass@8": 0.29492665036674814,
1273
+ "pass@16": 0.32793398533007334,
1274
+ "pass@32": 0.35146699266503667,
1275
+ "pass@64": 0.37163814180929094,
1276
+ "pass@128": 0.3921149144254279
1277
+ }
1278
+ },
1279
+ "teachers_in_school": {
1280
+ "per_op_pass_at_k": {
1281
+ "11": {
1282
+ "pass@1": 0.6506024096385542,
1283
+ "pass@2": 0.6987951807228916,
1284
+ "pass@4": 0.7801204819277109,
1285
+ "pass@8": 0.8283132530120482,
1286
+ "pass@16": 0.9006024096385542,
1287
+ "pass@32": 0.9337349397590361,
1288
+ "pass@64": 0.9578313253012049,
1289
+ "pass@128": 0.9698795180722891
1290
+ },
1291
+ "12": {
1292
+ "pass@1": 0.5454545454545454,
1293
+ "pass@2": 0.5987460815047022,
1294
+ "pass@4": 0.6614420062695925,
1295
+ "pass@8": 0.7492163009404389,
1296
+ "pass@16": 0.8181818181818182,
1297
+ "pass@32": 0.8432601880877743,
1298
+ "pass@64": 0.8557993730407524,
1299
+ "pass@128": 0.8589341692789969
1300
+ },
1301
+ "13": {
1302
+ "pass@1": 0.40896358543417366,
1303
+ "pass@2": 0.49019607843137253,
1304
+ "pass@4": 0.5686274509803921,
1305
+ "pass@8": 0.6386554621848739,
1306
+ "pass@16": 0.680672268907563,
1307
+ "pass@32": 0.7394957983193278,
1308
+ "pass@64": 0.7787114845938375,
1309
+ "pass@128": 0.8151260504201681
1310
+ },
1311
+ "14": {
1312
+ "pass@1": 0.22807017543859648,
1313
+ "pass@2": 0.26900584795321636,
1314
+ "pass@4": 0.30994152046783624,
1315
+ "pass@8": 0.35964912280701755,
1316
+ "pass@16": 0.40350877192982454,
1317
+ "pass@32": 0.4649122807017544,
1318
+ "pass@64": 0.5321637426900585,
1319
+ "pass@128": 0.5877192982456141
1320
+ },
1321
+ "15": {
1322
+ "pass@1": 0.12121212121212122,
1323
+ "pass@2": 0.1484848484848485,
1324
+ "pass@4": 0.19090909090909092,
1325
+ "pass@8": 0.23636363636363636,
1326
+ "pass@16": 0.27575757575757576,
1327
+ "pass@32": 0.32727272727272727,
1328
+ "pass@64": 0.36666666666666664,
1329
+ "pass@128": 0.4090909090909091
1330
+ },
1331
+ "16": {
1332
+ "pass@1": 0.05128205128205128,
1333
+ "pass@2": 0.07977207977207977,
1334
+ "pass@4": 0.09401709401709402,
1335
+ "pass@8": 0.1111111111111111,
1336
+ "pass@16": 0.1225071225071225,
1337
+ "pass@32": 0.1396011396011396,
1338
+ "pass@64": 0.1623931623931624,
1339
+ "pass@128": 0.19658119658119658
1340
+ },
1341
+ "17": {
1342
+ "pass@1": 0.021739130434782608,
1343
+ "pass@2": 0.037267080745341616,
1344
+ "pass@4": 0.046583850931677016,
1345
+ "pass@8": 0.06521739130434782,
1346
+ "pass@16": 0.06832298136645963,
1347
+ "pass@32": 0.06832298136645963,
1348
+ "pass@64": 0.07763975155279502,
1349
+ "pass@128": 0.09937888198757763
1350
+ },
1351
+ "18": {
1352
+ "pass@1": 0.008823529411764706,
1353
+ "pass@2": 0.008823529411764706,
1354
+ "pass@4": 0.011764705882352941,
1355
+ "pass@8": 0.011764705882352941,
1356
+ "pass@16": 0.023529411764705882,
1357
+ "pass@32": 0.029411764705882353,
1358
+ "pass@64": 0.03235294117647059,
1359
+ "pass@128": 0.041176470588235294
1360
+ },
1361
+ "19": {
1362
+ "pass@1": 0.002976190476190476,
1363
+ "pass@2": 0.002976190476190476,
1364
+ "pass@4": 0.008928571428571428,
1365
+ "pass@8": 0.01488095238095238,
1366
+ "pass@16": 0.01488095238095238,
1367
+ "pass@32": 0.01488095238095238,
1368
+ "pass@64": 0.017857142857142856,
1369
+ "pass@128": 0.023809523809523808
1370
+ },
1371
+ "20": {
1372
+ "pass@1": 0.0,
1373
+ "pass@2": 0.0029940119760479044,
1374
+ "pass@4": 0.0029940119760479044,
1375
+ "pass@8": 0.0029940119760479044,
1376
+ "pass@16": 0.0029940119760479044,
1377
+ "pass@32": 0.0029940119760479044,
1378
+ "pass@64": 0.0029940119760479044,
1379
+ "pass@128": 0.0029940119760479044
1380
+ }
1381
+ },
1382
+ "per_op_pass_at_columns": {
1383
+ "pass@1": {
1384
+ "11": 0.6506024096385542,
1385
+ "12": 0.5454545454545454,
1386
+ "13": 0.40896358543417366,
1387
+ "14": 0.22807017543859648,
1388
+ "15": 0.12121212121212122,
1389
+ "16": 0.05128205128205128,
1390
+ "17": 0.021739130434782608,
1391
+ "18": 0.008823529411764706,
1392
+ "19": 0.002976190476190476,
1393
+ "20": 0.0
1394
+ },
1395
+ "pass@2": {
1396
+ "11": 0.6987951807228916,
1397
+ "12": 0.5987460815047022,
1398
+ "13": 0.49019607843137253,
1399
+ "14": 0.26900584795321636,
1400
+ "15": 0.1484848484848485,
1401
+ "16": 0.07977207977207977,
1402
+ "17": 0.037267080745341616,
1403
+ "18": 0.008823529411764706,
1404
+ "19": 0.002976190476190476,
1405
+ "20": 0.0029940119760479044
1406
+ },
1407
+ "pass@4": {
1408
+ "11": 0.7801204819277109,
1409
+ "12": 0.6614420062695925,
1410
+ "13": 0.5686274509803921,
1411
+ "14": 0.30994152046783624,
1412
+ "15": 0.19090909090909092,
1413
+ "16": 0.09401709401709402,
1414
+ "17": 0.046583850931677016,
1415
+ "18": 0.011764705882352941,
1416
+ "19": 0.008928571428571428,
1417
+ "20": 0.0029940119760479044
1418
+ },
1419
+ "pass@8": {
1420
+ "11": 0.8283132530120482,
1421
+ "12": 0.7492163009404389,
1422
+ "13": 0.6386554621848739,
1423
+ "14": 0.35964912280701755,
1424
+ "15": 0.23636363636363636,
1425
+ "16": 0.1111111111111111,
1426
+ "17": 0.06521739130434782,
1427
+ "18": 0.011764705882352941,
1428
+ "19": 0.01488095238095238,
1429
+ "20": 0.0029940119760479044
1430
+ },
1431
+ "pass@16": {
1432
+ "11": 0.9006024096385542,
1433
+ "12": 0.8181818181818182,
1434
+ "13": 0.680672268907563,
1435
+ "14": 0.40350877192982454,
1436
+ "15": 0.27575757575757576,
1437
+ "16": 0.1225071225071225,
1438
+ "17": 0.06832298136645963,
1439
+ "18": 0.023529411764705882,
1440
+ "19": 0.01488095238095238,
1441
+ "20": 0.0029940119760479044
1442
+ },
1443
+ "pass@32": {
1444
+ "11": 0.9337349397590361,
1445
+ "12": 0.8432601880877743,
1446
+ "13": 0.7394957983193278,
1447
+ "14": 0.4649122807017544,
1448
+ "15": 0.32727272727272727,
1449
+ "16": 0.1396011396011396,
1450
+ "17": 0.06832298136645963,
1451
+ "18": 0.029411764705882353,
1452
+ "19": 0.01488095238095238,
1453
+ "20": 0.0029940119760479044
1454
+ },
1455
+ "pass@64": {
1456
+ "11": 0.9578313253012049,
1457
+ "12": 0.8557993730407524,
1458
+ "13": 0.7787114845938375,
1459
+ "14": 0.5321637426900585,
1460
+ "15": 0.36666666666666664,
1461
+ "16": 0.1623931623931624,
1462
+ "17": 0.07763975155279502,
1463
+ "18": 0.03235294117647059,
1464
+ "19": 0.017857142857142856,
1465
+ "20": 0.0029940119760479044
1466
+ },
1467
+ "pass@128": {
1468
+ "11": 0.9698795180722891,
1469
+ "12": 0.8589341692789969,
1470
+ "13": 0.8151260504201681,
1471
+ "14": 0.5877192982456141,
1472
+ "15": 0.4090909090909091,
1473
+ "16": 0.19658119658119658,
1474
+ "17": 0.09937888198757763,
1475
+ "18": 0.041176470588235294,
1476
+ "19": 0.023809523809523808,
1477
+ "20": 0.0029940119760479044
1478
+ }
1479
+ },
1480
+ "total_pass_at_k": {
1481
+ "pass@1": 0.2030924769550996,
1482
+ "pass@2": 0.23312518584597086,
1483
+ "pass@4": 0.26702349093071664,
1484
+ "pass@8": 0.30121914956883733,
1485
+ "pass@16": 0.3303597977995837,
1486
+ "pass@32": 0.3559322033898305,
1487
+ "pass@64": 0.37823371989295274,
1488
+ "pass@128": 0.4005352363960749
1489
+ }
1490
+ }
1491
+ },
1492
+ "total": {
1493
+ "per_op_pass_at_k": {
1494
+ "11": {
1495
+ "pass@1": 0.607,
1496
+ "pass@2": 0.669,
1497
+ "pass@4": 0.75,
1498
+ "pass@8": 0.832,
1499
+ "pass@16": 0.906,
1500
+ "pass@32": 0.938,
1501
+ "pass@64": 0.957,
1502
+ "pass@128": 0.963
1503
+ },
1504
+ "12": {
1505
+ "pass@1": 0.572,
1506
+ "pass@2": 0.625,
1507
+ "pass@4": 0.685,
1508
+ "pass@8": 0.76,
1509
+ "pass@16": 0.821,
1510
+ "pass@32": 0.851,
1511
+ "pass@64": 0.864,
1512
+ "pass@128": 0.873
1513
+ },
1514
+ "13": {
1515
+ "pass@1": 0.415,
1516
+ "pass@2": 0.477,
1517
+ "pass@4": 0.556,
1518
+ "pass@8": 0.619,
1519
+ "pass@16": 0.67,
1520
+ "pass@32": 0.715,
1521
+ "pass@64": 0.752,
1522
+ "pass@128": 0.777
1523
+ },
1524
+ "14": {
1525
+ "pass@1": 0.235,
1526
+ "pass@2": 0.296,
1527
+ "pass@4": 0.348,
1528
+ "pass@8": 0.413,
1529
+ "pass@16": 0.473,
1530
+ "pass@32": 0.528,
1531
+ "pass@64": 0.584,
1532
+ "pass@128": 0.64
1533
+ },
1534
+ "15": {
1535
+ "pass@1": 0.121,
1536
+ "pass@2": 0.154,
1537
+ "pass@4": 0.194,
1538
+ "pass@8": 0.232,
1539
+ "pass@16": 0.284,
1540
+ "pass@32": 0.334,
1541
+ "pass@64": 0.393,
1542
+ "pass@128": 0.438
1543
+ },
1544
+ "16": {
1545
+ "pass@1": 0.046,
1546
+ "pass@2": 0.075,
1547
+ "pass@4": 0.088,
1548
+ "pass@8": 0.105,
1549
+ "pass@16": 0.12,
1550
+ "pass@32": 0.139,
1551
+ "pass@64": 0.161,
1552
+ "pass@128": 0.185
1553
+ },
1554
+ "17": {
1555
+ "pass@1": 0.025,
1556
+ "pass@2": 0.036,
1557
+ "pass@4": 0.047,
1558
+ "pass@8": 0.057,
1559
+ "pass@16": 0.067,
1560
+ "pass@32": 0.082,
1561
+ "pass@64": 0.094,
1562
+ "pass@128": 0.115
1563
+ },
1564
+ "18": {
1565
+ "pass@1": 0.01,
1566
+ "pass@2": 0.011,
1567
+ "pass@4": 0.014,
1568
+ "pass@8": 0.019,
1569
+ "pass@16": 0.028,
1570
+ "pass@32": 0.036,
1571
+ "pass@64": 0.041,
1572
+ "pass@128": 0.052
1573
+ },
1574
+ "19": {
1575
+ "pass@1": 0.002,
1576
+ "pass@2": 0.004,
1577
+ "pass@4": 0.007,
1578
+ "pass@8": 0.011,
1579
+ "pass@16": 0.012,
1580
+ "pass@32": 0.013,
1581
+ "pass@64": 0.015,
1582
+ "pass@128": 0.018
1583
+ },
1584
+ "20": {
1585
+ "pass@1": 0.001,
1586
+ "pass@2": 0.002,
1587
+ "pass@4": 0.003,
1588
+ "pass@8": 0.005,
1589
+ "pass@16": 0.006,
1590
+ "pass@32": 0.007,
1591
+ "pass@64": 0.007,
1592
+ "pass@128": 0.008
1593
+ }
1594
+ },
1595
+ "per_op_pass_at_columns": {
1596
+ "pass@1": {
1597
+ "11": 0.607,
1598
+ "12": 0.572,
1599
+ "13": 0.415,
1600
+ "14": 0.235,
1601
+ "15": 0.121,
1602
+ "16": 0.046,
1603
+ "17": 0.025,
1604
+ "18": 0.01,
1605
+ "19": 0.002,
1606
+ "20": 0.001
1607
+ },
1608
+ "pass@2": {
1609
+ "11": 0.669,
1610
+ "12": 0.625,
1611
+ "13": 0.477,
1612
+ "14": 0.296,
1613
+ "15": 0.154,
1614
+ "16": 0.075,
1615
+ "17": 0.036,
1616
+ "18": 0.011,
1617
+ "19": 0.004,
1618
+ "20": 0.002
1619
+ },
1620
+ "pass@4": {
1621
+ "11": 0.75,
1622
+ "12": 0.685,
1623
+ "13": 0.556,
1624
+ "14": 0.348,
1625
+ "15": 0.194,
1626
+ "16": 0.088,
1627
+ "17": 0.047,
1628
+ "18": 0.014,
1629
+ "19": 0.007,
1630
+ "20": 0.003
1631
+ },
1632
+ "pass@8": {
1633
+ "11": 0.832,
1634
+ "12": 0.76,
1635
+ "13": 0.619,
1636
+ "14": 0.413,
1637
+ "15": 0.232,
1638
+ "16": 0.105,
1639
+ "17": 0.057,
1640
+ "18": 0.019,
1641
+ "19": 0.011,
1642
+ "20": 0.005
1643
+ },
1644
+ "pass@16": {
1645
+ "11": 0.906,
1646
+ "12": 0.821,
1647
+ "13": 0.67,
1648
+ "14": 0.473,
1649
+ "15": 0.284,
1650
+ "16": 0.12,
1651
+ "17": 0.067,
1652
+ "18": 0.028,
1653
+ "19": 0.012,
1654
+ "20": 0.006
1655
+ },
1656
+ "pass@32": {
1657
+ "11": 0.938,
1658
+ "12": 0.851,
1659
+ "13": 0.715,
1660
+ "14": 0.528,
1661
+ "15": 0.334,
1662
+ "16": 0.139,
1663
+ "17": 0.082,
1664
+ "18": 0.036,
1665
+ "19": 0.013,
1666
+ "20": 0.007
1667
+ },
1668
+ "pass@64": {
1669
+ "11": 0.957,
1670
+ "12": 0.864,
1671
+ "13": 0.752,
1672
+ "14": 0.584,
1673
+ "15": 0.393,
1674
+ "16": 0.161,
1675
+ "17": 0.094,
1676
+ "18": 0.041,
1677
+ "19": 0.015,
1678
+ "20": 0.007
1679
+ },
1680
+ "pass@128": {
1681
+ "11": 0.963,
1682
+ "12": 0.873,
1683
+ "13": 0.777,
1684
+ "14": 0.64,
1685
+ "15": 0.438,
1686
+ "16": 0.185,
1687
+ "17": 0.115,
1688
+ "18": 0.052,
1689
+ "19": 0.018,
1690
+ "20": 0.008
1691
+ }
1692
+ },
1693
+ "total_pass_at_k": {
1694
+ "pass@1": 0.2034,
1695
+ "pass@2": 0.2349,
1696
+ "pass@4": 0.2692,
1697
+ "pass@8": 0.3053,
1698
+ "pass@16": 0.3387,
1699
+ "pass@32": 0.3643,
1700
+ "pass@64": 0.3868,
1701
+ "pass@128": 0.4069
1702
+ }
1703
+ },
1704
+ "ks": [
1705
+ 1,
1706
+ 2,
1707
+ 4,
1708
+ 8,
1709
+ 16,
1710
+ 32,
1711
+ 64,
1712
+ 128
1713
+ ],
1714
+ "prompt_counts": {
1715
+ "per_template": {
1716
+ "crazy_zootopia": {
1717
+ "per_op": {
1718
+ "11": 353,
1719
+ "12": 354,
1720
+ "13": 319,
1721
+ "14": 321,
1722
+ "15": 346,
1723
+ "16": 310,
1724
+ "17": 346,
1725
+ "18": 350,
1726
+ "19": 333,
1727
+ "20": 333
1728
+ },
1729
+ "total": 3365
1730
+ },
1731
+ "movie_festival_awards": {
1732
+ "per_op": {
1733
+ "11": 315,
1734
+ "12": 327,
1735
+ "13": 324,
1736
+ "14": 337,
1737
+ "15": 324,
1738
+ "16": 339,
1739
+ "17": 332,
1740
+ "18": 310,
1741
+ "19": 331,
1742
+ "20": 333
1743
+ },
1744
+ "total": 3272
1745
+ },
1746
+ "teachers_in_school": {
1747
+ "per_op": {
1748
+ "11": 332,
1749
+ "12": 319,
1750
+ "13": 357,
1751
+ "14": 342,
1752
+ "15": 330,
1753
+ "16": 351,
1754
+ "17": 322,
1755
+ "18": 340,
1756
+ "19": 336,
1757
+ "20": 334
1758
+ },
1759
+ "total": 3363
1760
+ }
1761
+ },
1762
+ "total": {
1763
+ "per_op": {
1764
+ "11": 1000,
1765
+ "12": 1000,
1766
+ "13": 1000,
1767
+ "14": 1000,
1768
+ "15": 1000,
1769
+ "16": 1000,
1770
+ "17": 1000,
1771
+ "18": 1000,
1772
+ "19": 1000,
1773
+ "20": 1000
1774
+ },
1775
+ "total": 10000
1776
+ }
1777
+ }
1778
+ }
1779
+ }
1780
+ }
Qwen3-100M-ep4/composition/summary.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint,id_acc,ood_acc,total_acc,id_avg_loss,ood_avg_loss,total_avg_loss,id_avg_resp_len,ood_avg_resp_len,count_id,count_ood,count_total
2
+ checkpoint-85276,0.9949305555555555,0.44683984375,0.7064617598684211,0.0,0.0,0.0,200.0108559027778,327.42891796875,1152000,1280000,2432000
Qwen3-100M-ep4/composition/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "checkpoint-85276",
4
+ "id_acc": 0.9949305555555555,
5
+ "ood_acc": 0.44683984375,
6
+ "total_acc": 0.7064617598684211,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 200.0108559027778,
11
+ "ood_avg_resp_len": 327.42891796875,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 576855,
19
+ "answer_accuracy": 0.7124058943250079,
20
+ "avg_response_len": 256.26435790784063,
21
+ "resp_tokens_sum": 207504426,
22
+ "pass_at_k": {
23
+ "pass@1": 0.7124058943250079,
24
+ "pass@2": 0.7482848133624225,
25
+ "pass@4": 0.7797965772724061,
26
+ "pass@8": 0.8060704977403156,
27
+ "pass@16": 0.8268832725059063,
28
+ "pass@32": 0.8434735001446694,
29
+ "pass@64": 0.8574080645300883,
30
+ "pass@128": 0.8695858362314258
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.964855272861357,
35
+ "pass@2": 0.9744083600445962,
36
+ "pass@4": 0.980863755415529,
37
+ "pass@8": 0.9845045622809016,
38
+ "pass@16": 0.9864817601267433,
39
+ "pass@32": 0.988192742885706,
40
+ "pass@64": 0.9911504413060571,
41
+ "pass@128": 0.9970501474926253
42
+ },
43
+ "2": {
44
+ "pass@1": 1.0,
45
+ "pass@2": 1.0,
46
+ "pass@4": 1.0,
47
+ "pass@8": 1.0,
48
+ "pass@16": 1.0,
49
+ "pass@32": 1.0,
50
+ "pass@64": 1.0,
51
+ "pass@128": 1.0
52
+ },
53
+ "3": {
54
+ "pass@1": 1.0,
55
+ "pass@2": 1.0,
56
+ "pass@4": 1.0,
57
+ "pass@8": 1.0,
58
+ "pass@16": 1.0,
59
+ "pass@32": 1.0,
60
+ "pass@64": 1.0,
61
+ "pass@128": 1.0
62
+ },
63
+ "4": {
64
+ "pass@1": 1.0,
65
+ "pass@2": 1.0,
66
+ "pass@4": 1.0,
67
+ "pass@8": 1.0,
68
+ "pass@16": 1.0,
69
+ "pass@32": 1.0,
70
+ "pass@64": 1.0,
71
+ "pass@128": 1.0
72
+ },
73
+ "5": {
74
+ "pass@1": 0.9985367063492063,
75
+ "pass@2": 0.99933172415948,
76
+ "pass@4": 0.999864562762988,
77
+ "pass@8": 0.999995076184736,
78
+ "pass@16": 0.999999996268659,
79
+ "pass@32": 1.0,
80
+ "pass@64": 1.0,
81
+ "pass@128": 1.0
82
+ },
83
+ "6": {
84
+ "pass@1": 1.0,
85
+ "pass@2": 1.0,
86
+ "pass@4": 1.0,
87
+ "pass@8": 1.0,
88
+ "pass@16": 1.0,
89
+ "pass@32": 1.0,
90
+ "pass@64": 1.0,
91
+ "pass@128": 1.0
92
+ },
93
+ "7": {
94
+ "pass@1": 0.9997688609467456,
95
+ "pass@2": 0.9999836200670922,
96
+ "pass@4": 0.9999999417602385,
97
+ "pass@8": 0.9999999999999069,
98
+ "pass@16": 1.0,
99
+ "pass@32": 1.0,
100
+ "pass@64": 1.0,
101
+ "pass@128": 1.0
102
+ },
103
+ "8": {
104
+ "pass@1": 0.999824719551282,
105
+ "pass@2": 0.9999976340096912,
106
+ "pass@4": 0.9999999996995569,
107
+ "pass@8": 1.0,
108
+ "pass@16": 1.0,
109
+ "pass@32": 1.0,
110
+ "pass@64": 1.0,
111
+ "pass@128": 1.0
112
+ },
113
+ "9": {
114
+ "pass@1": 0.997337147887324,
115
+ "pass@2": 0.9977261700121991,
116
+ "pass@4": 0.9981745219347582,
117
+ "pass@8": 0.9988346121771267,
118
+ "pass@16": 0.9995479293349335,
119
+ "pass@32": 0.9999462946812021,
120
+ "pass@64": 0.9999998252073432,
121
+ "pass@128": 1.0
122
+ },
123
+ "11": {
124
+ "pass@1": 0.9568431303116147,
125
+ "pass@2": 0.966704122147621,
126
+ "pass@4": 0.9737702782725814,
127
+ "pass@8": 0.9797293556840062,
128
+ "pass@16": 0.9839171023985908,
129
+ "pass@32": 0.9864784015256126,
130
+ "pass@64": 0.9885864447521222,
131
+ "pass@128": 0.9915014164305949
132
+ },
133
+ "12": {
134
+ "pass@1": 0.8533501059322034,
135
+ "pass@2": 0.8813041477601309,
136
+ "pass@4": 0.8969065471688916,
137
+ "pass@8": 0.9103012428913164,
138
+ "pass@16": 0.9232330989994582,
139
+ "pass@32": 0.9356599220900689,
140
+ "pass@64": 0.9473396438691338,
141
+ "pass@128": 0.9548022598870056
142
+ },
143
+ "13": {
144
+ "pass@1": 0.760384012539185,
145
+ "pass@2": 0.8294336077308518,
146
+ "pass@4": 0.874541486977137,
147
+ "pass@8": 0.9027689973847379,
148
+ "pass@16": 0.9198466852847369,
149
+ "pass@32": 0.9308948171804944,
150
+ "pass@64": 0.9399058726440269,
151
+ "pass@128": 0.9498432601880877
152
+ },
153
+ "14": {
154
+ "pass@1": 0.6034852024922118,
155
+ "pass@2": 0.6929789259695341,
156
+ "pass@4": 0.7630072742075453,
157
+ "pass@8": 0.8164932601872855,
158
+ "pass@16": 0.8526563967709537,
159
+ "pass@32": 0.8763087593659933,
160
+ "pass@64": 0.8936422032813724,
161
+ "pass@128": 0.9065420560747663
162
+ },
163
+ "15": {
164
+ "pass@1": 0.4252619219653179,
165
+ "pass@2": 0.5253370209594465,
166
+ "pass@4": 0.6099591160209015,
167
+ "pass@8": 0.6784789856366449,
168
+ "pass@16": 0.7314473595873143,
169
+ "pass@32": 0.7713284427298922,
170
+ "pass@64": 0.8031345386516523,
171
+ "pass@128": 0.8294797687861272
172
+ },
173
+ "16": {
174
+ "pass@1": 0.26829637096774195,
175
+ "pass@2": 0.3590876619253239,
176
+ "pass@4": 0.44438377874136703,
177
+ "pass@8": 0.5160205150620084,
178
+ "pass@16": 0.572072708861716,
179
+ "pass@32": 0.6173416875891375,
180
+ "pass@64": 0.6591309169128403,
181
+ "pass@128": 0.6967741935483871
182
+ },
183
+ "17": {
184
+ "pass@1": 0.210305274566474,
185
+ "pass@2": 0.2880021534067633,
186
+ "pass@4": 0.36638274885075767,
187
+ "pass@8": 0.4354115772958514,
188
+ "pass@16": 0.4924820483803051,
189
+ "pass@32": 0.5414044485040482,
190
+ "pass@64": 0.5843553236837202,
191
+ "pass@128": 0.6242774566473989
192
+ },
193
+ "18": {
194
+ "pass@1": 0.19066964285714286,
195
+ "pass@2": 0.2540649606299211,
196
+ "pass@4": 0.3153792696448659,
197
+ "pass@8": 0.3744374956178368,
198
+ "pass@16": 0.4304686242139373,
199
+ "pass@32": 0.4799023237679476,
200
+ "pass@64": 0.5191885486106175,
201
+ "pass@128": 0.5485714285714286
202
+ },
203
+ "19": {
204
+ "pass@1": 0.17203922672672672,
205
+ "pass@2": 0.2452760339079237,
206
+ "pass@4": 0.31713847114831356,
207
+ "pass@8": 0.3807029920118585,
208
+ "pass@16": 0.43294372077217796,
209
+ "pass@32": 0.47306262676523364,
210
+ "pass@64": 0.5035309613007347,
211
+ "pass@128": 0.5315315315315315
212
+ },
213
+ "20": {
214
+ "pass@1": 0.16786317567567569,
215
+ "pass@2": 0.23649646201319421,
216
+ "pass@4": 0.3076818460755471,
217
+ "pass@8": 0.3678730399252492,
218
+ "pass@16": 0.41342134802722214,
219
+ "pass@32": 0.450621229184501,
220
+ "pass@64": 0.48393762875113866,
221
+ "pass@128": 0.5135135135135135
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 578426,
228
+ "answer_accuracy": 0.704435405300078,
229
+ "avg_response_len": 263.05899381332813,
230
+ "resp_tokens_sum": 216003001,
231
+ "pass_at_k": {
232
+ "pass@1": 0.704435405300078,
233
+ "pass@2": 0.7394285546608842,
234
+ "pass@4": 0.7702634267559836,
235
+ "pass@8": 0.7961202574484137,
236
+ "pass@16": 0.8169219087902136,
237
+ "pass@32": 0.8337421048859038,
238
+ "pass@64": 0.8480070379164071,
239
+ "pass@128": 0.8607950116913484
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.9569833205521472,
244
+ "pass@2": 0.9659142372349164,
245
+ "pass@4": 0.9719421844700393,
246
+ "pass@8": 0.9748675318830776,
247
+ "pass@16": 0.9757861748653367,
248
+ "pass@32": 0.9762266888126843,
249
+ "pass@64": 0.9769938650304216,
250
+ "pass@128": 0.9785276073619632
251
+ },
252
+ "2": {
253
+ "pass@1": 1.0,
254
+ "pass@2": 1.0,
255
+ "pass@4": 1.0,
256
+ "pass@8": 1.0,
257
+ "pass@16": 1.0,
258
+ "pass@32": 1.0,
259
+ "pass@64": 1.0,
260
+ "pass@128": 1.0
261
+ },
262
+ "3": {
263
+ "pass@1": 1.0,
264
+ "pass@2": 1.0,
265
+ "pass@4": 1.0,
266
+ "pass@8": 1.0,
267
+ "pass@16": 1.0,
268
+ "pass@32": 1.0,
269
+ "pass@64": 1.0,
270
+ "pass@128": 1.0
271
+ },
272
+ "4": {
273
+ "pass@1": 1.0,
274
+ "pass@2": 1.0,
275
+ "pass@4": 1.0,
276
+ "pass@8": 1.0,
277
+ "pass@16": 1.0,
278
+ "pass@32": 1.0,
279
+ "pass@64": 1.0,
280
+ "pass@128": 1.0
281
+ },
282
+ "5": {
283
+ "pass@1": 0.9998414855072464,
284
+ "pass@2": 0.9999967904827115,
285
+ "pass@4": 0.9999999997282949,
286
+ "pass@8": 1.0,
287
+ "pass@16": 1.0,
288
+ "pass@32": 1.0,
289
+ "pass@64": 1.0,
290
+ "pass@128": 1.0
291
+ },
292
+ "6": {
293
+ "pass@1": 0.9999776146131805,
294
+ "pass@2": 1.0,
295
+ "pass@4": 1.0,
296
+ "pass@8": 1.0,
297
+ "pass@16": 1.0,
298
+ "pass@32": 1.0,
299
+ "pass@64": 1.0,
300
+ "pass@128": 1.0
301
+ },
302
+ "7": {
303
+ "pass@1": 1.0,
304
+ "pass@2": 1.0,
305
+ "pass@4": 1.0,
306
+ "pass@8": 1.0,
307
+ "pass@16": 1.0,
308
+ "pass@32": 1.0,
309
+ "pass@64": 1.0,
310
+ "pass@128": 1.0
311
+ },
312
+ "8": {
313
+ "pass@1": 0.9948283450704225,
314
+ "pass@2": 0.9955154153266054,
315
+ "pass@4": 0.9962789690901313,
316
+ "pass@8": 0.9971273245981712,
317
+ "pass@16": 0.997797475275284,
318
+ "pass@32": 0.9984192527437615,
319
+ "pass@64": 0.9993013197287653,
320
+ "pass@128": 1.0
321
+ },
322
+ "9": {
323
+ "pass@1": 0.9957662799401198,
324
+ "pass@2": 0.9974428603423076,
325
+ "pass@4": 0.9988750589372435,
326
+ "pass@8": 0.9997585789040461,
327
+ "pass@16": 0.9999876161726882,
328
+ "pass@32": 0.9999999824517899,
329
+ "pass@64": 0.9999999999999998,
330
+ "pass@128": 1.0
331
+ },
332
+ "11": {
333
+ "pass@1": 0.9643731174698795,
334
+ "pass@2": 0.9750883455080163,
335
+ "pass@4": 0.9803072865138847,
336
+ "pass@8": 0.9823661486047269,
337
+ "pass@16": 0.9832962407555205,
338
+ "pass@32": 0.9844320989052803,
339
+ "pass@64": 0.9860781709515227,
340
+ "pass@128": 0.9879518072289156
341
+ },
342
+ "12": {
343
+ "pass@1": 0.8863636363636364,
344
+ "pass@2": 0.9133642287660749,
345
+ "pass@4": 0.9258904760729354,
346
+ "pass@8": 0.9354300779654707,
347
+ "pass@16": 0.945221377305145,
348
+ "pass@32": 0.9540520042583904,
349
+ "pass@64": 0.9598380142135106,
350
+ "pass@128": 0.9623824451410659
351
+ },
352
+ "13": {
353
+ "pass@1": 0.6867997198879552,
354
+ "pass@2": 0.7681042397273864,
355
+ "pass@4": 0.824483724986057,
356
+ "pass@8": 0.8627893286369971,
357
+ "pass@16": 0.8897924787212615,
358
+ "pass@32": 0.9118141519741789,
359
+ "pass@64": 0.9305813041850224,
360
+ "pass@128": 0.9439775910364145
361
+ },
362
+ "14": {
363
+ "pass@1": 0.5445906432748538,
364
+ "pass@2": 0.6282847970483952,
365
+ "pass@4": 0.6919824232497251,
366
+ "pass@8": 0.7401227434606403,
367
+ "pass@16": 0.7772650766591268,
368
+ "pass@32": 0.8067142511689581,
369
+ "pass@64": 0.8289431092869494,
370
+ "pass@128": 0.8450292397660819
371
+ },
372
+ "15": {
373
+ "pass@1": 0.3677556818181818,
374
+ "pass@2": 0.4612525351944643,
375
+ "pass@4": 0.5395015228210107,
376
+ "pass@8": 0.6038984673310392,
377
+ "pass@16": 0.6548475782041733,
378
+ "pass@32": 0.695211253240757,
379
+ "pass@64": 0.7307349783554408,
380
+ "pass@128": 0.7636363636363637
381
+ },
382
+ "16": {
383
+ "pass@1": 0.23595530626780628,
384
+ "pass@2": 0.30808173217129914,
385
+ "pass@4": 0.37879288913672104,
386
+ "pass@8": 0.44199327843430775,
387
+ "pass@16": 0.49717687261406224,
388
+ "pass@32": 0.5475518095537767,
389
+ "pass@64": 0.5956511172414417,
390
+ "pass@128": 0.6410256410256411
391
+ },
392
+ "17": {
393
+ "pass@1": 0.23090547360248448,
394
+ "pass@2": 0.31294512948109743,
395
+ "pass@4": 0.3923752244478753,
396
+ "pass@8": 0.4620048777355182,
397
+ "pass@16": 0.5184937076070995,
398
+ "pass@32": 0.5641996443460395,
399
+ "pass@64": 0.6058905683329744,
400
+ "pass@128": 0.6490683229813664
401
+ },
402
+ "18": {
403
+ "pass@1": 0.19181985294117648,
404
+ "pass@2": 0.2639264416396479,
405
+ "pass@4": 0.3402037715873749,
406
+ "pass@8": 0.41292313703410055,
407
+ "pass@16": 0.4755867515992984,
408
+ "pass@32": 0.5242663505584598,
409
+ "pass@64": 0.5607374408176437,
410
+ "pass@128": 0.5911764705882353
411
+ },
412
+ "19": {
413
+ "pass@1": 0.17740885416666666,
414
+ "pass@2": 0.24643025578833894,
415
+ "pass@4": 0.3146818307867766,
416
+ "pass@8": 0.37225657621985075,
417
+ "pass@16": 0.4180985090398595,
418
+ "pass@32": 0.4553241566350863,
419
+ "pass@64": 0.48681976016382017,
420
+ "pass@128": 0.5178571428571429
421
+ },
422
+ "20": {
423
+ "pass@1": 0.1394320733532934,
424
+ "pass@2": 0.2010787725729644,
425
+ "pass@4": 0.26803790703183067,
426
+ "pass@8": 0.32950827537338695,
427
+ "pass@16": 0.37733200724855503,
428
+ "pass@32": 0.4121459313058152,
429
+ "pass@64": 0.43980782684006975,
430
+ "pass@128": 0.46407185628742514
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 562834,
437
+ "answer_accuracy": 0.7025308555679821,
438
+ "avg_response_len": 282.1113771169516,
439
+ "resp_tokens_sum": 226014094,
440
+ "pass_at_k": {
441
+ "pass@1": 0.7025308555679821,
442
+ "pass@2": 0.736340083665345,
443
+ "pass@4": 0.7661264757077474,
444
+ "pass@8": 0.791289508043559,
445
+ "pass@16": 0.8116318796222768,
446
+ "pass@32": 0.8281989841030529,
447
+ "pass@64": 0.8425176638526883,
448
+ "pass@128": 0.8555679821057677
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.9654617537313432,
453
+ "pass@2": 0.974182483253026,
454
+ "pass@4": 0.9814832566638125,
455
+ "pass@8": 0.9865134381095033,
456
+ "pass@16": 0.990010567366735,
457
+ "pass@32": 0.9930920761226464,
458
+ "pass@64": 0.9962352974533647,
459
+ "pass@128": 1.0
460
+ },
461
+ "2": {
462
+ "pass@1": 1.0,
463
+ "pass@2": 1.0,
464
+ "pass@4": 1.0,
465
+ "pass@8": 1.0,
466
+ "pass@16": 1.0,
467
+ "pass@32": 1.0,
468
+ "pass@64": 1.0,
469
+ "pass@128": 1.0
470
+ },
471
+ "3": {
472
+ "pass@1": 1.0,
473
+ "pass@2": 1.0,
474
+ "pass@4": 1.0,
475
+ "pass@8": 1.0,
476
+ "pass@16": 1.0,
477
+ "pass@32": 1.0,
478
+ "pass@64": 1.0,
479
+ "pass@128": 1.0
480
+ },
481
+ "4": {
482
+ "pass@1": 1.0,
483
+ "pass@2": 1.0,
484
+ "pass@4": 1.0,
485
+ "pass@8": 1.0,
486
+ "pass@16": 1.0,
487
+ "pass@32": 1.0,
488
+ "pass@64": 1.0,
489
+ "pass@128": 1.0
490
+ },
491
+ "5": {
492
+ "pass@1": 0.9999080882352941,
493
+ "pass@2": 0.9999992762853173,
494
+ "pass@4": 1.0,
495
+ "pass@8": 1.0,
496
+ "pass@16": 1.0,
497
+ "pass@32": 1.0,
498
+ "pass@64": 1.0,
499
+ "pass@128": 1.0
500
+ },
501
+ "6": {
502
+ "pass@1": 1.0,
503
+ "pass@2": 1.0,
504
+ "pass@4": 1.0,
505
+ "pass@8": 1.0,
506
+ "pass@16": 1.0,
507
+ "pass@32": 1.0,
508
+ "pass@64": 1.0,
509
+ "pass@128": 1.0
510
+ },
511
+ "7": {
512
+ "pass@1": 0.9999258306962026,
513
+ "pass@2": 1.0,
514
+ "pass@4": 1.0,
515
+ "pass@8": 1.0,
516
+ "pass@16": 1.0,
517
+ "pass@32": 1.0,
518
+ "pass@64": 1.0,
519
+ "pass@128": 1.0
520
+ },
521
+ "8": {
522
+ "pass@1": 0.9954016516516516,
523
+ "pass@2": 0.9980015694828687,
524
+ "pass@4": 0.9994780266768457,
525
+ "pass@8": 0.9999541707109151,
526
+ "pass@16": 0.9999996450540588,
527
+ "pass@32": 0.9999999999945218,
528
+ "pass@64": 1.0,
529
+ "pass@128": 1.0
530
+ },
531
+ "9": {
532
+ "pass@1": 0.994599075562701,
533
+ "pass@2": 0.9959007962630074,
534
+ "pass@4": 0.9973834390074231,
535
+ "pass@8": 0.9989100635493507,
536
+ "pass@16": 0.9998018508583297,
537
+ "pass@32": 0.9999941260810753,
538
+ "pass@64": 0.9999999994727716,
539
+ "pass@128": 1.0
540
+ },
541
+ "11": {
542
+ "pass@1": 0.9669642857142857,
543
+ "pass@2": 0.977667635295588,
544
+ "pass@4": 0.9834914713041819,
545
+ "pass@8": 0.987697919919454,
546
+ "pass@16": 0.9903756780268099,
547
+ "pass@32": 0.9920980050763724,
548
+ "pass@64": 0.9932587543558059,
549
+ "pass@128": 0.9936507936507937
550
+ },
551
+ "12": {
552
+ "pass@1": 0.8925602064220184,
553
+ "pass@2": 0.927709778106865,
554
+ "pass@4": 0.9466711294115757,
555
+ "pass@8": 0.9594735205095442,
556
+ "pass@16": 0.968631391961948,
557
+ "pass@32": 0.9747149407936225,
558
+ "pass@64": 0.9783565974863963,
559
+ "pass@128": 0.981651376146789
560
+ },
561
+ "13": {
562
+ "pass@1": 0.6791087962962963,
563
+ "pass@2": 0.7509379252940609,
564
+ "pass@4": 0.8003636541960031,
565
+ "pass@8": 0.836590700158435,
566
+ "pass@16": 0.8634558161248805,
567
+ "pass@32": 0.8838359924574606,
568
+ "pass@64": 0.8998857884792347,
569
+ "pass@128": 0.9135802469135802
570
+ },
571
+ "14": {
572
+ "pass@1": 0.5279349035608308,
573
+ "pass@2": 0.6192675354564355,
574
+ "pass@4": 0.6896984853896232,
575
+ "pass@8": 0.7423055698396044,
576
+ "pass@16": 0.7843204109962838,
577
+ "pass@32": 0.8204913013870107,
578
+ "pass@64": 0.8477207957073809,
579
+ "pass@128": 0.8664688427299704
580
+ },
581
+ "15": {
582
+ "pass@1": 0.36140046296296297,
583
+ "pass@2": 0.4426244137017595,
584
+ "pass@4": 0.5132164547139938,
585
+ "pass@8": 0.5721977881442194,
586
+ "pass@16": 0.6197088824105395,
587
+ "pass@32": 0.658967059013711,
588
+ "pass@64": 0.6955853807708048,
589
+ "pass@128": 0.7345679012345679
590
+ },
591
+ "16": {
592
+ "pass@1": 0.21766685103244837,
593
+ "pass@2": 0.2878512385896452,
594
+ "pass@4": 0.35677422180634516,
595
+ "pass@8": 0.4192935319550409,
596
+ "pass@16": 0.4744116086421201,
597
+ "pass@32": 0.5235822279834264,
598
+ "pass@64": 0.5713460103429768,
599
+ "pass@128": 0.6194690265486725
600
+ },
601
+ "17": {
602
+ "pass@1": 0.19837161144578314,
603
+ "pass@2": 0.26883901254624787,
604
+ "pass@4": 0.33928608895650064,
605
+ "pass@8": 0.40176271614166426,
606
+ "pass@16": 0.4530815948293738,
607
+ "pass@32": 0.49619312239293656,
608
+ "pass@64": 0.536260897714176,
609
+ "pass@128": 0.5692771084337349
610
+ },
611
+ "18": {
612
+ "pass@1": 0.19788306451612903,
613
+ "pass@2": 0.2630076041402083,
614
+ "pass@4": 0.3281824866649735,
615
+ "pass@8": 0.38767325712032175,
616
+ "pass@16": 0.4352260441352987,
617
+ "pass@32": 0.47043974442309966,
618
+ "pass@64": 0.4992493451488665,
619
+ "pass@128": 0.5258064516129032
620
+ },
621
+ "19": {
622
+ "pass@1": 0.17987632175226587,
623
+ "pass@2": 0.247976856697671,
624
+ "pass@4": 0.3147488179347673,
625
+ "pass@8": 0.37247260884174876,
626
+ "pass@16": 0.41889090519709676,
627
+ "pass@32": 0.45572123675521775,
628
+ "pass@64": 0.4860676102567291,
629
+ "pass@128": 0.513595166163142
630
+ },
631
+ "20": {
632
+ "pass@1": 0.15899493243243243,
633
+ "pass@2": 0.2257040505071999,
634
+ "pass@4": 0.29573212638960666,
635
+ "pass@8": 0.3606103751183562,
636
+ "pass@16": 0.41446968279744983,
637
+ "pass@32": 0.457917316065741,
638
+ "pass@64": 0.49484972985591286,
639
+ "pass@128": 0.5285285285285285
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]
Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_id_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b5c20ac734fd52011e03baa0922792ae458dfcbd90a7ea26ab05c31d2a740e
3
+ size 1789986458
Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_metrics.json ADDED
@@ -0,0 +1,1897 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "checkpoint-38646",
3
+ "id": {
4
+ "answer_accuracy": 0.9932248263888889,
5
+ "avg_response_len": 200.3281736111111,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.9932248263888889,
11
+ "pass@2": 0.9952680036089231,
12
+ "pass@4": 0.9965955903532892,
13
+ "pass@8": 0.9974907332779658,
14
+ "pass@16": 0.9981196797512945,
15
+ "pass@32": 0.9985813699315721,
16
+ "pass@64": 0.9989574187426506,
17
+ "pass@128": 0.9993333333333333
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.95884375,
22
+ "pass@2": 0.9682652559055118,
23
+ "pass@4": 0.9756639486314218,
24
+ "pass@8": 0.9813791969954038,
25
+ "pass@16": 0.9855953958960963,
26
+ "pass@32": 0.9888302276998161,
27
+ "pass@64": 0.9917058153968907,
28
+ "pass@128": 0.995
29
+ },
30
+ "2": {
31
+ "pass@1": 1.0,
32
+ "pass@2": 1.0,
33
+ "pass@4": 1.0,
34
+ "pass@8": 1.0,
35
+ "pass@16": 1.0,
36
+ "pass@32": 1.0,
37
+ "pass@64": 1.0,
38
+ "pass@128": 1.0
39
+ },
40
+ "3": {
41
+ "pass@1": 0.999390625,
42
+ "pass@2": 0.9997413877952757,
43
+ "pass@4": 0.9999365339332582,
44
+ "pass@8": 0.9999964696284563,
45
+ "pass@16": 0.9999999930573713,
46
+ "pass@32": 0.9999999999999976,
47
+ "pass@64": 1.0,
48
+ "pass@128": 1.0
49
+ },
50
+ "4": {
51
+ "pass@1": 0.9999921875,
52
+ "pass@2": 1.0,
53
+ "pass@4": 1.0,
54
+ "pass@8": 1.0,
55
+ "pass@16": 1.0,
56
+ "pass@32": 1.0,
57
+ "pass@64": 1.0,
58
+ "pass@128": 1.0
59
+ },
60
+ "5": {
61
+ "pass@1": 0.9945,
62
+ "pass@2": 0.9970660679133861,
63
+ "pass@4": 0.9983636825084363,
64
+ "pass@8": 0.9990063609804485,
65
+ "pass@16": 0.9993881074316475,
66
+ "pass@32": 0.999688172223201,
67
+ "pass@64": 0.9999404409407284,
68
+ "pass@128": 1.0
69
+ },
70
+ "6": {
71
+ "pass@1": 0.9991796875,
72
+ "pass@2": 0.9996582185039371,
73
+ "pass@4": 0.9999079231346082,
74
+ "pass@8": 0.9999925579902273,
75
+ "pass@16": 0.9999999657010183,
76
+ "pass@32": 0.9999999999998928,
77
+ "pass@64": 1.0,
78
+ "pass@128": 1.0
79
+ },
80
+ "7": {
81
+ "pass@1": 0.997015625,
82
+ "pass@2": 0.9979917568897638,
83
+ "pass@4": 0.9985803902324709,
84
+ "pass@8": 0.9990458205281643,
85
+ "pass@16": 0.9994464582913845,
86
+ "pass@32": 0.999767693754703,
87
+ "pass@64": 0.9999711810355609,
88
+ "pass@128": 1.0
89
+ },
90
+ "8": {
91
+ "pass@1": 0.9955234375,
92
+ "pass@2": 0.9983201279527558,
93
+ "pass@4": 0.9996303053055869,
94
+ "pass@8": 0.999974862902426,
95
+ "pass@16": 0.9999998996583422,
96
+ "pass@32": 0.9999999999997113,
97
+ "pass@64": 1.0,
98
+ "pass@128": 1.0
99
+ },
100
+ "9": {
101
+ "pass@1": 0.994578125,
102
+ "pass@2": 0.996369217519685,
103
+ "pass@4": 0.9972775294338206,
104
+ "pass@8": 0.9980213304765657,
105
+ "pass@16": 0.9986472977257898,
106
+ "pass@32": 0.9989462357068267,
107
+ "pass@64": 0.9989993313106743,
108
+ "pass@128": 0.999
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.95884375,
113
+ "2": 1.0,
114
+ "3": 0.999390625,
115
+ "4": 0.9999921875,
116
+ "5": 0.9945,
117
+ "6": 0.9991796875,
118
+ "7": 0.997015625,
119
+ "8": 0.9955234375,
120
+ "9": 0.994578125
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 281.7881875,
124
+ "2": 115.6349609375,
125
+ "3": 144.9606328125,
126
+ "4": 159.9038359375,
127
+ "5": 173.56409375,
128
+ "6": 199.1092890625,
129
+ "7": 224.44571875,
130
+ "8": 243.821984375,
131
+ "9": 259.724859375
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 281.7881875,
136
+ "2": 115.6349609375,
137
+ "3": 144.9606328125,
138
+ "4": 159.9038359375,
139
+ "5": 173.56409375,
140
+ "6": 199.1092890625,
141
+ "7": 224.44571875,
142
+ "8": 243.821984375,
143
+ "9": 259.724859375
144
+ },
145
+ "per_op_loss": {},
146
+ "per_template": {
147
+ "crazy_zootopia": {
148
+ "count": 379008,
149
+ "correct": 376776,
150
+ "answer_accuracy": 0.9941109422492401,
151
+ "avg_response_len": 190.80592494089834,
152
+ "resp_tokens_sum": 72316972,
153
+ "pass_at_k": {
154
+ "pass@1": 0.9941109422492401,
155
+ "pass@2": 0.9958522471925055,
156
+ "pass@4": 0.9969521343709948,
157
+ "pass@8": 0.997695466193822,
158
+ "pass@16": 0.9982193570151264,
159
+ "pass@32": 0.9985217552165557,
160
+ "pass@64": 0.9987341050585805,
161
+ "pass@128": 0.9989868287740629
162
+ },
163
+ "per_op_pass_at_k": {
164
+ "10": {
165
+ "pass@1": 0.9643482669616519,
166
+ "pass@2": 0.9724997386941677,
167
+ "pass@4": 0.9787036025917114,
168
+ "pass@8": 0.9837184467724707,
169
+ "pass@16": 0.9876176547055514,
170
+ "pass@32": 0.990048743242238,
171
+ "pass@64": 0.9918928791392225,
172
+ "pass@128": 0.9941002949852508
173
+ },
174
+ "2": {
175
+ "pass@1": 1.0,
176
+ "pass@2": 1.0,
177
+ "pass@4": 1.0,
178
+ "pass@8": 1.0,
179
+ "pass@16": 1.0,
180
+ "pass@32": 1.0,
181
+ "pass@64": 1.0,
182
+ "pass@128": 1.0
183
+ },
184
+ "3": {
185
+ "pass@1": 0.9998805428134556,
186
+ "pass@2": 0.9999977425413568,
187
+ "pass@4": 0.9999999997133384,
188
+ "pass@8": 1.0,
189
+ "pass@16": 1.0,
190
+ "pass@32": 1.0,
191
+ "pass@64": 1.0,
192
+ "pass@128": 1.0
193
+ },
194
+ "4": {
195
+ "pass@1": 1.0,
196
+ "pass@2": 1.0,
197
+ "pass@4": 1.0,
198
+ "pass@8": 1.0,
199
+ "pass@16": 1.0,
200
+ "pass@32": 1.0,
201
+ "pass@64": 1.0,
202
+ "pass@128": 1.0
203
+ },
204
+ "5": {
205
+ "pass@1": 0.9967757936507936,
206
+ "pass@2": 0.9988044463192103,
207
+ "pass@4": 0.9997930303354938,
208
+ "pass@8": 0.9999940728357846,
209
+ "pass@16": 0.999999996928095,
210
+ "pass@32": 1.0,
211
+ "pass@64": 1.0,
212
+ "pass@128": 1.0
213
+ },
214
+ "6": {
215
+ "pass@1": 0.9981521332335329,
216
+ "pass@2": 0.999078737210618,
217
+ "pass@4": 0.9997273029868273,
218
+ "pass@8": 0.9999777200738017,
219
+ "pass@16": 0.9999998973084382,
220
+ "pass@32": 0.999999999999679,
221
+ "pass@64": 1.0,
222
+ "pass@128": 1.0
223
+ },
224
+ "7": {
225
+ "pass@1": 0.998959874260355,
226
+ "pass@2": 0.9998143607603783,
227
+ "pass@4": 0.9999912155026479,
228
+ "pass@8": 0.9999999836752375,
229
+ "pass@16": 0.9999999999999905,
230
+ "pass@32": 1.0,
231
+ "pass@64": 1.0,
232
+ "pass@128": 1.0
233
+ },
234
+ "8": {
235
+ "pass@1": 0.9960687099358975,
236
+ "pass@2": 0.9985512252675145,
237
+ "pass@4": 0.9996649123787412,
238
+ "pass@8": 0.9999730867256917,
239
+ "pass@16": 0.9999998586577866,
240
+ "pass@32": 0.9999999999993815,
241
+ "pass@64": 1.0,
242
+ "pass@128": 1.0
243
+ },
244
+ "9": {
245
+ "pass@1": 0.9940801056338028,
246
+ "pass@2": 0.9950447765332151,
247
+ "pass@4": 0.9956578631896364,
248
+ "pass@8": 0.996375867480201,
249
+ "pass@16": 0.9969724240620078,
250
+ "pass@32": 0.9971729386969103,
251
+ "pass@64": 0.9971830959162251,
252
+ "pass@128": 0.9971830985915493
253
+ }
254
+ }
255
+ },
256
+ "teachers_in_school": {
257
+ "count": 390656,
258
+ "correct": 387835,
259
+ "answer_accuracy": 0.9927788130733946,
260
+ "avg_response_len": 198.29017345183487,
261
+ "resp_tokens_sum": 77463246,
262
+ "pass_at_k": {
263
+ "pass@1": 0.9927788130733946,
264
+ "pass@2": 0.9945622255575279,
265
+ "pass@4": 0.9957723347122567,
266
+ "pass@8": 0.9965841163949335,
267
+ "pass@16": 0.9972021928309309,
268
+ "pass@32": 0.9978155261463467,
269
+ "pass@64": 0.9984095685624238,
270
+ "pass@128": 0.9990170380078637
271
+ },
272
+ "per_op_pass_at_k": {
273
+ "10": {
274
+ "pass@1": 0.9476131134969326,
275
+ "pass@2": 0.9578519002705184,
276
+ "pass@4": 0.9660574474778076,
277
+ "pass@8": 0.9719991236070697,
278
+ "pass@16": 0.9763583249372905,
279
+ "pass@32": 0.980656765738378,
280
+ "pass@64": 0.9852951841811889,
281
+ "pass@128": 0.99079754601227
282
+ },
283
+ "2": {
284
+ "pass@1": 1.0,
285
+ "pass@2": 1.0,
286
+ "pass@4": 1.0,
287
+ "pass@8": 1.0,
288
+ "pass@16": 1.0,
289
+ "pass@32": 1.0,
290
+ "pass@64": 1.0,
291
+ "pass@128": 1.0
292
+ },
293
+ "3": {
294
+ "pass@1": 0.9982717803030303,
295
+ "pass@2": 0.9992185635886424,
296
+ "pass@4": 0.9998076788696866,
297
+ "pass@8": 0.9999893019044129,
298
+ "pass@16": 0.9999999789617312,
299
+ "pass@32": 0.9999999999999926,
300
+ "pass@64": 1.0,
301
+ "pass@128": 1.0
302
+ },
303
+ "4": {
304
+ "pass@1": 0.9999768860946746,
305
+ "pass@2": 1.0,
306
+ "pass@4": 1.0,
307
+ "pass@8": 1.0,
308
+ "pass@16": 1.0,
309
+ "pass@32": 1.0,
310
+ "pass@64": 1.0,
311
+ "pass@128": 1.0
312
+ },
313
+ "5": {
314
+ "pass@1": 0.9955842391304348,
315
+ "pass@2": 0.9970807657195024,
316
+ "pass@4": 0.9974464667460045,
317
+ "pass@8": 0.9977680565376104,
318
+ "pass@16": 0.9983124881128989,
319
+ "pass@32": 0.999097406302473,
320
+ "pass@64": 0.9998273650576287,
321
+ "pass@128": 1.0
322
+ },
323
+ "6": {
324
+ "pass@1": 0.9994627507163324,
325
+ "pass@2": 0.9999027028856349,
326
+ "pass@4": 0.9999971459513118,
327
+ "pass@8": 0.9999999985260104,
328
+ "pass@16": 1.0,
329
+ "pass@32": 1.0,
330
+ "pass@64": 1.0,
331
+ "pass@128": 1.0
332
+ },
333
+ "7": {
334
+ "pass@1": 0.9984420158959537,
335
+ "pass@2": 0.9991658037868099,
336
+ "pass@4": 0.9997657894822396,
337
+ "pass@8": 0.999983097148883,
338
+ "pass@16": 0.9999999407613452,
339
+ "pass@32": 0.9999999999999076,
340
+ "pass@64": 1.0,
341
+ "pass@128": 1.0
342
+ },
343
+ "8": {
344
+ "pass@1": 0.9972711267605634,
345
+ "pass@2": 0.9988802401020296,
346
+ "pass@4": 0.9997421626874106,
347
+ "pass@8": 0.9999832931204404,
348
+ "pass@16": 0.9999999422581453,
349
+ "pass@32": 0.99999999999991,
350
+ "pass@64": 1.0,
351
+ "pass@128": 1.0
352
+ },
353
+ "9": {
354
+ "pass@1": 0.9965147829341318,
355
+ "pass@2": 0.9973931320430004,
356
+ "pass@4": 0.9978456220292824,
357
+ "pass@8": 0.998468082786387,
358
+ "pass@16": 0.9992530482905866,
359
+ "pass@32": 0.999851122735485,
360
+ "pass@64": 0.9999980007921191,
361
+ "pass@128": 1.0
362
+ }
363
+ }
364
+ },
365
+ "movie_festival_awards": {
366
+ "count": 382336,
367
+ "correct": 379584,
368
+ "answer_accuracy": 0.9928021426180114,
369
+ "avg_response_len": 211.8498859641781,
370
+ "resp_tokens_sum": 80997838,
371
+ "pass_at_k": {
372
+ "pass@1": 0.9928021426180114,
373
+ "pass@2": 0.9954099819691105,
374
+ "pass@4": 0.9970833203097687,
375
+ "pass@8": 0.9982141281769159,
376
+ "pass@16": 0.9989583224371812,
377
+ "pass@32": 0.9994229750215191,
378
+ "pass@64": 0.9997385605466621,
379
+ "pass@128": 1.0
380
+ },
381
+ "per_op_pass_at_k": {
382
+ "10": {
383
+ "pass@1": 0.9642024253731343,
384
+ "pass@2": 0.9741138059701494,
385
+ "pass@4": 0.9819364163434796,
386
+ "pass@8": 0.9881400872944226,
387
+ "pass@16": 0.9925379015562921,
388
+ "pass@32": 0.9955510391342886,
389
+ "pass@64": 0.997754923360079,
390
+ "pass@128": 1.0
391
+ },
392
+ "2": {
393
+ "pass@1": 1.0,
394
+ "pass@2": 1.0,
395
+ "pass@4": 1.0,
396
+ "pass@8": 1.0,
397
+ "pass@16": 1.0,
398
+ "pass@32": 1.0,
399
+ "pass@64": 1.0,
400
+ "pass@128": 1.0
401
+ },
402
+ "3": {
403
+ "pass@1": 1.0,
404
+ "pass@2": 1.0,
405
+ "pass@4": 1.0,
406
+ "pass@8": 1.0,
407
+ "pass@16": 1.0,
408
+ "pass@32": 1.0,
409
+ "pass@64": 1.0,
410
+ "pass@128": 1.0
411
+ },
412
+ "4": {
413
+ "pass@1": 1.0,
414
+ "pass@2": 1.0,
415
+ "pass@4": 1.0,
416
+ "pass@8": 1.0,
417
+ "pass@16": 1.0,
418
+ "pass@32": 1.0,
419
+ "pass@64": 1.0,
420
+ "pass@128": 1.0
421
+ },
422
+ "5": {
423
+ "pass@1": 0.9912913602941177,
424
+ "pass@2": 0.9954405974988421,
425
+ "pass@4": 0.9979701380158362,
426
+ "pass@8": 0.9993477897991202,
427
+ "pass@16": 0.9999126470598457,
428
+ "pass@32": 0.999998726614258,
429
+ "pass@64": 0.999999999987784,
430
+ "pass@128": 1.0
431
+ },
432
+ "6": {
433
+ "pass@1": 0.9999507097791798,
434
+ "pass@2": 0.999999611888025,
435
+ "pass@4": 1.0,
436
+ "pass@8": 1.0,
437
+ "pass@16": 1.0,
438
+ "pass@32": 1.0,
439
+ "pass@64": 1.0,
440
+ "pass@128": 1.0
441
+ },
442
+ "7": {
443
+ "pass@1": 0.9933742088607594,
444
+ "pass@2": 0.9947567558307585,
445
+ "pass@4": 0.9957734057965857,
446
+ "pass@8": 0.9969989697228501,
447
+ "pass@16": 0.9982483505948174,
448
+ "pass@32": 0.9992648536542246,
449
+ "pass@64": 0.9999088007454459,
450
+ "pass@128": 1.0
451
+ },
452
+ "8": {
453
+ "pass@1": 0.9931493993993994,
454
+ "pass@2": 0.9975064877869996,
455
+ "pass@4": 0.999478633301468,
456
+ "pass@8": 0.9999675398986609,
457
+ "pass@16": 0.9999998926590724,
458
+ "pass@32": 0.9999999999998089,
459
+ "pass@64": 1.0,
460
+ "pass@128": 1.0
461
+ },
462
+ "9": {
463
+ "pass@1": 0.9930667202572347,
464
+ "pass@2": 0.9967814011190724,
465
+ "pass@4": 0.9985162387257863,
466
+ "pass@8": 0.9994198002264989,
467
+ "pass@16": 0.9999085821695214,
468
+ "pass@32": 0.999998609246854,
469
+ "pass@64": 0.9999999999866449,
470
+ "pass@128": 1.0
471
+ }
472
+ }
473
+ }
474
+ }
475
+ },
476
+ "ood": {
477
+ "answer_accuracy": 0.83598125,
478
+ "avg_response_len": 378.03591796875,
479
+ "avg_loss": 0.0,
480
+ "count": 1280000,
481
+ "validation_metrics": {},
482
+ "pass_at_k": {
483
+ "pass@1": 0.83598125,
484
+ "pass@2": 0.8769260949802976,
485
+ "pass@4": 0.9062144027652703,
486
+ "pass@8": 0.927088376859717,
487
+ "pass@16": 0.9418586434981504,
488
+ "pass@32": 0.9525318270976024,
489
+ "pass@64": 0.9609100985370623,
490
+ "pass@128": 0.9681
491
+ },
492
+ "per_op_pass_at_k": {
493
+ "11": {
494
+ "pass@1": 0.970671875,
495
+ "pass@2": 0.9794998769685037,
496
+ "pass@4": 0.9857863502999626,
497
+ "pass@8": 0.9900398112371814,
498
+ "pass@16": 0.9931495940187157,
499
+ "pass@32": 0.9953983463354901,
500
+ "pass@64": 0.9969441662809593,
501
+ "pass@128": 0.998
502
+ },
503
+ "12": {
504
+ "pass@1": 0.966296875,
505
+ "pass@2": 0.9809158464566927,
506
+ "pass@4": 0.9901372777465317,
507
+ "pass@8": 0.9945470208837859,
508
+ "pass@16": 0.996475576710408,
509
+ "pass@32": 0.9975372922449343,
510
+ "pass@64": 0.9982497123716464,
511
+ "pass@128": 0.999
512
+ },
513
+ "13": {
514
+ "pass@1": 0.9553671875,
515
+ "pass@2": 0.973431348425197,
516
+ "pass@4": 0.9843508790776158,
517
+ "pass@8": 0.9907141222601963,
518
+ "pass@16": 0.9945169364443083,
519
+ "pass@32": 0.99655956862069,
520
+ "pass@64": 0.9974491256090368,
521
+ "pass@128": 0.998
522
+ },
523
+ "14": {
524
+ "pass@1": 0.949578125,
525
+ "pass@2": 0.9686524360236218,
526
+ "pass@4": 0.9809611437007878,
527
+ "pass@8": 0.9883708817653398,
528
+ "pass@16": 0.9925049124837143,
529
+ "pass@32": 0.9948066901098008,
530
+ "pass@64": 0.9961112856236247,
531
+ "pass@128": 0.997
532
+ },
533
+ "15": {
534
+ "pass@1": 0.965375,
535
+ "pass@2": 0.9803630659448824,
536
+ "pass@4": 0.988369140607424,
537
+ "pass@8": 0.9930486759883792,
538
+ "pass@16": 0.9955475560142018,
539
+ "pass@32": 0.9967154674849088,
540
+ "pass@64": 0.997376405398854,
541
+ "pass@128": 0.998
542
+ },
543
+ "16": {
544
+ "pass@1": 0.887765625,
545
+ "pass@2": 0.9196377952755908,
546
+ "pass@4": 0.9421223665166858,
547
+ "pass@8": 0.9573031508529518,
548
+ "pass@16": 0.9670828002231159,
549
+ "pass@32": 0.9741994820696727,
550
+ "pass@64": 0.9803724490952007,
551
+ "pass@128": 0.986
552
+ },
553
+ "17": {
554
+ "pass@1": 0.856984375,
555
+ "pass@2": 0.8984932332677166,
556
+ "pass@4": 0.924790269216348,
557
+ "pass@8": 0.9417427006423036,
558
+ "pass@16": 0.9525526931446574,
559
+ "pass@32": 0.9599937953920628,
560
+ "pass@64": 0.9663307158630652,
561
+ "pass@128": 0.972
562
+ },
563
+ "18": {
564
+ "pass@1": 0.77284375,
565
+ "pass@2": 0.8381781496062998,
566
+ "pass@4": 0.8801090434008246,
567
+ "pass@8": 0.9078199779722668,
568
+ "pass@16": 0.9261821010586693,
569
+ "pass@32": 0.9385224656210279,
570
+ "pass@64": 0.9478627592988191,
571
+ "pass@128": 0.957
572
+ },
573
+ "19": {
574
+ "pass@1": 0.584125,
575
+ "pass@2": 0.6814692421259851,
576
+ "pass@4": 0.7541173871391076,
577
+ "pass@8": 0.8081890874701764,
578
+ "pass@16": 0.8491870017860157,
579
+ "pass@32": 0.8800031510922511,
580
+ "pass@64": 0.9043406794110973,
581
+ "pass@128": 0.924
582
+ },
583
+ "20": {
584
+ "pass@1": 0.4508046875,
585
+ "pass@2": 0.5486199557086607,
586
+ "pass@4": 0.6314001699475059,
587
+ "pass@8": 0.6991083395246123,
588
+ "pass@16": 0.7513872630976118,
589
+ "pass@32": 0.7915820120051243,
590
+ "pass@64": 0.8240636864182797,
591
+ "pass@128": 0.852
592
+ }
593
+ },
594
+ "per_op_accuracy": {
595
+ "11": 0.970671875,
596
+ "12": 0.966296875,
597
+ "13": 0.9553671875,
598
+ "14": 0.949578125,
599
+ "15": 0.965375,
600
+ "16": 0.887765625,
601
+ "17": 0.856984375,
602
+ "18": 0.77284375,
603
+ "19": 0.584125,
604
+ "20": 0.4508046875
605
+ },
606
+ "per_op_avg_response_len": {
607
+ "11": 301.01784375,
608
+ "12": 313.407609375,
609
+ "13": 334.547984375,
610
+ "14": 361.579859375,
611
+ "15": 381.650609375,
612
+ "16": 390.577,
613
+ "17": 411.0501640625,
614
+ "18": 426.7855859375,
615
+ "19": 424.2508671875,
616
+ "20": 435.49165625
617
+ },
618
+ "per_op_avg_loss": {},
619
+ "per_op_length": {
620
+ "11": 301.01784375,
621
+ "12": 313.407609375,
622
+ "13": 334.547984375,
623
+ "14": 361.579859375,
624
+ "15": 381.650609375,
625
+ "16": 390.577,
626
+ "17": 411.0501640625,
627
+ "18": 426.7855859375,
628
+ "19": 424.2508671875,
629
+ "20": 435.49165625
630
+ },
631
+ "per_op_loss": {},
632
+ "per_template": {
633
+ "crazy_zootopia": {
634
+ "count": 430720,
635
+ "correct": 359051,
636
+ "answer_accuracy": 0.8336065193164933,
637
+ "avg_response_len": 360.013558692422,
638
+ "resp_tokens_sum": 155065040,
639
+ "pass_at_k": {
640
+ "pass@1": 0.8336065193164933,
641
+ "pass@2": 0.8731902853014514,
642
+ "pass@4": 0.9019876336223236,
643
+ "pass@8": 0.9227793245050241,
644
+ "pass@16": 0.9379346127968918,
645
+ "pass@32": 0.9493515835193701,
646
+ "pass@64": 0.9586937969666259,
647
+ "pass@128": 0.9667161961367013
648
+ },
649
+ "per_op_pass_at_k": {
650
+ "11": {
651
+ "pass@1": 0.9711623583569405,
652
+ "pass@2": 0.9805191998840088,
653
+ "pass@4": 0.986303336286222,
654
+ "pass@8": 0.989850641477996,
655
+ "pass@16": 0.99240868699634,
656
+ "pass@32": 0.994293234140082,
657
+ "pass@64": 0.9956686613210934,
658
+ "pass@128": 0.9971671388101983
659
+ },
660
+ "12": {
661
+ "pass@1": 0.9658368644067796,
662
+ "pass@2": 0.979869405889942,
663
+ "pass@4": 0.9899045508612269,
664
+ "pass@8": 0.9949535165900368,
665
+ "pass@16": 0.9969359713595375,
666
+ "pass@32": 0.9982218320963844,
667
+ "pass@64": 0.9992952648675736,
668
+ "pass@128": 1.0
669
+ },
670
+ "13": {
671
+ "pass@1": 0.9498187695924765,
672
+ "pass@2": 0.9693292893639082,
673
+ "pass@4": 0.9815207164543299,
674
+ "pass@8": 0.9885514952344922,
675
+ "pass@16": 0.993030758542598,
676
+ "pass@32": 0.9957866897580077,
677
+ "pass@64": 0.9968002718717178,
678
+ "pass@128": 0.9968652037617555
679
+ },
680
+ "14": {
681
+ "pass@1": 0.9244548286604362,
682
+ "pass@2": 0.9464950971373904,
683
+ "pass@4": 0.962845547343965,
684
+ "pass@8": 0.9744775229835171,
685
+ "pass@16": 0.9831241464032126,
686
+ "pass@32": 0.9892894037314296,
687
+ "pass@64": 0.9925585252418944,
688
+ "pass@128": 0.9937694704049844
689
+ },
690
+ "15": {
691
+ "pass@1": 0.9763367052023122,
692
+ "pass@2": 0.9890843327568163,
693
+ "pass@4": 0.995195050131017,
694
+ "pass@8": 0.9987062171803248,
695
+ "pass@16": 0.9998947926322176,
696
+ "pass@32": 0.9999995163740522,
697
+ "pass@64": 0.9999999999997273,
698
+ "pass@128": 1.0
699
+ },
700
+ "16": {
701
+ "pass@1": 0.8670362903225807,
702
+ "pass@2": 0.9042973710947418,
703
+ "pass@4": 0.9324377792493678,
704
+ "pass@8": 0.9511663793058849,
705
+ "pass@16": 0.9632457765868611,
706
+ "pass@32": 0.972380137786845,
707
+ "pass@64": 0.9803184368887754,
708
+ "pass@128": 0.9870967741935484
709
+ },
710
+ "17": {
711
+ "pass@1": 0.8796739523121387,
712
+ "pass@2": 0.9130583354194169,
713
+ "pass@4": 0.9346565702950422,
714
+ "pass@8": 0.949022076996675,
715
+ "pass@16": 0.9577801252538675,
716
+ "pass@32": 0.9642535207391926,
717
+ "pass@64": 0.9711417638827387,
718
+ "pass@128": 0.976878612716763
719
+ },
720
+ "18": {
721
+ "pass@1": 0.7535491071428572,
722
+ "pass@2": 0.8142751687289084,
723
+ "pass@4": 0.854199288124698,
724
+ "pass@8": 0.8827058936508151,
725
+ "pass@16": 0.9034225204407647,
726
+ "pass@32": 0.9183155907983432,
727
+ "pass@64": 0.9304605804851537,
728
+ "pass@128": 0.9428571428571428
729
+ },
730
+ "19": {
731
+ "pass@1": 0.5902073948948949,
732
+ "pass@2": 0.6823130955758907,
733
+ "pass@4": 0.7493216109810598,
734
+ "pass@8": 0.7968110404034479,
735
+ "pass@16": 0.8325350334716398,
736
+ "pass@32": 0.859961150550141,
737
+ "pass@64": 0.8827473329655091,
738
+ "pass@128": 0.9009009009009009
739
+ },
740
+ "20": {
741
+ "pass@1": 0.4485735735735736,
742
+ "pass@2": 0.5452467723629141,
743
+ "pass@4": 0.6280490980294128,
744
+ "pass@8": 0.6976146762314849,
745
+ "pass@16": 0.7542370813489142,
746
+ "pass@32": 0.799241057750153,
747
+ "pass@64": 0.8368248092112288,
748
+ "pass@128": 0.8708708708708709
749
+ }
750
+ }
751
+ },
752
+ "teachers_in_school": {
753
+ "count": 430464,
754
+ "correct": 363264,
755
+ "answer_accuracy": 0.8438893844781445,
756
+ "avg_response_len": 373.32513287986916,
757
+ "resp_tokens_sum": 160703030,
758
+ "pass_at_k": {
759
+ "pass@1": 0.8438893844781445,
760
+ "pass@2": 0.8844832296693336,
761
+ "pass@4": 0.9135616027200477,
762
+ "pass@8": 0.9341262715675477,
763
+ "pass@16": 0.9485360735641319,
764
+ "pass@32": 0.9589141991748595,
765
+ "pass@64": 0.9667030192282954,
766
+ "pass@128": 0.9726434730895034
767
+ },
768
+ "per_op_pass_at_k": {
769
+ "11": {
770
+ "pass@1": 0.9768213478915663,
771
+ "pass@2": 0.982426507209942,
772
+ "pass@4": 0.9875867705919291,
773
+ "pass@8": 0.9916699109297928,
774
+ "pass@16": 0.9941198985224184,
775
+ "pass@32": 0.9952745122110707,
776
+ "pass@64": 0.9962408632343975,
777
+ "pass@128": 0.9969879518072289
778
+ },
779
+ "12": {
780
+ "pass@1": 0.965492750783699,
781
+ "pass@2": 0.9797927517093281,
782
+ "pass@4": 0.9877445484870819,
783
+ "pass@8": 0.9923678770900078,
784
+ "pass@16": 0.9955227193860775,
785
+ "pass@32": 0.9973880317416322,
786
+ "pass@64": 0.9984300583339356,
787
+ "pass@128": 1.0
788
+ },
789
+ "13": {
790
+ "pass@1": 0.9623599439775911,
791
+ "pass@2": 0.9779697804318578,
792
+ "pass@4": 0.9872410336838148,
793
+ "pass@8": 0.9920194344744313,
794
+ "pass@16": 0.9942491977157041,
795
+ "pass@32": 0.9950794358980206,
796
+ "pass@64": 0.9957983155432268,
797
+ "pass@128": 0.9971988795518207
798
+ },
799
+ "14": {
800
+ "pass@1": 0.9557291666666666,
801
+ "pass@2": 0.9763930618870013,
802
+ "pass@4": 0.9898799393496869,
803
+ "pass@8": 0.9971921128374414,
804
+ "pass@16": 0.9996866455629769,
805
+ "pass@32": 0.9999957420781709,
806
+ "pass@64": 0.9999999999150341,
807
+ "pass@128": 1.0
808
+ },
809
+ "15": {
810
+ "pass@1": 0.9709043560606061,
811
+ "pass@2": 0.9843362264376043,
812
+ "pass@4": 0.9913319070911589,
813
+ "pass@8": 0.9957115636967746,
814
+ "pass@16": 0.9984277498659098,
815
+ "pass@32": 0.9997408383719552,
816
+ "pass@64": 0.9999955357422065,
817
+ "pass@128": 1.0
818
+ },
819
+ "16": {
820
+ "pass@1": 0.9107015669515669,
821
+ "pass@2": 0.9377124133521775,
822
+ "pass@4": 0.9564160948898481,
823
+ "pass@8": 0.9692630161138946,
824
+ "pass@16": 0.9776624723599159,
825
+ "pass@32": 0.9832541934776856,
826
+ "pass@64": 0.9874615955124632,
827
+ "pass@128": 0.9914529914529915
828
+ },
829
+ "17": {
830
+ "pass@1": 0.8672360248447205,
831
+ "pass@2": 0.9112839750330124,
832
+ "pass@4": 0.9387636921937549,
833
+ "pass@8": 0.9558194693071742,
834
+ "pass@16": 0.9657225480978907,
835
+ "pass@32": 0.9716417279156446,
836
+ "pass@64": 0.9759516660247486,
837
+ "pass@128": 0.9782608695652174
838
+ },
839
+ "18": {
840
+ "pass@1": 0.7839613970588235,
841
+ "pass@2": 0.8523347035664656,
842
+ "pass@4": 0.8947464600013231,
843
+ "pass@8": 0.9214377697528552,
844
+ "pass@16": 0.9388117402083257,
845
+ "pass@32": 0.951005420422579,
846
+ "pass@64": 0.9607119551856902,
847
+ "pass@128": 0.9705882352941176
848
+ },
849
+ "19": {
850
+ "pass@1": 0.5933547247023809,
851
+ "pass@2": 0.6915281830005624,
852
+ "pass@4": 0.766301561356169,
853
+ "pass@8": 0.8222817559953494,
854
+ "pass@16": 0.8649021620408612,
855
+ "pass@32": 0.8975421565193381,
856
+ "pass@64": 0.9221817078073432,
857
+ "pass@128": 0.9404761904761905
858
+ },
859
+ "20": {
860
+ "pass@1": 0.4492889221556886,
861
+ "pass@2": 0.5484648321467304,
862
+ "pass@4": 0.6333525578202419,
863
+ "pass@8": 0.7015890174857582,
864
+ "pass@16": 0.7546736568184237,
865
+ "pass@32": 0.796908044139665,
866
+ "pass@64": 0.829107778372377,
867
+ "pass@128": 0.8502994011976048
868
+ }
869
+ }
870
+ },
871
+ "movie_festival_awards": {
872
+ "count": 418816,
873
+ "correct": 347741,
874
+ "answer_accuracy": 0.8302954041870416,
875
+ "avg_response_len": 401.41232665418704,
876
+ "resp_tokens_sum": 168117905,
877
+ "pass_at_k": {
878
+ "pass@1": 0.8302954041870416,
879
+ "pass@2": 0.8730007757902922,
880
+ "pass@4": 0.9030097709554368,
881
+ "pass@8": 0.9242862745587226,
882
+ "pass@16": 0.9390310658691144,
883
+ "pass@32": 0.9492425857604578,
884
+ "pass@64": 0.9572353621372555,
885
+ "pass@128": 0.9648533007334963
886
+ },
887
+ "per_op_pass_at_k": {
888
+ "11": {
889
+ "pass@1": 0.963640873015873,
890
+ "pass@2": 0.9752730127484065,
891
+ "pass@4": 0.9833094119187484,
892
+ "pass@8": 0.9885337281484384,
893
+ "pass@16": 0.9929572101573484,
894
+ "pass@32": 0.9967672908887808,
895
+ "pass@64": 0.9991148007644227,
896
+ "pass@128": 1.0
897
+ },
898
+ "12": {
899
+ "pass@1": 0.9675793195718655,
900
+ "pass@2": 0.9831443087962632,
901
+ "pass@4": 0.9927234121537561,
902
+ "pass@8": 0.9962327927192676,
903
+ "pass@16": 0.9969067136543522,
904
+ "pass@32": 0.9969418396245668,
905
+ "pass@64": 0.9969418960244639,
906
+ "pass@128": 0.9969418960244648
907
+ },
908
+ "13": {
909
+ "pass@1": 0.953125,
910
+ "pass@2": 0.9724694243948675,
911
+ "pass@4": 0.9839528441467964,
912
+ "pass@8": 0.9914051147315478,
913
+ "pass@16": 0.9962751879157801,
914
+ "pass@32": 0.9989514073218897,
915
+ "pass@64": 0.9999069142994649,
916
+ "pass@128": 1.0
917
+ },
918
+ "14": {
919
+ "pass@1": 0.9672663204747775,
920
+ "pass@2": 0.9819023224841703,
921
+ "pass@4": 0.9891655304029129,
922
+ "pass@8": 0.9926525053330164,
923
+ "pass@16": 0.9941520139636356,
924
+ "pass@32": 0.9947959873034944,
925
+ "pass@64": 0.9955489586054439,
926
+ "pass@128": 0.9970326409495549
927
+ },
928
+ "15": {
929
+ "pass@1": 0.9480372299382716,
930
+ "pass@2": 0.9670028768105379,
931
+ "pass@4": 0.9780621108704005,
932
+ "pass@8": 0.9842947803211456,
933
+ "pass@16": 0.9879716058879758,
934
+ "pass@32": 0.9901270313479683,
935
+ "pass@64": 0.9919070327284573,
936
+ "pass@128": 0.9938271604938271
937
+ },
938
+ "16": {
939
+ "pass@1": 0.882973820058997,
940
+ "pass@2": 0.9149514842171274,
941
+ "pass@4": 0.9361787777080962,
942
+ "pass@8": 0.9505317245196182,
943
+ "pass@16": 0.95963740909398,
944
+ "pass@32": 0.9664879570651409,
945
+ "pass@64": 0.9730817511351202,
946
+ "pass@128": 0.9793510324483776
947
+ },
948
+ "17": {
949
+ "pass@1": 0.8233951430722891,
950
+ "pass@2": 0.8709084616023144,
951
+ "pass@4": 0.900955382553837,
952
+ "pass@8": 0.920503593025735,
953
+ "pass@16": 0.9343316545762004,
954
+ "pass@32": 0.9442573518899536,
955
+ "pass@64": 0.9519856298182777,
956
+ "pass@128": 0.9608433734939759
957
+ },
958
+ "18": {
959
+ "pass@1": 0.7824344758064516,
960
+ "pass@2": 0.8496388430276858,
961
+ "pass@4": 0.8933080521184847,
962
+ "pass@8": 0.9212389467048724,
963
+ "pass@16": 0.9380265394631339,
964
+ "pass@32": 0.9476456964449388,
965
+ "pass@64": 0.9534177140834851,
966
+ "pass@128": 0.9580645161290322
967
+ },
968
+ "19": {
969
+ "pass@1": 0.5686367069486404,
970
+ "pass@2": 0.6704094012417636,
971
+ "pass@4": 0.7465739156094909,
972
+ "pass@8": 0.8053303353516325,
973
+ "pass@16": 0.8499870368405819,
974
+ "pass@32": 0.8823623062494177,
975
+ "pass@64": 0.907953968913336,
976
+ "pass@128": 0.9305135951661632
977
+ },
978
+ "20": {
979
+ "pass@1": 0.4545561186186186,
980
+ "pass@2": 0.5521487284528623,
981
+ "pass@4": 0.6327929909662195,
982
+ "pass@8": 0.6981138753732286,
983
+ "pass@16": 0.7452411820752879,
984
+ "pass@32": 0.7785809400350618,
985
+ "pass@64": 0.8062433242479462,
986
+ "pass@128": 0.8348348348348348
987
+ }
988
+ }
989
+ }
990
+ }
991
+ },
992
+ "total": {
993
+ "answer_accuracy": 0.9104650493421053,
994
+ "avg_loss": 0.0,
995
+ "count": 2432000,
996
+ "validation_metrics": {
997
+ "id": {},
998
+ "ood": {}
999
+ },
1000
+ "pass_at_k": {
1001
+ "pass@1": 0.9104650493421053,
1002
+ "pass@2": 0.9329827885412267,
1003
+ "pass@4": 0.9490265442543343,
1004
+ "pass@8": 0.960436861478886,
1005
+ "pass@16": 0.968508608039099,
1006
+ "pass@32": 0.9743447684400129,
1007
+ "pass@64": 0.9789325133712852,
1008
+ "pass@128": 0.9828947368421053
1009
+ },
1010
+ "per_op_pass_at_k": {
1011
+ "10": {
1012
+ "pass@1": 0.95884375,
1013
+ "pass@2": 0.9682652559055118,
1014
+ "pass@4": 0.9756639486314218,
1015
+ "pass@8": 0.9813791969954038,
1016
+ "pass@16": 0.9855953958960963,
1017
+ "pass@32": 0.9888302276998161,
1018
+ "pass@64": 0.9917058153968907,
1019
+ "pass@128": 0.995
1020
+ },
1021
+ "2": {
1022
+ "pass@1": 1.0,
1023
+ "pass@2": 1.0,
1024
+ "pass@4": 1.0,
1025
+ "pass@8": 1.0,
1026
+ "pass@16": 1.0,
1027
+ "pass@32": 1.0,
1028
+ "pass@64": 1.0,
1029
+ "pass@128": 1.0
1030
+ },
1031
+ "3": {
1032
+ "pass@1": 0.999390625,
1033
+ "pass@2": 0.9997413877952757,
1034
+ "pass@4": 0.9999365339332582,
1035
+ "pass@8": 0.9999964696284563,
1036
+ "pass@16": 0.9999999930573713,
1037
+ "pass@32": 0.9999999999999976,
1038
+ "pass@64": 1.0,
1039
+ "pass@128": 1.0
1040
+ },
1041
+ "4": {
1042
+ "pass@1": 0.9999921875,
1043
+ "pass@2": 1.0,
1044
+ "pass@4": 1.0,
1045
+ "pass@8": 1.0,
1046
+ "pass@16": 1.0,
1047
+ "pass@32": 1.0,
1048
+ "pass@64": 1.0,
1049
+ "pass@128": 1.0
1050
+ },
1051
+ "5": {
1052
+ "pass@1": 0.9945,
1053
+ "pass@2": 0.9970660679133861,
1054
+ "pass@4": 0.9983636825084363,
1055
+ "pass@8": 0.9990063609804485,
1056
+ "pass@16": 0.9993881074316475,
1057
+ "pass@32": 0.999688172223201,
1058
+ "pass@64": 0.9999404409407284,
1059
+ "pass@128": 1.0
1060
+ },
1061
+ "6": {
1062
+ "pass@1": 0.9991796875,
1063
+ "pass@2": 0.9996582185039371,
1064
+ "pass@4": 0.9999079231346082,
1065
+ "pass@8": 0.9999925579902273,
1066
+ "pass@16": 0.9999999657010183,
1067
+ "pass@32": 0.9999999999998928,
1068
+ "pass@64": 1.0,
1069
+ "pass@128": 1.0
1070
+ },
1071
+ "7": {
1072
+ "pass@1": 0.997015625,
1073
+ "pass@2": 0.9979917568897638,
1074
+ "pass@4": 0.9985803902324709,
1075
+ "pass@8": 0.9990458205281643,
1076
+ "pass@16": 0.9994464582913845,
1077
+ "pass@32": 0.999767693754703,
1078
+ "pass@64": 0.9999711810355609,
1079
+ "pass@128": 1.0
1080
+ },
1081
+ "8": {
1082
+ "pass@1": 0.9955234375,
1083
+ "pass@2": 0.9983201279527558,
1084
+ "pass@4": 0.9996303053055869,
1085
+ "pass@8": 0.999974862902426,
1086
+ "pass@16": 0.9999998996583422,
1087
+ "pass@32": 0.9999999999997113,
1088
+ "pass@64": 1.0,
1089
+ "pass@128": 1.0
1090
+ },
1091
+ "9": {
1092
+ "pass@1": 0.994578125,
1093
+ "pass@2": 0.996369217519685,
1094
+ "pass@4": 0.9972775294338206,
1095
+ "pass@8": 0.9980213304765657,
1096
+ "pass@16": 0.9986472977257898,
1097
+ "pass@32": 0.9989462357068267,
1098
+ "pass@64": 0.9989993313106743,
1099
+ "pass@128": 0.999
1100
+ },
1101
+ "11": {
1102
+ "pass@1": 0.970671875,
1103
+ "pass@2": 0.9794998769685037,
1104
+ "pass@4": 0.9857863502999626,
1105
+ "pass@8": 0.9900398112371814,
1106
+ "pass@16": 0.9931495940187157,
1107
+ "pass@32": 0.9953983463354901,
1108
+ "pass@64": 0.9969441662809593,
1109
+ "pass@128": 0.998
1110
+ },
1111
+ "12": {
1112
+ "pass@1": 0.966296875,
1113
+ "pass@2": 0.9809158464566927,
1114
+ "pass@4": 0.9901372777465317,
1115
+ "pass@8": 0.9945470208837859,
1116
+ "pass@16": 0.996475576710408,
1117
+ "pass@32": 0.9975372922449343,
1118
+ "pass@64": 0.9982497123716464,
1119
+ "pass@128": 0.999
1120
+ },
1121
+ "13": {
1122
+ "pass@1": 0.9553671875,
1123
+ "pass@2": 0.973431348425197,
1124
+ "pass@4": 0.9843508790776158,
1125
+ "pass@8": 0.9907141222601963,
1126
+ "pass@16": 0.9945169364443083,
1127
+ "pass@32": 0.99655956862069,
1128
+ "pass@64": 0.9974491256090368,
1129
+ "pass@128": 0.998
1130
+ },
1131
+ "14": {
1132
+ "pass@1": 0.949578125,
1133
+ "pass@2": 0.9686524360236218,
1134
+ "pass@4": 0.9809611437007878,
1135
+ "pass@8": 0.9883708817653398,
1136
+ "pass@16": 0.9925049124837143,
1137
+ "pass@32": 0.9948066901098008,
1138
+ "pass@64": 0.9961112856236247,
1139
+ "pass@128": 0.997
1140
+ },
1141
+ "15": {
1142
+ "pass@1": 0.965375,
1143
+ "pass@2": 0.9803630659448824,
1144
+ "pass@4": 0.988369140607424,
1145
+ "pass@8": 0.9930486759883792,
1146
+ "pass@16": 0.9955475560142018,
1147
+ "pass@32": 0.9967154674849088,
1148
+ "pass@64": 0.997376405398854,
1149
+ "pass@128": 0.998
1150
+ },
1151
+ "16": {
1152
+ "pass@1": 0.887765625,
1153
+ "pass@2": 0.9196377952755908,
1154
+ "pass@4": 0.9421223665166858,
1155
+ "pass@8": 0.9573031508529518,
1156
+ "pass@16": 0.9670828002231159,
1157
+ "pass@32": 0.9741994820696727,
1158
+ "pass@64": 0.9803724490952007,
1159
+ "pass@128": 0.986
1160
+ },
1161
+ "17": {
1162
+ "pass@1": 0.856984375,
1163
+ "pass@2": 0.8984932332677166,
1164
+ "pass@4": 0.924790269216348,
1165
+ "pass@8": 0.9417427006423036,
1166
+ "pass@16": 0.9525526931446574,
1167
+ "pass@32": 0.9599937953920628,
1168
+ "pass@64": 0.9663307158630652,
1169
+ "pass@128": 0.972
1170
+ },
1171
+ "18": {
1172
+ "pass@1": 0.77284375,
1173
+ "pass@2": 0.8381781496062998,
1174
+ "pass@4": 0.8801090434008246,
1175
+ "pass@8": 0.9078199779722668,
1176
+ "pass@16": 0.9261821010586693,
1177
+ "pass@32": 0.9385224656210279,
1178
+ "pass@64": 0.9478627592988191,
1179
+ "pass@128": 0.957
1180
+ },
1181
+ "19": {
1182
+ "pass@1": 0.584125,
1183
+ "pass@2": 0.6814692421259851,
1184
+ "pass@4": 0.7541173871391076,
1185
+ "pass@8": 0.8081890874701764,
1186
+ "pass@16": 0.8491870017860157,
1187
+ "pass@32": 0.8800031510922511,
1188
+ "pass@64": 0.9043406794110973,
1189
+ "pass@128": 0.924
1190
+ },
1191
+ "20": {
1192
+ "pass@1": 0.4508046875,
1193
+ "pass@2": 0.5486199557086607,
1194
+ "pass@4": 0.6314001699475059,
1195
+ "pass@8": 0.6991083395246123,
1196
+ "pass@16": 0.7513872630976118,
1197
+ "pass@32": 0.7915820120051243,
1198
+ "pass@64": 0.8240636864182797,
1199
+ "pass@128": 0.852
1200
+ }
1201
+ },
1202
+ "per_op_accuracy": {
1203
+ "10": 0.95884375,
1204
+ "2": 1.0,
1205
+ "3": 0.999390625,
1206
+ "4": 0.9999921875,
1207
+ "5": 0.9945,
1208
+ "6": 0.9991796875,
1209
+ "7": 0.997015625,
1210
+ "8": 0.9955234375,
1211
+ "9": 0.994578125,
1212
+ "11": 0.970671875,
1213
+ "12": 0.966296875,
1214
+ "13": 0.9553671875,
1215
+ "14": 0.949578125,
1216
+ "15": 0.965375,
1217
+ "16": 0.887765625,
1218
+ "17": 0.856984375,
1219
+ "18": 0.77284375,
1220
+ "19": 0.584125,
1221
+ "20": 0.4508046875
1222
+ },
1223
+ "per_op_avg_response_len": {
1224
+ "10": 281.7881875,
1225
+ "2": 115.6349609375,
1226
+ "3": 144.9606328125,
1227
+ "4": 159.9038359375,
1228
+ "5": 173.56409375,
1229
+ "6": 199.1092890625,
1230
+ "7": 224.44571875,
1231
+ "8": 243.821984375,
1232
+ "9": 259.724859375,
1233
+ "11": 301.01784375,
1234
+ "12": 313.407609375,
1235
+ "13": 334.547984375,
1236
+ "14": 361.579859375,
1237
+ "15": 381.650609375,
1238
+ "16": 390.577,
1239
+ "17": 411.0501640625,
1240
+ "18": 426.7855859375,
1241
+ "19": 424.2508671875,
1242
+ "20": 435.49165625
1243
+ },
1244
+ "per_op_avg_loss": {},
1245
+ "per_op_length": {
1246
+ "10": 281.7881875,
1247
+ "2": 115.6349609375,
1248
+ "3": 144.9606328125,
1249
+ "4": 159.9038359375,
1250
+ "5": 173.56409375,
1251
+ "6": 199.1092890625,
1252
+ "7": 224.44571875,
1253
+ "8": 243.821984375,
1254
+ "9": 259.724859375,
1255
+ "11": 301.01784375,
1256
+ "12": 313.407609375,
1257
+ "13": 334.547984375,
1258
+ "14": 361.579859375,
1259
+ "15": 381.650609375,
1260
+ "16": 390.577,
1261
+ "17": 411.0501640625,
1262
+ "18": 426.7855859375,
1263
+ "19": 424.2508671875,
1264
+ "20": 435.49165625
1265
+ },
1266
+ "per_op_loss": {},
1267
+ "per_template": {
1268
+ "crazy_zootopia": {
1269
+ "count": 809728,
1270
+ "correct": 735827,
1271
+ "answer_accuracy": 0.9087335500316156,
1272
+ "avg_response_len": 280.81283097533986,
1273
+ "resp_tokens_sum": 227382012,
1274
+ "pass_at_k": {
1275
+ "pass@1": 0.9087335500316156,
1276
+ "pass@2": 0.9306044600025811,
1277
+ "pass@4": 0.9464375050603238,
1278
+ "pass@8": 0.9578451948086137,
1279
+ "pass@16": 0.9661519899120048,
1280
+ "pass@32": 0.9723665816849368,
1281
+ "pass@64": 0.9774353954902267,
1282
+ "pass@128": 0.9818210559595321
1283
+ },
1284
+ "per_op_pass_at_k": {
1285
+ "10": {
1286
+ "pass@1": 0.9643482669616519,
1287
+ "pass@2": 0.9724997386941677,
1288
+ "pass@4": 0.9787036025917114,
1289
+ "pass@8": 0.9837184467724707,
1290
+ "pass@16": 0.9876176547055514,
1291
+ "pass@32": 0.990048743242238,
1292
+ "pass@64": 0.9918928791392225,
1293
+ "pass@128": 0.9941002949852508
1294
+ },
1295
+ "2": {
1296
+ "pass@1": 1.0,
1297
+ "pass@2": 1.0,
1298
+ "pass@4": 1.0,
1299
+ "pass@8": 1.0,
1300
+ "pass@16": 1.0,
1301
+ "pass@32": 1.0,
1302
+ "pass@64": 1.0,
1303
+ "pass@128": 1.0
1304
+ },
1305
+ "3": {
1306
+ "pass@1": 0.9998805428134556,
1307
+ "pass@2": 0.9999977425413568,
1308
+ "pass@4": 0.9999999997133384,
1309
+ "pass@8": 1.0,
1310
+ "pass@16": 1.0,
1311
+ "pass@32": 1.0,
1312
+ "pass@64": 1.0,
1313
+ "pass@128": 1.0
1314
+ },
1315
+ "4": {
1316
+ "pass@1": 1.0,
1317
+ "pass@2": 1.0,
1318
+ "pass@4": 1.0,
1319
+ "pass@8": 1.0,
1320
+ "pass@16": 1.0,
1321
+ "pass@32": 1.0,
1322
+ "pass@64": 1.0,
1323
+ "pass@128": 1.0
1324
+ },
1325
+ "5": {
1326
+ "pass@1": 0.9967757936507936,
1327
+ "pass@2": 0.9988044463192103,
1328
+ "pass@4": 0.9997930303354938,
1329
+ "pass@8": 0.9999940728357846,
1330
+ "pass@16": 0.999999996928095,
1331
+ "pass@32": 1.0,
1332
+ "pass@64": 1.0,
1333
+ "pass@128": 1.0
1334
+ },
1335
+ "6": {
1336
+ "pass@1": 0.9981521332335329,
1337
+ "pass@2": 0.999078737210618,
1338
+ "pass@4": 0.9997273029868273,
1339
+ "pass@8": 0.9999777200738017,
1340
+ "pass@16": 0.9999998973084382,
1341
+ "pass@32": 0.999999999999679,
1342
+ "pass@64": 1.0,
1343
+ "pass@128": 1.0
1344
+ },
1345
+ "7": {
1346
+ "pass@1": 0.998959874260355,
1347
+ "pass@2": 0.9998143607603783,
1348
+ "pass@4": 0.9999912155026479,
1349
+ "pass@8": 0.9999999836752375,
1350
+ "pass@16": 0.9999999999999905,
1351
+ "pass@32": 1.0,
1352
+ "pass@64": 1.0,
1353
+ "pass@128": 1.0
1354
+ },
1355
+ "8": {
1356
+ "pass@1": 0.9960687099358975,
1357
+ "pass@2": 0.9985512252675145,
1358
+ "pass@4": 0.9996649123787412,
1359
+ "pass@8": 0.9999730867256917,
1360
+ "pass@16": 0.9999998586577866,
1361
+ "pass@32": 0.9999999999993815,
1362
+ "pass@64": 1.0,
1363
+ "pass@128": 1.0
1364
+ },
1365
+ "9": {
1366
+ "pass@1": 0.9940801056338028,
1367
+ "pass@2": 0.9950447765332151,
1368
+ "pass@4": 0.9956578631896364,
1369
+ "pass@8": 0.996375867480201,
1370
+ "pass@16": 0.9969724240620078,
1371
+ "pass@32": 0.9971729386969103,
1372
+ "pass@64": 0.9971830959162251,
1373
+ "pass@128": 0.9971830985915493
1374
+ },
1375
+ "11": {
1376
+ "pass@1": 0.9711623583569405,
1377
+ "pass@2": 0.9805191998840088,
1378
+ "pass@4": 0.986303336286222,
1379
+ "pass@8": 0.989850641477996,
1380
+ "pass@16": 0.99240868699634,
1381
+ "pass@32": 0.994293234140082,
1382
+ "pass@64": 0.9956686613210934,
1383
+ "pass@128": 0.9971671388101983
1384
+ },
1385
+ "12": {
1386
+ "pass@1": 0.9658368644067796,
1387
+ "pass@2": 0.979869405889942,
1388
+ "pass@4": 0.9899045508612269,
1389
+ "pass@8": 0.9949535165900368,
1390
+ "pass@16": 0.9969359713595375,
1391
+ "pass@32": 0.9982218320963844,
1392
+ "pass@64": 0.9992952648675736,
1393
+ "pass@128": 1.0
1394
+ },
1395
+ "13": {
1396
+ "pass@1": 0.9498187695924765,
1397
+ "pass@2": 0.9693292893639082,
1398
+ "pass@4": 0.9815207164543299,
1399
+ "pass@8": 0.9885514952344922,
1400
+ "pass@16": 0.993030758542598,
1401
+ "pass@32": 0.9957866897580077,
1402
+ "pass@64": 0.9968002718717178,
1403
+ "pass@128": 0.9968652037617555
1404
+ },
1405
+ "14": {
1406
+ "pass@1": 0.9244548286604362,
1407
+ "pass@2": 0.9464950971373904,
1408
+ "pass@4": 0.962845547343965,
1409
+ "pass@8": 0.9744775229835171,
1410
+ "pass@16": 0.9831241464032126,
1411
+ "pass@32": 0.9892894037314296,
1412
+ "pass@64": 0.9925585252418944,
1413
+ "pass@128": 0.9937694704049844
1414
+ },
1415
+ "15": {
1416
+ "pass@1": 0.9763367052023122,
1417
+ "pass@2": 0.9890843327568163,
1418
+ "pass@4": 0.995195050131017,
1419
+ "pass@8": 0.9987062171803248,
1420
+ "pass@16": 0.9998947926322176,
1421
+ "pass@32": 0.9999995163740522,
1422
+ "pass@64": 0.9999999999997273,
1423
+ "pass@128": 1.0
1424
+ },
1425
+ "16": {
1426
+ "pass@1": 0.8670362903225807,
1427
+ "pass@2": 0.9042973710947418,
1428
+ "pass@4": 0.9324377792493678,
1429
+ "pass@8": 0.9511663793058849,
1430
+ "pass@16": 0.9632457765868611,
1431
+ "pass@32": 0.972380137786845,
1432
+ "pass@64": 0.9803184368887754,
1433
+ "pass@128": 0.9870967741935484
1434
+ },
1435
+ "17": {
1436
+ "pass@1": 0.8796739523121387,
1437
+ "pass@2": 0.9130583354194169,
1438
+ "pass@4": 0.9346565702950422,
1439
+ "pass@8": 0.949022076996675,
1440
+ "pass@16": 0.9577801252538675,
1441
+ "pass@32": 0.9642535207391926,
1442
+ "pass@64": 0.9711417638827387,
1443
+ "pass@128": 0.976878612716763
1444
+ },
1445
+ "18": {
1446
+ "pass@1": 0.7535491071428572,
1447
+ "pass@2": 0.8142751687289084,
1448
+ "pass@4": 0.854199288124698,
1449
+ "pass@8": 0.8827058936508151,
1450
+ "pass@16": 0.9034225204407647,
1451
+ "pass@32": 0.9183155907983432,
1452
+ "pass@64": 0.9304605804851537,
1453
+ "pass@128": 0.9428571428571428
1454
+ },
1455
+ "19": {
1456
+ "pass@1": 0.5902073948948949,
1457
+ "pass@2": 0.6823130955758907,
1458
+ "pass@4": 0.7493216109810598,
1459
+ "pass@8": 0.7968110404034479,
1460
+ "pass@16": 0.8325350334716398,
1461
+ "pass@32": 0.859961150550141,
1462
+ "pass@64": 0.8827473329655091,
1463
+ "pass@128": 0.9009009009009009
1464
+ },
1465
+ "20": {
1466
+ "pass@1": 0.4485735735735736,
1467
+ "pass@2": 0.5452467723629141,
1468
+ "pass@4": 0.6280490980294128,
1469
+ "pass@8": 0.6976146762314849,
1470
+ "pass@16": 0.7542370813489142,
1471
+ "pass@32": 0.799241057750153,
1472
+ "pass@64": 0.8368248092112288,
1473
+ "pass@128": 0.8708708708708709
1474
+ }
1475
+ }
1476
+ },
1477
+ "teachers_in_school": {
1478
+ "count": 821120,
1479
+ "correct": 751099,
1480
+ "answer_accuracy": 0.9147250097427904,
1481
+ "avg_response_len": 290.0505114964926,
1482
+ "resp_tokens_sum": 238166276,
1483
+ "pass_at_k": {
1484
+ "pass@1": 0.9147250097427904,
1485
+ "pass@2": 0.9368544058892373,
1486
+ "pass@4": 0.9526741754464987,
1487
+ "pass@8": 0.9638412119281327,
1488
+ "pass@16": 0.9716894634319847,
1489
+ "pass@32": 0.9774218920691676,
1490
+ "pass@64": 0.9817877251624777,
1491
+ "pass@128": 0.9851909586905689
1492
+ },
1493
+ "per_op_pass_at_k": {
1494
+ "10": {
1495
+ "pass@1": 0.9476131134969326,
1496
+ "pass@2": 0.9578519002705184,
1497
+ "pass@4": 0.9660574474778076,
1498
+ "pass@8": 0.9719991236070697,
1499
+ "pass@16": 0.9763583249372905,
1500
+ "pass@32": 0.980656765738378,
1501
+ "pass@64": 0.9852951841811889,
1502
+ "pass@128": 0.99079754601227
1503
+ },
1504
+ "2": {
1505
+ "pass@1": 1.0,
1506
+ "pass@2": 1.0,
1507
+ "pass@4": 1.0,
1508
+ "pass@8": 1.0,
1509
+ "pass@16": 1.0,
1510
+ "pass@32": 1.0,
1511
+ "pass@64": 1.0,
1512
+ "pass@128": 1.0
1513
+ },
1514
+ "3": {
1515
+ "pass@1": 0.9982717803030303,
1516
+ "pass@2": 0.9992185635886424,
1517
+ "pass@4": 0.9998076788696866,
1518
+ "pass@8": 0.9999893019044129,
1519
+ "pass@16": 0.9999999789617312,
1520
+ "pass@32": 0.9999999999999926,
1521
+ "pass@64": 1.0,
1522
+ "pass@128": 1.0
1523
+ },
1524
+ "4": {
1525
+ "pass@1": 0.9999768860946746,
1526
+ "pass@2": 1.0,
1527
+ "pass@4": 1.0,
1528
+ "pass@8": 1.0,
1529
+ "pass@16": 1.0,
1530
+ "pass@32": 1.0,
1531
+ "pass@64": 1.0,
1532
+ "pass@128": 1.0
1533
+ },
1534
+ "5": {
1535
+ "pass@1": 0.9955842391304348,
1536
+ "pass@2": 0.9970807657195024,
1537
+ "pass@4": 0.9974464667460045,
1538
+ "pass@8": 0.9977680565376104,
1539
+ "pass@16": 0.9983124881128989,
1540
+ "pass@32": 0.999097406302473,
1541
+ "pass@64": 0.9998273650576287,
1542
+ "pass@128": 1.0
1543
+ },
1544
+ "6": {
1545
+ "pass@1": 0.9994627507163324,
1546
+ "pass@2": 0.9999027028856349,
1547
+ "pass@4": 0.9999971459513118,
1548
+ "pass@8": 0.9999999985260104,
1549
+ "pass@16": 1.0,
1550
+ "pass@32": 1.0,
1551
+ "pass@64": 1.0,
1552
+ "pass@128": 1.0
1553
+ },
1554
+ "7": {
1555
+ "pass@1": 0.9984420158959537,
1556
+ "pass@2": 0.9991658037868099,
1557
+ "pass@4": 0.9997657894822396,
1558
+ "pass@8": 0.999983097148883,
1559
+ "pass@16": 0.9999999407613452,
1560
+ "pass@32": 0.9999999999999076,
1561
+ "pass@64": 1.0,
1562
+ "pass@128": 1.0
1563
+ },
1564
+ "8": {
1565
+ "pass@1": 0.9972711267605634,
1566
+ "pass@2": 0.9988802401020296,
1567
+ "pass@4": 0.9997421626874106,
1568
+ "pass@8": 0.9999832931204404,
1569
+ "pass@16": 0.9999999422581453,
1570
+ "pass@32": 0.99999999999991,
1571
+ "pass@64": 1.0,
1572
+ "pass@128": 1.0
1573
+ },
1574
+ "9": {
1575
+ "pass@1": 0.9965147829341318,
1576
+ "pass@2": 0.9973931320430004,
1577
+ "pass@4": 0.9978456220292824,
1578
+ "pass@8": 0.998468082786387,
1579
+ "pass@16": 0.9992530482905866,
1580
+ "pass@32": 0.999851122735485,
1581
+ "pass@64": 0.9999980007921191,
1582
+ "pass@128": 1.0
1583
+ },
1584
+ "11": {
1585
+ "pass@1": 0.9768213478915663,
1586
+ "pass@2": 0.982426507209942,
1587
+ "pass@4": 0.9875867705919291,
1588
+ "pass@8": 0.9916699109297928,
1589
+ "pass@16": 0.9941198985224184,
1590
+ "pass@32": 0.9952745122110707,
1591
+ "pass@64": 0.9962408632343975,
1592
+ "pass@128": 0.9969879518072289
1593
+ },
1594
+ "12": {
1595
+ "pass@1": 0.965492750783699,
1596
+ "pass@2": 0.9797927517093281,
1597
+ "pass@4": 0.9877445484870819,
1598
+ "pass@8": 0.9923678770900078,
1599
+ "pass@16": 0.9955227193860775,
1600
+ "pass@32": 0.9973880317416322,
1601
+ "pass@64": 0.9984300583339356,
1602
+ "pass@128": 1.0
1603
+ },
1604
+ "13": {
1605
+ "pass@1": 0.9623599439775911,
1606
+ "pass@2": 0.9779697804318578,
1607
+ "pass@4": 0.9872410336838148,
1608
+ "pass@8": 0.9920194344744313,
1609
+ "pass@16": 0.9942491977157041,
1610
+ "pass@32": 0.9950794358980206,
1611
+ "pass@64": 0.9957983155432268,
1612
+ "pass@128": 0.9971988795518207
1613
+ },
1614
+ "14": {
1615
+ "pass@1": 0.9557291666666666,
1616
+ "pass@2": 0.9763930618870013,
1617
+ "pass@4": 0.9898799393496869,
1618
+ "pass@8": 0.9971921128374414,
1619
+ "pass@16": 0.9996866455629769,
1620
+ "pass@32": 0.9999957420781709,
1621
+ "pass@64": 0.9999999999150341,
1622
+ "pass@128": 1.0
1623
+ },
1624
+ "15": {
1625
+ "pass@1": 0.9709043560606061,
1626
+ "pass@2": 0.9843362264376043,
1627
+ "pass@4": 0.9913319070911589,
1628
+ "pass@8": 0.9957115636967746,
1629
+ "pass@16": 0.9984277498659098,
1630
+ "pass@32": 0.9997408383719552,
1631
+ "pass@64": 0.9999955357422065,
1632
+ "pass@128": 1.0
1633
+ },
1634
+ "16": {
1635
+ "pass@1": 0.9107015669515669,
1636
+ "pass@2": 0.9377124133521775,
1637
+ "pass@4": 0.9564160948898481,
1638
+ "pass@8": 0.9692630161138946,
1639
+ "pass@16": 0.9776624723599159,
1640
+ "pass@32": 0.9832541934776856,
1641
+ "pass@64": 0.9874615955124632,
1642
+ "pass@128": 0.9914529914529915
1643
+ },
1644
+ "17": {
1645
+ "pass@1": 0.8672360248447205,
1646
+ "pass@2": 0.9112839750330124,
1647
+ "pass@4": 0.9387636921937549,
1648
+ "pass@8": 0.9558194693071742,
1649
+ "pass@16": 0.9657225480978907,
1650
+ "pass@32": 0.9716417279156446,
1651
+ "pass@64": 0.9759516660247486,
1652
+ "pass@128": 0.9782608695652174
1653
+ },
1654
+ "18": {
1655
+ "pass@1": 0.7839613970588235,
1656
+ "pass@2": 0.8523347035664656,
1657
+ "pass@4": 0.8947464600013231,
1658
+ "pass@8": 0.9214377697528552,
1659
+ "pass@16": 0.9388117402083257,
1660
+ "pass@32": 0.951005420422579,
1661
+ "pass@64": 0.9607119551856902,
1662
+ "pass@128": 0.9705882352941176
1663
+ },
1664
+ "19": {
1665
+ "pass@1": 0.5933547247023809,
1666
+ "pass@2": 0.6915281830005624,
1667
+ "pass@4": 0.766301561356169,
1668
+ "pass@8": 0.8222817559953494,
1669
+ "pass@16": 0.8649021620408612,
1670
+ "pass@32": 0.8975421565193381,
1671
+ "pass@64": 0.9221817078073432,
1672
+ "pass@128": 0.9404761904761905
1673
+ },
1674
+ "20": {
1675
+ "pass@1": 0.4492889221556886,
1676
+ "pass@2": 0.5484648321467304,
1677
+ "pass@4": 0.6333525578202419,
1678
+ "pass@8": 0.7015890174857582,
1679
+ "pass@16": 0.7546736568184237,
1680
+ "pass@32": 0.796908044139665,
1681
+ "pass@64": 0.829107778372377,
1682
+ "pass@128": 0.8502994011976048
1683
+ }
1684
+ }
1685
+ },
1686
+ "movie_festival_awards": {
1687
+ "count": 801152,
1688
+ "correct": 727325,
1689
+ "answer_accuracy": 0.9078489475155775,
1690
+ "avg_response_len": 310.94691519212336,
1691
+ "resp_tokens_sum": 249115743,
1692
+ "pass_at_k": {
1693
+ "pass@1": 0.9078489475155775,
1694
+ "pass@2": 0.9314184621389209,
1695
+ "pass@4": 0.9479047528888704,
1696
+ "pass@8": 0.959567070014469,
1697
+ "pass@16": 0.9676303174059113,
1698
+ "pass@32": 0.9731903126693562,
1699
+ "pass@64": 0.9775192818766577,
1700
+ "pass@128": 0.9816264579006231
1701
+ },
1702
+ "per_op_pass_at_k": {
1703
+ "10": {
1704
+ "pass@1": 0.9642024253731343,
1705
+ "pass@2": 0.9741138059701494,
1706
+ "pass@4": 0.9819364163434796,
1707
+ "pass@8": 0.9881400872944226,
1708
+ "pass@16": 0.9925379015562921,
1709
+ "pass@32": 0.9955510391342886,
1710
+ "pass@64": 0.997754923360079,
1711
+ "pass@128": 1.0
1712
+ },
1713
+ "2": {
1714
+ "pass@1": 1.0,
1715
+ "pass@2": 1.0,
1716
+ "pass@4": 1.0,
1717
+ "pass@8": 1.0,
1718
+ "pass@16": 1.0,
1719
+ "pass@32": 1.0,
1720
+ "pass@64": 1.0,
1721
+ "pass@128": 1.0
1722
+ },
1723
+ "3": {
1724
+ "pass@1": 1.0,
1725
+ "pass@2": 1.0,
1726
+ "pass@4": 1.0,
1727
+ "pass@8": 1.0,
1728
+ "pass@16": 1.0,
1729
+ "pass@32": 1.0,
1730
+ "pass@64": 1.0,
1731
+ "pass@128": 1.0
1732
+ },
1733
+ "4": {
1734
+ "pass@1": 1.0,
1735
+ "pass@2": 1.0,
1736
+ "pass@4": 1.0,
1737
+ "pass@8": 1.0,
1738
+ "pass@16": 1.0,
1739
+ "pass@32": 1.0,
1740
+ "pass@64": 1.0,
1741
+ "pass@128": 1.0
1742
+ },
1743
+ "5": {
1744
+ "pass@1": 0.9912913602941177,
1745
+ "pass@2": 0.9954405974988421,
1746
+ "pass@4": 0.9979701380158362,
1747
+ "pass@8": 0.9993477897991202,
1748
+ "pass@16": 0.9999126470598457,
1749
+ "pass@32": 0.999998726614258,
1750
+ "pass@64": 0.999999999987784,
1751
+ "pass@128": 1.0
1752
+ },
1753
+ "6": {
1754
+ "pass@1": 0.9999507097791798,
1755
+ "pass@2": 0.999999611888025,
1756
+ "pass@4": 1.0,
1757
+ "pass@8": 1.0,
1758
+ "pass@16": 1.0,
1759
+ "pass@32": 1.0,
1760
+ "pass@64": 1.0,
1761
+ "pass@128": 1.0
1762
+ },
1763
+ "7": {
1764
+ "pass@1": 0.9933742088607594,
1765
+ "pass@2": 0.9947567558307585,
1766
+ "pass@4": 0.9957734057965857,
1767
+ "pass@8": 0.9969989697228501,
1768
+ "pass@16": 0.9982483505948174,
1769
+ "pass@32": 0.9992648536542246,
1770
+ "pass@64": 0.9999088007454459,
1771
+ "pass@128": 1.0
1772
+ },
1773
+ "8": {
1774
+ "pass@1": 0.9931493993993994,
1775
+ "pass@2": 0.9975064877869996,
1776
+ "pass@4": 0.999478633301468,
1777
+ "pass@8": 0.9999675398986609,
1778
+ "pass@16": 0.9999998926590724,
1779
+ "pass@32": 0.9999999999998089,
1780
+ "pass@64": 1.0,
1781
+ "pass@128": 1.0
1782
+ },
1783
+ "9": {
1784
+ "pass@1": 0.9930667202572347,
1785
+ "pass@2": 0.9967814011190724,
1786
+ "pass@4": 0.9985162387257863,
1787
+ "pass@8": 0.9994198002264989,
1788
+ "pass@16": 0.9999085821695214,
1789
+ "pass@32": 0.999998609246854,
1790
+ "pass@64": 0.9999999999866449,
1791
+ "pass@128": 1.0
1792
+ },
1793
+ "11": {
1794
+ "pass@1": 0.963640873015873,
1795
+ "pass@2": 0.9752730127484065,
1796
+ "pass@4": 0.9833094119187484,
1797
+ "pass@8": 0.9885337281484384,
1798
+ "pass@16": 0.9929572101573484,
1799
+ "pass@32": 0.9967672908887808,
1800
+ "pass@64": 0.9991148007644227,
1801
+ "pass@128": 1.0
1802
+ },
1803
+ "12": {
1804
+ "pass@1": 0.9675793195718655,
1805
+ "pass@2": 0.9831443087962632,
1806
+ "pass@4": 0.9927234121537561,
1807
+ "pass@8": 0.9962327927192676,
1808
+ "pass@16": 0.9969067136543522,
1809
+ "pass@32": 0.9969418396245668,
1810
+ "pass@64": 0.9969418960244639,
1811
+ "pass@128": 0.9969418960244648
1812
+ },
1813
+ "13": {
1814
+ "pass@1": 0.953125,
1815
+ "pass@2": 0.9724694243948675,
1816
+ "pass@4": 0.9839528441467964,
1817
+ "pass@8": 0.9914051147315478,
1818
+ "pass@16": 0.9962751879157801,
1819
+ "pass@32": 0.9989514073218897,
1820
+ "pass@64": 0.9999069142994649,
1821
+ "pass@128": 1.0
1822
+ },
1823
+ "14": {
1824
+ "pass@1": 0.9672663204747775,
1825
+ "pass@2": 0.9819023224841703,
1826
+ "pass@4": 0.9891655304029129,
1827
+ "pass@8": 0.9926525053330164,
1828
+ "pass@16": 0.9941520139636356,
1829
+ "pass@32": 0.9947959873034944,
1830
+ "pass@64": 0.9955489586054439,
1831
+ "pass@128": 0.9970326409495549
1832
+ },
1833
+ "15": {
1834
+ "pass@1": 0.9480372299382716,
1835
+ "pass@2": 0.9670028768105379,
1836
+ "pass@4": 0.9780621108704005,
1837
+ "pass@8": 0.9842947803211456,
1838
+ "pass@16": 0.9879716058879758,
1839
+ "pass@32": 0.9901270313479683,
1840
+ "pass@64": 0.9919070327284573,
1841
+ "pass@128": 0.9938271604938271
1842
+ },
1843
+ "16": {
1844
+ "pass@1": 0.882973820058997,
1845
+ "pass@2": 0.9149514842171274,
1846
+ "pass@4": 0.9361787777080962,
1847
+ "pass@8": 0.9505317245196182,
1848
+ "pass@16": 0.95963740909398,
1849
+ "pass@32": 0.9664879570651409,
1850
+ "pass@64": 0.9730817511351202,
1851
+ "pass@128": 0.9793510324483776
1852
+ },
1853
+ "17": {
1854
+ "pass@1": 0.8233951430722891,
1855
+ "pass@2": 0.8709084616023144,
1856
+ "pass@4": 0.900955382553837,
1857
+ "pass@8": 0.920503593025735,
1858
+ "pass@16": 0.9343316545762004,
1859
+ "pass@32": 0.9442573518899536,
1860
+ "pass@64": 0.9519856298182777,
1861
+ "pass@128": 0.9608433734939759
1862
+ },
1863
+ "18": {
1864
+ "pass@1": 0.7824344758064516,
1865
+ "pass@2": 0.8496388430276858,
1866
+ "pass@4": 0.8933080521184847,
1867
+ "pass@8": 0.9212389467048724,
1868
+ "pass@16": 0.9380265394631339,
1869
+ "pass@32": 0.9476456964449388,
1870
+ "pass@64": 0.9534177140834851,
1871
+ "pass@128": 0.9580645161290322
1872
+ },
1873
+ "19": {
1874
+ "pass@1": 0.5686367069486404,
1875
+ "pass@2": 0.6704094012417636,
1876
+ "pass@4": 0.7465739156094909,
1877
+ "pass@8": 0.8053303353516325,
1878
+ "pass@16": 0.8499870368405819,
1879
+ "pass@32": 0.8823623062494177,
1880
+ "pass@64": 0.907953968913336,
1881
+ "pass@128": 0.9305135951661632
1882
+ },
1883
+ "20": {
1884
+ "pass@1": 0.4545561186186186,
1885
+ "pass@2": 0.5521487284528623,
1886
+ "pass@4": 0.6327929909662195,
1887
+ "pass@8": 0.6981138753732286,
1888
+ "pass@16": 0.7452411820752879,
1889
+ "pass@32": 0.7785809400350618,
1890
+ "pass@64": 0.8062433242479462,
1891
+ "pass@128": 0.8348348348348348
1892
+ }
1893
+ }
1894
+ }
1895
+ }
1896
+ }
1897
+ }
Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_ood_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0856a41fc6d7287904e654c1ed69815ee5a8f798e27f64f141ecc468cdecafbb
3
+ size 2712047402
Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9a1aa48fa3d36bc185d3cb2f6d68fc7570f68245d5df5e58c01a6513a1f052
3
+ size 373191713
Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5be0f75384b390f6e7f5e8b423d9aac35197e5a6a4420a6907c1ef23577736c4
3
+ size 423962866
Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/composition_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/composition/op-difficulty-10B/graphs", "generated_path": "results/Qwen3-100M-midtrain-diff_ar-block16/composition", "results_dir": "results/Qwen3-100M-midtrain-diff_ar-block16/composition/graphs", "per_file": [{"file": "results/Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1024126, "value_mismatch": 8591, "dependency_mismatch": 126456, "answer_mismatch": 7805, "extra_nodes": 12243, "missing_nodes": 9153, "perfect_with_extra": 1350, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 337616, "dependency_mismatch": 40996, "extra_nodes": 3880, "perfect_with_extra": 438, "value_mismatch": 2510, "answer_mismatch": 2232, "missing_nodes": 2903}, "teachers_in_school": {"total": 390656, "perfect": 347014, "dependency_mismatch": 43146, "extra_nodes": 4142, "perfect_with_extra": 377, "value_mismatch": 2961, "answer_mismatch": 2821, "missing_nodes": 3349}, "movie_festival_awards": {"total": 382336, "perfect": 339496, "dependency_mismatch": 42314, "value_mismatch": 3120, "answer_mismatch": 2752, "extra_nodes": 4221, "missing_nodes": 2901, "perfect_with_extra": 535}}, "results_path": "results/Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/Qwen3-100M-midtrain-diff_ar-block16/composition/checkpoint-38646_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 619464, "value_mismatch": 264879, "dependency_mismatch": 640281, "answer_mismatch": 209944, "extra_nodes": 42043, "missing_nodes": 154289, "perfect_with_extra": 301, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "perfect": 208964, "value_mismatch": 88980, "dependency_mismatch": 214494, "answer_mismatch": 71669, "extra_nodes": 15885, "missing_nodes": 55017, "perfect_with_extra": 70}, "movie_festival_awards": {"total": 418816, "perfect": 201602, "value_mismatch": 90032, "dependency_mismatch": 210582, "answer_mismatch": 71075, "missing_nodes": 48991, "extra_nodes": 13389, "perfect_with_extra": 47}, "teachers_in_school": {"total": 430464, "perfect": 208898, "extra_nodes": 12769, "perfect_with_extra": 184, "dependency_mismatch": 215205, "missing_nodes": 50281, "value_mismatch": 85867, "answer_mismatch": 67200}}, "results_path": "results/Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1643590, "value_mismatch": 273470, "dependency_mismatch": 766737, "answer_mismatch": 217749, "extra_nodes": 54286, "missing_nodes": 163442, "perfect_with_extra": 1651, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/composition_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 546580, "dependency_mismatch": 255490, "extra_nodes": 19765, "perfect_with_extra": 508, "value_mismatch": 91490, "answer_mismatch": 73901, "missing_nodes": 57920}, "teachers_in_school": {"total": 821120, "perfect": 555912, "dependency_mismatch": 258351, "extra_nodes": 16911, "perfect_with_extra": 561, "value_mismatch": 88828, "answer_mismatch": 70021, "missing_nodes": 53630}, "movie_festival_awards": {"total": 801152, "perfect": 541098, "dependency_mismatch": 252896, "value_mismatch": 93152, "answer_mismatch": 73827, "extra_nodes": 17610, "missing_nodes": 51892, "perfect_with_extra": 582}}}}
Qwen3-100M-midtrain-diff_ar-block16/composition/graphs/results.json ADDED
@@ -0,0 +1,1780 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "checkpoint-38646_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "crazy_zootopia": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 1.0,
9
+ "pass@2": 1.0,
10
+ "pass@4": 1.0,
11
+ "pass@8": 1.0,
12
+ "pass@16": 1.0,
13
+ "pass@32": 1.0,
14
+ "pass@64": 1.0,
15
+ "pass@128": 1.0
16
+ },
17
+ "3": {
18
+ "pass@1": 1.0,
19
+ "pass@2": 1.0,
20
+ "pass@4": 1.0,
21
+ "pass@8": 1.0,
22
+ "pass@16": 1.0,
23
+ "pass@32": 1.0,
24
+ "pass@64": 1.0,
25
+ "pass@128": 1.0
26
+ },
27
+ "4": {
28
+ "pass@1": 0.996875,
29
+ "pass@2": 1.0,
30
+ "pass@4": 1.0,
31
+ "pass@8": 1.0,
32
+ "pass@16": 1.0,
33
+ "pass@32": 1.0,
34
+ "pass@64": 1.0,
35
+ "pass@128": 1.0
36
+ },
37
+ "5": {
38
+ "pass@1": 0.9619047619047619,
39
+ "pass@2": 0.9809523809523809,
40
+ "pass@4": 0.9968253968253968,
41
+ "pass@8": 0.9968253968253968,
42
+ "pass@16": 0.9968253968253968,
43
+ "pass@32": 0.9968253968253968,
44
+ "pass@64": 0.9968253968253968,
45
+ "pass@128": 0.9968253968253968
46
+ },
47
+ "6": {
48
+ "pass@1": 0.9580838323353293,
49
+ "pass@2": 0.9700598802395209,
50
+ "pass@4": 0.9850299401197605,
51
+ "pass@8": 0.9910179640718563,
52
+ "pass@16": 0.9970059880239521,
53
+ "pass@32": 1.0,
54
+ "pass@64": 1.0,
55
+ "pass@128": 1.0
56
+ },
57
+ "7": {
58
+ "pass@1": 0.8875739644970414,
59
+ "pass@2": 0.9556213017751479,
60
+ "pass@4": 0.9733727810650887,
61
+ "pass@8": 0.9970414201183432,
62
+ "pass@16": 1.0,
63
+ "pass@32": 1.0,
64
+ "pass@64": 1.0,
65
+ "pass@128": 1.0
66
+ },
67
+ "8": {
68
+ "pass@1": 0.8076923076923077,
69
+ "pass@2": 0.8782051282051282,
70
+ "pass@4": 0.9358974358974359,
71
+ "pass@8": 0.9775641025641025,
72
+ "pass@16": 0.9871794871794872,
73
+ "pass@32": 0.9967948717948718,
74
+ "pass@64": 1.0,
75
+ "pass@128": 1.0
76
+ },
77
+ "9": {
78
+ "pass@1": 0.7098591549295775,
79
+ "pass@2": 0.7887323943661971,
80
+ "pass@4": 0.8901408450704226,
81
+ "pass@8": 0.9323943661971831,
82
+ "pass@16": 0.9774647887323944,
83
+ "pass@32": 0.9971830985915493,
84
+ "pass@64": 0.9971830985915493,
85
+ "pass@128": 0.9971830985915493
86
+ },
87
+ "10": {
88
+ "pass@1": 0.6430678466076696,
89
+ "pass@2": 0.696165191740413,
90
+ "pass@4": 0.7905604719764012,
91
+ "pass@8": 0.8790560471976401,
92
+ "pass@16": 0.9351032448377581,
93
+ "pass@32": 0.9528023598820059,
94
+ "pass@64": 0.9587020648967551,
95
+ "pass@128": 0.9646017699115044
96
+ }
97
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 1.0,
101
+ "3": 1.0,
102
+ "4": 0.996875,
103
+ "5": 0.9619047619047619,
104
+ "6": 0.9580838323353293,
105
+ "7": 0.8875739644970414,
106
+ "8": 0.8076923076923077,
107
+ "9": 0.7098591549295775,
108
+ "10": 0.6430678466076696
109
+ },
110
+ "pass@2": {
111
+ "2": 1.0,
112
+ "3": 1.0,
113
+ "4": 1.0,
114
+ "5": 0.9809523809523809,
115
+ "6": 0.9700598802395209,
116
+ "7": 0.9556213017751479,
117
+ "8": 0.8782051282051282,
118
+ "9": 0.7887323943661971,
119
+ "10": 0.696165191740413
120
+ },
121
+ "pass@4": {
122
+ "2": 1.0,
123
+ "3": 1.0,
124
+ "4": 1.0,
125
+ "5": 0.9968253968253968,
126
+ "6": 0.9850299401197605,
127
+ "7": 0.9733727810650887,
128
+ "8": 0.9358974358974359,
129
+ "9": 0.8901408450704226,
130
+ "10": 0.7905604719764012
131
+ },
132
+ "pass@8": {
133
+ "2": 1.0,
134
+ "3": 1.0,
135
+ "4": 1.0,
136
+ "5": 0.9968253968253968,
137
+ "6": 0.9910179640718563,
138
+ "7": 0.9970414201183432,
139
+ "8": 0.9775641025641025,
140
+ "9": 0.9323943661971831,
141
+ "10": 0.8790560471976401
142
+ },
143
+ "pass@16": {
144
+ "2": 1.0,
145
+ "3": 1.0,
146
+ "4": 1.0,
147
+ "5": 0.9968253968253968,
148
+ "6": 0.9970059880239521,
149
+ "7": 1.0,
150
+ "8": 0.9871794871794872,
151
+ "9": 0.9774647887323944,
152
+ "10": 0.9351032448377581
153
+ },
154
+ "pass@32": {
155
+ "2": 1.0,
156
+ "3": 1.0,
157
+ "4": 1.0,
158
+ "5": 0.9968253968253968,
159
+ "6": 1.0,
160
+ "7": 1.0,
161
+ "8": 0.9967948717948718,
162
+ "9": 0.9971830985915493,
163
+ "10": 0.9528023598820059
164
+ },
165
+ "pass@64": {
166
+ "2": 1.0,
167
+ "3": 1.0,
168
+ "4": 1.0,
169
+ "5": 0.9968253968253968,
170
+ "6": 1.0,
171
+ "7": 1.0,
172
+ "8": 1.0,
173
+ "9": 0.9971830985915493,
174
+ "10": 0.9587020648967551
175
+ },
176
+ "pass@128": {
177
+ "2": 1.0,
178
+ "3": 1.0,
179
+ "4": 1.0,
180
+ "5": 0.9968253968253968,
181
+ "6": 1.0,
182
+ "7": 1.0,
183
+ "8": 1.0,
184
+ "9": 0.9971830985915493,
185
+ "10": 0.9646017699115044
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.8821344140493077,
190
+ "pass@2": 0.9165822357311719,
191
+ "pass@4": 0.9510300574130361,
192
+ "pass@8": 0.9739952718676123,
193
+ "pass@16": 0.9878419452887538,
194
+ "pass@32": 0.9935832489023978,
195
+ "pass@64": 0.994596420128335,
196
+ "pass@128": 0.9952718676122931
197
+ }
198
+ },
199
+ "movie_festival_awards": {
200
+ "per_op_pass_at_k": {
201
+ "2": {
202
+ "pass@1": 1.0,
203
+ "pass@2": 1.0,
204
+ "pass@4": 1.0,
205
+ "pass@8": 1.0,
206
+ "pass@16": 1.0,
207
+ "pass@32": 1.0,
208
+ "pass@64": 1.0,
209
+ "pass@128": 1.0
210
+ },
211
+ "3": {
212
+ "pass@1": 1.0,
213
+ "pass@2": 1.0,
214
+ "pass@4": 1.0,
215
+ "pass@8": 1.0,
216
+ "pass@16": 1.0,
217
+ "pass@32": 1.0,
218
+ "pass@64": 1.0,
219
+ "pass@128": 1.0
220
+ },
221
+ "4": {
222
+ "pass@1": 0.9912280701754386,
223
+ "pass@2": 0.9912280701754386,
224
+ "pass@4": 1.0,
225
+ "pass@8": 1.0,
226
+ "pass@16": 1.0,
227
+ "pass@32": 1.0,
228
+ "pass@64": 1.0,
229
+ "pass@128": 1.0
230
+ },
231
+ "5": {
232
+ "pass@1": 0.9470588235294117,
233
+ "pass@2": 0.9823529411764705,
234
+ "pass@4": 0.9970588235294118,
235
+ "pass@8": 1.0,
236
+ "pass@16": 1.0,
237
+ "pass@32": 1.0,
238
+ "pass@64": 1.0,
239
+ "pass@128": 1.0
240
+ },
241
+ "6": {
242
+ "pass@1": 0.9716088328075709,
243
+ "pass@2": 0.9779179810725552,
244
+ "pass@4": 0.9905362776025236,
245
+ "pass@8": 1.0,
246
+ "pass@16": 1.0,
247
+ "pass@32": 1.0,
248
+ "pass@64": 1.0,
249
+ "pass@128": 1.0
250
+ },
251
+ "7": {
252
+ "pass@1": 0.879746835443038,
253
+ "pass@2": 0.930379746835443,
254
+ "pass@4": 0.9683544303797469,
255
+ "pass@8": 0.9841772151898734,
256
+ "pass@16": 0.9936708860759493,
257
+ "pass@32": 0.9968354430379747,
258
+ "pass@64": 0.9968354430379747,
259
+ "pass@128": 1.0
260
+ },
261
+ "8": {
262
+ "pass@1": 0.8018018018018018,
263
+ "pass@2": 0.8498498498498499,
264
+ "pass@4": 0.918918918918919,
265
+ "pass@8": 0.9669669669669669,
266
+ "pass@16": 0.990990990990991,
267
+ "pass@32": 0.996996996996997,
268
+ "pass@64": 1.0,
269
+ "pass@128": 1.0
270
+ },
271
+ "9": {
272
+ "pass@1": 0.7620578778135049,
273
+ "pass@2": 0.8231511254019293,
274
+ "pass@4": 0.9067524115755627,
275
+ "pass@8": 0.9678456591639871,
276
+ "pass@16": 0.9807073954983923,
277
+ "pass@32": 0.9967845659163987,
278
+ "pass@64": 1.0,
279
+ "pass@128": 1.0
280
+ },
281
+ "10": {
282
+ "pass@1": 0.6,
283
+ "pass@2": 0.6597014925373135,
284
+ "pass@4": 0.7492537313432835,
285
+ "pass@8": 0.8597014925373134,
286
+ "pass@16": 0.9194029850746268,
287
+ "pass@32": 0.9432835820895522,
288
+ "pass@64": 0.9641791044776119,
289
+ "pass@128": 0.9731343283582089
290
+ }
291
+ },
292
+ "per_op_pass_at_columns": {
293
+ "pass@1": {
294
+ "2": 1.0,
295
+ "3": 1.0,
296
+ "4": 0.9912280701754386,
297
+ "5": 0.9470588235294117,
298
+ "6": 0.9716088328075709,
299
+ "7": 0.879746835443038,
300
+ "8": 0.8018018018018018,
301
+ "9": 0.7620578778135049,
302
+ "10": 0.6
303
+ },
304
+ "pass@2": {
305
+ "2": 1.0,
306
+ "3": 1.0,
307
+ "4": 0.9912280701754386,
308
+ "5": 0.9823529411764705,
309
+ "6": 0.9779179810725552,
310
+ "7": 0.930379746835443,
311
+ "8": 0.8498498498498499,
312
+ "9": 0.8231511254019293,
313
+ "10": 0.6597014925373135
314
+ },
315
+ "pass@4": {
316
+ "2": 1.0,
317
+ "3": 1.0,
318
+ "4": 1.0,
319
+ "5": 0.9970588235294118,
320
+ "6": 0.9905362776025236,
321
+ "7": 0.9683544303797469,
322
+ "8": 0.918918918918919,
323
+ "9": 0.9067524115755627,
324
+ "10": 0.7492537313432835
325
+ },
326
+ "pass@8": {
327
+ "2": 1.0,
328
+ "3": 1.0,
329
+ "4": 1.0,
330
+ "5": 1.0,
331
+ "6": 1.0,
332
+ "7": 0.9841772151898734,
333
+ "8": 0.9669669669669669,
334
+ "9": 0.9678456591639871,
335
+ "10": 0.8597014925373134
336
+ },
337
+ "pass@16": {
338
+ "2": 1.0,
339
+ "3": 1.0,
340
+ "4": 1.0,
341
+ "5": 1.0,
342
+ "6": 1.0,
343
+ "7": 0.9936708860759493,
344
+ "8": 0.990990990990991,
345
+ "9": 0.9807073954983923,
346
+ "10": 0.9194029850746268
347
+ },
348
+ "pass@32": {
349
+ "2": 1.0,
350
+ "3": 1.0,
351
+ "4": 1.0,
352
+ "5": 1.0,
353
+ "6": 1.0,
354
+ "7": 0.9968354430379747,
355
+ "8": 0.996996996996997,
356
+ "9": 0.9967845659163987,
357
+ "10": 0.9432835820895522
358
+ },
359
+ "pass@64": {
360
+ "2": 1.0,
361
+ "3": 1.0,
362
+ "4": 1.0,
363
+ "5": 1.0,
364
+ "6": 1.0,
365
+ "7": 0.9968354430379747,
366
+ "8": 1.0,
367
+ "9": 1.0,
368
+ "10": 0.9641791044776119
369
+ },
370
+ "pass@128": {
371
+ "2": 1.0,
372
+ "3": 1.0,
373
+ "4": 1.0,
374
+ "5": 1.0,
375
+ "6": 1.0,
376
+ "7": 1.0,
377
+ "8": 1.0,
378
+ "9": 1.0,
379
+ "10": 0.9731343283582089
380
+ }
381
+ },
382
+ "total_pass_at_k": {
383
+ "pass@1": 0.8855038500167393,
384
+ "pass@2": 0.9139604954804151,
385
+ "pass@4": 0.9484432541011047,
386
+ "pass@8": 0.9755607633076665,
387
+ "pass@16": 0.9872782055574155,
388
+ "pass@32": 0.9926347505858721,
389
+ "pass@64": 0.995647807164379,
390
+ "pass@128": 0.9969869434214932
391
+ }
392
+ },
393
+ "teachers_in_school": {
394
+ "per_op_pass_at_k": {
395
+ "2": {
396
+ "pass@1": 1.0,
397
+ "pass@2": 1.0,
398
+ "pass@4": 1.0,
399
+ "pass@8": 1.0,
400
+ "pass@16": 1.0,
401
+ "pass@32": 1.0,
402
+ "pass@64": 1.0,
403
+ "pass@128": 1.0
404
+ },
405
+ "3": {
406
+ "pass@1": 1.0,
407
+ "pass@2": 1.0,
408
+ "pass@4": 1.0,
409
+ "pass@8": 1.0,
410
+ "pass@16": 1.0,
411
+ "pass@32": 1.0,
412
+ "pass@64": 1.0,
413
+ "pass@128": 1.0
414
+ },
415
+ "4": {
416
+ "pass@1": 0.9792899408284024,
417
+ "pass@2": 0.9881656804733728,
418
+ "pass@4": 0.9940828402366864,
419
+ "pass@8": 1.0,
420
+ "pass@16": 1.0,
421
+ "pass@32": 1.0,
422
+ "pass@64": 1.0,
423
+ "pass@128": 1.0
424
+ },
425
+ "5": {
426
+ "pass@1": 0.9681159420289855,
427
+ "pass@2": 0.9884057971014493,
428
+ "pass@4": 0.991304347826087,
429
+ "pass@8": 0.9971014492753624,
430
+ "pass@16": 0.9971014492753624,
431
+ "pass@32": 0.9971014492753624,
432
+ "pass@64": 1.0,
433
+ "pass@128": 1.0
434
+ },
435
+ "6": {
436
+ "pass@1": 0.9742120343839542,
437
+ "pass@2": 0.9799426934097422,
438
+ "pass@4": 0.9885386819484241,
439
+ "pass@8": 0.9914040114613181,
440
+ "pass@16": 0.997134670487106,
441
+ "pass@32": 1.0,
442
+ "pass@64": 1.0,
443
+ "pass@128": 1.0
444
+ },
445
+ "7": {
446
+ "pass@1": 0.8583815028901735,
447
+ "pass@2": 0.9132947976878613,
448
+ "pass@4": 0.9508670520231214,
449
+ "pass@8": 0.9884393063583815,
450
+ "pass@16": 1.0,
451
+ "pass@32": 1.0,
452
+ "pass@64": 1.0,
453
+ "pass@128": 1.0
454
+ },
455
+ "8": {
456
+ "pass@1": 0.7971830985915493,
457
+ "pass@2": 0.8732394366197183,
458
+ "pass@4": 0.9577464788732394,
459
+ "pass@8": 0.9887323943661972,
460
+ "pass@16": 0.9971830985915493,
461
+ "pass@32": 1.0,
462
+ "pass@64": 1.0,
463
+ "pass@128": 1.0
464
+ },
465
+ "9": {
466
+ "pass@1": 0.7425149700598802,
467
+ "pass@2": 0.8053892215568862,
468
+ "pass@4": 0.8922155688622755,
469
+ "pass@8": 0.9730538922155688,
470
+ "pass@16": 0.9970059880239521,
471
+ "pass@32": 0.9970059880239521,
472
+ "pass@64": 1.0,
473
+ "pass@128": 1.0
474
+ },
475
+ "10": {
476
+ "pass@1": 0.656441717791411,
477
+ "pass@2": 0.7208588957055214,
478
+ "pass@4": 0.8006134969325154,
479
+ "pass@8": 0.8650306748466258,
480
+ "pass@16": 0.9079754601226994,
481
+ "pass@32": 0.9447852760736196,
482
+ "pass@64": 0.9478527607361963,
483
+ "pass@128": 0.950920245398773
484
+ }
485
+ },
486
+ "per_op_pass_at_columns": {
487
+ "pass@1": {
488
+ "2": 1.0,
489
+ "3": 1.0,
490
+ "4": 0.9792899408284024,
491
+ "5": 0.9681159420289855,
492
+ "6": 0.9742120343839542,
493
+ "7": 0.8583815028901735,
494
+ "8": 0.7971830985915493,
495
+ "9": 0.7425149700598802,
496
+ "10": 0.656441717791411
497
+ },
498
+ "pass@2": {
499
+ "2": 1.0,
500
+ "3": 1.0,
501
+ "4": 0.9881656804733728,
502
+ "5": 0.9884057971014493,
503
+ "6": 0.9799426934097422,
504
+ "7": 0.9132947976878613,
505
+ "8": 0.8732394366197183,
506
+ "9": 0.8053892215568862,
507
+ "10": 0.7208588957055214
508
+ },
509
+ "pass@4": {
510
+ "2": 1.0,
511
+ "3": 1.0,
512
+ "4": 0.9940828402366864,
513
+ "5": 0.991304347826087,
514
+ "6": 0.9885386819484241,
515
+ "7": 0.9508670520231214,
516
+ "8": 0.9577464788732394,
517
+ "9": 0.8922155688622755,
518
+ "10": 0.8006134969325154
519
+ },
520
+ "pass@8": {
521
+ "2": 1.0,
522
+ "3": 1.0,
523
+ "4": 1.0,
524
+ "5": 0.9971014492753624,
525
+ "6": 0.9914040114613181,
526
+ "7": 0.9884393063583815,
527
+ "8": 0.9887323943661972,
528
+ "9": 0.9730538922155688,
529
+ "10": 0.8650306748466258
530
+ },
531
+ "pass@16": {
532
+ "2": 1.0,
533
+ "3": 1.0,
534
+ "4": 1.0,
535
+ "5": 0.9971014492753624,
536
+ "6": 0.997134670487106,
537
+ "7": 1.0,
538
+ "8": 0.9971830985915493,
539
+ "9": 0.9970059880239521,
540
+ "10": 0.9079754601226994
541
+ },
542
+ "pass@32": {
543
+ "2": 1.0,
544
+ "3": 1.0,
545
+ "4": 1.0,
546
+ "5": 0.9971014492753624,
547
+ "6": 1.0,
548
+ "7": 1.0,
549
+ "8": 1.0,
550
+ "9": 0.9970059880239521,
551
+ "10": 0.9447852760736196
552
+ },
553
+ "pass@64": {
554
+ "2": 1.0,
555
+ "3": 1.0,
556
+ "4": 1.0,
557
+ "5": 1.0,
558
+ "6": 1.0,
559
+ "7": 1.0,
560
+ "8": 1.0,
561
+ "9": 1.0,
562
+ "10": 0.9478527607361963
563
+ },
564
+ "pass@128": {
565
+ "2": 1.0,
566
+ "3": 1.0,
567
+ "4": 1.0,
568
+ "5": 1.0,
569
+ "6": 1.0,
570
+ "7": 1.0,
571
+ "8": 1.0,
572
+ "9": 1.0,
573
+ "10": 0.950920245398773
574
+ }
575
+ },
576
+ "total_pass_at_k": {
577
+ "pass@1": 0.8866317169069463,
578
+ "pass@2": 0.919397116644823,
579
+ "pass@4": 0.953473132372215,
580
+ "pass@8": 0.97870249017038,
581
+ "pass@16": 0.9888597640891219,
582
+ "pass@32": 0.9934469200524246,
583
+ "pass@64": 0.994429882044561,
584
+ "pass@128": 0.9947575360419397
585
+ }
586
+ }
587
+ },
588
+ "total": {
589
+ "per_op_pass_at_k": {
590
+ "2": {
591
+ "pass@1": 1.0,
592
+ "pass@2": 1.0,
593
+ "pass@4": 1.0,
594
+ "pass@8": 1.0,
595
+ "pass@16": 1.0,
596
+ "pass@32": 1.0,
597
+ "pass@64": 1.0,
598
+ "pass@128": 1.0
599
+ },
600
+ "3": {
601
+ "pass@1": 1.0,
602
+ "pass@2": 1.0,
603
+ "pass@4": 1.0,
604
+ "pass@8": 1.0,
605
+ "pass@16": 1.0,
606
+ "pass@32": 1.0,
607
+ "pass@64": 1.0,
608
+ "pass@128": 1.0
609
+ },
610
+ "4": {
611
+ "pass@1": 0.989,
612
+ "pass@2": 0.993,
613
+ "pass@4": 0.998,
614
+ "pass@8": 1.0,
615
+ "pass@16": 1.0,
616
+ "pass@32": 1.0,
617
+ "pass@64": 1.0,
618
+ "pass@128": 1.0
619
+ },
620
+ "5": {
621
+ "pass@1": 0.959,
622
+ "pass@2": 0.984,
623
+ "pass@4": 0.995,
624
+ "pass@8": 0.998,
625
+ "pass@16": 0.998,
626
+ "pass@32": 0.998,
627
+ "pass@64": 0.999,
628
+ "pass@128": 0.999
629
+ },
630
+ "6": {
631
+ "pass@1": 0.968,
632
+ "pass@2": 0.976,
633
+ "pass@4": 0.988,
634
+ "pass@8": 0.994,
635
+ "pass@16": 0.998,
636
+ "pass@32": 1.0,
637
+ "pass@64": 1.0,
638
+ "pass@128": 1.0
639
+ },
640
+ "7": {
641
+ "pass@1": 0.875,
642
+ "pass@2": 0.933,
643
+ "pass@4": 0.964,
644
+ "pass@8": 0.99,
645
+ "pass@16": 0.998,
646
+ "pass@32": 0.999,
647
+ "pass@64": 0.999,
648
+ "pass@128": 1.0
649
+ },
650
+ "8": {
651
+ "pass@1": 0.802,
652
+ "pass@2": 0.867,
653
+ "pass@4": 0.938,
654
+ "pass@8": 0.978,
655
+ "pass@16": 0.992,
656
+ "pass@32": 0.998,
657
+ "pass@64": 1.0,
658
+ "pass@128": 1.0
659
+ },
660
+ "9": {
661
+ "pass@1": 0.737,
662
+ "pass@2": 0.805,
663
+ "pass@4": 0.896,
664
+ "pass@8": 0.957,
665
+ "pass@16": 0.985,
666
+ "pass@32": 0.997,
667
+ "pass@64": 0.999,
668
+ "pass@128": 0.999
669
+ },
670
+ "10": {
671
+ "pass@1": 0.633,
672
+ "pass@2": 0.692,
673
+ "pass@4": 0.78,
674
+ "pass@8": 0.868,
675
+ "pass@16": 0.921,
676
+ "pass@32": 0.947,
677
+ "pass@64": 0.957,
678
+ "pass@128": 0.963
679
+ }
680
+ },
681
+ "per_op_pass_at_columns": {
682
+ "pass@1": {
683
+ "2": 1.0,
684
+ "3": 1.0,
685
+ "4": 0.989,
686
+ "5": 0.959,
687
+ "6": 0.968,
688
+ "7": 0.875,
689
+ "8": 0.802,
690
+ "9": 0.737,
691
+ "10": 0.633
692
+ },
693
+ "pass@2": {
694
+ "2": 1.0,
695
+ "3": 1.0,
696
+ "4": 0.993,
697
+ "5": 0.984,
698
+ "6": 0.976,
699
+ "7": 0.933,
700
+ "8": 0.867,
701
+ "9": 0.805,
702
+ "10": 0.692
703
+ },
704
+ "pass@4": {
705
+ "2": 1.0,
706
+ "3": 1.0,
707
+ "4": 0.998,
708
+ "5": 0.995,
709
+ "6": 0.988,
710
+ "7": 0.964,
711
+ "8": 0.938,
712
+ "9": 0.896,
713
+ "10": 0.78
714
+ },
715
+ "pass@8": {
716
+ "2": 1.0,
717
+ "3": 1.0,
718
+ "4": 1.0,
719
+ "5": 0.998,
720
+ "6": 0.994,
721
+ "7": 0.99,
722
+ "8": 0.978,
723
+ "9": 0.957,
724
+ "10": 0.868
725
+ },
726
+ "pass@16": {
727
+ "2": 1.0,
728
+ "3": 1.0,
729
+ "4": 1.0,
730
+ "5": 0.998,
731
+ "6": 0.998,
732
+ "7": 0.998,
733
+ "8": 0.992,
734
+ "9": 0.985,
735
+ "10": 0.921
736
+ },
737
+ "pass@32": {
738
+ "2": 1.0,
739
+ "3": 1.0,
740
+ "4": 1.0,
741
+ "5": 0.998,
742
+ "6": 1.0,
743
+ "7": 0.999,
744
+ "8": 0.998,
745
+ "9": 0.997,
746
+ "10": 0.947
747
+ },
748
+ "pass@64": {
749
+ "2": 1.0,
750
+ "3": 1.0,
751
+ "4": 1.0,
752
+ "5": 0.999,
753
+ "6": 1.0,
754
+ "7": 0.999,
755
+ "8": 1.0,
756
+ "9": 0.999,
757
+ "10": 0.957
758
+ },
759
+ "pass@128": {
760
+ "2": 1.0,
761
+ "3": 1.0,
762
+ "4": 1.0,
763
+ "5": 0.999,
764
+ "6": 1.0,
765
+ "7": 1.0,
766
+ "8": 1.0,
767
+ "9": 0.999,
768
+ "10": 0.963
769
+ }
770
+ },
771
+ "total_pass_at_k": {
772
+ "pass@1": 0.8847777777777778,
773
+ "pass@2": 0.9166666666666666,
774
+ "pass@4": 0.951,
775
+ "pass@8": 0.9761111111111112,
776
+ "pass@16": 0.988,
777
+ "pass@32": 0.9932222222222222,
778
+ "pass@64": 0.9948888888888889,
779
+ "pass@128": 0.9956666666666667
780
+ }
781
+ },
782
+ "ks": [
783
+ 1,
784
+ 2,
785
+ 4,
786
+ 8,
787
+ 16,
788
+ 32,
789
+ 64,
790
+ 128
791
+ ],
792
+ "prompt_counts": {
793
+ "per_template": {
794
+ "crazy_zootopia": {
795
+ "per_op": {
796
+ "2": 321,
797
+ "3": 327,
798
+ "4": 320,
799
+ "5": 315,
800
+ "6": 334,
801
+ "7": 338,
802
+ "8": 312,
803
+ "9": 355,
804
+ "10": 339
805
+ },
806
+ "total": 2961
807
+ },
808
+ "movie_festival_awards": {
809
+ "per_op": {
810
+ "2": 350,
811
+ "3": 343,
812
+ "4": 342,
813
+ "5": 340,
814
+ "6": 317,
815
+ "7": 316,
816
+ "8": 333,
817
+ "9": 311,
818
+ "10": 335
819
+ },
820
+ "total": 2987
821
+ },
822
+ "teachers_in_school": {
823
+ "per_op": {
824
+ "2": 329,
825
+ "3": 330,
826
+ "4": 338,
827
+ "5": 345,
828
+ "6": 349,
829
+ "7": 346,
830
+ "8": 355,
831
+ "9": 334,
832
+ "10": 326
833
+ },
834
+ "total": 3052
835
+ }
836
+ },
837
+ "total": {
838
+ "per_op": {
839
+ "2": 1000,
840
+ "3": 1000,
841
+ "4": 1000,
842
+ "5": 1000,
843
+ "6": 1000,
844
+ "7": 1000,
845
+ "8": 1000,
846
+ "9": 1000,
847
+ "10": 1000
848
+ },
849
+ "total": 9000
850
+ }
851
+ }
852
+ },
853
+ "checkpoint-38646_ood_generations.jsonl.graph_results.jsonl": {
854
+ "per_template": {
855
+ "crazy_zootopia": {
856
+ "per_op_pass_at_k": {
857
+ "11": {
858
+ "pass@1": 0.6005665722379604,
859
+ "pass@2": 0.6742209631728046,
860
+ "pass@4": 0.773371104815864,
861
+ "pass@8": 0.8640226628895185,
862
+ "pass@16": 0.9178470254957507,
863
+ "pass@32": 0.9518413597733711,
864
+ "pass@64": 0.9745042492917847,
865
+ "pass@128": 0.9830028328611898
866
+ },
867
+ "12": {
868
+ "pass@1": 0.6638418079096046,
869
+ "pass@2": 0.7231638418079096,
870
+ "pass@4": 0.8022598870056498,
871
+ "pass@8": 0.8813559322033898,
872
+ "pass@16": 0.9293785310734464,
873
+ "pass@32": 0.9491525423728814,
874
+ "pass@64": 0.963276836158192,
875
+ "pass@128": 0.9745762711864406
876
+ },
877
+ "13": {
878
+ "pass@1": 0.5893416927899686,
879
+ "pass@2": 0.6394984326018809,
880
+ "pass@4": 0.7272727272727273,
881
+ "pass@8": 0.8056426332288401,
882
+ "pass@16": 0.8714733542319749,
883
+ "pass@32": 0.9122257053291536,
884
+ "pass@64": 0.9467084639498433,
885
+ "pass@128": 0.9717868338557993
886
+ },
887
+ "14": {
888
+ "pass@1": 0.5607476635514018,
889
+ "pass@2": 0.5919003115264797,
890
+ "pass@4": 0.6417445482866043,
891
+ "pass@8": 0.7227414330218068,
892
+ "pass@16": 0.7757009345794392,
893
+ "pass@32": 0.8286604361370716,
894
+ "pass@64": 0.8847352024922118,
895
+ "pass@128": 0.9283489096573209
896
+ },
897
+ "15": {
898
+ "pass@1": 0.5057803468208093,
899
+ "pass@2": 0.5549132947976878,
900
+ "pass@4": 0.5953757225433526,
901
+ "pass@8": 0.6647398843930635,
902
+ "pass@16": 0.7456647398843931,
903
+ "pass@32": 0.8179190751445087,
904
+ "pass@64": 0.9104046242774566,
905
+ "pass@128": 0.9450867052023122
906
+ },
907
+ "16": {
908
+ "pass@1": 0.4935483870967742,
909
+ "pass@2": 0.5193548387096775,
910
+ "pass@4": 0.5548387096774193,
911
+ "pass@8": 0.5870967741935483,
912
+ "pass@16": 0.6548387096774193,
913
+ "pass@32": 0.7032258064516129,
914
+ "pass@64": 0.7354838709677419,
915
+ "pass@128": 0.7709677419354839
916
+ },
917
+ "17": {
918
+ "pass@1": 0.5289017341040463,
919
+ "pass@2": 0.546242774566474,
920
+ "pass@4": 0.5809248554913294,
921
+ "pass@8": 0.6184971098265896,
922
+ "pass@16": 0.6705202312138728,
923
+ "pass@32": 0.7167630057803468,
924
+ "pass@64": 0.7803468208092486,
925
+ "pass@128": 0.8294797687861272
926
+ },
927
+ "18": {
928
+ "pass@1": 0.4,
929
+ "pass@2": 0.4142857142857143,
930
+ "pass@4": 0.4514285714285714,
931
+ "pass@8": 0.49714285714285716,
932
+ "pass@16": 0.5457142857142857,
933
+ "pass@32": 0.6057142857142858,
934
+ "pass@64": 0.6714285714285714,
935
+ "pass@128": 0.7314285714285714
936
+ },
937
+ "19": {
938
+ "pass@1": 0.3063063063063063,
939
+ "pass@2": 0.33633633633633636,
940
+ "pass@4": 0.39039039039039036,
941
+ "pass@8": 0.4174174174174174,
942
+ "pass@16": 0.45645645645645644,
943
+ "pass@32": 0.5015015015015015,
944
+ "pass@64": 0.5555555555555556,
945
+ "pass@128": 0.5825825825825826
946
+ },
947
+ "20": {
948
+ "pass@1": 0.21621621621621623,
949
+ "pass@2": 0.24924924924924924,
950
+ "pass@4": 0.2822822822822823,
951
+ "pass@8": 0.3153153153153153,
952
+ "pass@16": 0.34234234234234234,
953
+ "pass@32": 0.39039039039039036,
954
+ "pass@64": 0.43843843843843844,
955
+ "pass@128": 0.4924924924924925
956
+ }
957
+ },
958
+ "per_op_pass_at_columns": {
959
+ "pass@1": {
960
+ "11": 0.6005665722379604,
961
+ "12": 0.6638418079096046,
962
+ "13": 0.5893416927899686,
963
+ "14": 0.5607476635514018,
964
+ "15": 0.5057803468208093,
965
+ "16": 0.4935483870967742,
966
+ "17": 0.5289017341040463,
967
+ "18": 0.4,
968
+ "19": 0.3063063063063063,
969
+ "20": 0.21621621621621623
970
+ },
971
+ "pass@2": {
972
+ "11": 0.6742209631728046,
973
+ "12": 0.7231638418079096,
974
+ "13": 0.6394984326018809,
975
+ "14": 0.5919003115264797,
976
+ "15": 0.5549132947976878,
977
+ "16": 0.5193548387096775,
978
+ "17": 0.546242774566474,
979
+ "18": 0.4142857142857143,
980
+ "19": 0.33633633633633636,
981
+ "20": 0.24924924924924924
982
+ },
983
+ "pass@4": {
984
+ "11": 0.773371104815864,
985
+ "12": 0.8022598870056498,
986
+ "13": 0.7272727272727273,
987
+ "14": 0.6417445482866043,
988
+ "15": 0.5953757225433526,
989
+ "16": 0.5548387096774193,
990
+ "17": 0.5809248554913294,
991
+ "18": 0.4514285714285714,
992
+ "19": 0.39039039039039036,
993
+ "20": 0.2822822822822823
994
+ },
995
+ "pass@8": {
996
+ "11": 0.8640226628895185,
997
+ "12": 0.8813559322033898,
998
+ "13": 0.8056426332288401,
999
+ "14": 0.7227414330218068,
1000
+ "15": 0.6647398843930635,
1001
+ "16": 0.5870967741935483,
1002
+ "17": 0.6184971098265896,
1003
+ "18": 0.49714285714285716,
1004
+ "19": 0.4174174174174174,
1005
+ "20": 0.3153153153153153
1006
+ },
1007
+ "pass@16": {
1008
+ "11": 0.9178470254957507,
1009
+ "12": 0.9293785310734464,
1010
+ "13": 0.8714733542319749,
1011
+ "14": 0.7757009345794392,
1012
+ "15": 0.7456647398843931,
1013
+ "16": 0.6548387096774193,
1014
+ "17": 0.6705202312138728,
1015
+ "18": 0.5457142857142857,
1016
+ "19": 0.45645645645645644,
1017
+ "20": 0.34234234234234234
1018
+ },
1019
+ "pass@32": {
1020
+ "11": 0.9518413597733711,
1021
+ "12": 0.9491525423728814,
1022
+ "13": 0.9122257053291536,
1023
+ "14": 0.8286604361370716,
1024
+ "15": 0.8179190751445087,
1025
+ "16": 0.7032258064516129,
1026
+ "17": 0.7167630057803468,
1027
+ "18": 0.6057142857142858,
1028
+ "19": 0.5015015015015015,
1029
+ "20": 0.39039039039039036
1030
+ },
1031
+ "pass@64": {
1032
+ "11": 0.9745042492917847,
1033
+ "12": 0.963276836158192,
1034
+ "13": 0.9467084639498433,
1035
+ "14": 0.8847352024922118,
1036
+ "15": 0.9104046242774566,
1037
+ "16": 0.7354838709677419,
1038
+ "17": 0.7803468208092486,
1039
+ "18": 0.6714285714285714,
1040
+ "19": 0.5555555555555556,
1041
+ "20": 0.43843843843843844
1042
+ },
1043
+ "pass@128": {
1044
+ "11": 0.9830028328611898,
1045
+ "12": 0.9745762711864406,
1046
+ "13": 0.9717868338557993,
1047
+ "14": 0.9283489096573209,
1048
+ "15": 0.9450867052023122,
1049
+ "16": 0.7709677419354839,
1050
+ "17": 0.8294797687861272,
1051
+ "18": 0.7314285714285714,
1052
+ "19": 0.5825825825825826,
1053
+ "20": 0.4924924924924925
1054
+ }
1055
+ },
1056
+ "total_pass_at_k": {
1057
+ "pass@1": 0.487369985141159,
1058
+ "pass@2": 0.5260029717682021,
1059
+ "pass@4": 0.5812778603268945,
1060
+ "pass@8": 0.6389301634472511,
1061
+ "pass@16": 0.6924219910846954,
1062
+ "pass@32": 0.7390787518573552,
1063
+ "pass@64": 0.787518573551263,
1064
+ "pass@128": 0.8222882615156017
1065
+ }
1066
+ },
1067
+ "movie_festival_awards": {
1068
+ "per_op_pass_at_k": {
1069
+ "11": {
1070
+ "pass@1": 0.6095238095238096,
1071
+ "pass@2": 0.6952380952380952,
1072
+ "pass@4": 0.8095238095238095,
1073
+ "pass@8": 0.873015873015873,
1074
+ "pass@16": 0.9333333333333333,
1075
+ "pass@32": 0.9619047619047619,
1076
+ "pass@64": 0.9841269841269841,
1077
+ "pass@128": 0.9904761904761905
1078
+ },
1079
+ "12": {
1080
+ "pass@1": 0.617737003058104,
1081
+ "pass@2": 0.6788990825688074,
1082
+ "pass@4": 0.7675840978593272,
1083
+ "pass@8": 0.8837920489296636,
1084
+ "pass@16": 0.9327217125382263,
1085
+ "pass@32": 0.9724770642201835,
1086
+ "pass@64": 0.981651376146789,
1087
+ "pass@128": 0.9938837920489296
1088
+ },
1089
+ "13": {
1090
+ "pass@1": 0.5864197530864198,
1091
+ "pass@2": 0.6851851851851852,
1092
+ "pass@4": 0.7623456790123457,
1093
+ "pass@8": 0.8302469135802469,
1094
+ "pass@16": 0.8796296296296297,
1095
+ "pass@32": 0.9197530864197531,
1096
+ "pass@64": 0.9506172839506173,
1097
+ "pass@128": 0.9629629629629629
1098
+ },
1099
+ "14": {
1100
+ "pass@1": 0.56973293768546,
1101
+ "pass@2": 0.599406528189911,
1102
+ "pass@4": 0.6528189910979229,
1103
+ "pass@8": 0.7151335311572701,
1104
+ "pass@16": 0.7833827893175074,
1105
+ "pass@32": 0.8486646884272997,
1106
+ "pass@64": 0.9287833827893175,
1107
+ "pass@128": 0.9584569732937686
1108
+ },
1109
+ "15": {
1110
+ "pass@1": 0.5,
1111
+ "pass@2": 0.5308641975308642,
1112
+ "pass@4": 0.5802469135802469,
1113
+ "pass@8": 0.6481481481481481,
1114
+ "pass@16": 0.7314814814814815,
1115
+ "pass@32": 0.7962962962962963,
1116
+ "pass@64": 0.8765432098765432,
1117
+ "pass@128": 0.9320987654320988
1118
+ },
1119
+ "16": {
1120
+ "pass@1": 0.5398230088495575,
1121
+ "pass@2": 0.5781710914454278,
1122
+ "pass@4": 0.6106194690265486,
1123
+ "pass@8": 0.6460176991150443,
1124
+ "pass@16": 0.7050147492625368,
1125
+ "pass@32": 0.7463126843657817,
1126
+ "pass@64": 0.7935103244837758,
1127
+ "pass@128": 0.8230088495575221
1128
+ },
1129
+ "17": {
1130
+ "pass@1": 0.4759036144578313,
1131
+ "pass@2": 0.5090361445783133,
1132
+ "pass@4": 0.536144578313253,
1133
+ "pass@8": 0.5662650602409639,
1134
+ "pass@16": 0.6234939759036144,
1135
+ "pass@32": 0.7018072289156626,
1136
+ "pass@64": 0.7680722891566265,
1137
+ "pass@128": 0.7891566265060241
1138
+ },
1139
+ "18": {
1140
+ "pass@1": 0.4290322580645161,
1141
+ "pass@2": 0.45483870967741935,
1142
+ "pass@4": 0.4870967741935484,
1143
+ "pass@8": 0.535483870967742,
1144
+ "pass@16": 0.5709677419354838,
1145
+ "pass@32": 0.6387096774193548,
1146
+ "pass@64": 0.7258064516129032,
1147
+ "pass@128": 0.7741935483870968
1148
+ },
1149
+ "19": {
1150
+ "pass@1": 0.2990936555891239,
1151
+ "pass@2": 0.3564954682779456,
1152
+ "pass@4": 0.3867069486404834,
1153
+ "pass@8": 0.4199395770392749,
1154
+ "pass@16": 0.459214501510574,
1155
+ "pass@32": 0.4743202416918429,
1156
+ "pass@64": 0.525679758308157,
1157
+ "pass@128": 0.5770392749244713
1158
+ },
1159
+ "20": {
1160
+ "pass@1": 0.1921921921921922,
1161
+ "pass@2": 0.24324324324324326,
1162
+ "pass@4": 0.2822822822822823,
1163
+ "pass@8": 0.30930930930930933,
1164
+ "pass@16": 0.3333333333333333,
1165
+ "pass@32": 0.36036036036036034,
1166
+ "pass@64": 0.4144144144144144,
1167
+ "pass@128": 0.46846846846846846
1168
+ }
1169
+ },
1170
+ "per_op_pass_at_columns": {
1171
+ "pass@1": {
1172
+ "11": 0.6095238095238096,
1173
+ "12": 0.617737003058104,
1174
+ "13": 0.5864197530864198,
1175
+ "14": 0.56973293768546,
1176
+ "15": 0.5,
1177
+ "16": 0.5398230088495575,
1178
+ "17": 0.4759036144578313,
1179
+ "18": 0.4290322580645161,
1180
+ "19": 0.2990936555891239,
1181
+ "20": 0.1921921921921922
1182
+ },
1183
+ "pass@2": {
1184
+ "11": 0.6952380952380952,
1185
+ "12": 0.6788990825688074,
1186
+ "13": 0.6851851851851852,
1187
+ "14": 0.599406528189911,
1188
+ "15": 0.5308641975308642,
1189
+ "16": 0.5781710914454278,
1190
+ "17": 0.5090361445783133,
1191
+ "18": 0.45483870967741935,
1192
+ "19": 0.3564954682779456,
1193
+ "20": 0.24324324324324326
1194
+ },
1195
+ "pass@4": {
1196
+ "11": 0.8095238095238095,
1197
+ "12": 0.7675840978593272,
1198
+ "13": 0.7623456790123457,
1199
+ "14": 0.6528189910979229,
1200
+ "15": 0.5802469135802469,
1201
+ "16": 0.6106194690265486,
1202
+ "17": 0.536144578313253,
1203
+ "18": 0.4870967741935484,
1204
+ "19": 0.3867069486404834,
1205
+ "20": 0.2822822822822823
1206
+ },
1207
+ "pass@8": {
1208
+ "11": 0.873015873015873,
1209
+ "12": 0.8837920489296636,
1210
+ "13": 0.8302469135802469,
1211
+ "14": 0.7151335311572701,
1212
+ "15": 0.6481481481481481,
1213
+ "16": 0.6460176991150443,
1214
+ "17": 0.5662650602409639,
1215
+ "18": 0.535483870967742,
1216
+ "19": 0.4199395770392749,
1217
+ "20": 0.30930930930930933
1218
+ },
1219
+ "pass@16": {
1220
+ "11": 0.9333333333333333,
1221
+ "12": 0.9327217125382263,
1222
+ "13": 0.8796296296296297,
1223
+ "14": 0.7833827893175074,
1224
+ "15": 0.7314814814814815,
1225
+ "16": 0.7050147492625368,
1226
+ "17": 0.6234939759036144,
1227
+ "18": 0.5709677419354838,
1228
+ "19": 0.459214501510574,
1229
+ "20": 0.3333333333333333
1230
+ },
1231
+ "pass@32": {
1232
+ "11": 0.9619047619047619,
1233
+ "12": 0.9724770642201835,
1234
+ "13": 0.9197530864197531,
1235
+ "14": 0.8486646884272997,
1236
+ "15": 0.7962962962962963,
1237
+ "16": 0.7463126843657817,
1238
+ "17": 0.7018072289156626,
1239
+ "18": 0.6387096774193548,
1240
+ "19": 0.4743202416918429,
1241
+ "20": 0.36036036036036034
1242
+ },
1243
+ "pass@64": {
1244
+ "11": 0.9841269841269841,
1245
+ "12": 0.981651376146789,
1246
+ "13": 0.9506172839506173,
1247
+ "14": 0.9287833827893175,
1248
+ "15": 0.8765432098765432,
1249
+ "16": 0.7935103244837758,
1250
+ "17": 0.7680722891566265,
1251
+ "18": 0.7258064516129032,
1252
+ "19": 0.525679758308157,
1253
+ "20": 0.4144144144144144
1254
+ },
1255
+ "pass@128": {
1256
+ "11": 0.9904761904761905,
1257
+ "12": 0.9938837920489296,
1258
+ "13": 0.9629629629629629,
1259
+ "14": 0.9584569732937686,
1260
+ "15": 0.9320987654320988,
1261
+ "16": 0.8230088495575221,
1262
+ "17": 0.7891566265060241,
1263
+ "18": 0.7741935483870968,
1264
+ "19": 0.5770392749244713,
1265
+ "20": 0.46846846846846846
1266
+ }
1267
+ },
1268
+ "total_pass_at_k": {
1269
+ "pass@1": 0.48135696821515894,
1270
+ "pass@2": 0.53239608801956,
1271
+ "pass@4": 0.5864914425427873,
1272
+ "pass@8": 0.6415036674816625,
1273
+ "pass@16": 0.6940709046454768,
1274
+ "pass@32": 0.7408312958435208,
1275
+ "pass@64": 0.7937041564792175,
1276
+ "pass@128": 0.8257946210268948
1277
+ }
1278
+ },
1279
+ "teachers_in_school": {
1280
+ "per_op_pass_at_k": {
1281
+ "11": {
1282
+ "pass@1": 0.6686746987951807,
1283
+ "pass@2": 0.7228915662650602,
1284
+ "pass@4": 0.8042168674698795,
1285
+ "pass@8": 0.8825301204819277,
1286
+ "pass@16": 0.9216867469879518,
1287
+ "pass@32": 0.9578313253012049,
1288
+ "pass@64": 0.9819277108433735,
1289
+ "pass@128": 0.9879518072289156
1290
+ },
1291
+ "12": {
1292
+ "pass@1": 0.5987460815047022,
1293
+ "pass@2": 0.658307210031348,
1294
+ "pass@4": 0.7711598746081505,
1295
+ "pass@8": 0.8369905956112853,
1296
+ "pass@16": 0.9122257053291536,
1297
+ "pass@32": 0.9467084639498433,
1298
+ "pass@64": 0.9717868338557993,
1299
+ "pass@128": 0.9811912225705329
1300
+ },
1301
+ "13": {
1302
+ "pass@1": 0.6162464985994398,
1303
+ "pass@2": 0.6750700280112045,
1304
+ "pass@4": 0.7675070028011205,
1305
+ "pass@8": 0.8487394957983193,
1306
+ "pass@16": 0.9131652661064426,
1307
+ "pass@32": 0.938375350140056,
1308
+ "pass@64": 0.9635854341736695,
1309
+ "pass@128": 0.9831932773109243
1310
+ },
1311
+ "14": {
1312
+ "pass@1": 0.5672514619883041,
1313
+ "pass@2": 0.6023391812865497,
1314
+ "pass@4": 0.6374269005847953,
1315
+ "pass@8": 0.716374269005848,
1316
+ "pass@16": 0.7923976608187134,
1317
+ "pass@32": 0.8713450292397661,
1318
+ "pass@64": 0.9385964912280702,
1319
+ "pass@128": 0.9590643274853801
1320
+ },
1321
+ "15": {
1322
+ "pass@1": 0.5545454545454546,
1323
+ "pass@2": 0.5848484848484848,
1324
+ "pass@4": 0.6242424242424243,
1325
+ "pass@8": 0.6818181818181818,
1326
+ "pass@16": 0.7545454545454545,
1327
+ "pass@32": 0.8121212121212121,
1328
+ "pass@64": 0.8727272727272727,
1329
+ "pass@128": 0.9272727272727272
1330
+ },
1331
+ "16": {
1332
+ "pass@1": 0.5156695156695157,
1333
+ "pass@2": 0.5384615384615384,
1334
+ "pass@4": 0.5726495726495726,
1335
+ "pass@8": 0.6296296296296297,
1336
+ "pass@16": 0.6837606837606838,
1337
+ "pass@32": 0.7492877492877493,
1338
+ "pass@64": 0.7977207977207977,
1339
+ "pass@128": 0.8319088319088319
1340
+ },
1341
+ "17": {
1342
+ "pass@1": 0.43478260869565216,
1343
+ "pass@2": 0.45652173913043476,
1344
+ "pass@4": 0.5186335403726708,
1345
+ "pass@8": 0.5403726708074534,
1346
+ "pass@16": 0.6180124223602484,
1347
+ "pass@32": 0.6770186335403726,
1348
+ "pass@64": 0.7298136645962733,
1349
+ "pass@128": 0.7888198757763976
1350
+ },
1351
+ "18": {
1352
+ "pass@1": 0.39705882352941174,
1353
+ "pass@2": 0.4323529411764706,
1354
+ "pass@4": 0.45294117647058824,
1355
+ "pass@8": 0.5,
1356
+ "pass@16": 0.5323529411764706,
1357
+ "pass@32": 0.5823529411764706,
1358
+ "pass@64": 0.6529411764705882,
1359
+ "pass@128": 0.7205882352941176
1360
+ },
1361
+ "19": {
1362
+ "pass@1": 0.2976190476190476,
1363
+ "pass@2": 0.3601190476190476,
1364
+ "pass@4": 0.39880952380952384,
1365
+ "pass@8": 0.4375,
1366
+ "pass@16": 0.4732142857142857,
1367
+ "pass@32": 0.5148809523809523,
1368
+ "pass@64": 0.5625,
1369
+ "pass@128": 0.6101190476190477
1370
+ },
1371
+ "20": {
1372
+ "pass@1": 0.19760479041916168,
1373
+ "pass@2": 0.24251497005988024,
1374
+ "pass@4": 0.2934131736526946,
1375
+ "pass@8": 0.32934131736526945,
1376
+ "pass@16": 0.3532934131736527,
1377
+ "pass@32": 0.3772455089820359,
1378
+ "pass@64": 0.4251497005988024,
1379
+ "pass@128": 0.46407185628742514
1380
+ }
1381
+ },
1382
+ "per_op_pass_at_columns": {
1383
+ "pass@1": {
1384
+ "11": 0.6686746987951807,
1385
+ "12": 0.5987460815047022,
1386
+ "13": 0.6162464985994398,
1387
+ "14": 0.5672514619883041,
1388
+ "15": 0.5545454545454546,
1389
+ "16": 0.5156695156695157,
1390
+ "17": 0.43478260869565216,
1391
+ "18": 0.39705882352941174,
1392
+ "19": 0.2976190476190476,
1393
+ "20": 0.19760479041916168
1394
+ },
1395
+ "pass@2": {
1396
+ "11": 0.7228915662650602,
1397
+ "12": 0.658307210031348,
1398
+ "13": 0.6750700280112045,
1399
+ "14": 0.6023391812865497,
1400
+ "15": 0.5848484848484848,
1401
+ "16": 0.5384615384615384,
1402
+ "17": 0.45652173913043476,
1403
+ "18": 0.4323529411764706,
1404
+ "19": 0.3601190476190476,
1405
+ "20": 0.24251497005988024
1406
+ },
1407
+ "pass@4": {
1408
+ "11": 0.8042168674698795,
1409
+ "12": 0.7711598746081505,
1410
+ "13": 0.7675070028011205,
1411
+ "14": 0.6374269005847953,
1412
+ "15": 0.6242424242424243,
1413
+ "16": 0.5726495726495726,
1414
+ "17": 0.5186335403726708,
1415
+ "18": 0.45294117647058824,
1416
+ "19": 0.39880952380952384,
1417
+ "20": 0.2934131736526946
1418
+ },
1419
+ "pass@8": {
1420
+ "11": 0.8825301204819277,
1421
+ "12": 0.8369905956112853,
1422
+ "13": 0.8487394957983193,
1423
+ "14": 0.716374269005848,
1424
+ "15": 0.6818181818181818,
1425
+ "16": 0.6296296296296297,
1426
+ "17": 0.5403726708074534,
1427
+ "18": 0.5,
1428
+ "19": 0.4375,
1429
+ "20": 0.32934131736526945
1430
+ },
1431
+ "pass@16": {
1432
+ "11": 0.9216867469879518,
1433
+ "12": 0.9122257053291536,
1434
+ "13": 0.9131652661064426,
1435
+ "14": 0.7923976608187134,
1436
+ "15": 0.7545454545454545,
1437
+ "16": 0.6837606837606838,
1438
+ "17": 0.6180124223602484,
1439
+ "18": 0.5323529411764706,
1440
+ "19": 0.4732142857142857,
1441
+ "20": 0.3532934131736527
1442
+ },
1443
+ "pass@32": {
1444
+ "11": 0.9578313253012049,
1445
+ "12": 0.9467084639498433,
1446
+ "13": 0.938375350140056,
1447
+ "14": 0.8713450292397661,
1448
+ "15": 0.8121212121212121,
1449
+ "16": 0.7492877492877493,
1450
+ "17": 0.6770186335403726,
1451
+ "18": 0.5823529411764706,
1452
+ "19": 0.5148809523809523,
1453
+ "20": 0.3772455089820359
1454
+ },
1455
+ "pass@64": {
1456
+ "11": 0.9819277108433735,
1457
+ "12": 0.9717868338557993,
1458
+ "13": 0.9635854341736695,
1459
+ "14": 0.9385964912280702,
1460
+ "15": 0.8727272727272727,
1461
+ "16": 0.7977207977207977,
1462
+ "17": 0.7298136645962733,
1463
+ "18": 0.6529411764705882,
1464
+ "19": 0.5625,
1465
+ "20": 0.4251497005988024
1466
+ },
1467
+ "pass@128": {
1468
+ "11": 0.9879518072289156,
1469
+ "12": 0.9811912225705329,
1470
+ "13": 0.9831932773109243,
1471
+ "14": 0.9590643274853801,
1472
+ "15": 0.9272727272727272,
1473
+ "16": 0.8319088319088319,
1474
+ "17": 0.7888198757763976,
1475
+ "18": 0.7205882352941176,
1476
+ "19": 0.6101190476190477,
1477
+ "20": 0.46407185628742514
1478
+ }
1479
+ },
1480
+ "total_pass_at_k": {
1481
+ "pass@1": 0.4852809991079393,
1482
+ "pass@2": 0.527802557240559,
1483
+ "pass@4": 0.584299732381802,
1484
+ "pass@8": 0.6407969075230449,
1485
+ "pass@16": 0.695807314897413,
1486
+ "pass@32": 0.7430865298840321,
1487
+ "pass@64": 0.7900683913172762,
1488
+ "pass@128": 0.8257508177222718
1489
+ }
1490
+ }
1491
+ },
1492
+ "total": {
1493
+ "per_op_pass_at_k": {
1494
+ "11": {
1495
+ "pass@1": 0.626,
1496
+ "pass@2": 0.697,
1497
+ "pass@4": 0.795,
1498
+ "pass@8": 0.873,
1499
+ "pass@16": 0.924,
1500
+ "pass@32": 0.957,
1501
+ "pass@64": 0.98,
1502
+ "pass@128": 0.987
1503
+ },
1504
+ "12": {
1505
+ "pass@1": 0.628,
1506
+ "pass@2": 0.688,
1507
+ "pass@4": 0.781,
1508
+ "pass@8": 0.868,
1509
+ "pass@16": 0.925,
1510
+ "pass@32": 0.956,
1511
+ "pass@64": 0.972,
1512
+ "pass@128": 0.983
1513
+ },
1514
+ "13": {
1515
+ "pass@1": 0.598,
1516
+ "pass@2": 0.667,
1517
+ "pass@4": 0.753,
1518
+ "pass@8": 0.829,
1519
+ "pass@16": 0.889,
1520
+ "pass@32": 0.924,
1521
+ "pass@64": 0.954,
1522
+ "pass@128": 0.973
1523
+ },
1524
+ "14": {
1525
+ "pass@1": 0.566,
1526
+ "pass@2": 0.598,
1527
+ "pass@4": 0.644,
1528
+ "pass@8": 0.718,
1529
+ "pass@16": 0.784,
1530
+ "pass@32": 0.85,
1531
+ "pass@64": 0.918,
1532
+ "pass@128": 0.949
1533
+ },
1534
+ "15": {
1535
+ "pass@1": 0.52,
1536
+ "pass@2": 0.557,
1537
+ "pass@4": 0.6,
1538
+ "pass@8": 0.665,
1539
+ "pass@16": 0.744,
1540
+ "pass@32": 0.809,
1541
+ "pass@64": 0.887,
1542
+ "pass@128": 0.935
1543
+ },
1544
+ "16": {
1545
+ "pass@1": 0.517,
1546
+ "pass@2": 0.546,
1547
+ "pass@4": 0.58,
1548
+ "pass@8": 0.622,
1549
+ "pass@16": 0.682,
1550
+ "pass@32": 0.734,
1551
+ "pass@64": 0.777,
1552
+ "pass@128": 0.81
1553
+ },
1554
+ "17": {
1555
+ "pass@1": 0.481,
1556
+ "pass@2": 0.505,
1557
+ "pass@4": 0.546,
1558
+ "pass@8": 0.576,
1559
+ "pass@16": 0.638,
1560
+ "pass@32": 0.699,
1561
+ "pass@64": 0.76,
1562
+ "pass@128": 0.803
1563
+ },
1564
+ "18": {
1565
+ "pass@1": 0.408,
1566
+ "pass@2": 0.433,
1567
+ "pass@4": 0.463,
1568
+ "pass@8": 0.51,
1569
+ "pass@16": 0.549,
1570
+ "pass@32": 0.608,
1571
+ "pass@64": 0.682,
1572
+ "pass@128": 0.741
1573
+ },
1574
+ "19": {
1575
+ "pass@1": 0.301,
1576
+ "pass@2": 0.351,
1577
+ "pass@4": 0.392,
1578
+ "pass@8": 0.425,
1579
+ "pass@16": 0.463,
1580
+ "pass@32": 0.497,
1581
+ "pass@64": 0.548,
1582
+ "pass@128": 0.59
1583
+ },
1584
+ "20": {
1585
+ "pass@1": 0.202,
1586
+ "pass@2": 0.245,
1587
+ "pass@4": 0.286,
1588
+ "pass@8": 0.318,
1589
+ "pass@16": 0.343,
1590
+ "pass@32": 0.376,
1591
+ "pass@64": 0.426,
1592
+ "pass@128": 0.475
1593
+ }
1594
+ },
1595
+ "per_op_pass_at_columns": {
1596
+ "pass@1": {
1597
+ "11": 0.626,
1598
+ "12": 0.628,
1599
+ "13": 0.598,
1600
+ "14": 0.566,
1601
+ "15": 0.52,
1602
+ "16": 0.517,
1603
+ "17": 0.481,
1604
+ "18": 0.408,
1605
+ "19": 0.301,
1606
+ "20": 0.202
1607
+ },
1608
+ "pass@2": {
1609
+ "11": 0.697,
1610
+ "12": 0.688,
1611
+ "13": 0.667,
1612
+ "14": 0.598,
1613
+ "15": 0.557,
1614
+ "16": 0.546,
1615
+ "17": 0.505,
1616
+ "18": 0.433,
1617
+ "19": 0.351,
1618
+ "20": 0.245
1619
+ },
1620
+ "pass@4": {
1621
+ "11": 0.795,
1622
+ "12": 0.781,
1623
+ "13": 0.753,
1624
+ "14": 0.644,
1625
+ "15": 0.6,
1626
+ "16": 0.58,
1627
+ "17": 0.546,
1628
+ "18": 0.463,
1629
+ "19": 0.392,
1630
+ "20": 0.286
1631
+ },
1632
+ "pass@8": {
1633
+ "11": 0.873,
1634
+ "12": 0.868,
1635
+ "13": 0.829,
1636
+ "14": 0.718,
1637
+ "15": 0.665,
1638
+ "16": 0.622,
1639
+ "17": 0.576,
1640
+ "18": 0.51,
1641
+ "19": 0.425,
1642
+ "20": 0.318
1643
+ },
1644
+ "pass@16": {
1645
+ "11": 0.924,
1646
+ "12": 0.925,
1647
+ "13": 0.889,
1648
+ "14": 0.784,
1649
+ "15": 0.744,
1650
+ "16": 0.682,
1651
+ "17": 0.638,
1652
+ "18": 0.549,
1653
+ "19": 0.463,
1654
+ "20": 0.343
1655
+ },
1656
+ "pass@32": {
1657
+ "11": 0.957,
1658
+ "12": 0.956,
1659
+ "13": 0.924,
1660
+ "14": 0.85,
1661
+ "15": 0.809,
1662
+ "16": 0.734,
1663
+ "17": 0.699,
1664
+ "18": 0.608,
1665
+ "19": 0.497,
1666
+ "20": 0.376
1667
+ },
1668
+ "pass@64": {
1669
+ "11": 0.98,
1670
+ "12": 0.972,
1671
+ "13": 0.954,
1672
+ "14": 0.918,
1673
+ "15": 0.887,
1674
+ "16": 0.777,
1675
+ "17": 0.76,
1676
+ "18": 0.682,
1677
+ "19": 0.548,
1678
+ "20": 0.426
1679
+ },
1680
+ "pass@128": {
1681
+ "11": 0.987,
1682
+ "12": 0.983,
1683
+ "13": 0.973,
1684
+ "14": 0.949,
1685
+ "15": 0.935,
1686
+ "16": 0.81,
1687
+ "17": 0.803,
1688
+ "18": 0.741,
1689
+ "19": 0.59,
1690
+ "20": 0.475
1691
+ }
1692
+ },
1693
+ "total_pass_at_k": {
1694
+ "pass@1": 0.4847,
1695
+ "pass@2": 0.5287,
1696
+ "pass@4": 0.584,
1697
+ "pass@8": 0.6404,
1698
+ "pass@16": 0.6941,
1699
+ "pass@32": 0.741,
1700
+ "pass@64": 0.7904,
1701
+ "pass@128": 0.8246
1702
+ }
1703
+ },
1704
+ "ks": [
1705
+ 1,
1706
+ 2,
1707
+ 4,
1708
+ 8,
1709
+ 16,
1710
+ 32,
1711
+ 64,
1712
+ 128
1713
+ ],
1714
+ "prompt_counts": {
1715
+ "per_template": {
1716
+ "crazy_zootopia": {
1717
+ "per_op": {
1718
+ "11": 353,
1719
+ "12": 354,
1720
+ "13": 319,
1721
+ "14": 321,
1722
+ "15": 346,
1723
+ "16": 310,
1724
+ "17": 346,
1725
+ "18": 350,
1726
+ "19": 333,
1727
+ "20": 333
1728
+ },
1729
+ "total": 3365
1730
+ },
1731
+ "movie_festival_awards": {
1732
+ "per_op": {
1733
+ "11": 315,
1734
+ "12": 327,
1735
+ "13": 324,
1736
+ "14": 337,
1737
+ "15": 324,
1738
+ "16": 339,
1739
+ "17": 332,
1740
+ "18": 310,
1741
+ "19": 331,
1742
+ "20": 333
1743
+ },
1744
+ "total": 3272
1745
+ },
1746
+ "teachers_in_school": {
1747
+ "per_op": {
1748
+ "11": 332,
1749
+ "12": 319,
1750
+ "13": 357,
1751
+ "14": 342,
1752
+ "15": 330,
1753
+ "16": 351,
1754
+ "17": 322,
1755
+ "18": 340,
1756
+ "19": 336,
1757
+ "20": 334
1758
+ },
1759
+ "total": 3363
1760
+ }
1761
+ },
1762
+ "total": {
1763
+ "per_op": {
1764
+ "11": 1000,
1765
+ "12": 1000,
1766
+ "13": 1000,
1767
+ "14": 1000,
1768
+ "15": 1000,
1769
+ "16": 1000,
1770
+ "17": 1000,
1771
+ "18": 1000,
1772
+ "19": 1000,
1773
+ "20": 1000
1774
+ },
1775
+ "total": 10000
1776
+ }
1777
+ }
1778
+ }
1779
+ }
1780
+ }
Qwen3-100M-midtrain-diff_ar-block16/composition/summary.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint,id_acc,ood_acc,total_acc,id_avg_loss,ood_avg_loss,total_avg_loss,id_avg_resp_len,ood_avg_resp_len,count_id,count_ood,count_total
2
+ checkpoint-38646,0.9932248263888889,0.83598125,0.9104650493421053,0.0,0.0,0.0,200.3281736111111,378.03591796875,1152000,1280000,2432000
Qwen3-100M-midtrain-diff_ar-block16/composition/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "checkpoint-38646",
4
+ "id_acc": 0.9932248263888889,
5
+ "ood_acc": 0.83598125,
6
+ "total_acc": 0.9104650493421053,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 200.3281736111111,
11
+ "ood_avg_resp_len": 378.03591796875,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 735827,
19
+ "answer_accuracy": 0.9087335500316156,
20
+ "avg_response_len": 280.81283097533986,
21
+ "resp_tokens_sum": 227382012,
22
+ "pass_at_k": {
23
+ "pass@1": 0.9087335500316156,
24
+ "pass@2": 0.9306044600025811,
25
+ "pass@4": 0.9464375050603238,
26
+ "pass@8": 0.9578451948086137,
27
+ "pass@16": 0.9661519899120048,
28
+ "pass@32": 0.9723665816849368,
29
+ "pass@64": 0.9774353954902267,
30
+ "pass@128": 0.9818210559595321
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.9643482669616519,
35
+ "pass@2": 0.9724997386941677,
36
+ "pass@4": 0.9787036025917114,
37
+ "pass@8": 0.9837184467724707,
38
+ "pass@16": 0.9876176547055514,
39
+ "pass@32": 0.990048743242238,
40
+ "pass@64": 0.9918928791392225,
41
+ "pass@128": 0.9941002949852508
42
+ },
43
+ "2": {
44
+ "pass@1": 1.0,
45
+ "pass@2": 1.0,
46
+ "pass@4": 1.0,
47
+ "pass@8": 1.0,
48
+ "pass@16": 1.0,
49
+ "pass@32": 1.0,
50
+ "pass@64": 1.0,
51
+ "pass@128": 1.0
52
+ },
53
+ "3": {
54
+ "pass@1": 0.9998805428134556,
55
+ "pass@2": 0.9999977425413568,
56
+ "pass@4": 0.9999999997133384,
57
+ "pass@8": 1.0,
58
+ "pass@16": 1.0,
59
+ "pass@32": 1.0,
60
+ "pass@64": 1.0,
61
+ "pass@128": 1.0
62
+ },
63
+ "4": {
64
+ "pass@1": 1.0,
65
+ "pass@2": 1.0,
66
+ "pass@4": 1.0,
67
+ "pass@8": 1.0,
68
+ "pass@16": 1.0,
69
+ "pass@32": 1.0,
70
+ "pass@64": 1.0,
71
+ "pass@128": 1.0
72
+ },
73
+ "5": {
74
+ "pass@1": 0.9967757936507936,
75
+ "pass@2": 0.9988044463192103,
76
+ "pass@4": 0.9997930303354938,
77
+ "pass@8": 0.9999940728357846,
78
+ "pass@16": 0.999999996928095,
79
+ "pass@32": 1.0,
80
+ "pass@64": 1.0,
81
+ "pass@128": 1.0
82
+ },
83
+ "6": {
84
+ "pass@1": 0.9981521332335329,
85
+ "pass@2": 0.999078737210618,
86
+ "pass@4": 0.9997273029868273,
87
+ "pass@8": 0.9999777200738017,
88
+ "pass@16": 0.9999998973084382,
89
+ "pass@32": 0.999999999999679,
90
+ "pass@64": 1.0,
91
+ "pass@128": 1.0
92
+ },
93
+ "7": {
94
+ "pass@1": 0.998959874260355,
95
+ "pass@2": 0.9998143607603783,
96
+ "pass@4": 0.9999912155026479,
97
+ "pass@8": 0.9999999836752375,
98
+ "pass@16": 0.9999999999999905,
99
+ "pass@32": 1.0,
100
+ "pass@64": 1.0,
101
+ "pass@128": 1.0
102
+ },
103
+ "8": {
104
+ "pass@1": 0.9960687099358975,
105
+ "pass@2": 0.9985512252675145,
106
+ "pass@4": 0.9996649123787412,
107
+ "pass@8": 0.9999730867256917,
108
+ "pass@16": 0.9999998586577866,
109
+ "pass@32": 0.9999999999993815,
110
+ "pass@64": 1.0,
111
+ "pass@128": 1.0
112
+ },
113
+ "9": {
114
+ "pass@1": 0.9940801056338028,
115
+ "pass@2": 0.9950447765332151,
116
+ "pass@4": 0.9956578631896364,
117
+ "pass@8": 0.996375867480201,
118
+ "pass@16": 0.9969724240620078,
119
+ "pass@32": 0.9971729386969103,
120
+ "pass@64": 0.9971830959162251,
121
+ "pass@128": 0.9971830985915493
122
+ },
123
+ "11": {
124
+ "pass@1": 0.9711623583569405,
125
+ "pass@2": 0.9805191998840088,
126
+ "pass@4": 0.986303336286222,
127
+ "pass@8": 0.989850641477996,
128
+ "pass@16": 0.99240868699634,
129
+ "pass@32": 0.994293234140082,
130
+ "pass@64": 0.9956686613210934,
131
+ "pass@128": 0.9971671388101983
132
+ },
133
+ "12": {
134
+ "pass@1": 0.9658368644067796,
135
+ "pass@2": 0.979869405889942,
136
+ "pass@4": 0.9899045508612269,
137
+ "pass@8": 0.9949535165900368,
138
+ "pass@16": 0.9969359713595375,
139
+ "pass@32": 0.9982218320963844,
140
+ "pass@64": 0.9992952648675736,
141
+ "pass@128": 1.0
142
+ },
143
+ "13": {
144
+ "pass@1": 0.9498187695924765,
145
+ "pass@2": 0.9693292893639082,
146
+ "pass@4": 0.9815207164543299,
147
+ "pass@8": 0.9885514952344922,
148
+ "pass@16": 0.993030758542598,
149
+ "pass@32": 0.9957866897580077,
150
+ "pass@64": 0.9968002718717178,
151
+ "pass@128": 0.9968652037617555
152
+ },
153
+ "14": {
154
+ "pass@1": 0.9244548286604362,
155
+ "pass@2": 0.9464950971373904,
156
+ "pass@4": 0.962845547343965,
157
+ "pass@8": 0.9744775229835171,
158
+ "pass@16": 0.9831241464032126,
159
+ "pass@32": 0.9892894037314296,
160
+ "pass@64": 0.9925585252418944,
161
+ "pass@128": 0.9937694704049844
162
+ },
163
+ "15": {
164
+ "pass@1": 0.9763367052023122,
165
+ "pass@2": 0.9890843327568163,
166
+ "pass@4": 0.995195050131017,
167
+ "pass@8": 0.9987062171803248,
168
+ "pass@16": 0.9998947926322176,
169
+ "pass@32": 0.9999995163740522,
170
+ "pass@64": 0.9999999999997273,
171
+ "pass@128": 1.0
172
+ },
173
+ "16": {
174
+ "pass@1": 0.8670362903225807,
175
+ "pass@2": 0.9042973710947418,
176
+ "pass@4": 0.9324377792493678,
177
+ "pass@8": 0.9511663793058849,
178
+ "pass@16": 0.9632457765868611,
179
+ "pass@32": 0.972380137786845,
180
+ "pass@64": 0.9803184368887754,
181
+ "pass@128": 0.9870967741935484
182
+ },
183
+ "17": {
184
+ "pass@1": 0.8796739523121387,
185
+ "pass@2": 0.9130583354194169,
186
+ "pass@4": 0.9346565702950422,
187
+ "pass@8": 0.949022076996675,
188
+ "pass@16": 0.9577801252538675,
189
+ "pass@32": 0.9642535207391926,
190
+ "pass@64": 0.9711417638827387,
191
+ "pass@128": 0.976878612716763
192
+ },
193
+ "18": {
194
+ "pass@1": 0.7535491071428572,
195
+ "pass@2": 0.8142751687289084,
196
+ "pass@4": 0.854199288124698,
197
+ "pass@8": 0.8827058936508151,
198
+ "pass@16": 0.9034225204407647,
199
+ "pass@32": 0.9183155907983432,
200
+ "pass@64": 0.9304605804851537,
201
+ "pass@128": 0.9428571428571428
202
+ },
203
+ "19": {
204
+ "pass@1": 0.5902073948948949,
205
+ "pass@2": 0.6823130955758907,
206
+ "pass@4": 0.7493216109810598,
207
+ "pass@8": 0.7968110404034479,
208
+ "pass@16": 0.8325350334716398,
209
+ "pass@32": 0.859961150550141,
210
+ "pass@64": 0.8827473329655091,
211
+ "pass@128": 0.9009009009009009
212
+ },
213
+ "20": {
214
+ "pass@1": 0.4485735735735736,
215
+ "pass@2": 0.5452467723629141,
216
+ "pass@4": 0.6280490980294128,
217
+ "pass@8": 0.6976146762314849,
218
+ "pass@16": 0.7542370813489142,
219
+ "pass@32": 0.799241057750153,
220
+ "pass@64": 0.8368248092112288,
221
+ "pass@128": 0.8708708708708709
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 751099,
228
+ "answer_accuracy": 0.9147250097427904,
229
+ "avg_response_len": 290.0505114964926,
230
+ "resp_tokens_sum": 238166276,
231
+ "pass_at_k": {
232
+ "pass@1": 0.9147250097427904,
233
+ "pass@2": 0.9368544058892373,
234
+ "pass@4": 0.9526741754464987,
235
+ "pass@8": 0.9638412119281327,
236
+ "pass@16": 0.9716894634319847,
237
+ "pass@32": 0.9774218920691676,
238
+ "pass@64": 0.9817877251624777,
239
+ "pass@128": 0.9851909586905689
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.9476131134969326,
244
+ "pass@2": 0.9578519002705184,
245
+ "pass@4": 0.9660574474778076,
246
+ "pass@8": 0.9719991236070697,
247
+ "pass@16": 0.9763583249372905,
248
+ "pass@32": 0.980656765738378,
249
+ "pass@64": 0.9852951841811889,
250
+ "pass@128": 0.99079754601227
251
+ },
252
+ "2": {
253
+ "pass@1": 1.0,
254
+ "pass@2": 1.0,
255
+ "pass@4": 1.0,
256
+ "pass@8": 1.0,
257
+ "pass@16": 1.0,
258
+ "pass@32": 1.0,
259
+ "pass@64": 1.0,
260
+ "pass@128": 1.0
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9982717803030303,
264
+ "pass@2": 0.9992185635886424,
265
+ "pass@4": 0.9998076788696866,
266
+ "pass@8": 0.9999893019044129,
267
+ "pass@16": 0.9999999789617312,
268
+ "pass@32": 0.9999999999999926,
269
+ "pass@64": 1.0,
270
+ "pass@128": 1.0
271
+ },
272
+ "4": {
273
+ "pass@1": 0.9999768860946746,
274
+ "pass@2": 1.0,
275
+ "pass@4": 1.0,
276
+ "pass@8": 1.0,
277
+ "pass@16": 1.0,
278
+ "pass@32": 1.0,
279
+ "pass@64": 1.0,
280
+ "pass@128": 1.0
281
+ },
282
+ "5": {
283
+ "pass@1": 0.9955842391304348,
284
+ "pass@2": 0.9970807657195024,
285
+ "pass@4": 0.9974464667460045,
286
+ "pass@8": 0.9977680565376104,
287
+ "pass@16": 0.9983124881128989,
288
+ "pass@32": 0.999097406302473,
289
+ "pass@64": 0.9998273650576287,
290
+ "pass@128": 1.0
291
+ },
292
+ "6": {
293
+ "pass@1": 0.9994627507163324,
294
+ "pass@2": 0.9999027028856349,
295
+ "pass@4": 0.9999971459513118,
296
+ "pass@8": 0.9999999985260104,
297
+ "pass@16": 1.0,
298
+ "pass@32": 1.0,
299
+ "pass@64": 1.0,
300
+ "pass@128": 1.0
301
+ },
302
+ "7": {
303
+ "pass@1": 0.9984420158959537,
304
+ "pass@2": 0.9991658037868099,
305
+ "pass@4": 0.9997657894822396,
306
+ "pass@8": 0.999983097148883,
307
+ "pass@16": 0.9999999407613452,
308
+ "pass@32": 0.9999999999999076,
309
+ "pass@64": 1.0,
310
+ "pass@128": 1.0
311
+ },
312
+ "8": {
313
+ "pass@1": 0.9972711267605634,
314
+ "pass@2": 0.9988802401020296,
315
+ "pass@4": 0.9997421626874106,
316
+ "pass@8": 0.9999832931204404,
317
+ "pass@16": 0.9999999422581453,
318
+ "pass@32": 0.99999999999991,
319
+ "pass@64": 1.0,
320
+ "pass@128": 1.0
321
+ },
322
+ "9": {
323
+ "pass@1": 0.9965147829341318,
324
+ "pass@2": 0.9973931320430004,
325
+ "pass@4": 0.9978456220292824,
326
+ "pass@8": 0.998468082786387,
327
+ "pass@16": 0.9992530482905866,
328
+ "pass@32": 0.999851122735485,
329
+ "pass@64": 0.9999980007921191,
330
+ "pass@128": 1.0
331
+ },
332
+ "11": {
333
+ "pass@1": 0.9768213478915663,
334
+ "pass@2": 0.982426507209942,
335
+ "pass@4": 0.9875867705919291,
336
+ "pass@8": 0.9916699109297928,
337
+ "pass@16": 0.9941198985224184,
338
+ "pass@32": 0.9952745122110707,
339
+ "pass@64": 0.9962408632343975,
340
+ "pass@128": 0.9969879518072289
341
+ },
342
+ "12": {
343
+ "pass@1": 0.965492750783699,
344
+ "pass@2": 0.9797927517093281,
345
+ "pass@4": 0.9877445484870819,
346
+ "pass@8": 0.9923678770900078,
347
+ "pass@16": 0.9955227193860775,
348
+ "pass@32": 0.9973880317416322,
349
+ "pass@64": 0.9984300583339356,
350
+ "pass@128": 1.0
351
+ },
352
+ "13": {
353
+ "pass@1": 0.9623599439775911,
354
+ "pass@2": 0.9779697804318578,
355
+ "pass@4": 0.9872410336838148,
356
+ "pass@8": 0.9920194344744313,
357
+ "pass@16": 0.9942491977157041,
358
+ "pass@32": 0.9950794358980206,
359
+ "pass@64": 0.9957983155432268,
360
+ "pass@128": 0.9971988795518207
361
+ },
362
+ "14": {
363
+ "pass@1": 0.9557291666666666,
364
+ "pass@2": 0.9763930618870013,
365
+ "pass@4": 0.9898799393496869,
366
+ "pass@8": 0.9971921128374414,
367
+ "pass@16": 0.9996866455629769,
368
+ "pass@32": 0.9999957420781709,
369
+ "pass@64": 0.9999999999150341,
370
+ "pass@128": 1.0
371
+ },
372
+ "15": {
373
+ "pass@1": 0.9709043560606061,
374
+ "pass@2": 0.9843362264376043,
375
+ "pass@4": 0.9913319070911589,
376
+ "pass@8": 0.9957115636967746,
377
+ "pass@16": 0.9984277498659098,
378
+ "pass@32": 0.9997408383719552,
379
+ "pass@64": 0.9999955357422065,
380
+ "pass@128": 1.0
381
+ },
382
+ "16": {
383
+ "pass@1": 0.9107015669515669,
384
+ "pass@2": 0.9377124133521775,
385
+ "pass@4": 0.9564160948898481,
386
+ "pass@8": 0.9692630161138946,
387
+ "pass@16": 0.9776624723599159,
388
+ "pass@32": 0.9832541934776856,
389
+ "pass@64": 0.9874615955124632,
390
+ "pass@128": 0.9914529914529915
391
+ },
392
+ "17": {
393
+ "pass@1": 0.8672360248447205,
394
+ "pass@2": 0.9112839750330124,
395
+ "pass@4": 0.9387636921937549,
396
+ "pass@8": 0.9558194693071742,
397
+ "pass@16": 0.9657225480978907,
398
+ "pass@32": 0.9716417279156446,
399
+ "pass@64": 0.9759516660247486,
400
+ "pass@128": 0.9782608695652174
401
+ },
402
+ "18": {
403
+ "pass@1": 0.7839613970588235,
404
+ "pass@2": 0.8523347035664656,
405
+ "pass@4": 0.8947464600013231,
406
+ "pass@8": 0.9214377697528552,
407
+ "pass@16": 0.9388117402083257,
408
+ "pass@32": 0.951005420422579,
409
+ "pass@64": 0.9607119551856902,
410
+ "pass@128": 0.9705882352941176
411
+ },
412
+ "19": {
413
+ "pass@1": 0.5933547247023809,
414
+ "pass@2": 0.6915281830005624,
415
+ "pass@4": 0.766301561356169,
416
+ "pass@8": 0.8222817559953494,
417
+ "pass@16": 0.8649021620408612,
418
+ "pass@32": 0.8975421565193381,
419
+ "pass@64": 0.9221817078073432,
420
+ "pass@128": 0.9404761904761905
421
+ },
422
+ "20": {
423
+ "pass@1": 0.4492889221556886,
424
+ "pass@2": 0.5484648321467304,
425
+ "pass@4": 0.6333525578202419,
426
+ "pass@8": 0.7015890174857582,
427
+ "pass@16": 0.7546736568184237,
428
+ "pass@32": 0.796908044139665,
429
+ "pass@64": 0.829107778372377,
430
+ "pass@128": 0.8502994011976048
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 727325,
437
+ "answer_accuracy": 0.9078489475155775,
438
+ "avg_response_len": 310.94691519212336,
439
+ "resp_tokens_sum": 249115743,
440
+ "pass_at_k": {
441
+ "pass@1": 0.9078489475155775,
442
+ "pass@2": 0.9314184621389209,
443
+ "pass@4": 0.9479047528888704,
444
+ "pass@8": 0.959567070014469,
445
+ "pass@16": 0.9676303174059113,
446
+ "pass@32": 0.9731903126693562,
447
+ "pass@64": 0.9775192818766577,
448
+ "pass@128": 0.9816264579006231
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.9642024253731343,
453
+ "pass@2": 0.9741138059701494,
454
+ "pass@4": 0.9819364163434796,
455
+ "pass@8": 0.9881400872944226,
456
+ "pass@16": 0.9925379015562921,
457
+ "pass@32": 0.9955510391342886,
458
+ "pass@64": 0.997754923360079,
459
+ "pass@128": 1.0
460
+ },
461
+ "2": {
462
+ "pass@1": 1.0,
463
+ "pass@2": 1.0,
464
+ "pass@4": 1.0,
465
+ "pass@8": 1.0,
466
+ "pass@16": 1.0,
467
+ "pass@32": 1.0,
468
+ "pass@64": 1.0,
469
+ "pass@128": 1.0
470
+ },
471
+ "3": {
472
+ "pass@1": 1.0,
473
+ "pass@2": 1.0,
474
+ "pass@4": 1.0,
475
+ "pass@8": 1.0,
476
+ "pass@16": 1.0,
477
+ "pass@32": 1.0,
478
+ "pass@64": 1.0,
479
+ "pass@128": 1.0
480
+ },
481
+ "4": {
482
+ "pass@1": 1.0,
483
+ "pass@2": 1.0,
484
+ "pass@4": 1.0,
485
+ "pass@8": 1.0,
486
+ "pass@16": 1.0,
487
+ "pass@32": 1.0,
488
+ "pass@64": 1.0,
489
+ "pass@128": 1.0
490
+ },
491
+ "5": {
492
+ "pass@1": 0.9912913602941177,
493
+ "pass@2": 0.9954405974988421,
494
+ "pass@4": 0.9979701380158362,
495
+ "pass@8": 0.9993477897991202,
496
+ "pass@16": 0.9999126470598457,
497
+ "pass@32": 0.999998726614258,
498
+ "pass@64": 0.999999999987784,
499
+ "pass@128": 1.0
500
+ },
501
+ "6": {
502
+ "pass@1": 0.9999507097791798,
503
+ "pass@2": 0.999999611888025,
504
+ "pass@4": 1.0,
505
+ "pass@8": 1.0,
506
+ "pass@16": 1.0,
507
+ "pass@32": 1.0,
508
+ "pass@64": 1.0,
509
+ "pass@128": 1.0
510
+ },
511
+ "7": {
512
+ "pass@1": 0.9933742088607594,
513
+ "pass@2": 0.9947567558307585,
514
+ "pass@4": 0.9957734057965857,
515
+ "pass@8": 0.9969989697228501,
516
+ "pass@16": 0.9982483505948174,
517
+ "pass@32": 0.9992648536542246,
518
+ "pass@64": 0.9999088007454459,
519
+ "pass@128": 1.0
520
+ },
521
+ "8": {
522
+ "pass@1": 0.9931493993993994,
523
+ "pass@2": 0.9975064877869996,
524
+ "pass@4": 0.999478633301468,
525
+ "pass@8": 0.9999675398986609,
526
+ "pass@16": 0.9999998926590724,
527
+ "pass@32": 0.9999999999998089,
528
+ "pass@64": 1.0,
529
+ "pass@128": 1.0
530
+ },
531
+ "9": {
532
+ "pass@1": 0.9930667202572347,
533
+ "pass@2": 0.9967814011190724,
534
+ "pass@4": 0.9985162387257863,
535
+ "pass@8": 0.9994198002264989,
536
+ "pass@16": 0.9999085821695214,
537
+ "pass@32": 0.999998609246854,
538
+ "pass@64": 0.9999999999866449,
539
+ "pass@128": 1.0
540
+ },
541
+ "11": {
542
+ "pass@1": 0.963640873015873,
543
+ "pass@2": 0.9752730127484065,
544
+ "pass@4": 0.9833094119187484,
545
+ "pass@8": 0.9885337281484384,
546
+ "pass@16": 0.9929572101573484,
547
+ "pass@32": 0.9967672908887808,
548
+ "pass@64": 0.9991148007644227,
549
+ "pass@128": 1.0
550
+ },
551
+ "12": {
552
+ "pass@1": 0.9675793195718655,
553
+ "pass@2": 0.9831443087962632,
554
+ "pass@4": 0.9927234121537561,
555
+ "pass@8": 0.9962327927192676,
556
+ "pass@16": 0.9969067136543522,
557
+ "pass@32": 0.9969418396245668,
558
+ "pass@64": 0.9969418960244639,
559
+ "pass@128": 0.9969418960244648
560
+ },
561
+ "13": {
562
+ "pass@1": 0.953125,
563
+ "pass@2": 0.9724694243948675,
564
+ "pass@4": 0.9839528441467964,
565
+ "pass@8": 0.9914051147315478,
566
+ "pass@16": 0.9962751879157801,
567
+ "pass@32": 0.9989514073218897,
568
+ "pass@64": 0.9999069142994649,
569
+ "pass@128": 1.0
570
+ },
571
+ "14": {
572
+ "pass@1": 0.9672663204747775,
573
+ "pass@2": 0.9819023224841703,
574
+ "pass@4": 0.9891655304029129,
575
+ "pass@8": 0.9926525053330164,
576
+ "pass@16": 0.9941520139636356,
577
+ "pass@32": 0.9947959873034944,
578
+ "pass@64": 0.9955489586054439,
579
+ "pass@128": 0.9970326409495549
580
+ },
581
+ "15": {
582
+ "pass@1": 0.9480372299382716,
583
+ "pass@2": 0.9670028768105379,
584
+ "pass@4": 0.9780621108704005,
585
+ "pass@8": 0.9842947803211456,
586
+ "pass@16": 0.9879716058879758,
587
+ "pass@32": 0.9901270313479683,
588
+ "pass@64": 0.9919070327284573,
589
+ "pass@128": 0.9938271604938271
590
+ },
591
+ "16": {
592
+ "pass@1": 0.882973820058997,
593
+ "pass@2": 0.9149514842171274,
594
+ "pass@4": 0.9361787777080962,
595
+ "pass@8": 0.9505317245196182,
596
+ "pass@16": 0.95963740909398,
597
+ "pass@32": 0.9664879570651409,
598
+ "pass@64": 0.9730817511351202,
599
+ "pass@128": 0.9793510324483776
600
+ },
601
+ "17": {
602
+ "pass@1": 0.8233951430722891,
603
+ "pass@2": 0.8709084616023144,
604
+ "pass@4": 0.900955382553837,
605
+ "pass@8": 0.920503593025735,
606
+ "pass@16": 0.9343316545762004,
607
+ "pass@32": 0.9442573518899536,
608
+ "pass@64": 0.9519856298182777,
609
+ "pass@128": 0.9608433734939759
610
+ },
611
+ "18": {
612
+ "pass@1": 0.7824344758064516,
613
+ "pass@2": 0.8496388430276858,
614
+ "pass@4": 0.8933080521184847,
615
+ "pass@8": 0.9212389467048724,
616
+ "pass@16": 0.9380265394631339,
617
+ "pass@32": 0.9476456964449388,
618
+ "pass@64": 0.9534177140834851,
619
+ "pass@128": 0.9580645161290322
620
+ },
621
+ "19": {
622
+ "pass@1": 0.5686367069486404,
623
+ "pass@2": 0.6704094012417636,
624
+ "pass@4": 0.7465739156094909,
625
+ "pass@8": 0.8053303353516325,
626
+ "pass@16": 0.8499870368405819,
627
+ "pass@32": 0.8823623062494177,
628
+ "pass@64": 0.907953968913336,
629
+ "pass@128": 0.9305135951661632
630
+ },
631
+ "20": {
632
+ "pass@1": 0.4545561186186186,
633
+ "pass@2": 0.5521487284528623,
634
+ "pass@4": 0.6327929909662195,
635
+ "pass@8": 0.6981138753732286,
636
+ "pass@16": 0.7452411820752879,
637
+ "pass@32": 0.7785809400350618,
638
+ "pass@64": 0.8062433242479462,
639
+ "pass@128": 0.8348348348348348
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]
Qwen3-100M-midtrain-diff_ar-block4/composition/checkpoint-38646_id_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad599636b8c33c4e7935cbaeff8d20f8a960498bbfaef9961b706eaa1c1595f1
3
+ size 1789731521
Qwen3-100M-midtrain-diff_ar-block4/composition/checkpoint-38646_metrics.json ADDED
@@ -0,0 +1,1897 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "checkpoint-38646",
3
+ "id": {
4
+ "answer_accuracy": 0.9930946180555555,
5
+ "avg_response_len": 200.28550694444445,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.9930946180555555,
11
+ "pass@2": 0.9949989473972002,
12
+ "pass@4": 0.9963422400845728,
13
+ "pass@8": 0.9972624951869838,
14
+ "pass@16": 0.9979487555732529,
15
+ "pass@32": 0.9985491774462739,
16
+ "pass@64": 0.9991352162559932,
17
+ "pass@128": 0.9996666666666667
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.9540625,
22
+ "pass@2": 0.9639723179133853,
23
+ "pass@4": 0.9723782580614919,
24
+ "pass@8": 0.9787925265522301,
25
+ "pass@16": 0.9837687276335041,
26
+ "pass@32": 0.9881571311082412,
27
+ "pass@64": 0.9927600328966237,
28
+ "pass@128": 0.997
29
+ },
30
+ "2": {
31
+ "pass@1": 1.0,
32
+ "pass@2": 1.0,
33
+ "pass@4": 1.0,
34
+ "pass@8": 1.0,
35
+ "pass@16": 1.0,
36
+ "pass@32": 1.0,
37
+ "pass@64": 1.0,
38
+ "pass@128": 1.0
39
+ },
40
+ "3": {
41
+ "pass@1": 0.99946875,
42
+ "pass@2": 0.9998220964566928,
43
+ "pass@4": 0.9999744520997375,
44
+ "pass@8": 0.9999994736310946,
45
+ "pass@16": 0.9999999998889773,
46
+ "pass@32": 1.0,
47
+ "pass@64": 1.0,
48
+ "pass@128": 1.0
49
+ },
50
+ "4": {
51
+ "pass@1": 0.999890625,
52
+ "pass@2": 0.9999948326771654,
53
+ "pass@4": 0.9999999880952382,
54
+ "pass@8": 0.9999999999999937,
55
+ "pass@16": 1.0,
56
+ "pass@32": 1.0,
57
+ "pass@64": 1.0,
58
+ "pass@128": 1.0
59
+ },
60
+ "5": {
61
+ "pass@1": 0.9944765625,
62
+ "pass@2": 0.9970152559055121,
63
+ "pass@4": 0.9982060622422197,
64
+ "pass@8": 0.9988426718080923,
65
+ "pass@16": 0.9993716905884307,
66
+ "pass@32": 0.9998027430992852,
67
+ "pass@64": 0.9999860378787945,
68
+ "pass@128": 1.0
69
+ },
70
+ "6": {
71
+ "pass@1": 0.9999140625,
72
+ "pass@2": 0.9999985236220473,
73
+ "pass@4": 0.9999999999062616,
74
+ "pass@8": 1.0,
75
+ "pass@16": 1.0,
76
+ "pass@32": 1.0,
77
+ "pass@64": 1.0,
78
+ "pass@128": 1.0
79
+ },
80
+ "7": {
81
+ "pass@1": 0.99834375,
82
+ "pass@2": 0.9991849163385828,
83
+ "pass@4": 0.9996791599175103,
84
+ "pass@8": 0.9999399336710925,
85
+ "pass@16": 0.9999976797361912,
86
+ "pass@32": 0.9999999983745138,
87
+ "pass@64": 1.0,
88
+ "pass@128": 1.0
89
+ },
90
+ "8": {
91
+ "pass@1": 0.9961796875,
92
+ "pass@2": 0.9982639025590552,
93
+ "pass@4": 0.9995023362392201,
94
+ "pass@8": 0.999940916408823,
95
+ "pass@16": 0.9999986572834463,
96
+ "pass@32": 0.9999999995728239,
97
+ "pass@64": 1.0,
98
+ "pass@128": 1.0
99
+ },
100
+ "9": {
101
+ "pass@1": 0.995515625,
102
+ "pass@2": 0.9967386811023622,
103
+ "pass@4": 0.9973399041994752,
104
+ "pass@8": 0.9978469346115266,
105
+ "pass@16": 0.9984020450287275,
106
+ "pass@32": 0.9989827248615993,
107
+ "pass@64": 0.9994708755285203,
108
+ "pass@128": 1.0
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.9540625,
113
+ "2": 1.0,
114
+ "3": 0.99946875,
115
+ "4": 0.999890625,
116
+ "5": 0.9944765625,
117
+ "6": 0.9999140625,
118
+ "7": 0.99834375,
119
+ "8": 0.9961796875,
120
+ "9": 0.995515625
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 281.6685703125,
124
+ "2": 115.6646328125,
125
+ "3": 144.9749609375,
126
+ "4": 159.97440625,
127
+ "5": 173.51565625,
128
+ "6": 198.98446875,
129
+ "7": 224.252796875,
130
+ "8": 243.7776015625,
131
+ "9": 259.75646875
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 281.6685703125,
136
+ "2": 115.6646328125,
137
+ "3": 144.9749609375,
138
+ "4": 159.97440625,
139
+ "5": 173.51565625,
140
+ "6": 198.98446875,
141
+ "7": 224.252796875,
142
+ "8": 243.7776015625,
143
+ "9": 259.75646875
144
+ },
145
+ "per_op_loss": {},
146
+ "per_template": {
147
+ "crazy_zootopia": {
148
+ "count": 379008,
149
+ "correct": 376657,
150
+ "answer_accuracy": 0.9937969647078689,
151
+ "avg_response_len": 190.8121912993921,
152
+ "resp_tokens_sum": 72319347,
153
+ "pass_at_k": {
154
+ "pass@1": 0.9937969647078689,
155
+ "pass@2": 0.9952953437336292,
156
+ "pass@4": 0.9963559719042212,
157
+ "pass@8": 0.9972608428511113,
158
+ "pass@16": 0.9980648749134898,
159
+ "pass@32": 0.9986967786412437,
160
+ "pass@64": 0.9991892593315244,
161
+ "pass@128": 0.999662276258021
162
+ },
163
+ "per_op_pass_at_k": {
164
+ "10": {
165
+ "pass@1": 0.954484697640118,
166
+ "pass@2": 0.9629707860079438,
167
+ "pass@4": 0.9709464638269774,
168
+ "pass@8": 0.9782191819839355,
169
+ "pass@16": 0.984593484638989,
170
+ "pass@32": 0.9892985145351701,
171
+ "pass@64": 0.9930035863666121,
172
+ "pass@128": 0.9970501474926253
173
+ },
174
+ "2": {
175
+ "pass@1": 1.0,
176
+ "pass@2": 1.0,
177
+ "pass@4": 1.0,
178
+ "pass@8": 1.0,
179
+ "pass@16": 1.0,
180
+ "pass@32": 1.0,
181
+ "pass@64": 1.0,
182
+ "pass@128": 1.0
183
+ },
184
+ "3": {
185
+ "pass@1": 1.0,
186
+ "pass@2": 1.0,
187
+ "pass@4": 1.0,
188
+ "pass@8": 1.0,
189
+ "pass@16": 1.0,
190
+ "pass@32": 1.0,
191
+ "pass@64": 1.0,
192
+ "pass@128": 1.0
193
+ },
194
+ "4": {
195
+ "pass@1": 1.0,
196
+ "pass@2": 1.0,
197
+ "pass@4": 1.0,
198
+ "pass@8": 1.0,
199
+ "pass@16": 1.0,
200
+ "pass@32": 1.0,
201
+ "pass@64": 1.0,
202
+ "pass@128": 1.0
203
+ },
204
+ "5": {
205
+ "pass@1": 0.9980902777777778,
206
+ "pass@2": 0.9997808867641542,
207
+ "pass@4": 0.9999950205629058,
208
+ "pass@8": 0.9999999974305525,
209
+ "pass@16": 1.0,
210
+ "pass@32": 1.0,
211
+ "pass@64": 1.0,
212
+ "pass@128": 1.0
213
+ },
214
+ "6": {
215
+ "pass@1": 0.9998830464071856,
216
+ "pass@2": 0.9999977898533642,
217
+ "pass@4": 0.9999999997193464,
218
+ "pass@8": 1.0,
219
+ "pass@16": 1.0,
220
+ "pass@32": 1.0,
221
+ "pass@64": 1.0,
222
+ "pass@128": 1.0
223
+ },
224
+ "7": {
225
+ "pass@1": 0.9991910133136095,
226
+ "pass@2": 0.9999253803056423,
227
+ "pass@4": 0.9999992966855474,
228
+ "pass@8": 0.9999999999707041,
229
+ "pass@16": 1.0,
230
+ "pass@32": 1.0,
231
+ "pass@64": 1.0,
232
+ "pass@128": 1.0
233
+ },
234
+ "8": {
235
+ "pass@1": 0.9977964743589743,
236
+ "pass@2": 0.9990386192711489,
237
+ "pass@4": 0.9997245203123646,
238
+ "pass@8": 0.9999788364839716,
239
+ "pass@16": 0.9999999148409177,
240
+ "pass@32": 0.9999999999998113,
241
+ "pass@64": 1.0,
242
+ "pass@128": 1.0
243
+ },
244
+ "9": {
245
+ "pass@1": 0.9962367957746479,
246
+ "pass@2": 0.9972319646223802,
247
+ "pass@4": 0.9975970072402921,
248
+ "pass@8": 0.9979708642982112,
249
+ "pass@16": 0.9985716335094632,
250
+ "pass@32": 0.9993491975474896,
251
+ "pass@64": 0.9999188200066541,
252
+ "pass@128": 1.0
253
+ }
254
+ }
255
+ },
256
+ "teachers_in_school": {
257
+ "count": 390656,
258
+ "correct": 387649,
259
+ "answer_accuracy": 0.9923026908584535,
260
+ "avg_response_len": 198.26654652686761,
261
+ "resp_tokens_sum": 77454016,
262
+ "pass_at_k": {
263
+ "pass@1": 0.9923026908584535,
264
+ "pass@2": 0.9942880249558829,
265
+ "pass@4": 0.9956853823809375,
266
+ "pass@8": 0.9965860027278677,
267
+ "pass@16": 0.997238113916091,
268
+ "pass@32": 0.9979263130447362,
269
+ "pass@64": 0.9987312934569264,
270
+ "pass@128": 0.9993446920052425
271
+ },
272
+ "per_op_pass_at_k": {
273
+ "10": {
274
+ "pass@1": 0.9433713573619632,
275
+ "pass@2": 0.9535782540698516,
276
+ "pass@4": 0.9618546829460732,
277
+ "pass@8": 0.968359742151891,
278
+ "pass@16": 0.9741511694787096,
279
+ "pass@32": 0.9805862212217205,
280
+ "pass@64": 0.9881224160445984,
281
+ "pass@128": 0.9938650306748467
282
+ },
283
+ "2": {
284
+ "pass@1": 1.0,
285
+ "pass@2": 1.0,
286
+ "pass@4": 1.0,
287
+ "pass@8": 1.0,
288
+ "pass@16": 1.0,
289
+ "pass@32": 1.0,
290
+ "pass@64": 1.0,
291
+ "pass@128": 1.0
292
+ },
293
+ "3": {
294
+ "pass@1": 0.9983901515151515,
295
+ "pass@2": 0.999460898353615,
296
+ "pass@4": 0.9999225821204167,
297
+ "pass@8": 0.9999984049427112,
298
+ "pass@16": 0.9999999996635676,
299
+ "pass@32": 1.0,
300
+ "pass@64": 1.0,
301
+ "pass@128": 1.0
302
+ },
303
+ "4": {
304
+ "pass@1": 0.999791974852071,
305
+ "pass@2": 0.9999868960536739,
306
+ "pass@4": 0.9999999650561431,
307
+ "pass@8": 0.9999999999999813,
308
+ "pass@16": 1.0,
309
+ "pass@32": 1.0,
310
+ "pass@64": 1.0,
311
+ "pass@128": 1.0
312
+ },
313
+ "5": {
314
+ "pass@1": 0.9935914855072464,
315
+ "pass@2": 0.9972134257674314,
316
+ "pass@4": 0.9991986126734157,
317
+ "pass@8": 0.9998860811105759,
318
+ "pass@16": 0.9999969943734291,
319
+ "pass@32": 0.9999999992176973,
320
+ "pass@64": 1.0,
321
+ "pass@128": 1.0
322
+ },
323
+ "6": {
324
+ "pass@1": 0.9999328438395415,
325
+ "pass@2": 0.99999894242267,
326
+ "pass@4": 1.0,
327
+ "pass@8": 1.0,
328
+ "pass@16": 1.0,
329
+ "pass@32": 1.0,
330
+ "pass@64": 1.0,
331
+ "pass@128": 1.0
332
+ },
333
+ "7": {
334
+ "pass@1": 0.9981484826589595,
335
+ "pass@2": 0.9991423353511447,
336
+ "pass@4": 0.9997656553768929,
337
+ "pass@8": 0.9999830971478822,
338
+ "pass@16": 0.9999999407613452,
339
+ "pass@32": 0.9999999999999076,
340
+ "pass@64": 1.0,
341
+ "pass@128": 1.0
342
+ },
343
+ "8": {
344
+ "pass@1": 0.9978213028169014,
345
+ "pass@2": 0.998696212709327,
346
+ "pass@4": 0.9994122448602376,
347
+ "pass@8": 0.9998848700630322,
348
+ "pass@16": 0.9999964254002791,
349
+ "pass@32": 0.9999999987973975,
350
+ "pass@64": 1.0,
351
+ "pass@128": 1.0
352
+ },
353
+ "9": {
354
+ "pass@1": 0.9976609281437125,
355
+ "pass@2": 0.9988149930454053,
356
+ "pass@4": 0.9995776498184733,
357
+ "pass@8": 0.9999453661202221,
358
+ "pass@16": 0.9999993082440582,
359
+ "pass@32": 0.9999999999733661,
360
+ "pass@64": 1.0,
361
+ "pass@128": 1.0
362
+ }
363
+ }
364
+ },
365
+ "movie_festival_awards": {
366
+ "count": 382336,
367
+ "correct": 379739,
368
+ "answer_accuracy": 0.9932075451958486,
369
+ "avg_response_len": 211.73925813943757,
370
+ "resp_tokens_sum": 80955541,
371
+ "pass_at_k": {
372
+ "pass@1": 0.9932075451958486,
373
+ "pass@2": 0.9954315238078923,
374
+ "pass@4": 0.9969997793525728,
375
+ "pass@8": 0.9979553467275731,
376
+ "pass@16": 0.9985597528853449,
377
+ "pass@32": 0.9990392795604974,
378
+ "pass@64": 0.9994943561408621,
379
+ "pass@128": 1.0
380
+ },
381
+ "per_op_pass_at_k": {
382
+ "10": {
383
+ "pass@1": 0.9640391791044776,
384
+ "pass@2": 0.9751006287460335,
385
+ "pass@4": 0.9840680005484389,
386
+ "pass@8": 0.989525217666148,
387
+ "pass@16": 0.9922932987785924,
388
+ "pass@32": 0.9943696315299635,
389
+ "pass@64": 0.9970265954859788,
390
+ "pass@128": 1.0
391
+ },
392
+ "2": {
393
+ "pass@1": 1.0,
394
+ "pass@2": 1.0,
395
+ "pass@4": 1.0,
396
+ "pass@8": 1.0,
397
+ "pass@16": 1.0,
398
+ "pass@32": 1.0,
399
+ "pass@64": 1.0,
400
+ "pass@128": 1.0
401
+ },
402
+ "3": {
403
+ "pass@1": 1.0,
404
+ "pass@2": 1.0,
405
+ "pass@4": 1.0,
406
+ "pass@8": 1.0,
407
+ "pass@16": 1.0,
408
+ "pass@32": 1.0,
409
+ "pass@64": 1.0,
410
+ "pass@128": 1.0
411
+ },
412
+ "4": {
413
+ "pass@1": 0.9998857821637427,
414
+ "pass@2": 0.9999978415527007,
415
+ "pass@4": 0.9999999997259115,
416
+ "pass@8": 1.0,
417
+ "pass@16": 1.0,
418
+ "pass@32": 1.0,
419
+ "pass@64": 1.0,
420
+ "pass@128": 1.0
421
+ },
422
+ "5": {
423
+ "pass@1": 0.9920266544117647,
424
+ "pass@2": 0.9942518961324689,
425
+ "pass@4": 0.9955414982134585,
426
+ "pass@8": 0.9967116901009395,
427
+ "pass@16": 0.998155080969405,
428
+ "pass@32": 0.9994198334387632,
429
+ "pass@64": 0.9999589349376307,
430
+ "pass@128": 1.0
431
+ },
432
+ "6": {
433
+ "pass@1": 0.9999260646687698,
434
+ "pass@2": 0.9999988356640751,
435
+ "pass@4": 1.0,
436
+ "pass@8": 1.0,
437
+ "pass@16": 1.0,
438
+ "pass@32": 1.0,
439
+ "pass@64": 1.0,
440
+ "pass@128": 1.0
441
+ },
442
+ "7": {
443
+ "pass@1": 0.9976513053797469,
444
+ "pass@2": 0.9984395245689226,
445
+ "pass@4": 0.9992420280930073,
446
+ "pass@8": 0.9998284242652762,
447
+ "pass@16": 0.9999927222555876,
448
+ "pass@32": 0.9999999948561573,
449
+ "pass@64": 1.0,
450
+ "pass@128": 1.0
451
+ },
452
+ "8": {
453
+ "pass@1": 0.9929147897897898,
454
+ "pass@2": 0.9970771706746117,
455
+ "pass@4": 0.9993902071362702,
456
+ "pass@8": 0.9999651367971397,
457
+ "pass@16": 0.9999998583663093,
458
+ "pass@32": 0.9999999999994196,
459
+ "pass@64": 1.0,
460
+ "pass@128": 1.0
461
+ },
462
+ "9": {
463
+ "pass@1": 0.9923884646302251,
464
+ "pass@2": 0.9939457427146365,
465
+ "pass@4": 0.994643188391644,
466
+ "pass@8": 0.995451850487162,
467
+ "pass@16": 0.9964930745316808,
468
+ "pass@32": 0.9974718962737498,
469
+ "pass@64": 0.9983913004056533,
470
+ "pass@128": 1.0
471
+ }
472
+ }
473
+ }
474
+ }
475
+ },
476
+ "ood": {
477
+ "answer_accuracy": 0.870721875,
478
+ "avg_response_len": 379.828709375,
479
+ "avg_loss": 0.0,
480
+ "count": 1280000,
481
+ "validation_metrics": {},
482
+ "pass_at_k": {
483
+ "pass@1": 0.870721875,
484
+ "pass@2": 0.9070165846456469,
485
+ "pass@4": 0.9310222992875821,
486
+ "pass@8": 0.9473439413551321,
487
+ "pass@16": 0.9587791727410775,
488
+ "pass@32": 0.9673418489786182,
489
+ "pass@64": 0.9738290079881573,
490
+ "pass@128": 0.9788
491
+ },
492
+ "per_op_pass_at_k": {
493
+ "11": {
494
+ "pass@1": 0.9725234375,
495
+ "pass@2": 0.9814163385826772,
496
+ "pass@4": 0.9876329908136482,
497
+ "pass@8": 0.9918884097903063,
498
+ "pass@16": 0.9949111139255706,
499
+ "pass@32": 0.9969289474459831,
500
+ "pass@64": 0.9981950900579236,
501
+ "pass@128": 0.999
502
+ },
503
+ "12": {
504
+ "pass@1": 0.9633828125,
505
+ "pass@2": 0.9799354084645666,
506
+ "pass@4": 0.9903667950881146,
507
+ "pass@8": 0.9952444450104463,
508
+ "pass@16": 0.9974553279156712,
509
+ "pass@32": 0.9988006564676271,
510
+ "pass@64": 0.9996719396956972,
511
+ "pass@128": 1.0
512
+ },
513
+ "13": {
514
+ "pass@1": 0.9512578125,
515
+ "pass@2": 0.9713690944881891,
516
+ "pass@4": 0.9840455555868022,
517
+ "pass@8": 0.9908545724750295,
518
+ "pass@16": 0.9943492242524582,
519
+ "pass@32": 0.9960756104075091,
520
+ "pass@64": 0.9969796143219964,
521
+ "pass@128": 0.998
522
+ },
523
+ "14": {
524
+ "pass@1": 0.9520390625,
525
+ "pass@2": 0.9693324311023619,
526
+ "pass@4": 0.9814703537682793,
527
+ "pass@8": 0.9892758228409231,
528
+ "pass@16": 0.9936319146442153,
529
+ "pass@32": 0.9960982517605781,
530
+ "pass@64": 0.9977339665394206,
531
+ "pass@128": 0.999
532
+ },
533
+ "15": {
534
+ "pass@1": 0.959546875,
535
+ "pass@2": 0.9762183809055123,
536
+ "pass@4": 0.9848403532995874,
537
+ "pass@8": 0.9897748141534157,
538
+ "pass@16": 0.9926387666188844,
539
+ "pass@32": 0.9944456451139438,
540
+ "pass@64": 0.9959166661010433,
541
+ "pass@128": 0.997
542
+ },
543
+ "16": {
544
+ "pass@1": 0.896828125,
545
+ "pass@2": 0.9233396899606302,
546
+ "pass@4": 0.9414247777465318,
547
+ "pass@8": 0.953458790870688,
548
+ "pass@16": 0.9612533257789929,
549
+ "pass@32": 0.9673482732504611,
550
+ "pass@64": 0.9725713413565941,
551
+ "pass@128": 0.977
552
+ },
553
+ "17": {
554
+ "pass@1": 0.8799609375,
555
+ "pass@2": 0.9119715797244108,
556
+ "pass@4": 0.9323001194225726,
557
+ "pass@8": 0.9465483790840621,
558
+ "pass@16": 0.9567859939940381,
559
+ "pass@32": 0.9648555078508166,
560
+ "pass@64": 0.9711329473830459,
561
+ "pass@128": 0.976
562
+ },
563
+ "18": {
564
+ "pass@1": 0.83540625,
565
+ "pass@2": 0.8872344980314973,
566
+ "pass@4": 0.9175925875515554,
567
+ "pass@8": 0.9373478636623114,
568
+ "pass@16": 0.9512725593857325,
569
+ "pass@32": 0.9618185543165673,
570
+ "pass@64": 0.9696181077106221,
571
+ "pass@128": 0.975
572
+ },
573
+ "19": {
574
+ "pass@1": 0.6875390625,
575
+ "pass@2": 0.7691173720472443,
576
+ "pass@4": 0.8240086892575941,
577
+ "pass@8": 0.8627536267659003,
578
+ "pass@16": 0.890500855679011,
579
+ "pass@32": 0.9109176601230866,
580
+ "pass@64": 0.9261058523936584,
581
+ "pass@128": 0.938
582
+ },
583
+ "20": {
584
+ "pass@1": 0.608734375,
585
+ "pass@2": 0.7002310531496069,
586
+ "pass@4": 0.7665407703412074,
587
+ "pass@8": 0.8162926888982398,
588
+ "pass@16": 0.854992645216184,
589
+ "pass@32": 0.88612938304957,
590
+ "pass@64": 0.9103645543215643,
591
+ "pass@128": 0.929
592
+ }
593
+ },
594
+ "per_op_accuracy": {
595
+ "11": 0.9725234375,
596
+ "12": 0.9633828125,
597
+ "13": 0.9512578125,
598
+ "14": 0.9520390625,
599
+ "15": 0.959546875,
600
+ "16": 0.896828125,
601
+ "17": 0.8799609375,
602
+ "18": 0.83540625,
603
+ "19": 0.6875390625,
604
+ "20": 0.608734375
605
+ },
606
+ "per_op_avg_response_len": {
607
+ "11": 301.0858671875,
608
+ "12": 313.5365234375,
609
+ "13": 334.6242578125,
610
+ "14": 361.643125,
611
+ "15": 381.6772421875,
612
+ "16": 390.87915625,
613
+ "17": 412.801421875,
614
+ "18": 429.3104140625,
615
+ "19": 428.1585078125,
616
+ "20": 444.570578125
617
+ },
618
+ "per_op_avg_loss": {},
619
+ "per_op_length": {
620
+ "11": 301.0858671875,
621
+ "12": 313.5365234375,
622
+ "13": 334.6242578125,
623
+ "14": 361.643125,
624
+ "15": 381.6772421875,
625
+ "16": 390.87915625,
626
+ "17": 412.801421875,
627
+ "18": 429.3104140625,
628
+ "19": 428.1585078125,
629
+ "20": 444.570578125
630
+ },
631
+ "per_op_loss": {},
632
+ "per_template": {
633
+ "crazy_zootopia": {
634
+ "count": 430720,
635
+ "correct": 371057,
636
+ "answer_accuracy": 0.8614807763744428,
637
+ "avg_response_len": 361.376033153789,
638
+ "resp_tokens_sum": 155651885,
639
+ "pass_at_k": {
640
+ "pass@1": 0.8614807763744428,
641
+ "pass@2": 0.8980265601783103,
642
+ "pass@4": 0.9228763205676597,
643
+ "pass@8": 0.9399765617471983,
644
+ "pass@16": 0.9521830805726366,
645
+ "pass@32": 0.9618381392489881,
646
+ "pass@64": 0.9695388585332727,
647
+ "pass@128": 0.975334323922734
648
+ },
649
+ "per_op_pass_at_k": {
650
+ "11": {
651
+ "pass@1": 0.9682852337110481,
652
+ "pass@2": 0.977452822823493,
653
+ "pass@4": 0.9842284054082472,
654
+ "pass@8": 0.9891870968251745,
655
+ "pass@16": 0.9931120473781875,
656
+ "pass@32": 0.9965309204049758,
657
+ "pass@64": 0.9991380576749798,
658
+ "pass@128": 1.0
659
+ },
660
+ "12": {
661
+ "pass@1": 0.9647775423728814,
662
+ "pass@2": 0.9793001245607014,
663
+ "pass@4": 0.9885038096403199,
664
+ "pass@8": 0.9930489687895803,
665
+ "pass@16": 0.9957842683111874,
666
+ "pass@32": 0.9978504659297166,
667
+ "pass@64": 0.9992600866784821,
668
+ "pass@128": 1.0
669
+ },
670
+ "13": {
671
+ "pass@1": 0.9408797021943573,
672
+ "pass@2": 0.9649356379433759,
673
+ "pass@4": 0.9808571087704949,
674
+ "pass@8": 0.9881229406714634,
675
+ "pass@16": 0.99055864455524,
676
+ "pass@32": 0.9913680560096522,
677
+ "pass@64": 0.9921630087220765,
678
+ "pass@128": 0.9937304075235109
679
+ },
680
+ "14": {
681
+ "pass@1": 0.9360640576323987,
682
+ "pass@2": 0.9562122856722352,
683
+ "pass@4": 0.9707606814919159,
684
+ "pass@8": 0.9804801905602375,
685
+ "pass@16": 0.9866715910082771,
686
+ "pass@32": 0.9909012287981317,
687
+ "pass@64": 0.9945214531172304,
688
+ "pass@128": 0.9968847352024922
689
+ },
690
+ "15": {
691
+ "pass@1": 0.9660404624277457,
692
+ "pass@2": 0.9819844198033775,
693
+ "pass@4": 0.989337811097312,
694
+ "pass@8": 0.9927511350152156,
695
+ "pass@16": 0.9945051007958996,
696
+ "pass@32": 0.9954700452049894,
697
+ "pass@64": 0.996392965878996,
698
+ "pass@128": 0.9971098265895953
699
+ },
700
+ "16": {
701
+ "pass@1": 0.8782762096774194,
702
+ "pass@2": 0.9086745142240289,
703
+ "pass@4": 0.9307146733674418,
704
+ "pass@8": 0.9456327971297461,
705
+ "pass@16": 0.9552193362938507,
706
+ "pass@32": 0.9633343766463572,
707
+ "pass@64": 0.9715414297733572,
708
+ "pass@128": 0.9806451612903225
709
+ },
710
+ "17": {
711
+ "pass@1": 0.8934248554913294,
712
+ "pass@2": 0.9237297175822676,
713
+ "pass@4": 0.9422482222236664,
714
+ "pass@8": 0.9540871391786083,
715
+ "pass@16": 0.9620315216397886,
716
+ "pass@32": 0.9683743703109818,
717
+ "pass@64": 0.9725996832538545,
718
+ "pass@128": 0.9739884393063584
719
+ },
720
+ "18": {
721
+ "pass@1": 0.8005357142857142,
722
+ "pass@2": 0.8531492547806522,
723
+ "pass@4": 0.8860468795864797,
724
+ "pass@8": 0.9091291155842222,
725
+ "pass@16": 0.9275554499538204,
726
+ "pass@32": 0.9442031158786668,
727
+ "pass@64": 0.9575396478067062,
728
+ "pass@128": 0.9657142857142857
729
+ },
730
+ "19": {
731
+ "pass@1": 0.6647428678678678,
732
+ "pass@2": 0.7474041462722564,
733
+ "pass@4": 0.8052284390689899,
734
+ "pass@8": 0.8453281707689558,
735
+ "pass@16": 0.8732022792173314,
736
+ "pass@32": 0.8947298964394246,
737
+ "pass@64": 0.9117678285429259,
738
+ "pass@128": 0.924924924924925
739
+ },
740
+ "20": {
741
+ "pass@1": 0.5938203828828829,
742
+ "pass@2": 0.6811821664183864,
743
+ "pass@4": 0.7462476041846112,
744
+ "pass@8": 0.7985336624704658,
745
+ "pass@16": 0.8402692553045812,
746
+ "pass@32": 0.8729885399962004,
747
+ "pass@64": 0.8982468595231101,
748
+ "pass@128": 0.918918918918919
749
+ }
750
+ }
751
+ },
752
+ "teachers_in_school": {
753
+ "count": 430464,
754
+ "correct": 378048,
755
+ "answer_accuracy": 0.8782337198929527,
756
+ "avg_response_len": 375.42510175066906,
757
+ "resp_tokens_sum": 161606991,
758
+ "pass_at_k": {
759
+ "pass@1": 0.8782337198929527,
760
+ "pass@2": 0.9133105372031476,
761
+ "pass@4": 0.936427513771977,
762
+ "pass@8": 0.9522564458294169,
763
+ "pass@16": 0.9631596491448439,
764
+ "pass@32": 0.9708932145154232,
765
+ "pass@64": 0.9767694340645282,
766
+ "pass@128": 0.9815640796907523
767
+ },
768
+ "per_op_pass_at_k": {
769
+ "11": {
770
+ "pass@1": 0.9791274472891566,
771
+ "pass@2": 0.9844943257281095,
772
+ "pass@4": 0.9885222114554959,
773
+ "pass@8": 0.9915842526776513,
774
+ "pass@16": 0.9936573596958077,
775
+ "pass@32": 0.9946784629745986,
776
+ "pass@64": 0.9954818436151764,
777
+ "pass@128": 0.9969879518072289
778
+ },
779
+ "12": {
780
+ "pass@1": 0.9556720219435737,
781
+ "pass@2": 0.9739207939426853,
782
+ "pass@4": 0.9861632180381843,
783
+ "pass@8": 0.9932283805113136,
784
+ "pass@16": 0.9967175800031935,
785
+ "pass@32": 0.9986257066354457,
786
+ "pass@64": 0.9997926928260641,
787
+ "pass@128": 1.0
788
+ },
789
+ "13": {
790
+ "pass@1": 0.9692752100840336,
791
+ "pass@2": 0.9822620977524867,
792
+ "pass@4": 0.9899195350056031,
793
+ "pass@8": 0.9950258375460176,
794
+ "pass@16": 0.9984359616586164,
795
+ "pass@32": 0.9998247453476256,
796
+ "pass@64": 0.9999989636921891,
797
+ "pass@128": 1.0
798
+ },
799
+ "14": {
800
+ "pass@1": 0.9544956140350878,
801
+ "pass@2": 0.9714041706957683,
802
+ "pass@4": 0.9850686652107085,
803
+ "pass@8": 0.9941410138686707,
804
+ "pass@16": 0.9982549357238066,
805
+ "pass@32": 0.9997482243275714,
806
+ "pass@64": 0.9999976075223646,
807
+ "pass@128": 1.0
808
+ },
809
+ "15": {
810
+ "pass@1": 0.962405303030303,
811
+ "pass@2": 0.9801527827487472,
812
+ "pass@4": 0.9897256777561895,
813
+ "pass@8": 0.9949554819709671,
814
+ "pass@16": 0.9975806792718727,
815
+ "pass@32": 0.9989957428151091,
816
+ "pass@64": 0.999819329898887,
817
+ "pass@128": 1.0
818
+ },
819
+ "16": {
820
+ "pass@1": 0.9157540954415955,
821
+ "pass@2": 0.9383107460125177,
822
+ "pass@4": 0.9528681665860143,
823
+ "pass@8": 0.9618255529076115,
824
+ "pass@16": 0.9666002487818389,
825
+ "pass@32": 0.9691287175972142,
826
+ "pass@64": 0.9713401996282022,
827
+ "pass@128": 0.9743589743589743
828
+ },
829
+ "17": {
830
+ "pass@1": 0.8866459627329193,
831
+ "pass@2": 0.9140307869125057,
832
+ "pass@4": 0.9320510835796145,
833
+ "pass@8": 0.9470251241563546,
834
+ "pass@16": 0.958828933724438,
835
+ "pass@32": 0.9669829599693496,
836
+ "pass@64": 0.9726542282720683,
837
+ "pass@128": 0.9782608695652174
838
+ },
839
+ "18": {
840
+ "pass@1": 0.8592830882352941,
841
+ "pass@2": 0.9078276980083376,
842
+ "pass@4": 0.9323671411477975,
843
+ "pass@8": 0.9477004466579106,
844
+ "pass@16": 0.9584144161429146,
845
+ "pass@32": 0.9654229587125491,
846
+ "pass@64": 0.9701825020374101,
847
+ "pass@128": 0.9735294117647059
848
+ },
849
+ "19": {
850
+ "pass@1": 0.6903366815476191,
851
+ "pass@2": 0.7712544232752157,
852
+ "pass@4": 0.8257569664841,
853
+ "pass@8": 0.8643543757323078,
854
+ "pass@16": 0.8929841094671906,
855
+ "pass@32": 0.914312749232494,
856
+ "pass@64": 0.9313348502509535,
857
+ "pass@128": 0.9464285714285714
858
+ },
859
+ "20": {
860
+ "pass@1": 0.6061938622754491,
861
+ "pass@2": 0.7069592360554483,
862
+ "pass@4": 0.779909319718268,
863
+ "pass@8": 0.8312956919046384,
864
+ "pass@16": 0.8691291374054729,
865
+ "pass@32": 0.9006392983887458,
866
+ "pass@64": 0.926877074969234,
867
+ "pass@128": 0.9461077844311377
868
+ }
869
+ }
870
+ },
871
+ "movie_festival_awards": {
872
+ "count": 418816,
873
+ "correct": 365419,
874
+ "answer_accuracy": 0.8725048708740831,
875
+ "avg_response_len": 403.3319452933985,
876
+ "resp_tokens_sum": 168921872,
877
+ "pass_at_k": {
878
+ "pass@1": 0.8725048708740831,
879
+ "pass@2": 0.9097931341205792,
880
+ "pass@4": 0.9338442681389322,
881
+ "pass@8": 0.9498715941160362,
882
+ "pass@16": 0.9610604404675287,
883
+ "pass@32": 0.9693518553783383,
884
+ "pass@64": 0.9752188918576026,
885
+ "pass@128": 0.9795232273838631
886
+ },
887
+ "per_op_pass_at_k": {
888
+ "11": {
889
+ "pass@1": 0.9703125,
890
+ "pass@2": 0.9826138920134985,
891
+ "pass@4": 0.9905110777819439,
892
+ "pass@8": 0.9952361673715535,
893
+ "pass@16": 0.9982486278795625,
894
+ "pass@32": 0.9997469296363813,
895
+ "pass@64": 0.9999980432330696,
896
+ "pass@128": 1.0
897
+ },
898
+ "12": {
899
+ "pass@1": 0.9693950688073395,
900
+ "pass@2": 0.9864906149919334,
901
+ "pass@4": 0.9964843422668495,
902
+ "pass@8": 0.999587940904666,
903
+ "pass@16": 0.9999840639525752,
904
+ "pass@32": 0.9999999728189605,
905
+ "pass@64": 0.9999999999999997,
906
+ "pass@128": 1.0
907
+ },
908
+ "13": {
909
+ "pass@1": 0.9416232638888888,
910
+ "pass@2": 0.9657007934772044,
911
+ "pass@4": 0.9807125428765847,
912
+ "pass@8": 0.9889479333237797,
913
+ "pass@16": 0.9935783281704044,
914
+ "pass@32": 0.9965795260843454,
915
+ "pass@64": 0.9983950138936485,
916
+ "pass@128": 1.0
917
+ },
918
+ "14": {
919
+ "pass@1": 0.9647626112759644,
920
+ "pass@2": 0.9797271840463564,
921
+ "pass@4": 0.988019856104782,
922
+ "pass@8": 0.992716483465879,
923
+ "pass@16": 0.9955701659139958,
924
+ "pass@32": 0.9973444053304108,
925
+ "pass@64": 0.9984967309084293,
926
+ "pass@128": 1.0
927
+ },
928
+ "15": {
929
+ "pass@1": 0.9497010030864198,
930
+ "pass@2": 0.9660535597112858,
931
+ "pass@4": 0.9750617191369597,
932
+ "pass@8": 0.9813197913201593,
933
+ "pass@16": 0.9856122764931645,
934
+ "pass@32": 0.9887173282223192,
935
+ "pass@64": 0.991433089630488,
936
+ "pass@128": 0.9938271604938271
937
+ },
938
+ "16": {
939
+ "pass@1": 0.8941970870206489,
940
+ "pass@2": 0.9212493177014375,
941
+ "pass@4": 0.9393702139555561,
942
+ "pass@8": 0.9519523737165061,
943
+ "pass@16": 0.9612349386592156,
944
+ "pass@32": 0.9691753292432682,
945
+ "pass@64": 0.9747878703756769,
946
+ "pass@128": 0.976401179941003
947
+ },
948
+ "17": {
949
+ "pass@1": 0.8594455948795181,
950
+ "pass@2": 0.897720433900958,
951
+ "pass@4": 0.922174053073938,
952
+ "pass@8": 0.9382293341864976,
953
+ "pass@16": 0.9493378639982005,
954
+ "pass@32": 0.959124887388815,
955
+ "pass@64": 0.9681289020289342,
956
+ "pass@128": 0.9759036144578314
957
+ },
958
+ "18": {
959
+ "pass@1": 0.8485887096774194,
960
+ "pass@2": 0.903131746888494,
961
+ "pass@4": 0.9370043603420539,
962
+ "pass@8": 0.9578532946585311,
963
+ "pass@16": 0.9702169368171149,
964
+ "pass@32": 0.9777537348282815,
965
+ "pass@64": 0.9826360654372754,
966
+ "pass@128": 0.9870967741935484
967
+ },
968
+ "19": {
969
+ "pass@1": 0.7076331193353474,
970
+ "pass@2": 0.7887924625924787,
971
+ "pass@4": 0.8411277290300948,
972
+ "pass@8": 0.878659443062788,
973
+ "pass@16": 0.9053831900865986,
974
+ "pass@32": 0.9237568606242907,
975
+ "pass@64": 0.9352225250892545,
976
+ "pass@128": 0.9425981873111783
977
+ },
978
+ "20": {
979
+ "pass@1": 0.626196509009009,
980
+ "pass@2": 0.7125315522215124,
981
+ "pass@4": 0.7734252413268156,
982
+ "pass@8": 0.8190036582565382,
983
+ "pass@16": 0.8555370910100033,
984
+ "pass@32": 0.8847167374444287,
985
+ "pass@64": 0.9059201413232556,
986
+ "pass@128": 0.9219219219219219
987
+ }
988
+ }
989
+ }
990
+ }
991
+ },
992
+ "total": {
993
+ "answer_accuracy": 0.9286879111842106,
994
+ "avg_loss": 0.0,
995
+ "count": 2432000,
996
+ "validation_metrics": {
997
+ "id": {},
998
+ "ood": {}
999
+ },
1000
+ "pass_at_k": {
1001
+ "pass@1": 0.9286879111842106,
1002
+ "pass@2": 0.9486924406858649,
1003
+ "pass@4": 0.9619633238756299,
1004
+ "pass@8": 0.970989572117595,
1005
+ "pass@16": 0.9773331856615709,
1006
+ "pass@32": 0.9821242677264577,
1007
+ "pass@64": 0.985816159272922,
1008
+ "pass@128": 0.9886842105263158
1009
+ },
1010
+ "per_op_pass_at_k": {
1011
+ "10": {
1012
+ "pass@1": 0.9540625,
1013
+ "pass@2": 0.9639723179133853,
1014
+ "pass@4": 0.9723782580614919,
1015
+ "pass@8": 0.9787925265522301,
1016
+ "pass@16": 0.9837687276335041,
1017
+ "pass@32": 0.9881571311082412,
1018
+ "pass@64": 0.9927600328966237,
1019
+ "pass@128": 0.997
1020
+ },
1021
+ "2": {
1022
+ "pass@1": 1.0,
1023
+ "pass@2": 1.0,
1024
+ "pass@4": 1.0,
1025
+ "pass@8": 1.0,
1026
+ "pass@16": 1.0,
1027
+ "pass@32": 1.0,
1028
+ "pass@64": 1.0,
1029
+ "pass@128": 1.0
1030
+ },
1031
+ "3": {
1032
+ "pass@1": 0.99946875,
1033
+ "pass@2": 0.9998220964566928,
1034
+ "pass@4": 0.9999744520997375,
1035
+ "pass@8": 0.9999994736310946,
1036
+ "pass@16": 0.9999999998889773,
1037
+ "pass@32": 1.0,
1038
+ "pass@64": 1.0,
1039
+ "pass@128": 1.0
1040
+ },
1041
+ "4": {
1042
+ "pass@1": 0.999890625,
1043
+ "pass@2": 0.9999948326771654,
1044
+ "pass@4": 0.9999999880952382,
1045
+ "pass@8": 0.9999999999999937,
1046
+ "pass@16": 1.0,
1047
+ "pass@32": 1.0,
1048
+ "pass@64": 1.0,
1049
+ "pass@128": 1.0
1050
+ },
1051
+ "5": {
1052
+ "pass@1": 0.9944765625,
1053
+ "pass@2": 0.9970152559055121,
1054
+ "pass@4": 0.9982060622422197,
1055
+ "pass@8": 0.9988426718080923,
1056
+ "pass@16": 0.9993716905884307,
1057
+ "pass@32": 0.9998027430992852,
1058
+ "pass@64": 0.9999860378787945,
1059
+ "pass@128": 1.0
1060
+ },
1061
+ "6": {
1062
+ "pass@1": 0.9999140625,
1063
+ "pass@2": 0.9999985236220473,
1064
+ "pass@4": 0.9999999999062616,
1065
+ "pass@8": 1.0,
1066
+ "pass@16": 1.0,
1067
+ "pass@32": 1.0,
1068
+ "pass@64": 1.0,
1069
+ "pass@128": 1.0
1070
+ },
1071
+ "7": {
1072
+ "pass@1": 0.99834375,
1073
+ "pass@2": 0.9991849163385828,
1074
+ "pass@4": 0.9996791599175103,
1075
+ "pass@8": 0.9999399336710925,
1076
+ "pass@16": 0.9999976797361912,
1077
+ "pass@32": 0.9999999983745138,
1078
+ "pass@64": 1.0,
1079
+ "pass@128": 1.0
1080
+ },
1081
+ "8": {
1082
+ "pass@1": 0.9961796875,
1083
+ "pass@2": 0.9982639025590552,
1084
+ "pass@4": 0.9995023362392201,
1085
+ "pass@8": 0.999940916408823,
1086
+ "pass@16": 0.9999986572834463,
1087
+ "pass@32": 0.9999999995728239,
1088
+ "pass@64": 1.0,
1089
+ "pass@128": 1.0
1090
+ },
1091
+ "9": {
1092
+ "pass@1": 0.995515625,
1093
+ "pass@2": 0.9967386811023622,
1094
+ "pass@4": 0.9973399041994752,
1095
+ "pass@8": 0.9978469346115266,
1096
+ "pass@16": 0.9984020450287275,
1097
+ "pass@32": 0.9989827248615993,
1098
+ "pass@64": 0.9994708755285203,
1099
+ "pass@128": 1.0
1100
+ },
1101
+ "11": {
1102
+ "pass@1": 0.9725234375,
1103
+ "pass@2": 0.9814163385826772,
1104
+ "pass@4": 0.9876329908136482,
1105
+ "pass@8": 0.9918884097903063,
1106
+ "pass@16": 0.9949111139255706,
1107
+ "pass@32": 0.9969289474459831,
1108
+ "pass@64": 0.9981950900579236,
1109
+ "pass@128": 0.999
1110
+ },
1111
+ "12": {
1112
+ "pass@1": 0.9633828125,
1113
+ "pass@2": 0.9799354084645666,
1114
+ "pass@4": 0.9903667950881146,
1115
+ "pass@8": 0.9952444450104463,
1116
+ "pass@16": 0.9974553279156712,
1117
+ "pass@32": 0.9988006564676271,
1118
+ "pass@64": 0.9996719396956972,
1119
+ "pass@128": 1.0
1120
+ },
1121
+ "13": {
1122
+ "pass@1": 0.9512578125,
1123
+ "pass@2": 0.9713690944881891,
1124
+ "pass@4": 0.9840455555868022,
1125
+ "pass@8": 0.9908545724750295,
1126
+ "pass@16": 0.9943492242524582,
1127
+ "pass@32": 0.9960756104075091,
1128
+ "pass@64": 0.9969796143219964,
1129
+ "pass@128": 0.998
1130
+ },
1131
+ "14": {
1132
+ "pass@1": 0.9520390625,
1133
+ "pass@2": 0.9693324311023619,
1134
+ "pass@4": 0.9814703537682793,
1135
+ "pass@8": 0.9892758228409231,
1136
+ "pass@16": 0.9936319146442153,
1137
+ "pass@32": 0.9960982517605781,
1138
+ "pass@64": 0.9977339665394206,
1139
+ "pass@128": 0.999
1140
+ },
1141
+ "15": {
1142
+ "pass@1": 0.959546875,
1143
+ "pass@2": 0.9762183809055123,
1144
+ "pass@4": 0.9848403532995874,
1145
+ "pass@8": 0.9897748141534157,
1146
+ "pass@16": 0.9926387666188844,
1147
+ "pass@32": 0.9944456451139438,
1148
+ "pass@64": 0.9959166661010433,
1149
+ "pass@128": 0.997
1150
+ },
1151
+ "16": {
1152
+ "pass@1": 0.896828125,
1153
+ "pass@2": 0.9233396899606302,
1154
+ "pass@4": 0.9414247777465318,
1155
+ "pass@8": 0.953458790870688,
1156
+ "pass@16": 0.9612533257789929,
1157
+ "pass@32": 0.9673482732504611,
1158
+ "pass@64": 0.9725713413565941,
1159
+ "pass@128": 0.977
1160
+ },
1161
+ "17": {
1162
+ "pass@1": 0.8799609375,
1163
+ "pass@2": 0.9119715797244108,
1164
+ "pass@4": 0.9323001194225726,
1165
+ "pass@8": 0.9465483790840621,
1166
+ "pass@16": 0.9567859939940381,
1167
+ "pass@32": 0.9648555078508166,
1168
+ "pass@64": 0.9711329473830459,
1169
+ "pass@128": 0.976
1170
+ },
1171
+ "18": {
1172
+ "pass@1": 0.83540625,
1173
+ "pass@2": 0.8872344980314973,
1174
+ "pass@4": 0.9175925875515554,
1175
+ "pass@8": 0.9373478636623114,
1176
+ "pass@16": 0.9512725593857325,
1177
+ "pass@32": 0.9618185543165673,
1178
+ "pass@64": 0.9696181077106221,
1179
+ "pass@128": 0.975
1180
+ },
1181
+ "19": {
1182
+ "pass@1": 0.6875390625,
1183
+ "pass@2": 0.7691173720472443,
1184
+ "pass@4": 0.8240086892575941,
1185
+ "pass@8": 0.8627536267659003,
1186
+ "pass@16": 0.890500855679011,
1187
+ "pass@32": 0.9109176601230866,
1188
+ "pass@64": 0.9261058523936584,
1189
+ "pass@128": 0.938
1190
+ },
1191
+ "20": {
1192
+ "pass@1": 0.608734375,
1193
+ "pass@2": 0.7002310531496069,
1194
+ "pass@4": 0.7665407703412074,
1195
+ "pass@8": 0.8162926888982398,
1196
+ "pass@16": 0.854992645216184,
1197
+ "pass@32": 0.88612938304957,
1198
+ "pass@64": 0.9103645543215643,
1199
+ "pass@128": 0.929
1200
+ }
1201
+ },
1202
+ "per_op_accuracy": {
1203
+ "10": 0.9540625,
1204
+ "2": 1.0,
1205
+ "3": 0.99946875,
1206
+ "4": 0.999890625,
1207
+ "5": 0.9944765625,
1208
+ "6": 0.9999140625,
1209
+ "7": 0.99834375,
1210
+ "8": 0.9961796875,
1211
+ "9": 0.995515625,
1212
+ "11": 0.9725234375,
1213
+ "12": 0.9633828125,
1214
+ "13": 0.9512578125,
1215
+ "14": 0.9520390625,
1216
+ "15": 0.959546875,
1217
+ "16": 0.896828125,
1218
+ "17": 0.8799609375,
1219
+ "18": 0.83540625,
1220
+ "19": 0.6875390625,
1221
+ "20": 0.608734375
1222
+ },
1223
+ "per_op_avg_response_len": {
1224
+ "10": 281.6685703125,
1225
+ "2": 115.6646328125,
1226
+ "3": 144.9749609375,
1227
+ "4": 159.97440625,
1228
+ "5": 173.51565625,
1229
+ "6": 198.98446875,
1230
+ "7": 224.252796875,
1231
+ "8": 243.7776015625,
1232
+ "9": 259.75646875,
1233
+ "11": 301.0858671875,
1234
+ "12": 313.5365234375,
1235
+ "13": 334.6242578125,
1236
+ "14": 361.643125,
1237
+ "15": 381.6772421875,
1238
+ "16": 390.87915625,
1239
+ "17": 412.801421875,
1240
+ "18": 429.3104140625,
1241
+ "19": 428.1585078125,
1242
+ "20": 444.570578125
1243
+ },
1244
+ "per_op_avg_loss": {},
1245
+ "per_op_length": {
1246
+ "10": 281.6685703125,
1247
+ "2": 115.6646328125,
1248
+ "3": 144.9749609375,
1249
+ "4": 159.97440625,
1250
+ "5": 173.51565625,
1251
+ "6": 198.98446875,
1252
+ "7": 224.252796875,
1253
+ "8": 243.7776015625,
1254
+ "9": 259.75646875,
1255
+ "11": 301.0858671875,
1256
+ "12": 313.5365234375,
1257
+ "13": 334.6242578125,
1258
+ "14": 361.643125,
1259
+ "15": 381.6772421875,
1260
+ "16": 390.87915625,
1261
+ "17": 412.801421875,
1262
+ "18": 429.3104140625,
1263
+ "19": 428.1585078125,
1264
+ "20": 444.570578125
1265
+ },
1266
+ "per_op_loss": {},
1267
+ "per_template": {
1268
+ "crazy_zootopia": {
1269
+ "count": 809728,
1270
+ "correct": 747714,
1271
+ "answer_accuracy": 0.9234137883338602,
1272
+ "avg_response_len": 281.5405074296554,
1273
+ "resp_tokens_sum": 227971232,
1274
+ "pass_at_k": {
1275
+ "pass@1": 0.9234137883338602,
1276
+ "pass@2": 0.9435549933283615,
1277
+ "pass@4": 0.9572698152890534,
1278
+ "pass@8": 0.9667895172243828,
1279
+ "pass@16": 0.9736588935734707,
1280
+ "pass@32": 0.9790904995462497,
1281
+ "pass@64": 0.9834172709208217,
1282
+ "pass@128": 0.9867214669617452
1283
+ },
1284
+ "per_op_pass_at_k": {
1285
+ "10": {
1286
+ "pass@1": 0.954484697640118,
1287
+ "pass@2": 0.9629707860079438,
1288
+ "pass@4": 0.9709464638269774,
1289
+ "pass@8": 0.9782191819839355,
1290
+ "pass@16": 0.984593484638989,
1291
+ "pass@32": 0.9892985145351701,
1292
+ "pass@64": 0.9930035863666121,
1293
+ "pass@128": 0.9970501474926253
1294
+ },
1295
+ "2": {
1296
+ "pass@1": 1.0,
1297
+ "pass@2": 1.0,
1298
+ "pass@4": 1.0,
1299
+ "pass@8": 1.0,
1300
+ "pass@16": 1.0,
1301
+ "pass@32": 1.0,
1302
+ "pass@64": 1.0,
1303
+ "pass@128": 1.0
1304
+ },
1305
+ "3": {
1306
+ "pass@1": 1.0,
1307
+ "pass@2": 1.0,
1308
+ "pass@4": 1.0,
1309
+ "pass@8": 1.0,
1310
+ "pass@16": 1.0,
1311
+ "pass@32": 1.0,
1312
+ "pass@64": 1.0,
1313
+ "pass@128": 1.0
1314
+ },
1315
+ "4": {
1316
+ "pass@1": 1.0,
1317
+ "pass@2": 1.0,
1318
+ "pass@4": 1.0,
1319
+ "pass@8": 1.0,
1320
+ "pass@16": 1.0,
1321
+ "pass@32": 1.0,
1322
+ "pass@64": 1.0,
1323
+ "pass@128": 1.0
1324
+ },
1325
+ "5": {
1326
+ "pass@1": 0.9980902777777778,
1327
+ "pass@2": 0.9997808867641542,
1328
+ "pass@4": 0.9999950205629058,
1329
+ "pass@8": 0.9999999974305525,
1330
+ "pass@16": 1.0,
1331
+ "pass@32": 1.0,
1332
+ "pass@64": 1.0,
1333
+ "pass@128": 1.0
1334
+ },
1335
+ "6": {
1336
+ "pass@1": 0.9998830464071856,
1337
+ "pass@2": 0.9999977898533642,
1338
+ "pass@4": 0.9999999997193464,
1339
+ "pass@8": 1.0,
1340
+ "pass@16": 1.0,
1341
+ "pass@32": 1.0,
1342
+ "pass@64": 1.0,
1343
+ "pass@128": 1.0
1344
+ },
1345
+ "7": {
1346
+ "pass@1": 0.9991910133136095,
1347
+ "pass@2": 0.9999253803056423,
1348
+ "pass@4": 0.9999992966855474,
1349
+ "pass@8": 0.9999999999707041,
1350
+ "pass@16": 1.0,
1351
+ "pass@32": 1.0,
1352
+ "pass@64": 1.0,
1353
+ "pass@128": 1.0
1354
+ },
1355
+ "8": {
1356
+ "pass@1": 0.9977964743589743,
1357
+ "pass@2": 0.9990386192711489,
1358
+ "pass@4": 0.9997245203123646,
1359
+ "pass@8": 0.9999788364839716,
1360
+ "pass@16": 0.9999999148409177,
1361
+ "pass@32": 0.9999999999998113,
1362
+ "pass@64": 1.0,
1363
+ "pass@128": 1.0
1364
+ },
1365
+ "9": {
1366
+ "pass@1": 0.9962367957746479,
1367
+ "pass@2": 0.9972319646223802,
1368
+ "pass@4": 0.9975970072402921,
1369
+ "pass@8": 0.9979708642982112,
1370
+ "pass@16": 0.9985716335094632,
1371
+ "pass@32": 0.9993491975474896,
1372
+ "pass@64": 0.9999188200066541,
1373
+ "pass@128": 1.0
1374
+ },
1375
+ "11": {
1376
+ "pass@1": 0.9682852337110481,
1377
+ "pass@2": 0.977452822823493,
1378
+ "pass@4": 0.9842284054082472,
1379
+ "pass@8": 0.9891870968251745,
1380
+ "pass@16": 0.9931120473781875,
1381
+ "pass@32": 0.9965309204049758,
1382
+ "pass@64": 0.9991380576749798,
1383
+ "pass@128": 1.0
1384
+ },
1385
+ "12": {
1386
+ "pass@1": 0.9647775423728814,
1387
+ "pass@2": 0.9793001245607014,
1388
+ "pass@4": 0.9885038096403199,
1389
+ "pass@8": 0.9930489687895803,
1390
+ "pass@16": 0.9957842683111874,
1391
+ "pass@32": 0.9978504659297166,
1392
+ "pass@64": 0.9992600866784821,
1393
+ "pass@128": 1.0
1394
+ },
1395
+ "13": {
1396
+ "pass@1": 0.9408797021943573,
1397
+ "pass@2": 0.9649356379433759,
1398
+ "pass@4": 0.9808571087704949,
1399
+ "pass@8": 0.9881229406714634,
1400
+ "pass@16": 0.99055864455524,
1401
+ "pass@32": 0.9913680560096522,
1402
+ "pass@64": 0.9921630087220765,
1403
+ "pass@128": 0.9937304075235109
1404
+ },
1405
+ "14": {
1406
+ "pass@1": 0.9360640576323987,
1407
+ "pass@2": 0.9562122856722352,
1408
+ "pass@4": 0.9707606814919159,
1409
+ "pass@8": 0.9804801905602375,
1410
+ "pass@16": 0.9866715910082771,
1411
+ "pass@32": 0.9909012287981317,
1412
+ "pass@64": 0.9945214531172304,
1413
+ "pass@128": 0.9968847352024922
1414
+ },
1415
+ "15": {
1416
+ "pass@1": 0.9660404624277457,
1417
+ "pass@2": 0.9819844198033775,
1418
+ "pass@4": 0.989337811097312,
1419
+ "pass@8": 0.9927511350152156,
1420
+ "pass@16": 0.9945051007958996,
1421
+ "pass@32": 0.9954700452049894,
1422
+ "pass@64": 0.996392965878996,
1423
+ "pass@128": 0.9971098265895953
1424
+ },
1425
+ "16": {
1426
+ "pass@1": 0.8782762096774194,
1427
+ "pass@2": 0.9086745142240289,
1428
+ "pass@4": 0.9307146733674418,
1429
+ "pass@8": 0.9456327971297461,
1430
+ "pass@16": 0.9552193362938507,
1431
+ "pass@32": 0.9633343766463572,
1432
+ "pass@64": 0.9715414297733572,
1433
+ "pass@128": 0.9806451612903225
1434
+ },
1435
+ "17": {
1436
+ "pass@1": 0.8934248554913294,
1437
+ "pass@2": 0.9237297175822676,
1438
+ "pass@4": 0.9422482222236664,
1439
+ "pass@8": 0.9540871391786083,
1440
+ "pass@16": 0.9620315216397886,
1441
+ "pass@32": 0.9683743703109818,
1442
+ "pass@64": 0.9725996832538545,
1443
+ "pass@128": 0.9739884393063584
1444
+ },
1445
+ "18": {
1446
+ "pass@1": 0.8005357142857142,
1447
+ "pass@2": 0.8531492547806522,
1448
+ "pass@4": 0.8860468795864797,
1449
+ "pass@8": 0.9091291155842222,
1450
+ "pass@16": 0.9275554499538204,
1451
+ "pass@32": 0.9442031158786668,
1452
+ "pass@64": 0.9575396478067062,
1453
+ "pass@128": 0.9657142857142857
1454
+ },
1455
+ "19": {
1456
+ "pass@1": 0.6647428678678678,
1457
+ "pass@2": 0.7474041462722564,
1458
+ "pass@4": 0.8052284390689899,
1459
+ "pass@8": 0.8453281707689558,
1460
+ "pass@16": 0.8732022792173314,
1461
+ "pass@32": 0.8947298964394246,
1462
+ "pass@64": 0.9117678285429259,
1463
+ "pass@128": 0.924924924924925
1464
+ },
1465
+ "20": {
1466
+ "pass@1": 0.5938203828828829,
1467
+ "pass@2": 0.6811821664183864,
1468
+ "pass@4": 0.7462476041846112,
1469
+ "pass@8": 0.7985336624704658,
1470
+ "pass@16": 0.8402692553045812,
1471
+ "pass@32": 0.8729885399962004,
1472
+ "pass@64": 0.8982468595231101,
1473
+ "pass@128": 0.918918918918919
1474
+ }
1475
+ }
1476
+ },
1477
+ "teachers_in_school": {
1478
+ "count": 821120,
1479
+ "correct": 765697,
1480
+ "answer_accuracy": 0.9325031664068589,
1481
+ "avg_response_len": 291.1401585639127,
1482
+ "resp_tokens_sum": 239061007,
1483
+ "pass_at_k": {
1484
+ "pass@1": 0.9325031664068589,
1485
+ "pass@2": 0.9518363817271153,
1486
+ "pass@4": 0.9646200336464147,
1487
+ "pass@8": 0.9733466730553039,
1488
+ "pass@16": 0.9793728174194902,
1489
+ "pass@32": 0.983754479786111,
1490
+ "pass@64": 0.9872180069196503,
1491
+ "pass@128": 0.9900233826968043
1492
+ },
1493
+ "per_op_pass_at_k": {
1494
+ "10": {
1495
+ "pass@1": 0.9433713573619632,
1496
+ "pass@2": 0.9535782540698516,
1497
+ "pass@4": 0.9618546829460732,
1498
+ "pass@8": 0.968359742151891,
1499
+ "pass@16": 0.9741511694787096,
1500
+ "pass@32": 0.9805862212217205,
1501
+ "pass@64": 0.9881224160445984,
1502
+ "pass@128": 0.9938650306748467
1503
+ },
1504
+ "2": {
1505
+ "pass@1": 1.0,
1506
+ "pass@2": 1.0,
1507
+ "pass@4": 1.0,
1508
+ "pass@8": 1.0,
1509
+ "pass@16": 1.0,
1510
+ "pass@32": 1.0,
1511
+ "pass@64": 1.0,
1512
+ "pass@128": 1.0
1513
+ },
1514
+ "3": {
1515
+ "pass@1": 0.9983901515151515,
1516
+ "pass@2": 0.999460898353615,
1517
+ "pass@4": 0.9999225821204167,
1518
+ "pass@8": 0.9999984049427112,
1519
+ "pass@16": 0.9999999996635676,
1520
+ "pass@32": 1.0,
1521
+ "pass@64": 1.0,
1522
+ "pass@128": 1.0
1523
+ },
1524
+ "4": {
1525
+ "pass@1": 0.999791974852071,
1526
+ "pass@2": 0.9999868960536739,
1527
+ "pass@4": 0.9999999650561431,
1528
+ "pass@8": 0.9999999999999813,
1529
+ "pass@16": 1.0,
1530
+ "pass@32": 1.0,
1531
+ "pass@64": 1.0,
1532
+ "pass@128": 1.0
1533
+ },
1534
+ "5": {
1535
+ "pass@1": 0.9935914855072464,
1536
+ "pass@2": 0.9972134257674314,
1537
+ "pass@4": 0.9991986126734157,
1538
+ "pass@8": 0.9998860811105759,
1539
+ "pass@16": 0.9999969943734291,
1540
+ "pass@32": 0.9999999992176973,
1541
+ "pass@64": 1.0,
1542
+ "pass@128": 1.0
1543
+ },
1544
+ "6": {
1545
+ "pass@1": 0.9999328438395415,
1546
+ "pass@2": 0.99999894242267,
1547
+ "pass@4": 1.0,
1548
+ "pass@8": 1.0,
1549
+ "pass@16": 1.0,
1550
+ "pass@32": 1.0,
1551
+ "pass@64": 1.0,
1552
+ "pass@128": 1.0
1553
+ },
1554
+ "7": {
1555
+ "pass@1": 0.9981484826589595,
1556
+ "pass@2": 0.9991423353511447,
1557
+ "pass@4": 0.9997656553768929,
1558
+ "pass@8": 0.9999830971478822,
1559
+ "pass@16": 0.9999999407613452,
1560
+ "pass@32": 0.9999999999999076,
1561
+ "pass@64": 1.0,
1562
+ "pass@128": 1.0
1563
+ },
1564
+ "8": {
1565
+ "pass@1": 0.9978213028169014,
1566
+ "pass@2": 0.998696212709327,
1567
+ "pass@4": 0.9994122448602376,
1568
+ "pass@8": 0.9998848700630322,
1569
+ "pass@16": 0.9999964254002791,
1570
+ "pass@32": 0.9999999987973975,
1571
+ "pass@64": 1.0,
1572
+ "pass@128": 1.0
1573
+ },
1574
+ "9": {
1575
+ "pass@1": 0.9976609281437125,
1576
+ "pass@2": 0.9988149930454053,
1577
+ "pass@4": 0.9995776498184733,
1578
+ "pass@8": 0.9999453661202221,
1579
+ "pass@16": 0.9999993082440582,
1580
+ "pass@32": 0.9999999999733661,
1581
+ "pass@64": 1.0,
1582
+ "pass@128": 1.0
1583
+ },
1584
+ "11": {
1585
+ "pass@1": 0.9791274472891566,
1586
+ "pass@2": 0.9844943257281095,
1587
+ "pass@4": 0.9885222114554959,
1588
+ "pass@8": 0.9915842526776513,
1589
+ "pass@16": 0.9936573596958077,
1590
+ "pass@32": 0.9946784629745986,
1591
+ "pass@64": 0.9954818436151764,
1592
+ "pass@128": 0.9969879518072289
1593
+ },
1594
+ "12": {
1595
+ "pass@1": 0.9556720219435737,
1596
+ "pass@2": 0.9739207939426853,
1597
+ "pass@4": 0.9861632180381843,
1598
+ "pass@8": 0.9932283805113136,
1599
+ "pass@16": 0.9967175800031935,
1600
+ "pass@32": 0.9986257066354457,
1601
+ "pass@64": 0.9997926928260641,
1602
+ "pass@128": 1.0
1603
+ },
1604
+ "13": {
1605
+ "pass@1": 0.9692752100840336,
1606
+ "pass@2": 0.9822620977524867,
1607
+ "pass@4": 0.9899195350056031,
1608
+ "pass@8": 0.9950258375460176,
1609
+ "pass@16": 0.9984359616586164,
1610
+ "pass@32": 0.9998247453476256,
1611
+ "pass@64": 0.9999989636921891,
1612
+ "pass@128": 1.0
1613
+ },
1614
+ "14": {
1615
+ "pass@1": 0.9544956140350878,
1616
+ "pass@2": 0.9714041706957683,
1617
+ "pass@4": 0.9850686652107085,
1618
+ "pass@8": 0.9941410138686707,
1619
+ "pass@16": 0.9982549357238066,
1620
+ "pass@32": 0.9997482243275714,
1621
+ "pass@64": 0.9999976075223646,
1622
+ "pass@128": 1.0
1623
+ },
1624
+ "15": {
1625
+ "pass@1": 0.962405303030303,
1626
+ "pass@2": 0.9801527827487472,
1627
+ "pass@4": 0.9897256777561895,
1628
+ "pass@8": 0.9949554819709671,
1629
+ "pass@16": 0.9975806792718727,
1630
+ "pass@32": 0.9989957428151091,
1631
+ "pass@64": 0.999819329898887,
1632
+ "pass@128": 1.0
1633
+ },
1634
+ "16": {
1635
+ "pass@1": 0.9157540954415955,
1636
+ "pass@2": 0.9383107460125177,
1637
+ "pass@4": 0.9528681665860143,
1638
+ "pass@8": 0.9618255529076115,
1639
+ "pass@16": 0.9666002487818389,
1640
+ "pass@32": 0.9691287175972142,
1641
+ "pass@64": 0.9713401996282022,
1642
+ "pass@128": 0.9743589743589743
1643
+ },
1644
+ "17": {
1645
+ "pass@1": 0.8866459627329193,
1646
+ "pass@2": 0.9140307869125057,
1647
+ "pass@4": 0.9320510835796145,
1648
+ "pass@8": 0.9470251241563546,
1649
+ "pass@16": 0.958828933724438,
1650
+ "pass@32": 0.9669829599693496,
1651
+ "pass@64": 0.9726542282720683,
1652
+ "pass@128": 0.9782608695652174
1653
+ },
1654
+ "18": {
1655
+ "pass@1": 0.8592830882352941,
1656
+ "pass@2": 0.9078276980083376,
1657
+ "pass@4": 0.9323671411477975,
1658
+ "pass@8": 0.9477004466579106,
1659
+ "pass@16": 0.9584144161429146,
1660
+ "pass@32": 0.9654229587125491,
1661
+ "pass@64": 0.9701825020374101,
1662
+ "pass@128": 0.9735294117647059
1663
+ },
1664
+ "19": {
1665
+ "pass@1": 0.6903366815476191,
1666
+ "pass@2": 0.7712544232752157,
1667
+ "pass@4": 0.8257569664841,
1668
+ "pass@8": 0.8643543757323078,
1669
+ "pass@16": 0.8929841094671906,
1670
+ "pass@32": 0.914312749232494,
1671
+ "pass@64": 0.9313348502509535,
1672
+ "pass@128": 0.9464285714285714
1673
+ },
1674
+ "20": {
1675
+ "pass@1": 0.6061938622754491,
1676
+ "pass@2": 0.7069592360554483,
1677
+ "pass@4": 0.779909319718268,
1678
+ "pass@8": 0.8312956919046384,
1679
+ "pass@16": 0.8691291374054729,
1680
+ "pass@32": 0.9006392983887458,
1681
+ "pass@64": 0.926877074969234,
1682
+ "pass@128": 0.9461077844311377
1683
+ }
1684
+ }
1685
+ },
1686
+ "movie_festival_awards": {
1687
+ "count": 801152,
1688
+ "correct": 745158,
1689
+ "answer_accuracy": 0.930108144272248,
1690
+ "avg_response_len": 311.89763365753316,
1691
+ "resp_tokens_sum": 249877413,
1692
+ "pass_at_k": {
1693
+ "pass@1": 0.930108144272248,
1694
+ "pass@2": 0.9506625813159659,
1695
+ "pass@4": 0.9639841486302464,
1696
+ "pass@8": 0.9728187372779841,
1697
+ "pass@16": 0.9789563417603896,
1698
+ "pass@32": 0.9835196674940303,
1699
+ "pass@64": 0.9868039392795732,
1700
+ "pass@128": 0.9892954146029718
1701
+ },
1702
+ "per_op_pass_at_k": {
1703
+ "10": {
1704
+ "pass@1": 0.9640391791044776,
1705
+ "pass@2": 0.9751006287460335,
1706
+ "pass@4": 0.9840680005484389,
1707
+ "pass@8": 0.989525217666148,
1708
+ "pass@16": 0.9922932987785924,
1709
+ "pass@32": 0.9943696315299635,
1710
+ "pass@64": 0.9970265954859788,
1711
+ "pass@128": 1.0
1712
+ },
1713
+ "2": {
1714
+ "pass@1": 1.0,
1715
+ "pass@2": 1.0,
1716
+ "pass@4": 1.0,
1717
+ "pass@8": 1.0,
1718
+ "pass@16": 1.0,
1719
+ "pass@32": 1.0,
1720
+ "pass@64": 1.0,
1721
+ "pass@128": 1.0
1722
+ },
1723
+ "3": {
1724
+ "pass@1": 1.0,
1725
+ "pass@2": 1.0,
1726
+ "pass@4": 1.0,
1727
+ "pass@8": 1.0,
1728
+ "pass@16": 1.0,
1729
+ "pass@32": 1.0,
1730
+ "pass@64": 1.0,
1731
+ "pass@128": 1.0
1732
+ },
1733
+ "4": {
1734
+ "pass@1": 0.9998857821637427,
1735
+ "pass@2": 0.9999978415527007,
1736
+ "pass@4": 0.9999999997259115,
1737
+ "pass@8": 1.0,
1738
+ "pass@16": 1.0,
1739
+ "pass@32": 1.0,
1740
+ "pass@64": 1.0,
1741
+ "pass@128": 1.0
1742
+ },
1743
+ "5": {
1744
+ "pass@1": 0.9920266544117647,
1745
+ "pass@2": 0.9942518961324689,
1746
+ "pass@4": 0.9955414982134585,
1747
+ "pass@8": 0.9967116901009395,
1748
+ "pass@16": 0.998155080969405,
1749
+ "pass@32": 0.9994198334387632,
1750
+ "pass@64": 0.9999589349376307,
1751
+ "pass@128": 1.0
1752
+ },
1753
+ "6": {
1754
+ "pass@1": 0.9999260646687698,
1755
+ "pass@2": 0.9999988356640751,
1756
+ "pass@4": 1.0,
1757
+ "pass@8": 1.0,
1758
+ "pass@16": 1.0,
1759
+ "pass@32": 1.0,
1760
+ "pass@64": 1.0,
1761
+ "pass@128": 1.0
1762
+ },
1763
+ "7": {
1764
+ "pass@1": 0.9976513053797469,
1765
+ "pass@2": 0.9984395245689226,
1766
+ "pass@4": 0.9992420280930073,
1767
+ "pass@8": 0.9998284242652762,
1768
+ "pass@16": 0.9999927222555876,
1769
+ "pass@32": 0.9999999948561573,
1770
+ "pass@64": 1.0,
1771
+ "pass@128": 1.0
1772
+ },
1773
+ "8": {
1774
+ "pass@1": 0.9929147897897898,
1775
+ "pass@2": 0.9970771706746117,
1776
+ "pass@4": 0.9993902071362702,
1777
+ "pass@8": 0.9999651367971397,
1778
+ "pass@16": 0.9999998583663093,
1779
+ "pass@32": 0.9999999999994196,
1780
+ "pass@64": 1.0,
1781
+ "pass@128": 1.0
1782
+ },
1783
+ "9": {
1784
+ "pass@1": 0.9923884646302251,
1785
+ "pass@2": 0.9939457427146365,
1786
+ "pass@4": 0.994643188391644,
1787
+ "pass@8": 0.995451850487162,
1788
+ "pass@16": 0.9964930745316808,
1789
+ "pass@32": 0.9974718962737498,
1790
+ "pass@64": 0.9983913004056533,
1791
+ "pass@128": 1.0
1792
+ },
1793
+ "11": {
1794
+ "pass@1": 0.9703125,
1795
+ "pass@2": 0.9826138920134985,
1796
+ "pass@4": 0.9905110777819439,
1797
+ "pass@8": 0.9952361673715535,
1798
+ "pass@16": 0.9982486278795625,
1799
+ "pass@32": 0.9997469296363813,
1800
+ "pass@64": 0.9999980432330696,
1801
+ "pass@128": 1.0
1802
+ },
1803
+ "12": {
1804
+ "pass@1": 0.9693950688073395,
1805
+ "pass@2": 0.9864906149919334,
1806
+ "pass@4": 0.9964843422668495,
1807
+ "pass@8": 0.999587940904666,
1808
+ "pass@16": 0.9999840639525752,
1809
+ "pass@32": 0.9999999728189605,
1810
+ "pass@64": 0.9999999999999997,
1811
+ "pass@128": 1.0
1812
+ },
1813
+ "13": {
1814
+ "pass@1": 0.9416232638888888,
1815
+ "pass@2": 0.9657007934772044,
1816
+ "pass@4": 0.9807125428765847,
1817
+ "pass@8": 0.9889479333237797,
1818
+ "pass@16": 0.9935783281704044,
1819
+ "pass@32": 0.9965795260843454,
1820
+ "pass@64": 0.9983950138936485,
1821
+ "pass@128": 1.0
1822
+ },
1823
+ "14": {
1824
+ "pass@1": 0.9647626112759644,
1825
+ "pass@2": 0.9797271840463564,
1826
+ "pass@4": 0.988019856104782,
1827
+ "pass@8": 0.992716483465879,
1828
+ "pass@16": 0.9955701659139958,
1829
+ "pass@32": 0.9973444053304108,
1830
+ "pass@64": 0.9984967309084293,
1831
+ "pass@128": 1.0
1832
+ },
1833
+ "15": {
1834
+ "pass@1": 0.9497010030864198,
1835
+ "pass@2": 0.9660535597112858,
1836
+ "pass@4": 0.9750617191369597,
1837
+ "pass@8": 0.9813197913201593,
1838
+ "pass@16": 0.9856122764931645,
1839
+ "pass@32": 0.9887173282223192,
1840
+ "pass@64": 0.991433089630488,
1841
+ "pass@128": 0.9938271604938271
1842
+ },
1843
+ "16": {
1844
+ "pass@1": 0.8941970870206489,
1845
+ "pass@2": 0.9212493177014375,
1846
+ "pass@4": 0.9393702139555561,
1847
+ "pass@8": 0.9519523737165061,
1848
+ "pass@16": 0.9612349386592156,
1849
+ "pass@32": 0.9691753292432682,
1850
+ "pass@64": 0.9747878703756769,
1851
+ "pass@128": 0.976401179941003
1852
+ },
1853
+ "17": {
1854
+ "pass@1": 0.8594455948795181,
1855
+ "pass@2": 0.897720433900958,
1856
+ "pass@4": 0.922174053073938,
1857
+ "pass@8": 0.9382293341864976,
1858
+ "pass@16": 0.9493378639982005,
1859
+ "pass@32": 0.959124887388815,
1860
+ "pass@64": 0.9681289020289342,
1861
+ "pass@128": 0.9759036144578314
1862
+ },
1863
+ "18": {
1864
+ "pass@1": 0.8485887096774194,
1865
+ "pass@2": 0.903131746888494,
1866
+ "pass@4": 0.9370043603420539,
1867
+ "pass@8": 0.9578532946585311,
1868
+ "pass@16": 0.9702169368171149,
1869
+ "pass@32": 0.9777537348282815,
1870
+ "pass@64": 0.9826360654372754,
1871
+ "pass@128": 0.9870967741935484
1872
+ },
1873
+ "19": {
1874
+ "pass@1": 0.7076331193353474,
1875
+ "pass@2": 0.7887924625924787,
1876
+ "pass@4": 0.8411277290300948,
1877
+ "pass@8": 0.878659443062788,
1878
+ "pass@16": 0.9053831900865986,
1879
+ "pass@32": 0.9237568606242907,
1880
+ "pass@64": 0.9352225250892545,
1881
+ "pass@128": 0.9425981873111783
1882
+ },
1883
+ "20": {
1884
+ "pass@1": 0.626196509009009,
1885
+ "pass@2": 0.7125315522215124,
1886
+ "pass@4": 0.7734252413268156,
1887
+ "pass@8": 0.8190036582565382,
1888
+ "pass@16": 0.8555370910100033,
1889
+ "pass@32": 0.8847167374444287,
1890
+ "pass@64": 0.9059201413232556,
1891
+ "pass@128": 0.9219219219219219
1892
+ }
1893
+ }
1894
+ }
1895
+ }
1896
+ }
1897
+ }
Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a5925978851386faf56119b57768e1caa74f21607b7ec7511375d93471a972
3
+ size 373196229
Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e985305d3fdfee25237f92c09828b1109fb641a1a34130bd6648ed3e186799e1
3
+ size 422225883
Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/composition_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/composition/op-difficulty-10B/graphs", "generated_path": "results/Qwen3-100M-midtrain-diff_ar-block4/composition", "results_dir": "results/Qwen3-100M-midtrain-diff_ar-block4/composition/graphs", "per_file": [{"file": "results/Qwen3-100M-midtrain-diff_ar-block4/composition/checkpoint-38646_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1024488, "value_mismatch": 8666, "dependency_mismatch": 126198, "answer_mismatch": 7955, "extra_nodes": 11048, "missing_nodes": 8581, "perfect_with_extra": 938, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 337887, "dependency_mismatch": 40758, "extra_nodes": 3484, "missing_nodes": 2571, "value_mismatch": 2633, "answer_mismatch": 2351, "perfect_with_extra": 420}, "teachers_in_school": {"total": 390656, "perfect": 346858, "value_mismatch": 3143, "answer_mismatch": 3007, "dependency_mismatch": 43394, "extra_nodes": 3920, "missing_nodes": 3330, "perfect_with_extra": 326}, "movie_festival_awards": {"total": 382336, "perfect": 339743, "dependency_mismatch": 42046, "extra_nodes": 3644, "missing_nodes": 2680, "perfect_with_extra": 192, "value_mismatch": 2890, "answer_mismatch": 2597}}, "results_path": "results/Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/Qwen3-100M-midtrain-diff_ar-block4/composition/checkpoint-38646_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 645759, "value_mismatch": 214993, "dependency_mismatch": 610706, "answer_mismatch": 165476, "extra_nodes": 40541, "missing_nodes": 147475, "perfect_with_extra": 294, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "perfect": 215781, "value_mismatch": 75701, "dependency_mismatch": 207056, "answer_mismatch": 59663, "extra_nodes": 15260, "perfect_with_extra": 59, "missing_nodes": 55087}, "movie_festival_awards": {"total": 418816, "perfect": 212276, "value_mismatch": 70597, "dependency_mismatch": 198554, "answer_mismatch": 53397, "missing_nodes": 45668, "extra_nodes": 12686, "perfect_with_extra": 95}, "teachers_in_school": {"total": 430464, "perfect": 217702, "value_mismatch": 68695, "dependency_mismatch": 205096, "answer_mismatch": 52416, "extra_nodes": 12595, "perfect_with_extra": 140, "missing_nodes": 46720}}, "results_path": "results/Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/checkpoint-38646_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1670247, "value_mismatch": 223659, "dependency_mismatch": 736904, "answer_mismatch": 173431, "extra_nodes": 51589, "missing_nodes": 156056, "perfect_with_extra": 1232, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/composition_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 553668, "dependency_mismatch": 247814, "extra_nodes": 18744, "missing_nodes": 57658, "value_mismatch": 78334, "answer_mismatch": 62014, "perfect_with_extra": 479}, "teachers_in_school": {"total": 821120, "perfect": 564560, "value_mismatch": 71838, "answer_mismatch": 55423, "dependency_mismatch": 248490, "extra_nodes": 16515, "missing_nodes": 50050, "perfect_with_extra": 466}, "movie_festival_awards": {"total": 801152, "perfect": 552019, "dependency_mismatch": 240600, "extra_nodes": 16330, "missing_nodes": 48348, "perfect_with_extra": 287, "value_mismatch": 73487, "answer_mismatch": 55994}}}}
Qwen3-100M-midtrain-diff_ar-block4/composition/graphs/results.json ADDED
@@ -0,0 +1,1780 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "checkpoint-38646_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "crazy_zootopia": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 1.0,
9
+ "pass@2": 1.0,
10
+ "pass@4": 1.0,
11
+ "pass@8": 1.0,
12
+ "pass@16": 1.0,
13
+ "pass@32": 1.0,
14
+ "pass@64": 1.0,
15
+ "pass@128": 1.0
16
+ },
17
+ "3": {
18
+ "pass@1": 1.0,
19
+ "pass@2": 1.0,
20
+ "pass@4": 1.0,
21
+ "pass@8": 1.0,
22
+ "pass@16": 1.0,
23
+ "pass@32": 1.0,
24
+ "pass@64": 1.0,
25
+ "pass@128": 1.0
26
+ },
27
+ "4": {
28
+ "pass@1": 0.99375,
29
+ "pass@2": 1.0,
30
+ "pass@4": 1.0,
31
+ "pass@8": 1.0,
32
+ "pass@16": 1.0,
33
+ "pass@32": 1.0,
34
+ "pass@64": 1.0,
35
+ "pass@128": 1.0
36
+ },
37
+ "5": {
38
+ "pass@1": 0.9587301587301588,
39
+ "pass@2": 0.9809523809523809,
40
+ "pass@4": 0.9936507936507937,
41
+ "pass@8": 1.0,
42
+ "pass@16": 1.0,
43
+ "pass@32": 1.0,
44
+ "pass@64": 1.0,
45
+ "pass@128": 1.0
46
+ },
47
+ "6": {
48
+ "pass@1": 0.9550898203592815,
49
+ "pass@2": 0.9640718562874252,
50
+ "pass@4": 0.9940119760479041,
51
+ "pass@8": 0.9940119760479041,
52
+ "pass@16": 1.0,
53
+ "pass@32": 1.0,
54
+ "pass@64": 1.0,
55
+ "pass@128": 1.0
56
+ },
57
+ "7": {
58
+ "pass@1": 0.893491124260355,
59
+ "pass@2": 0.9230769230769231,
60
+ "pass@4": 0.9644970414201184,
61
+ "pass@8": 0.985207100591716,
62
+ "pass@16": 0.9940828402366864,
63
+ "pass@32": 0.9970414201183432,
64
+ "pass@64": 1.0,
65
+ "pass@128": 1.0
66
+ },
67
+ "8": {
68
+ "pass@1": 0.8301282051282052,
69
+ "pass@2": 0.8782051282051282,
70
+ "pass@4": 0.9423076923076923,
71
+ "pass@8": 0.9807692307692307,
72
+ "pass@16": 0.9935897435897436,
73
+ "pass@32": 1.0,
74
+ "pass@64": 1.0,
75
+ "pass@128": 1.0
76
+ },
77
+ "9": {
78
+ "pass@1": 0.7633802816901408,
79
+ "pass@2": 0.8338028169014085,
80
+ "pass@4": 0.9070422535211268,
81
+ "pass@8": 0.9690140845070423,
82
+ "pass@16": 0.9887323943661972,
83
+ "pass@32": 1.0,
84
+ "pass@64": 1.0,
85
+ "pass@128": 1.0
86
+ },
87
+ "10": {
88
+ "pass@1": 0.6371681415929203,
89
+ "pass@2": 0.7109144542772862,
90
+ "pass@4": 0.7905604719764012,
91
+ "pass@8": 0.8584070796460177,
92
+ "pass@16": 0.9056047197640118,
93
+ "pass@32": 0.9410029498525073,
94
+ "pass@64": 0.9557522123893806,
95
+ "pass@128": 0.9616519174041298
96
+ }
97
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 1.0,
101
+ "3": 1.0,
102
+ "4": 0.99375,
103
+ "5": 0.9587301587301588,
104
+ "6": 0.9550898203592815,
105
+ "7": 0.893491124260355,
106
+ "8": 0.8301282051282052,
107
+ "9": 0.7633802816901408,
108
+ "10": 0.6371681415929203
109
+ },
110
+ "pass@2": {
111
+ "2": 1.0,
112
+ "3": 1.0,
113
+ "4": 1.0,
114
+ "5": 0.9809523809523809,
115
+ "6": 0.9640718562874252,
116
+ "7": 0.9230769230769231,
117
+ "8": 0.8782051282051282,
118
+ "9": 0.8338028169014085,
119
+ "10": 0.7109144542772862
120
+ },
121
+ "pass@4": {
122
+ "2": 1.0,
123
+ "3": 1.0,
124
+ "4": 1.0,
125
+ "5": 0.9936507936507937,
126
+ "6": 0.9940119760479041,
127
+ "7": 0.9644970414201184,
128
+ "8": 0.9423076923076923,
129
+ "9": 0.9070422535211268,
130
+ "10": 0.7905604719764012
131
+ },
132
+ "pass@8": {
133
+ "2": 1.0,
134
+ "3": 1.0,
135
+ "4": 1.0,
136
+ "5": 1.0,
137
+ "6": 0.9940119760479041,
138
+ "7": 0.985207100591716,
139
+ "8": 0.9807692307692307,
140
+ "9": 0.9690140845070423,
141
+ "10": 0.8584070796460177
142
+ },
143
+ "pass@16": {
144
+ "2": 1.0,
145
+ "3": 1.0,
146
+ "4": 1.0,
147
+ "5": 1.0,
148
+ "6": 1.0,
149
+ "7": 0.9940828402366864,
150
+ "8": 0.9935897435897436,
151
+ "9": 0.9887323943661972,
152
+ "10": 0.9056047197640118
153
+ },
154
+ "pass@32": {
155
+ "2": 1.0,
156
+ "3": 1.0,
157
+ "4": 1.0,
158
+ "5": 1.0,
159
+ "6": 1.0,
160
+ "7": 0.9970414201183432,
161
+ "8": 1.0,
162
+ "9": 1.0,
163
+ "10": 0.9410029498525073
164
+ },
165
+ "pass@64": {
166
+ "2": 1.0,
167
+ "3": 1.0,
168
+ "4": 1.0,
169
+ "5": 1.0,
170
+ "6": 1.0,
171
+ "7": 1.0,
172
+ "8": 1.0,
173
+ "9": 1.0,
174
+ "10": 0.9557522123893806
175
+ },
176
+ "pass@128": {
177
+ "2": 1.0,
178
+ "3": 1.0,
179
+ "4": 1.0,
180
+ "5": 1.0,
181
+ "6": 1.0,
182
+ "7": 1.0,
183
+ "8": 1.0,
184
+ "9": 1.0,
185
+ "10": 0.9616519174041298
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.8899020601148261,
190
+ "pass@2": 0.9192840256670044,
191
+ "pass@4": 0.9533941236068896,
192
+ "pass@8": 0.9756838905775076,
193
+ "pass@16": 0.9864910503208375,
194
+ "pass@32": 0.9929078014184397,
195
+ "pass@64": 0.9949341438703141,
196
+ "pass@128": 0.9956095913542722
197
+ }
198
+ },
199
+ "movie_festival_awards": {
200
+ "per_op_pass_at_k": {
201
+ "2": {
202
+ "pass@1": 1.0,
203
+ "pass@2": 1.0,
204
+ "pass@4": 1.0,
205
+ "pass@8": 1.0,
206
+ "pass@16": 1.0,
207
+ "pass@32": 1.0,
208
+ "pass@64": 1.0,
209
+ "pass@128": 1.0
210
+ },
211
+ "3": {
212
+ "pass@1": 1.0,
213
+ "pass@2": 1.0,
214
+ "pass@4": 1.0,
215
+ "pass@8": 1.0,
216
+ "pass@16": 1.0,
217
+ "pass@32": 1.0,
218
+ "pass@64": 1.0,
219
+ "pass@128": 1.0
220
+ },
221
+ "4": {
222
+ "pass@1": 0.9883040935672515,
223
+ "pass@2": 0.9941520467836257,
224
+ "pass@4": 1.0,
225
+ "pass@8": 1.0,
226
+ "pass@16": 1.0,
227
+ "pass@32": 1.0,
228
+ "pass@64": 1.0,
229
+ "pass@128": 1.0
230
+ },
231
+ "5": {
232
+ "pass@1": 0.95,
233
+ "pass@2": 0.9735294117647059,
234
+ "pass@4": 0.9911764705882353,
235
+ "pass@8": 0.9941176470588236,
236
+ "pass@16": 0.9970588235294118,
237
+ "pass@32": 0.9970588235294118,
238
+ "pass@64": 1.0,
239
+ "pass@128": 1.0
240
+ },
241
+ "6": {
242
+ "pass@1": 0.9684542586750788,
243
+ "pass@2": 0.9810725552050473,
244
+ "pass@4": 0.9842271293375394,
245
+ "pass@8": 0.9936908517350158,
246
+ "pass@16": 1.0,
247
+ "pass@32": 1.0,
248
+ "pass@64": 1.0,
249
+ "pass@128": 1.0
250
+ },
251
+ "7": {
252
+ "pass@1": 0.8575949367088608,
253
+ "pass@2": 0.9145569620253164,
254
+ "pass@4": 0.9651898734177216,
255
+ "pass@8": 0.9936708860759493,
256
+ "pass@16": 0.9968354430379747,
257
+ "pass@32": 1.0,
258
+ "pass@64": 1.0,
259
+ "pass@128": 1.0
260
+ },
261
+ "8": {
262
+ "pass@1": 0.8168168168168168,
263
+ "pass@2": 0.8708708708708709,
264
+ "pass@4": 0.9129129129129129,
265
+ "pass@8": 0.960960960960961,
266
+ "pass@16": 0.993993993993994,
267
+ "pass@32": 1.0,
268
+ "pass@64": 1.0,
269
+ "pass@128": 1.0
270
+ },
271
+ "9": {
272
+ "pass@1": 0.7652733118971061,
273
+ "pass@2": 0.8263665594855305,
274
+ "pass@4": 0.9035369774919614,
275
+ "pass@8": 0.9453376205787781,
276
+ "pass@16": 0.9646302250803859,
277
+ "pass@32": 0.9935691318327974,
278
+ "pass@64": 0.9967845659163987,
279
+ "pass@128": 0.9967845659163987
280
+ },
281
+ "10": {
282
+ "pass@1": 0.6149253731343284,
283
+ "pass@2": 0.6895522388059702,
284
+ "pass@4": 0.7701492537313432,
285
+ "pass@8": 0.8716417910447761,
286
+ "pass@16": 0.9343283582089552,
287
+ "pass@32": 0.9552238805970149,
288
+ "pass@64": 0.9791044776119403,
289
+ "pass@128": 0.9880597014925373
290
+ }
291
+ },
292
+ "per_op_pass_at_columns": {
293
+ "pass@1": {
294
+ "2": 1.0,
295
+ "3": 1.0,
296
+ "4": 0.9883040935672515,
297
+ "5": 0.95,
298
+ "6": 0.9684542586750788,
299
+ "7": 0.8575949367088608,
300
+ "8": 0.8168168168168168,
301
+ "9": 0.7652733118971061,
302
+ "10": 0.6149253731343284
303
+ },
304
+ "pass@2": {
305
+ "2": 1.0,
306
+ "3": 1.0,
307
+ "4": 0.9941520467836257,
308
+ "5": 0.9735294117647059,
309
+ "6": 0.9810725552050473,
310
+ "7": 0.9145569620253164,
311
+ "8": 0.8708708708708709,
312
+ "9": 0.8263665594855305,
313
+ "10": 0.6895522388059702
314
+ },
315
+ "pass@4": {
316
+ "2": 1.0,
317
+ "3": 1.0,
318
+ "4": 1.0,
319
+ "5": 0.9911764705882353,
320
+ "6": 0.9842271293375394,
321
+ "7": 0.9651898734177216,
322
+ "8": 0.9129129129129129,
323
+ "9": 0.9035369774919614,
324
+ "10": 0.7701492537313432
325
+ },
326
+ "pass@8": {
327
+ "2": 1.0,
328
+ "3": 1.0,
329
+ "4": 1.0,
330
+ "5": 0.9941176470588236,
331
+ "6": 0.9936908517350158,
332
+ "7": 0.9936708860759493,
333
+ "8": 0.960960960960961,
334
+ "9": 0.9453376205787781,
335
+ "10": 0.8716417910447761
336
+ },
337
+ "pass@16": {
338
+ "2": 1.0,
339
+ "3": 1.0,
340
+ "4": 1.0,
341
+ "5": 0.9970588235294118,
342
+ "6": 1.0,
343
+ "7": 0.9968354430379747,
344
+ "8": 0.993993993993994,
345
+ "9": 0.9646302250803859,
346
+ "10": 0.9343283582089552
347
+ },
348
+ "pass@32": {
349
+ "2": 1.0,
350
+ "3": 1.0,
351
+ "4": 1.0,
352
+ "5": 0.9970588235294118,
353
+ "6": 1.0,
354
+ "7": 1.0,
355
+ "8": 1.0,
356
+ "9": 0.9935691318327974,
357
+ "10": 0.9552238805970149
358
+ },
359
+ "pass@64": {
360
+ "2": 1.0,
361
+ "3": 1.0,
362
+ "4": 1.0,
363
+ "5": 1.0,
364
+ "6": 1.0,
365
+ "7": 1.0,
366
+ "8": 1.0,
367
+ "9": 0.9967845659163987,
368
+ "10": 0.9791044776119403
369
+ },
370
+ "pass@128": {
371
+ "2": 1.0,
372
+ "3": 1.0,
373
+ "4": 1.0,
374
+ "5": 1.0,
375
+ "6": 1.0,
376
+ "7": 1.0,
377
+ "8": 1.0,
378
+ "9": 0.9967845659163987,
379
+ "10": 0.9880597014925373
380
+ }
381
+ },
382
+ "total_pass_at_k": {
383
+ "pass@1": 0.8865082022095748,
384
+ "pass@2": 0.9179779042517576,
385
+ "pass@4": 0.9481084700368263,
386
+ "pass@8": 0.9735520589219954,
387
+ "pass@16": 0.987612989621694,
388
+ "pass@32": 0.9939738868429863,
389
+ "pass@64": 0.9973217274857716,
390
+ "pass@128": 0.9983260796786073
391
+ }
392
+ },
393
+ "teachers_in_school": {
394
+ "per_op_pass_at_k": {
395
+ "2": {
396
+ "pass@1": 1.0,
397
+ "pass@2": 1.0,
398
+ "pass@4": 1.0,
399
+ "pass@8": 1.0,
400
+ "pass@16": 1.0,
401
+ "pass@32": 1.0,
402
+ "pass@64": 1.0,
403
+ "pass@128": 1.0
404
+ },
405
+ "3": {
406
+ "pass@1": 1.0,
407
+ "pass@2": 1.0,
408
+ "pass@4": 1.0,
409
+ "pass@8": 1.0,
410
+ "pass@16": 1.0,
411
+ "pass@32": 1.0,
412
+ "pass@64": 1.0,
413
+ "pass@128": 1.0
414
+ },
415
+ "4": {
416
+ "pass@1": 0.985207100591716,
417
+ "pass@2": 0.9881656804733728,
418
+ "pass@4": 0.9970414201183432,
419
+ "pass@8": 1.0,
420
+ "pass@16": 1.0,
421
+ "pass@32": 1.0,
422
+ "pass@64": 1.0,
423
+ "pass@128": 1.0
424
+ },
425
+ "5": {
426
+ "pass@1": 0.9478260869565217,
427
+ "pass@2": 0.9826086956521739,
428
+ "pass@4": 0.991304347826087,
429
+ "pass@8": 0.9971014492753624,
430
+ "pass@16": 1.0,
431
+ "pass@32": 1.0,
432
+ "pass@64": 1.0,
433
+ "pass@128": 1.0
434
+ },
435
+ "6": {
436
+ "pass@1": 0.9770773638968482,
437
+ "pass@2": 0.9856733524355301,
438
+ "pass@4": 0.9914040114613181,
439
+ "pass@8": 0.997134670487106,
440
+ "pass@16": 0.997134670487106,
441
+ "pass@32": 1.0,
442
+ "pass@64": 1.0,
443
+ "pass@128": 1.0
444
+ },
445
+ "7": {
446
+ "pass@1": 0.8554913294797688,
447
+ "pass@2": 0.9017341040462428,
448
+ "pass@4": 0.9595375722543352,
449
+ "pass@8": 0.9826589595375722,
450
+ "pass@16": 0.9913294797687862,
451
+ "pass@32": 1.0,
452
+ "pass@64": 1.0,
453
+ "pass@128": 1.0
454
+ },
455
+ "8": {
456
+ "pass@1": 0.819718309859155,
457
+ "pass@2": 0.8788732394366198,
458
+ "pass@4": 0.952112676056338,
459
+ "pass@8": 0.9830985915492958,
460
+ "pass@16": 0.9971830985915493,
461
+ "pass@32": 1.0,
462
+ "pass@64": 1.0,
463
+ "pass@128": 1.0
464
+ },
465
+ "9": {
466
+ "pass@1": 0.7455089820359282,
467
+ "pass@2": 0.8023952095808383,
468
+ "pass@4": 0.8952095808383234,
469
+ "pass@8": 0.9580838323353293,
470
+ "pass@16": 0.9850299401197605,
471
+ "pass@32": 0.9910179640718563,
472
+ "pass@64": 1.0,
473
+ "pass@128": 1.0
474
+ },
475
+ "10": {
476
+ "pass@1": 0.6319018404907976,
477
+ "pass@2": 0.6932515337423313,
478
+ "pass@4": 0.7668711656441718,
479
+ "pass@8": 0.8312883435582822,
480
+ "pass@16": 0.8957055214723927,
481
+ "pass@32": 0.9478527607361963,
482
+ "pass@64": 0.9570552147239264,
483
+ "pass@128": 0.9693251533742331
484
+ }
485
+ },
486
+ "per_op_pass_at_columns": {
487
+ "pass@1": {
488
+ "2": 1.0,
489
+ "3": 1.0,
490
+ "4": 0.985207100591716,
491
+ "5": 0.9478260869565217,
492
+ "6": 0.9770773638968482,
493
+ "7": 0.8554913294797688,
494
+ "8": 0.819718309859155,
495
+ "9": 0.7455089820359282,
496
+ "10": 0.6319018404907976
497
+ },
498
+ "pass@2": {
499
+ "2": 1.0,
500
+ "3": 1.0,
501
+ "4": 0.9881656804733728,
502
+ "5": 0.9826086956521739,
503
+ "6": 0.9856733524355301,
504
+ "7": 0.9017341040462428,
505
+ "8": 0.8788732394366198,
506
+ "9": 0.8023952095808383,
507
+ "10": 0.6932515337423313
508
+ },
509
+ "pass@4": {
510
+ "2": 1.0,
511
+ "3": 1.0,
512
+ "4": 0.9970414201183432,
513
+ "5": 0.991304347826087,
514
+ "6": 0.9914040114613181,
515
+ "7": 0.9595375722543352,
516
+ "8": 0.952112676056338,
517
+ "9": 0.8952095808383234,
518
+ "10": 0.7668711656441718
519
+ },
520
+ "pass@8": {
521
+ "2": 1.0,
522
+ "3": 1.0,
523
+ "4": 1.0,
524
+ "5": 0.9971014492753624,
525
+ "6": 0.997134670487106,
526
+ "7": 0.9826589595375722,
527
+ "8": 0.9830985915492958,
528
+ "9": 0.9580838323353293,
529
+ "10": 0.8312883435582822
530
+ },
531
+ "pass@16": {
532
+ "2": 1.0,
533
+ "3": 1.0,
534
+ "4": 1.0,
535
+ "5": 1.0,
536
+ "6": 0.997134670487106,
537
+ "7": 0.9913294797687862,
538
+ "8": 0.9971830985915493,
539
+ "9": 0.9850299401197605,
540
+ "10": 0.8957055214723927
541
+ },
542
+ "pass@32": {
543
+ "2": 1.0,
544
+ "3": 1.0,
545
+ "4": 1.0,
546
+ "5": 1.0,
547
+ "6": 1.0,
548
+ "7": 1.0,
549
+ "8": 1.0,
550
+ "9": 0.9910179640718563,
551
+ "10": 0.9478527607361963
552
+ },
553
+ "pass@64": {
554
+ "2": 1.0,
555
+ "3": 1.0,
556
+ "4": 1.0,
557
+ "5": 1.0,
558
+ "6": 1.0,
559
+ "7": 1.0,
560
+ "8": 1.0,
561
+ "9": 1.0,
562
+ "10": 0.9570552147239264
563
+ },
564
+ "pass@128": {
565
+ "2": 1.0,
566
+ "3": 1.0,
567
+ "4": 1.0,
568
+ "5": 1.0,
569
+ "6": 1.0,
570
+ "7": 1.0,
571
+ "8": 1.0,
572
+ "9": 1.0,
573
+ "10": 0.9693251533742331
574
+ }
575
+ },
576
+ "total_pass_at_k": {
577
+ "pass@1": 0.8853211009174312,
578
+ "pass@2": 0.9154652686762779,
579
+ "pass@4": 0.9511795543905636,
580
+ "pass@8": 0.9728047182175622,
581
+ "pass@16": 0.9855832241153342,
582
+ "pass@32": 0.9934469200524246,
583
+ "pass@64": 0.9954128440366973,
584
+ "pass@128": 0.9967234600262124
585
+ }
586
+ }
587
+ },
588
+ "total": {
589
+ "per_op_pass_at_k": {
590
+ "2": {
591
+ "pass@1": 1.0,
592
+ "pass@2": 1.0,
593
+ "pass@4": 1.0,
594
+ "pass@8": 1.0,
595
+ "pass@16": 1.0,
596
+ "pass@32": 1.0,
597
+ "pass@64": 1.0,
598
+ "pass@128": 1.0
599
+ },
600
+ "3": {
601
+ "pass@1": 1.0,
602
+ "pass@2": 1.0,
603
+ "pass@4": 1.0,
604
+ "pass@8": 1.0,
605
+ "pass@16": 1.0,
606
+ "pass@32": 1.0,
607
+ "pass@64": 1.0,
608
+ "pass@128": 1.0
609
+ },
610
+ "4": {
611
+ "pass@1": 0.989,
612
+ "pass@2": 0.994,
613
+ "pass@4": 0.999,
614
+ "pass@8": 1.0,
615
+ "pass@16": 1.0,
616
+ "pass@32": 1.0,
617
+ "pass@64": 1.0,
618
+ "pass@128": 1.0
619
+ },
620
+ "5": {
621
+ "pass@1": 0.952,
622
+ "pass@2": 0.979,
623
+ "pass@4": 0.992,
624
+ "pass@8": 0.997,
625
+ "pass@16": 0.999,
626
+ "pass@32": 0.999,
627
+ "pass@64": 1.0,
628
+ "pass@128": 1.0
629
+ },
630
+ "6": {
631
+ "pass@1": 0.967,
632
+ "pass@2": 0.977,
633
+ "pass@4": 0.99,
634
+ "pass@8": 0.995,
635
+ "pass@16": 0.999,
636
+ "pass@32": 1.0,
637
+ "pass@64": 1.0,
638
+ "pass@128": 1.0
639
+ },
640
+ "7": {
641
+ "pass@1": 0.869,
642
+ "pass@2": 0.913,
643
+ "pass@4": 0.963,
644
+ "pass@8": 0.987,
645
+ "pass@16": 0.994,
646
+ "pass@32": 0.999,
647
+ "pass@64": 1.0,
648
+ "pass@128": 1.0
649
+ },
650
+ "8": {
651
+ "pass@1": 0.822,
652
+ "pass@2": 0.876,
653
+ "pass@4": 0.936,
654
+ "pass@8": 0.975,
655
+ "pass@16": 0.995,
656
+ "pass@32": 1.0,
657
+ "pass@64": 1.0,
658
+ "pass@128": 1.0
659
+ },
660
+ "9": {
661
+ "pass@1": 0.758,
662
+ "pass@2": 0.821,
663
+ "pass@4": 0.902,
664
+ "pass@8": 0.958,
665
+ "pass@16": 0.98,
666
+ "pass@32": 0.995,
667
+ "pass@64": 0.999,
668
+ "pass@128": 0.999
669
+ },
670
+ "10": {
671
+ "pass@1": 0.628,
672
+ "pass@2": 0.698,
673
+ "pass@4": 0.776,
674
+ "pass@8": 0.854,
675
+ "pass@16": 0.912,
676
+ "pass@32": 0.948,
677
+ "pass@64": 0.964,
678
+ "pass@128": 0.973
679
+ }
680
+ },
681
+ "per_op_pass_at_columns": {
682
+ "pass@1": {
683
+ "2": 1.0,
684
+ "3": 1.0,
685
+ "4": 0.989,
686
+ "5": 0.952,
687
+ "6": 0.967,
688
+ "7": 0.869,
689
+ "8": 0.822,
690
+ "9": 0.758,
691
+ "10": 0.628
692
+ },
693
+ "pass@2": {
694
+ "2": 1.0,
695
+ "3": 1.0,
696
+ "4": 0.994,
697
+ "5": 0.979,
698
+ "6": 0.977,
699
+ "7": 0.913,
700
+ "8": 0.876,
701
+ "9": 0.821,
702
+ "10": 0.698
703
+ },
704
+ "pass@4": {
705
+ "2": 1.0,
706
+ "3": 1.0,
707
+ "4": 0.999,
708
+ "5": 0.992,
709
+ "6": 0.99,
710
+ "7": 0.963,
711
+ "8": 0.936,
712
+ "9": 0.902,
713
+ "10": 0.776
714
+ },
715
+ "pass@8": {
716
+ "2": 1.0,
717
+ "3": 1.0,
718
+ "4": 1.0,
719
+ "5": 0.997,
720
+ "6": 0.995,
721
+ "7": 0.987,
722
+ "8": 0.975,
723
+ "9": 0.958,
724
+ "10": 0.854
725
+ },
726
+ "pass@16": {
727
+ "2": 1.0,
728
+ "3": 1.0,
729
+ "4": 1.0,
730
+ "5": 0.999,
731
+ "6": 0.999,
732
+ "7": 0.994,
733
+ "8": 0.995,
734
+ "9": 0.98,
735
+ "10": 0.912
736
+ },
737
+ "pass@32": {
738
+ "2": 1.0,
739
+ "3": 1.0,
740
+ "4": 1.0,
741
+ "5": 0.999,
742
+ "6": 1.0,
743
+ "7": 0.999,
744
+ "8": 1.0,
745
+ "9": 0.995,
746
+ "10": 0.948
747
+ },
748
+ "pass@64": {
749
+ "2": 1.0,
750
+ "3": 1.0,
751
+ "4": 1.0,
752
+ "5": 1.0,
753
+ "6": 1.0,
754
+ "7": 1.0,
755
+ "8": 1.0,
756
+ "9": 0.999,
757
+ "10": 0.964
758
+ },
759
+ "pass@128": {
760
+ "2": 1.0,
761
+ "3": 1.0,
762
+ "4": 1.0,
763
+ "5": 1.0,
764
+ "6": 1.0,
765
+ "7": 1.0,
766
+ "8": 1.0,
767
+ "9": 0.999,
768
+ "10": 0.973
769
+ }
770
+ },
771
+ "total_pass_at_k": {
772
+ "pass@1": 0.8872222222222222,
773
+ "pass@2": 0.9175555555555556,
774
+ "pass@4": 0.9508888888888889,
775
+ "pass@8": 0.974,
776
+ "pass@16": 0.9865555555555555,
777
+ "pass@32": 0.9934444444444445,
778
+ "pass@64": 0.9958888888888889,
779
+ "pass@128": 0.9968888888888889
780
+ }
781
+ },
782
+ "ks": [
783
+ 1,
784
+ 2,
785
+ 4,
786
+ 8,
787
+ 16,
788
+ 32,
789
+ 64,
790
+ 128
791
+ ],
792
+ "prompt_counts": {
793
+ "per_template": {
794
+ "crazy_zootopia": {
795
+ "per_op": {
796
+ "2": 321,
797
+ "3": 327,
798
+ "4": 320,
799
+ "5": 315,
800
+ "6": 334,
801
+ "7": 338,
802
+ "8": 312,
803
+ "9": 355,
804
+ "10": 339
805
+ },
806
+ "total": 2961
807
+ },
808
+ "movie_festival_awards": {
809
+ "per_op": {
810
+ "2": 350,
811
+ "3": 343,
812
+ "4": 342,
813
+ "5": 340,
814
+ "6": 317,
815
+ "7": 316,
816
+ "8": 333,
817
+ "9": 311,
818
+ "10": 335
819
+ },
820
+ "total": 2987
821
+ },
822
+ "teachers_in_school": {
823
+ "per_op": {
824
+ "2": 329,
825
+ "3": 330,
826
+ "4": 338,
827
+ "5": 345,
828
+ "6": 349,
829
+ "7": 346,
830
+ "8": 355,
831
+ "9": 334,
832
+ "10": 326
833
+ },
834
+ "total": 3052
835
+ }
836
+ },
837
+ "total": {
838
+ "per_op": {
839
+ "2": 1000,
840
+ "3": 1000,
841
+ "4": 1000,
842
+ "5": 1000,
843
+ "6": 1000,
844
+ "7": 1000,
845
+ "8": 1000,
846
+ "9": 1000,
847
+ "10": 1000
848
+ },
849
+ "total": 9000
850
+ }
851
+ }
852
+ },
853
+ "checkpoint-38646_ood_generations.jsonl.graph_results.jsonl": {
854
+ "per_template": {
855
+ "crazy_zootopia": {
856
+ "per_op_pass_at_k": {
857
+ "11": {
858
+ "pass@1": 0.5920679886685553,
859
+ "pass@2": 0.6798866855524079,
860
+ "pass@4": 0.7648725212464589,
861
+ "pass@8": 0.8470254957507082,
862
+ "pass@16": 0.9206798866855525,
863
+ "pass@32": 0.9603399433427762,
864
+ "pass@64": 0.9801699716713881,
865
+ "pass@128": 0.9858356940509915
866
+ },
867
+ "12": {
868
+ "pass@1": 0.6384180790960452,
869
+ "pass@2": 0.6836158192090396,
870
+ "pass@4": 0.768361581920904,
871
+ "pass@8": 0.867231638418079,
872
+ "pass@16": 0.923728813559322,
873
+ "pass@32": 0.9491525423728814,
874
+ "pass@64": 0.9717514124293786,
875
+ "pass@128": 0.9774011299435028
876
+ },
877
+ "13": {
878
+ "pass@1": 0.5862068965517241,
879
+ "pass@2": 0.6426332288401254,
880
+ "pass@4": 0.7241379310344828,
881
+ "pass@8": 0.8119122257053292,
882
+ "pass@16": 0.8746081504702194,
883
+ "pass@32": 0.9090909090909091,
884
+ "pass@64": 0.9373040752351097,
885
+ "pass@128": 0.9592476489028213
886
+ },
887
+ "14": {
888
+ "pass@1": 0.5514018691588785,
889
+ "pass@2": 0.5856697819314641,
890
+ "pass@4": 0.6261682242990654,
891
+ "pass@8": 0.6853582554517134,
892
+ "pass@16": 0.7476635514018691,
893
+ "pass@32": 0.8473520249221184,
894
+ "pass@64": 0.9003115264797508,
895
+ "pass@128": 0.9283489096573209
896
+ },
897
+ "15": {
898
+ "pass@1": 0.5028901734104047,
899
+ "pass@2": 0.5404624277456648,
900
+ "pass@4": 0.5867052023121387,
901
+ "pass@8": 0.6763005780346821,
902
+ "pass@16": 0.7485549132947977,
903
+ "pass@32": 0.838150289017341,
904
+ "pass@64": 0.9104046242774566,
905
+ "pass@128": 0.9508670520231214
906
+ },
907
+ "16": {
908
+ "pass@1": 0.4967741935483871,
909
+ "pass@2": 0.535483870967742,
910
+ "pass@4": 0.5838709677419355,
911
+ "pass@8": 0.6225806451612903,
912
+ "pass@16": 0.6838709677419355,
913
+ "pass@32": 0.7129032258064516,
914
+ "pass@64": 0.7645161290322581,
915
+ "pass@128": 0.7935483870967742
916
+ },
917
+ "17": {
918
+ "pass@1": 0.5433526011560693,
919
+ "pass@2": 0.5780346820809249,
920
+ "pass@4": 0.615606936416185,
921
+ "pass@8": 0.6445086705202312,
922
+ "pass@16": 0.6936416184971098,
923
+ "pass@32": 0.7312138728323699,
924
+ "pass@64": 0.7832369942196532,
925
+ "pass@128": 0.8352601156069365
926
+ },
927
+ "18": {
928
+ "pass@1": 0.43714285714285717,
929
+ "pass@2": 0.46,
930
+ "pass@4": 0.4828571428571429,
931
+ "pass@8": 0.5142857142857142,
932
+ "pass@16": 0.5742857142857143,
933
+ "pass@32": 0.6371428571428571,
934
+ "pass@64": 0.6971428571428572,
935
+ "pass@128": 0.7714285714285715
936
+ },
937
+ "19": {
938
+ "pass@1": 0.34234234234234234,
939
+ "pass@2": 0.4084084084084084,
940
+ "pass@4": 0.44144144144144143,
941
+ "pass@8": 0.4804804804804805,
942
+ "pass@16": 0.5225225225225225,
943
+ "pass@32": 0.5585585585585585,
944
+ "pass@64": 0.5975975975975976,
945
+ "pass@128": 0.6276276276276276
946
+ },
947
+ "20": {
948
+ "pass@1": 0.27627627627627627,
949
+ "pass@2": 0.3303303303303303,
950
+ "pass@4": 0.35135135135135137,
951
+ "pass@8": 0.4084084084084084,
952
+ "pass@16": 0.44744744744744747,
953
+ "pass@32": 0.5105105105105106,
954
+ "pass@64": 0.5705705705705706,
955
+ "pass@128": 0.6246246246246246
956
+ }
957
+ },
958
+ "per_op_pass_at_columns": {
959
+ "pass@1": {
960
+ "11": 0.5920679886685553,
961
+ "12": 0.6384180790960452,
962
+ "13": 0.5862068965517241,
963
+ "14": 0.5514018691588785,
964
+ "15": 0.5028901734104047,
965
+ "16": 0.4967741935483871,
966
+ "17": 0.5433526011560693,
967
+ "18": 0.43714285714285717,
968
+ "19": 0.34234234234234234,
969
+ "20": 0.27627627627627627
970
+ },
971
+ "pass@2": {
972
+ "11": 0.6798866855524079,
973
+ "12": 0.6836158192090396,
974
+ "13": 0.6426332288401254,
975
+ "14": 0.5856697819314641,
976
+ "15": 0.5404624277456648,
977
+ "16": 0.535483870967742,
978
+ "17": 0.5780346820809249,
979
+ "18": 0.46,
980
+ "19": 0.4084084084084084,
981
+ "20": 0.3303303303303303
982
+ },
983
+ "pass@4": {
984
+ "11": 0.7648725212464589,
985
+ "12": 0.768361581920904,
986
+ "13": 0.7241379310344828,
987
+ "14": 0.6261682242990654,
988
+ "15": 0.5867052023121387,
989
+ "16": 0.5838709677419355,
990
+ "17": 0.615606936416185,
991
+ "18": 0.4828571428571429,
992
+ "19": 0.44144144144144143,
993
+ "20": 0.35135135135135137
994
+ },
995
+ "pass@8": {
996
+ "11": 0.8470254957507082,
997
+ "12": 0.867231638418079,
998
+ "13": 0.8119122257053292,
999
+ "14": 0.6853582554517134,
1000
+ "15": 0.6763005780346821,
1001
+ "16": 0.6225806451612903,
1002
+ "17": 0.6445086705202312,
1003
+ "18": 0.5142857142857142,
1004
+ "19": 0.4804804804804805,
1005
+ "20": 0.4084084084084084
1006
+ },
1007
+ "pass@16": {
1008
+ "11": 0.9206798866855525,
1009
+ "12": 0.923728813559322,
1010
+ "13": 0.8746081504702194,
1011
+ "14": 0.7476635514018691,
1012
+ "15": 0.7485549132947977,
1013
+ "16": 0.6838709677419355,
1014
+ "17": 0.6936416184971098,
1015
+ "18": 0.5742857142857143,
1016
+ "19": 0.5225225225225225,
1017
+ "20": 0.44744744744744747
1018
+ },
1019
+ "pass@32": {
1020
+ "11": 0.9603399433427762,
1021
+ "12": 0.9491525423728814,
1022
+ "13": 0.9090909090909091,
1023
+ "14": 0.8473520249221184,
1024
+ "15": 0.838150289017341,
1025
+ "16": 0.7129032258064516,
1026
+ "17": 0.7312138728323699,
1027
+ "18": 0.6371428571428571,
1028
+ "19": 0.5585585585585585,
1029
+ "20": 0.5105105105105106
1030
+ },
1031
+ "pass@64": {
1032
+ "11": 0.9801699716713881,
1033
+ "12": 0.9717514124293786,
1034
+ "13": 0.9373040752351097,
1035
+ "14": 0.9003115264797508,
1036
+ "15": 0.9104046242774566,
1037
+ "16": 0.7645161290322581,
1038
+ "17": 0.7832369942196532,
1039
+ "18": 0.6971428571428572,
1040
+ "19": 0.5975975975975976,
1041
+ "20": 0.5705705705705706
1042
+ },
1043
+ "pass@128": {
1044
+ "11": 0.9858356940509915,
1045
+ "12": 0.9774011299435028,
1046
+ "13": 0.9592476489028213,
1047
+ "14": 0.9283489096573209,
1048
+ "15": 0.9508670520231214,
1049
+ "16": 0.7935483870967742,
1050
+ "17": 0.8352601156069365,
1051
+ "18": 0.7714285714285715,
1052
+ "19": 0.6276276276276276,
1053
+ "20": 0.6246246246246246
1054
+ }
1055
+ },
1056
+ "total_pass_at_k": {
1057
+ "pass@1": 0.4974739970282318,
1058
+ "pass@2": 0.5453194650817236,
1059
+ "pass@4": 0.5955423476968796,
1060
+ "pass@8": 0.6570579494799406,
1061
+ "pass@16": 0.7150074294205052,
1062
+ "pass@32": 0.7667161961367014,
1063
+ "pass@64": 0.812481426448737,
1064
+ "pass@128": 0.8466567607726597
1065
+ }
1066
+ },
1067
+ "movie_festival_awards": {
1068
+ "per_op_pass_at_k": {
1069
+ "11": {
1070
+ "pass@1": 0.6,
1071
+ "pass@2": 0.6666666666666666,
1072
+ "pass@4": 0.7619047619047619,
1073
+ "pass@8": 0.8698412698412699,
1074
+ "pass@16": 0.926984126984127,
1075
+ "pass@32": 0.9619047619047619,
1076
+ "pass@64": 0.9682539682539683,
1077
+ "pass@128": 0.9873015873015873
1078
+ },
1079
+ "12": {
1080
+ "pass@1": 0.636085626911315,
1081
+ "pass@2": 0.709480122324159,
1082
+ "pass@4": 0.7981651376146789,
1083
+ "pass@8": 0.8776758409785933,
1084
+ "pass@16": 0.9296636085626911,
1085
+ "pass@32": 0.963302752293578,
1086
+ "pass@64": 0.9755351681957186,
1087
+ "pass@128": 0.9877675840978594
1088
+ },
1089
+ "13": {
1090
+ "pass@1": 0.5802469135802469,
1091
+ "pass@2": 0.6820987654320988,
1092
+ "pass@4": 0.7561728395061729,
1093
+ "pass@8": 0.8240740740740741,
1094
+ "pass@16": 0.8827160493827161,
1095
+ "pass@32": 0.9320987654320988,
1096
+ "pass@64": 0.9629629629629629,
1097
+ "pass@128": 0.9722222222222222
1098
+ },
1099
+ "14": {
1100
+ "pass@1": 0.5608308605341247,
1101
+ "pass@2": 0.5964391691394659,
1102
+ "pass@4": 0.6617210682492581,
1103
+ "pass@8": 0.7388724035608308,
1104
+ "pass@16": 0.8011869436201781,
1105
+ "pass@32": 0.8545994065281899,
1106
+ "pass@64": 0.9109792284866469,
1107
+ "pass@128": 0.9376854599406528
1108
+ },
1109
+ "15": {
1110
+ "pass@1": 0.5,
1111
+ "pass@2": 0.5462962962962963,
1112
+ "pass@4": 0.5895061728395061,
1113
+ "pass@8": 0.6574074074074074,
1114
+ "pass@16": 0.7253086419753086,
1115
+ "pass@32": 0.7870370370370371,
1116
+ "pass@64": 0.8765432098765432,
1117
+ "pass@128": 0.9259259259259259
1118
+ },
1119
+ "16": {
1120
+ "pass@1": 0.5368731563421829,
1121
+ "pass@2": 0.584070796460177,
1122
+ "pass@4": 0.6135693215339233,
1123
+ "pass@8": 0.6666666666666666,
1124
+ "pass@16": 0.7168141592920354,
1125
+ "pass@32": 0.7699115044247787,
1126
+ "pass@64": 0.8082595870206489,
1127
+ "pass@128": 0.8348082595870207
1128
+ },
1129
+ "17": {
1130
+ "pass@1": 0.4939759036144578,
1131
+ "pass@2": 0.5120481927710844,
1132
+ "pass@4": 0.536144578313253,
1133
+ "pass@8": 0.5933734939759037,
1134
+ "pass@16": 0.6566265060240963,
1135
+ "pass@32": 0.7198795180722891,
1136
+ "pass@64": 0.7740963855421686,
1137
+ "pass@128": 0.8192771084337349
1138
+ },
1139
+ "18": {
1140
+ "pass@1": 0.44516129032258067,
1141
+ "pass@2": 0.5064516129032258,
1142
+ "pass@4": 0.532258064516129,
1143
+ "pass@8": 0.5645161290322581,
1144
+ "pass@16": 0.6258064516129033,
1145
+ "pass@32": 0.6774193548387096,
1146
+ "pass@64": 0.7483870967741936,
1147
+ "pass@128": 0.7935483870967742
1148
+ },
1149
+ "19": {
1150
+ "pass@1": 0.3776435045317221,
1151
+ "pass@2": 0.4501510574018127,
1152
+ "pass@4": 0.4652567975830816,
1153
+ "pass@8": 0.5105740181268882,
1154
+ "pass@16": 0.5317220543806647,
1155
+ "pass@32": 0.5800604229607251,
1156
+ "pass@64": 0.622356495468278,
1157
+ "pass@128": 0.6737160120845922
1158
+ },
1159
+ "20": {
1160
+ "pass@1": 0.2912912912912913,
1161
+ "pass@2": 0.34534534534534533,
1162
+ "pass@4": 0.37537537537537535,
1163
+ "pass@8": 0.4084084084084084,
1164
+ "pass@16": 0.4624624624624625,
1165
+ "pass@32": 0.5165165165165165,
1166
+ "pass@64": 0.5645645645645646,
1167
+ "pass@128": 0.6096096096096096
1168
+ }
1169
+ },
1170
+ "per_op_pass_at_columns": {
1171
+ "pass@1": {
1172
+ "11": 0.6,
1173
+ "12": 0.636085626911315,
1174
+ "13": 0.5802469135802469,
1175
+ "14": 0.5608308605341247,
1176
+ "15": 0.5,
1177
+ "16": 0.5368731563421829,
1178
+ "17": 0.4939759036144578,
1179
+ "18": 0.44516129032258067,
1180
+ "19": 0.3776435045317221,
1181
+ "20": 0.2912912912912913
1182
+ },
1183
+ "pass@2": {
1184
+ "11": 0.6666666666666666,
1185
+ "12": 0.709480122324159,
1186
+ "13": 0.6820987654320988,
1187
+ "14": 0.5964391691394659,
1188
+ "15": 0.5462962962962963,
1189
+ "16": 0.584070796460177,
1190
+ "17": 0.5120481927710844,
1191
+ "18": 0.5064516129032258,
1192
+ "19": 0.4501510574018127,
1193
+ "20": 0.34534534534534533
1194
+ },
1195
+ "pass@4": {
1196
+ "11": 0.7619047619047619,
1197
+ "12": 0.7981651376146789,
1198
+ "13": 0.7561728395061729,
1199
+ "14": 0.6617210682492581,
1200
+ "15": 0.5895061728395061,
1201
+ "16": 0.6135693215339233,
1202
+ "17": 0.536144578313253,
1203
+ "18": 0.532258064516129,
1204
+ "19": 0.4652567975830816,
1205
+ "20": 0.37537537537537535
1206
+ },
1207
+ "pass@8": {
1208
+ "11": 0.8698412698412699,
1209
+ "12": 0.8776758409785933,
1210
+ "13": 0.8240740740740741,
1211
+ "14": 0.7388724035608308,
1212
+ "15": 0.6574074074074074,
1213
+ "16": 0.6666666666666666,
1214
+ "17": 0.5933734939759037,
1215
+ "18": 0.5645161290322581,
1216
+ "19": 0.5105740181268882,
1217
+ "20": 0.4084084084084084
1218
+ },
1219
+ "pass@16": {
1220
+ "11": 0.926984126984127,
1221
+ "12": 0.9296636085626911,
1222
+ "13": 0.8827160493827161,
1223
+ "14": 0.8011869436201781,
1224
+ "15": 0.7253086419753086,
1225
+ "16": 0.7168141592920354,
1226
+ "17": 0.6566265060240963,
1227
+ "18": 0.6258064516129033,
1228
+ "19": 0.5317220543806647,
1229
+ "20": 0.4624624624624625
1230
+ },
1231
+ "pass@32": {
1232
+ "11": 0.9619047619047619,
1233
+ "12": 0.963302752293578,
1234
+ "13": 0.9320987654320988,
1235
+ "14": 0.8545994065281899,
1236
+ "15": 0.7870370370370371,
1237
+ "16": 0.7699115044247787,
1238
+ "17": 0.7198795180722891,
1239
+ "18": 0.6774193548387096,
1240
+ "19": 0.5800604229607251,
1241
+ "20": 0.5165165165165165
1242
+ },
1243
+ "pass@64": {
1244
+ "11": 0.9682539682539683,
1245
+ "12": 0.9755351681957186,
1246
+ "13": 0.9629629629629629,
1247
+ "14": 0.9109792284866469,
1248
+ "15": 0.8765432098765432,
1249
+ "16": 0.8082595870206489,
1250
+ "17": 0.7740963855421686,
1251
+ "18": 0.7483870967741936,
1252
+ "19": 0.622356495468278,
1253
+ "20": 0.5645645645645646
1254
+ },
1255
+ "pass@128": {
1256
+ "11": 0.9873015873015873,
1257
+ "12": 0.9877675840978594,
1258
+ "13": 0.9722222222222222,
1259
+ "14": 0.9376854599406528,
1260
+ "15": 0.9259259259259259,
1261
+ "16": 0.8348082595870207,
1262
+ "17": 0.8192771084337349,
1263
+ "18": 0.7935483870967742,
1264
+ "19": 0.6737160120845922,
1265
+ "20": 0.6096096096096096
1266
+ }
1267
+ },
1268
+ "total_pass_at_k": {
1269
+ "pass@1": 0.5018337408312958,
1270
+ "pass@2": 0.5592909535452323,
1271
+ "pass@4": 0.6081907090464548,
1272
+ "pass@8": 0.6702322738386308,
1273
+ "pass@16": 0.7249388753056235,
1274
+ "pass@32": 0.7753667481662592,
1275
+ "pass@64": 0.8202933985330073,
1276
+ "pass@128": 0.8533007334963325
1277
+ }
1278
+ },
1279
+ "teachers_in_school": {
1280
+ "per_op_pass_at_k": {
1281
+ "11": {
1282
+ "pass@1": 0.6626506024096386,
1283
+ "pass@2": 0.6987951807228916,
1284
+ "pass@4": 0.7921686746987951,
1285
+ "pass@8": 0.8524096385542169,
1286
+ "pass@16": 0.927710843373494,
1287
+ "pass@32": 0.963855421686747,
1288
+ "pass@64": 0.9728915662650602,
1289
+ "pass@128": 0.9789156626506024
1290
+ },
1291
+ "12": {
1292
+ "pass@1": 0.5862068965517241,
1293
+ "pass@2": 0.6551724137931034,
1294
+ "pass@4": 0.7492163009404389,
1295
+ "pass@8": 0.8401253918495298,
1296
+ "pass@16": 0.9090909090909091,
1297
+ "pass@32": 0.9561128526645768,
1298
+ "pass@64": 0.9780564263322884,
1299
+ "pass@128": 0.9811912225705329
1300
+ },
1301
+ "13": {
1302
+ "pass@1": 0.6106442577030813,
1303
+ "pass@2": 0.6694677871148459,
1304
+ "pass@4": 0.7675070028011205,
1305
+ "pass@8": 0.8711484593837535,
1306
+ "pass@16": 0.927170868347339,
1307
+ "pass@32": 0.9523809523809523,
1308
+ "pass@64": 0.969187675070028,
1309
+ "pass@128": 0.9915966386554622
1310
+ },
1311
+ "14": {
1312
+ "pass@1": 0.5760233918128655,
1313
+ "pass@2": 0.631578947368421,
1314
+ "pass@4": 0.6900584795321637,
1315
+ "pass@8": 0.7543859649122807,
1316
+ "pass@16": 0.8099415204678363,
1317
+ "pass@32": 0.8859649122807017,
1318
+ "pass@64": 0.9502923976608187,
1319
+ "pass@128": 0.9736842105263158
1320
+ },
1321
+ "15": {
1322
+ "pass@1": 0.5484848484848485,
1323
+ "pass@2": 0.5848484848484848,
1324
+ "pass@4": 0.6090909090909091,
1325
+ "pass@8": 0.6666666666666666,
1326
+ "pass@16": 0.7333333333333333,
1327
+ "pass@32": 0.8272727272727273,
1328
+ "pass@64": 0.896969696969697,
1329
+ "pass@128": 0.9454545454545454
1330
+ },
1331
+ "16": {
1332
+ "pass@1": 0.5384615384615384,
1333
+ "pass@2": 0.5641025641025641,
1334
+ "pass@4": 0.5982905982905983,
1335
+ "pass@8": 0.6524216524216524,
1336
+ "pass@16": 0.6866096866096866,
1337
+ "pass@32": 0.7606837606837606,
1338
+ "pass@64": 0.8034188034188035,
1339
+ "pass@128": 0.8376068376068376
1340
+ },
1341
+ "17": {
1342
+ "pass@1": 0.4254658385093168,
1343
+ "pass@2": 0.4472049689440994,
1344
+ "pass@4": 0.5093167701863354,
1345
+ "pass@8": 0.5683229813664596,
1346
+ "pass@16": 0.6242236024844721,
1347
+ "pass@32": 0.6956521739130435,
1348
+ "pass@64": 0.7795031055900621,
1349
+ "pass@128": 0.8136645962732919
1350
+ },
1351
+ "18": {
1352
+ "pass@1": 0.4176470588235294,
1353
+ "pass@2": 0.45,
1354
+ "pass@4": 0.47941176470588237,
1355
+ "pass@8": 0.5205882352941177,
1356
+ "pass@16": 0.5647058823529412,
1357
+ "pass@32": 0.5794117647058824,
1358
+ "pass@64": 0.6823529411764706,
1359
+ "pass@128": 0.7529411764705882
1360
+ },
1361
+ "19": {
1362
+ "pass@1": 0.375,
1363
+ "pass@2": 0.40773809523809523,
1364
+ "pass@4": 0.44047619047619047,
1365
+ "pass@8": 0.4851190476190476,
1366
+ "pass@16": 0.5208333333333334,
1367
+ "pass@32": 0.5744047619047619,
1368
+ "pass@64": 0.6190476190476191,
1369
+ "pass@128": 0.6755952380952381
1370
+ },
1371
+ "20": {
1372
+ "pass@1": 0.2844311377245509,
1373
+ "pass@2": 0.33532934131736525,
1374
+ "pass@4": 0.38323353293413176,
1375
+ "pass@8": 0.4281437125748503,
1376
+ "pass@16": 0.47005988023952094,
1377
+ "pass@32": 0.5209580838323353,
1378
+ "pass@64": 0.5658682634730539,
1379
+ "pass@128": 0.6287425149700598
1380
+ }
1381
+ },
1382
+ "per_op_pass_at_columns": {
1383
+ "pass@1": {
1384
+ "11": 0.6626506024096386,
1385
+ "12": 0.5862068965517241,
1386
+ "13": 0.6106442577030813,
1387
+ "14": 0.5760233918128655,
1388
+ "15": 0.5484848484848485,
1389
+ "16": 0.5384615384615384,
1390
+ "17": 0.4254658385093168,
1391
+ "18": 0.4176470588235294,
1392
+ "19": 0.375,
1393
+ "20": 0.2844311377245509
1394
+ },
1395
+ "pass@2": {
1396
+ "11": 0.6987951807228916,
1397
+ "12": 0.6551724137931034,
1398
+ "13": 0.6694677871148459,
1399
+ "14": 0.631578947368421,
1400
+ "15": 0.5848484848484848,
1401
+ "16": 0.5641025641025641,
1402
+ "17": 0.4472049689440994,
1403
+ "18": 0.45,
1404
+ "19": 0.40773809523809523,
1405
+ "20": 0.33532934131736525
1406
+ },
1407
+ "pass@4": {
1408
+ "11": 0.7921686746987951,
1409
+ "12": 0.7492163009404389,
1410
+ "13": 0.7675070028011205,
1411
+ "14": 0.6900584795321637,
1412
+ "15": 0.6090909090909091,
1413
+ "16": 0.5982905982905983,
1414
+ "17": 0.5093167701863354,
1415
+ "18": 0.47941176470588237,
1416
+ "19": 0.44047619047619047,
1417
+ "20": 0.38323353293413176
1418
+ },
1419
+ "pass@8": {
1420
+ "11": 0.8524096385542169,
1421
+ "12": 0.8401253918495298,
1422
+ "13": 0.8711484593837535,
1423
+ "14": 0.7543859649122807,
1424
+ "15": 0.6666666666666666,
1425
+ "16": 0.6524216524216524,
1426
+ "17": 0.5683229813664596,
1427
+ "18": 0.5205882352941177,
1428
+ "19": 0.4851190476190476,
1429
+ "20": 0.4281437125748503
1430
+ },
1431
+ "pass@16": {
1432
+ "11": 0.927710843373494,
1433
+ "12": 0.9090909090909091,
1434
+ "13": 0.927170868347339,
1435
+ "14": 0.8099415204678363,
1436
+ "15": 0.7333333333333333,
1437
+ "16": 0.6866096866096866,
1438
+ "17": 0.6242236024844721,
1439
+ "18": 0.5647058823529412,
1440
+ "19": 0.5208333333333334,
1441
+ "20": 0.47005988023952094
1442
+ },
1443
+ "pass@32": {
1444
+ "11": 0.963855421686747,
1445
+ "12": 0.9561128526645768,
1446
+ "13": 0.9523809523809523,
1447
+ "14": 0.8859649122807017,
1448
+ "15": 0.8272727272727273,
1449
+ "16": 0.7606837606837606,
1450
+ "17": 0.6956521739130435,
1451
+ "18": 0.5794117647058824,
1452
+ "19": 0.5744047619047619,
1453
+ "20": 0.5209580838323353
1454
+ },
1455
+ "pass@64": {
1456
+ "11": 0.9728915662650602,
1457
+ "12": 0.9780564263322884,
1458
+ "13": 0.969187675070028,
1459
+ "14": 0.9502923976608187,
1460
+ "15": 0.896969696969697,
1461
+ "16": 0.8034188034188035,
1462
+ "17": 0.7795031055900621,
1463
+ "18": 0.6823529411764706,
1464
+ "19": 0.6190476190476191,
1465
+ "20": 0.5658682634730539
1466
+ },
1467
+ "pass@128": {
1468
+ "11": 0.9789156626506024,
1469
+ "12": 0.9811912225705329,
1470
+ "13": 0.9915966386554622,
1471
+ "14": 0.9736842105263158,
1472
+ "15": 0.9454545454545454,
1473
+ "16": 0.8376068376068376,
1474
+ "17": 0.8136645962732919,
1475
+ "18": 0.7529411764705882,
1476
+ "19": 0.6755952380952381,
1477
+ "20": 0.6287425149700598
1478
+ }
1479
+ },
1480
+ "total_pass_at_k": {
1481
+ "pass@1": 0.5031222123104371,
1482
+ "pass@2": 0.5450490633363069,
1483
+ "pass@4": 0.6024382991376747,
1484
+ "pass@8": 0.6645851917930419,
1485
+ "pass@16": 0.7178114778471603,
1486
+ "pass@32": 0.7719298245614035,
1487
+ "pass@64": 0.8218852215283973,
1488
+ "pass@128": 0.8581623550401427
1489
+ }
1490
+ }
1491
+ },
1492
+ "total": {
1493
+ "per_op_pass_at_k": {
1494
+ "11": {
1495
+ "pass@1": 0.618,
1496
+ "pass@2": 0.682,
1497
+ "pass@4": 0.773,
1498
+ "pass@8": 0.856,
1499
+ "pass@16": 0.925,
1500
+ "pass@32": 0.962,
1501
+ "pass@64": 0.974,
1502
+ "pass@128": 0.984
1503
+ },
1504
+ "12": {
1505
+ "pass@1": 0.621,
1506
+ "pass@2": 0.683,
1507
+ "pass@4": 0.772,
1508
+ "pass@8": 0.862,
1509
+ "pass@16": 0.921,
1510
+ "pass@32": 0.956,
1511
+ "pass@64": 0.975,
1512
+ "pass@128": 0.982
1513
+ },
1514
+ "13": {
1515
+ "pass@1": 0.593,
1516
+ "pass@2": 0.665,
1517
+ "pass@4": 0.75,
1518
+ "pass@8": 0.837,
1519
+ "pass@16": 0.896,
1520
+ "pass@32": 0.932,
1521
+ "pass@64": 0.957,
1522
+ "pass@128": 0.975
1523
+ },
1524
+ "14": {
1525
+ "pass@1": 0.563,
1526
+ "pass@2": 0.605,
1527
+ "pass@4": 0.66,
1528
+ "pass@8": 0.727,
1529
+ "pass@16": 0.787,
1530
+ "pass@32": 0.863,
1531
+ "pass@64": 0.921,
1532
+ "pass@128": 0.947
1533
+ },
1534
+ "15": {
1535
+ "pass@1": 0.517,
1536
+ "pass@2": 0.557,
1537
+ "pass@4": 0.595,
1538
+ "pass@8": 0.667,
1539
+ "pass@16": 0.736,
1540
+ "pass@32": 0.818,
1541
+ "pass@64": 0.895,
1542
+ "pass@128": 0.941
1543
+ },
1544
+ "16": {
1545
+ "pass@1": 0.525,
1546
+ "pass@2": 0.562,
1547
+ "pass@4": 0.599,
1548
+ "pass@8": 0.648,
1549
+ "pass@16": 0.696,
1550
+ "pass@32": 0.749,
1551
+ "pass@64": 0.793,
1552
+ "pass@128": 0.823
1553
+ },
1554
+ "17": {
1555
+ "pass@1": 0.489,
1556
+ "pass@2": 0.514,
1557
+ "pass@4": 0.555,
1558
+ "pass@8": 0.603,
1559
+ "pass@16": 0.659,
1560
+ "pass@32": 0.716,
1561
+ "pass@64": 0.779,
1562
+ "pass@128": 0.823
1563
+ },
1564
+ "18": {
1565
+ "pass@1": 0.433,
1566
+ "pass@2": 0.471,
1567
+ "pass@4": 0.497,
1568
+ "pass@8": 0.532,
1569
+ "pass@16": 0.587,
1570
+ "pass@32": 0.63,
1571
+ "pass@64": 0.708,
1572
+ "pass@128": 0.772
1573
+ },
1574
+ "19": {
1575
+ "pass@1": 0.365,
1576
+ "pass@2": 0.422,
1577
+ "pass@4": 0.449,
1578
+ "pass@8": 0.492,
1579
+ "pass@16": 0.525,
1580
+ "pass@32": 0.571,
1581
+ "pass@64": 0.613,
1582
+ "pass@128": 0.659
1583
+ },
1584
+ "20": {
1585
+ "pass@1": 0.284,
1586
+ "pass@2": 0.337,
1587
+ "pass@4": 0.37,
1588
+ "pass@8": 0.415,
1589
+ "pass@16": 0.46,
1590
+ "pass@32": 0.516,
1591
+ "pass@64": 0.567,
1592
+ "pass@128": 0.621
1593
+ }
1594
+ },
1595
+ "per_op_pass_at_columns": {
1596
+ "pass@1": {
1597
+ "11": 0.618,
1598
+ "12": 0.621,
1599
+ "13": 0.593,
1600
+ "14": 0.563,
1601
+ "15": 0.517,
1602
+ "16": 0.525,
1603
+ "17": 0.489,
1604
+ "18": 0.433,
1605
+ "19": 0.365,
1606
+ "20": 0.284
1607
+ },
1608
+ "pass@2": {
1609
+ "11": 0.682,
1610
+ "12": 0.683,
1611
+ "13": 0.665,
1612
+ "14": 0.605,
1613
+ "15": 0.557,
1614
+ "16": 0.562,
1615
+ "17": 0.514,
1616
+ "18": 0.471,
1617
+ "19": 0.422,
1618
+ "20": 0.337
1619
+ },
1620
+ "pass@4": {
1621
+ "11": 0.773,
1622
+ "12": 0.772,
1623
+ "13": 0.75,
1624
+ "14": 0.66,
1625
+ "15": 0.595,
1626
+ "16": 0.599,
1627
+ "17": 0.555,
1628
+ "18": 0.497,
1629
+ "19": 0.449,
1630
+ "20": 0.37
1631
+ },
1632
+ "pass@8": {
1633
+ "11": 0.856,
1634
+ "12": 0.862,
1635
+ "13": 0.837,
1636
+ "14": 0.727,
1637
+ "15": 0.667,
1638
+ "16": 0.648,
1639
+ "17": 0.603,
1640
+ "18": 0.532,
1641
+ "19": 0.492,
1642
+ "20": 0.415
1643
+ },
1644
+ "pass@16": {
1645
+ "11": 0.925,
1646
+ "12": 0.921,
1647
+ "13": 0.896,
1648
+ "14": 0.787,
1649
+ "15": 0.736,
1650
+ "16": 0.696,
1651
+ "17": 0.659,
1652
+ "18": 0.587,
1653
+ "19": 0.525,
1654
+ "20": 0.46
1655
+ },
1656
+ "pass@32": {
1657
+ "11": 0.962,
1658
+ "12": 0.956,
1659
+ "13": 0.932,
1660
+ "14": 0.863,
1661
+ "15": 0.818,
1662
+ "16": 0.749,
1663
+ "17": 0.716,
1664
+ "18": 0.63,
1665
+ "19": 0.571,
1666
+ "20": 0.516
1667
+ },
1668
+ "pass@64": {
1669
+ "11": 0.974,
1670
+ "12": 0.975,
1671
+ "13": 0.957,
1672
+ "14": 0.921,
1673
+ "15": 0.895,
1674
+ "16": 0.793,
1675
+ "17": 0.779,
1676
+ "18": 0.708,
1677
+ "19": 0.613,
1678
+ "20": 0.567
1679
+ },
1680
+ "pass@128": {
1681
+ "11": 0.984,
1682
+ "12": 0.982,
1683
+ "13": 0.975,
1684
+ "14": 0.947,
1685
+ "15": 0.941,
1686
+ "16": 0.823,
1687
+ "17": 0.823,
1688
+ "18": 0.772,
1689
+ "19": 0.659,
1690
+ "20": 0.621
1691
+ }
1692
+ },
1693
+ "total_pass_at_k": {
1694
+ "pass@1": 0.5008,
1695
+ "pass@2": 0.5498,
1696
+ "pass@4": 0.602,
1697
+ "pass@8": 0.6639,
1698
+ "pass@16": 0.7192,
1699
+ "pass@32": 0.7713,
1700
+ "pass@64": 0.8182,
1701
+ "pass@128": 0.8527
1702
+ }
1703
+ },
1704
+ "ks": [
1705
+ 1,
1706
+ 2,
1707
+ 4,
1708
+ 8,
1709
+ 16,
1710
+ 32,
1711
+ 64,
1712
+ 128
1713
+ ],
1714
+ "prompt_counts": {
1715
+ "per_template": {
1716
+ "crazy_zootopia": {
1717
+ "per_op": {
1718
+ "11": 353,
1719
+ "12": 354,
1720
+ "13": 319,
1721
+ "14": 321,
1722
+ "15": 346,
1723
+ "16": 310,
1724
+ "17": 346,
1725
+ "18": 350,
1726
+ "19": 333,
1727
+ "20": 333
1728
+ },
1729
+ "total": 3365
1730
+ },
1731
+ "movie_festival_awards": {
1732
+ "per_op": {
1733
+ "11": 315,
1734
+ "12": 327,
1735
+ "13": 324,
1736
+ "14": 337,
1737
+ "15": 324,
1738
+ "16": 339,
1739
+ "17": 332,
1740
+ "18": 310,
1741
+ "19": 331,
1742
+ "20": 333
1743
+ },
1744
+ "total": 3272
1745
+ },
1746
+ "teachers_in_school": {
1747
+ "per_op": {
1748
+ "11": 332,
1749
+ "12": 319,
1750
+ "13": 357,
1751
+ "14": 342,
1752
+ "15": 330,
1753
+ "16": 351,
1754
+ "17": 322,
1755
+ "18": 340,
1756
+ "19": 336,
1757
+ "20": 334
1758
+ },
1759
+ "total": 3363
1760
+ }
1761
+ },
1762
+ "total": {
1763
+ "per_op": {
1764
+ "11": 1000,
1765
+ "12": 1000,
1766
+ "13": 1000,
1767
+ "14": 1000,
1768
+ "15": 1000,
1769
+ "16": 1000,
1770
+ "17": 1000,
1771
+ "18": 1000,
1772
+ "19": 1000,
1773
+ "20": 1000
1774
+ },
1775
+ "total": 10000
1776
+ }
1777
+ }
1778
+ }
1779
+ }
1780
+ }
Qwen3-100M-midtrain-diff_ar-block4/composition/summary.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint,id_acc,ood_acc,total_acc,id_avg_loss,ood_avg_loss,total_avg_loss,id_avg_resp_len,ood_avg_resp_len,count_id,count_ood,count_total
2
+ checkpoint-38646,0.9930946180555555,0.870721875,0.9286879111842106,0.0,0.0,0.0,200.28550694444445,379.828709375,1152000,1280000,2432000
Qwen3-100M-midtrain-diff_ar-block4/composition/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "checkpoint-38646",
4
+ "id_acc": 0.9930946180555555,
5
+ "ood_acc": 0.870721875,
6
+ "total_acc": 0.9286879111842106,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 200.28550694444445,
11
+ "ood_avg_resp_len": 379.828709375,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 747714,
19
+ "answer_accuracy": 0.9234137883338602,
20
+ "avg_response_len": 281.5405074296554,
21
+ "resp_tokens_sum": 227971232,
22
+ "pass_at_k": {
23
+ "pass@1": 0.9234137883338602,
24
+ "pass@2": 0.9435549933283615,
25
+ "pass@4": 0.9572698152890534,
26
+ "pass@8": 0.9667895172243828,
27
+ "pass@16": 0.9736588935734707,
28
+ "pass@32": 0.9790904995462497,
29
+ "pass@64": 0.9834172709208217,
30
+ "pass@128": 0.9867214669617452
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.954484697640118,
35
+ "pass@2": 0.9629707860079438,
36
+ "pass@4": 0.9709464638269774,
37
+ "pass@8": 0.9782191819839355,
38
+ "pass@16": 0.984593484638989,
39
+ "pass@32": 0.9892985145351701,
40
+ "pass@64": 0.9930035863666121,
41
+ "pass@128": 0.9970501474926253
42
+ },
43
+ "2": {
44
+ "pass@1": 1.0,
45
+ "pass@2": 1.0,
46
+ "pass@4": 1.0,
47
+ "pass@8": 1.0,
48
+ "pass@16": 1.0,
49
+ "pass@32": 1.0,
50
+ "pass@64": 1.0,
51
+ "pass@128": 1.0
52
+ },
53
+ "3": {
54
+ "pass@1": 1.0,
55
+ "pass@2": 1.0,
56
+ "pass@4": 1.0,
57
+ "pass@8": 1.0,
58
+ "pass@16": 1.0,
59
+ "pass@32": 1.0,
60
+ "pass@64": 1.0,
61
+ "pass@128": 1.0
62
+ },
63
+ "4": {
64
+ "pass@1": 1.0,
65
+ "pass@2": 1.0,
66
+ "pass@4": 1.0,
67
+ "pass@8": 1.0,
68
+ "pass@16": 1.0,
69
+ "pass@32": 1.0,
70
+ "pass@64": 1.0,
71
+ "pass@128": 1.0
72
+ },
73
+ "5": {
74
+ "pass@1": 0.9980902777777778,
75
+ "pass@2": 0.9997808867641542,
76
+ "pass@4": 0.9999950205629058,
77
+ "pass@8": 0.9999999974305525,
78
+ "pass@16": 1.0,
79
+ "pass@32": 1.0,
80
+ "pass@64": 1.0,
81
+ "pass@128": 1.0
82
+ },
83
+ "6": {
84
+ "pass@1": 0.9998830464071856,
85
+ "pass@2": 0.9999977898533642,
86
+ "pass@4": 0.9999999997193464,
87
+ "pass@8": 1.0,
88
+ "pass@16": 1.0,
89
+ "pass@32": 1.0,
90
+ "pass@64": 1.0,
91
+ "pass@128": 1.0
92
+ },
93
+ "7": {
94
+ "pass@1": 0.9991910133136095,
95
+ "pass@2": 0.9999253803056423,
96
+ "pass@4": 0.9999992966855474,
97
+ "pass@8": 0.9999999999707041,
98
+ "pass@16": 1.0,
99
+ "pass@32": 1.0,
100
+ "pass@64": 1.0,
101
+ "pass@128": 1.0
102
+ },
103
+ "8": {
104
+ "pass@1": 0.9977964743589743,
105
+ "pass@2": 0.9990386192711489,
106
+ "pass@4": 0.9997245203123646,
107
+ "pass@8": 0.9999788364839716,
108
+ "pass@16": 0.9999999148409177,
109
+ "pass@32": 0.9999999999998113,
110
+ "pass@64": 1.0,
111
+ "pass@128": 1.0
112
+ },
113
+ "9": {
114
+ "pass@1": 0.9962367957746479,
115
+ "pass@2": 0.9972319646223802,
116
+ "pass@4": 0.9975970072402921,
117
+ "pass@8": 0.9979708642982112,
118
+ "pass@16": 0.9985716335094632,
119
+ "pass@32": 0.9993491975474896,
120
+ "pass@64": 0.9999188200066541,
121
+ "pass@128": 1.0
122
+ },
123
+ "11": {
124
+ "pass@1": 0.9682852337110481,
125
+ "pass@2": 0.977452822823493,
126
+ "pass@4": 0.9842284054082472,
127
+ "pass@8": 0.9891870968251745,
128
+ "pass@16": 0.9931120473781875,
129
+ "pass@32": 0.9965309204049758,
130
+ "pass@64": 0.9991380576749798,
131
+ "pass@128": 1.0
132
+ },
133
+ "12": {
134
+ "pass@1": 0.9647775423728814,
135
+ "pass@2": 0.9793001245607014,
136
+ "pass@4": 0.9885038096403199,
137
+ "pass@8": 0.9930489687895803,
138
+ "pass@16": 0.9957842683111874,
139
+ "pass@32": 0.9978504659297166,
140
+ "pass@64": 0.9992600866784821,
141
+ "pass@128": 1.0
142
+ },
143
+ "13": {
144
+ "pass@1": 0.9408797021943573,
145
+ "pass@2": 0.9649356379433759,
146
+ "pass@4": 0.9808571087704949,
147
+ "pass@8": 0.9881229406714634,
148
+ "pass@16": 0.99055864455524,
149
+ "pass@32": 0.9913680560096522,
150
+ "pass@64": 0.9921630087220765,
151
+ "pass@128": 0.9937304075235109
152
+ },
153
+ "14": {
154
+ "pass@1": 0.9360640576323987,
155
+ "pass@2": 0.9562122856722352,
156
+ "pass@4": 0.9707606814919159,
157
+ "pass@8": 0.9804801905602375,
158
+ "pass@16": 0.9866715910082771,
159
+ "pass@32": 0.9909012287981317,
160
+ "pass@64": 0.9945214531172304,
161
+ "pass@128": 0.9968847352024922
162
+ },
163
+ "15": {
164
+ "pass@1": 0.9660404624277457,
165
+ "pass@2": 0.9819844198033775,
166
+ "pass@4": 0.989337811097312,
167
+ "pass@8": 0.9927511350152156,
168
+ "pass@16": 0.9945051007958996,
169
+ "pass@32": 0.9954700452049894,
170
+ "pass@64": 0.996392965878996,
171
+ "pass@128": 0.9971098265895953
172
+ },
173
+ "16": {
174
+ "pass@1": 0.8782762096774194,
175
+ "pass@2": 0.9086745142240289,
176
+ "pass@4": 0.9307146733674418,
177
+ "pass@8": 0.9456327971297461,
178
+ "pass@16": 0.9552193362938507,
179
+ "pass@32": 0.9633343766463572,
180
+ "pass@64": 0.9715414297733572,
181
+ "pass@128": 0.9806451612903225
182
+ },
183
+ "17": {
184
+ "pass@1": 0.8934248554913294,
185
+ "pass@2": 0.9237297175822676,
186
+ "pass@4": 0.9422482222236664,
187
+ "pass@8": 0.9540871391786083,
188
+ "pass@16": 0.9620315216397886,
189
+ "pass@32": 0.9683743703109818,
190
+ "pass@64": 0.9725996832538545,
191
+ "pass@128": 0.9739884393063584
192
+ },
193
+ "18": {
194
+ "pass@1": 0.8005357142857142,
195
+ "pass@2": 0.8531492547806522,
196
+ "pass@4": 0.8860468795864797,
197
+ "pass@8": 0.9091291155842222,
198
+ "pass@16": 0.9275554499538204,
199
+ "pass@32": 0.9442031158786668,
200
+ "pass@64": 0.9575396478067062,
201
+ "pass@128": 0.9657142857142857
202
+ },
203
+ "19": {
204
+ "pass@1": 0.6647428678678678,
205
+ "pass@2": 0.7474041462722564,
206
+ "pass@4": 0.8052284390689899,
207
+ "pass@8": 0.8453281707689558,
208
+ "pass@16": 0.8732022792173314,
209
+ "pass@32": 0.8947298964394246,
210
+ "pass@64": 0.9117678285429259,
211
+ "pass@128": 0.924924924924925
212
+ },
213
+ "20": {
214
+ "pass@1": 0.5938203828828829,
215
+ "pass@2": 0.6811821664183864,
216
+ "pass@4": 0.7462476041846112,
217
+ "pass@8": 0.7985336624704658,
218
+ "pass@16": 0.8402692553045812,
219
+ "pass@32": 0.8729885399962004,
220
+ "pass@64": 0.8982468595231101,
221
+ "pass@128": 0.918918918918919
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 765697,
228
+ "answer_accuracy": 0.9325031664068589,
229
+ "avg_response_len": 291.1401585639127,
230
+ "resp_tokens_sum": 239061007,
231
+ "pass_at_k": {
232
+ "pass@1": 0.9325031664068589,
233
+ "pass@2": 0.9518363817271153,
234
+ "pass@4": 0.9646200336464147,
235
+ "pass@8": 0.9733466730553039,
236
+ "pass@16": 0.9793728174194902,
237
+ "pass@32": 0.983754479786111,
238
+ "pass@64": 0.9872180069196503,
239
+ "pass@128": 0.9900233826968043
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.9433713573619632,
244
+ "pass@2": 0.9535782540698516,
245
+ "pass@4": 0.9618546829460732,
246
+ "pass@8": 0.968359742151891,
247
+ "pass@16": 0.9741511694787096,
248
+ "pass@32": 0.9805862212217205,
249
+ "pass@64": 0.9881224160445984,
250
+ "pass@128": 0.9938650306748467
251
+ },
252
+ "2": {
253
+ "pass@1": 1.0,
254
+ "pass@2": 1.0,
255
+ "pass@4": 1.0,
256
+ "pass@8": 1.0,
257
+ "pass@16": 1.0,
258
+ "pass@32": 1.0,
259
+ "pass@64": 1.0,
260
+ "pass@128": 1.0
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9983901515151515,
264
+ "pass@2": 0.999460898353615,
265
+ "pass@4": 0.9999225821204167,
266
+ "pass@8": 0.9999984049427112,
267
+ "pass@16": 0.9999999996635676,
268
+ "pass@32": 1.0,
269
+ "pass@64": 1.0,
270
+ "pass@128": 1.0
271
+ },
272
+ "4": {
273
+ "pass@1": 0.999791974852071,
274
+ "pass@2": 0.9999868960536739,
275
+ "pass@4": 0.9999999650561431,
276
+ "pass@8": 0.9999999999999813,
277
+ "pass@16": 1.0,
278
+ "pass@32": 1.0,
279
+ "pass@64": 1.0,
280
+ "pass@128": 1.0
281
+ },
282
+ "5": {
283
+ "pass@1": 0.9935914855072464,
284
+ "pass@2": 0.9972134257674314,
285
+ "pass@4": 0.9991986126734157,
286
+ "pass@8": 0.9998860811105759,
287
+ "pass@16": 0.9999969943734291,
288
+ "pass@32": 0.9999999992176973,
289
+ "pass@64": 1.0,
290
+ "pass@128": 1.0
291
+ },
292
+ "6": {
293
+ "pass@1": 0.9999328438395415,
294
+ "pass@2": 0.99999894242267,
295
+ "pass@4": 1.0,
296
+ "pass@8": 1.0,
297
+ "pass@16": 1.0,
298
+ "pass@32": 1.0,
299
+ "pass@64": 1.0,
300
+ "pass@128": 1.0
301
+ },
302
+ "7": {
303
+ "pass@1": 0.9981484826589595,
304
+ "pass@2": 0.9991423353511447,
305
+ "pass@4": 0.9997656553768929,
306
+ "pass@8": 0.9999830971478822,
307
+ "pass@16": 0.9999999407613452,
308
+ "pass@32": 0.9999999999999076,
309
+ "pass@64": 1.0,
310
+ "pass@128": 1.0
311
+ },
312
+ "8": {
313
+ "pass@1": 0.9978213028169014,
314
+ "pass@2": 0.998696212709327,
315
+ "pass@4": 0.9994122448602376,
316
+ "pass@8": 0.9998848700630322,
317
+ "pass@16": 0.9999964254002791,
318
+ "pass@32": 0.9999999987973975,
319
+ "pass@64": 1.0,
320
+ "pass@128": 1.0
321
+ },
322
+ "9": {
323
+ "pass@1": 0.9976609281437125,
324
+ "pass@2": 0.9988149930454053,
325
+ "pass@4": 0.9995776498184733,
326
+ "pass@8": 0.9999453661202221,
327
+ "pass@16": 0.9999993082440582,
328
+ "pass@32": 0.9999999999733661,
329
+ "pass@64": 1.0,
330
+ "pass@128": 1.0
331
+ },
332
+ "11": {
333
+ "pass@1": 0.9791274472891566,
334
+ "pass@2": 0.9844943257281095,
335
+ "pass@4": 0.9885222114554959,
336
+ "pass@8": 0.9915842526776513,
337
+ "pass@16": 0.9936573596958077,
338
+ "pass@32": 0.9946784629745986,
339
+ "pass@64": 0.9954818436151764,
340
+ "pass@128": 0.9969879518072289
341
+ },
342
+ "12": {
343
+ "pass@1": 0.9556720219435737,
344
+ "pass@2": 0.9739207939426853,
345
+ "pass@4": 0.9861632180381843,
346
+ "pass@8": 0.9932283805113136,
347
+ "pass@16": 0.9967175800031935,
348
+ "pass@32": 0.9986257066354457,
349
+ "pass@64": 0.9997926928260641,
350
+ "pass@128": 1.0
351
+ },
352
+ "13": {
353
+ "pass@1": 0.9692752100840336,
354
+ "pass@2": 0.9822620977524867,
355
+ "pass@4": 0.9899195350056031,
356
+ "pass@8": 0.9950258375460176,
357
+ "pass@16": 0.9984359616586164,
358
+ "pass@32": 0.9998247453476256,
359
+ "pass@64": 0.9999989636921891,
360
+ "pass@128": 1.0
361
+ },
362
+ "14": {
363
+ "pass@1": 0.9544956140350878,
364
+ "pass@2": 0.9714041706957683,
365
+ "pass@4": 0.9850686652107085,
366
+ "pass@8": 0.9941410138686707,
367
+ "pass@16": 0.9982549357238066,
368
+ "pass@32": 0.9997482243275714,
369
+ "pass@64": 0.9999976075223646,
370
+ "pass@128": 1.0
371
+ },
372
+ "15": {
373
+ "pass@1": 0.962405303030303,
374
+ "pass@2": 0.9801527827487472,
375
+ "pass@4": 0.9897256777561895,
376
+ "pass@8": 0.9949554819709671,
377
+ "pass@16": 0.9975806792718727,
378
+ "pass@32": 0.9989957428151091,
379
+ "pass@64": 0.999819329898887,
380
+ "pass@128": 1.0
381
+ },
382
+ "16": {
383
+ "pass@1": 0.9157540954415955,
384
+ "pass@2": 0.9383107460125177,
385
+ "pass@4": 0.9528681665860143,
386
+ "pass@8": 0.9618255529076115,
387
+ "pass@16": 0.9666002487818389,
388
+ "pass@32": 0.9691287175972142,
389
+ "pass@64": 0.9713401996282022,
390
+ "pass@128": 0.9743589743589743
391
+ },
392
+ "17": {
393
+ "pass@1": 0.8866459627329193,
394
+ "pass@2": 0.9140307869125057,
395
+ "pass@4": 0.9320510835796145,
396
+ "pass@8": 0.9470251241563546,
397
+ "pass@16": 0.958828933724438,
398
+ "pass@32": 0.9669829599693496,
399
+ "pass@64": 0.9726542282720683,
400
+ "pass@128": 0.9782608695652174
401
+ },
402
+ "18": {
403
+ "pass@1": 0.8592830882352941,
404
+ "pass@2": 0.9078276980083376,
405
+ "pass@4": 0.9323671411477975,
406
+ "pass@8": 0.9477004466579106,
407
+ "pass@16": 0.9584144161429146,
408
+ "pass@32": 0.9654229587125491,
409
+ "pass@64": 0.9701825020374101,
410
+ "pass@128": 0.9735294117647059
411
+ },
412
+ "19": {
413
+ "pass@1": 0.6903366815476191,
414
+ "pass@2": 0.7712544232752157,
415
+ "pass@4": 0.8257569664841,
416
+ "pass@8": 0.8643543757323078,
417
+ "pass@16": 0.8929841094671906,
418
+ "pass@32": 0.914312749232494,
419
+ "pass@64": 0.9313348502509535,
420
+ "pass@128": 0.9464285714285714
421
+ },
422
+ "20": {
423
+ "pass@1": 0.6061938622754491,
424
+ "pass@2": 0.7069592360554483,
425
+ "pass@4": 0.779909319718268,
426
+ "pass@8": 0.8312956919046384,
427
+ "pass@16": 0.8691291374054729,
428
+ "pass@32": 0.9006392983887458,
429
+ "pass@64": 0.926877074969234,
430
+ "pass@128": 0.9461077844311377
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 745158,
437
+ "answer_accuracy": 0.930108144272248,
438
+ "avg_response_len": 311.89763365753316,
439
+ "resp_tokens_sum": 249877413,
440
+ "pass_at_k": {
441
+ "pass@1": 0.930108144272248,
442
+ "pass@2": 0.9506625813159659,
443
+ "pass@4": 0.9639841486302464,
444
+ "pass@8": 0.9728187372779841,
445
+ "pass@16": 0.9789563417603896,
446
+ "pass@32": 0.9835196674940303,
447
+ "pass@64": 0.9868039392795732,
448
+ "pass@128": 0.9892954146029718
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.9640391791044776,
453
+ "pass@2": 0.9751006287460335,
454
+ "pass@4": 0.9840680005484389,
455
+ "pass@8": 0.989525217666148,
456
+ "pass@16": 0.9922932987785924,
457
+ "pass@32": 0.9943696315299635,
458
+ "pass@64": 0.9970265954859788,
459
+ "pass@128": 1.0
460
+ },
461
+ "2": {
462
+ "pass@1": 1.0,
463
+ "pass@2": 1.0,
464
+ "pass@4": 1.0,
465
+ "pass@8": 1.0,
466
+ "pass@16": 1.0,
467
+ "pass@32": 1.0,
468
+ "pass@64": 1.0,
469
+ "pass@128": 1.0
470
+ },
471
+ "3": {
472
+ "pass@1": 1.0,
473
+ "pass@2": 1.0,
474
+ "pass@4": 1.0,
475
+ "pass@8": 1.0,
476
+ "pass@16": 1.0,
477
+ "pass@32": 1.0,
478
+ "pass@64": 1.0,
479
+ "pass@128": 1.0
480
+ },
481
+ "4": {
482
+ "pass@1": 0.9998857821637427,
483
+ "pass@2": 0.9999978415527007,
484
+ "pass@4": 0.9999999997259115,
485
+ "pass@8": 1.0,
486
+ "pass@16": 1.0,
487
+ "pass@32": 1.0,
488
+ "pass@64": 1.0,
489
+ "pass@128": 1.0
490
+ },
491
+ "5": {
492
+ "pass@1": 0.9920266544117647,
493
+ "pass@2": 0.9942518961324689,
494
+ "pass@4": 0.9955414982134585,
495
+ "pass@8": 0.9967116901009395,
496
+ "pass@16": 0.998155080969405,
497
+ "pass@32": 0.9994198334387632,
498
+ "pass@64": 0.9999589349376307,
499
+ "pass@128": 1.0
500
+ },
501
+ "6": {
502
+ "pass@1": 0.9999260646687698,
503
+ "pass@2": 0.9999988356640751,
504
+ "pass@4": 1.0,
505
+ "pass@8": 1.0,
506
+ "pass@16": 1.0,
507
+ "pass@32": 1.0,
508
+ "pass@64": 1.0,
509
+ "pass@128": 1.0
510
+ },
511
+ "7": {
512
+ "pass@1": 0.9976513053797469,
513
+ "pass@2": 0.9984395245689226,
514
+ "pass@4": 0.9992420280930073,
515
+ "pass@8": 0.9998284242652762,
516
+ "pass@16": 0.9999927222555876,
517
+ "pass@32": 0.9999999948561573,
518
+ "pass@64": 1.0,
519
+ "pass@128": 1.0
520
+ },
521
+ "8": {
522
+ "pass@1": 0.9929147897897898,
523
+ "pass@2": 0.9970771706746117,
524
+ "pass@4": 0.9993902071362702,
525
+ "pass@8": 0.9999651367971397,
526
+ "pass@16": 0.9999998583663093,
527
+ "pass@32": 0.9999999999994196,
528
+ "pass@64": 1.0,
529
+ "pass@128": 1.0
530
+ },
531
+ "9": {
532
+ "pass@1": 0.9923884646302251,
533
+ "pass@2": 0.9939457427146365,
534
+ "pass@4": 0.994643188391644,
535
+ "pass@8": 0.995451850487162,
536
+ "pass@16": 0.9964930745316808,
537
+ "pass@32": 0.9974718962737498,
538
+ "pass@64": 0.9983913004056533,
539
+ "pass@128": 1.0
540
+ },
541
+ "11": {
542
+ "pass@1": 0.9703125,
543
+ "pass@2": 0.9826138920134985,
544
+ "pass@4": 0.9905110777819439,
545
+ "pass@8": 0.9952361673715535,
546
+ "pass@16": 0.9982486278795625,
547
+ "pass@32": 0.9997469296363813,
548
+ "pass@64": 0.9999980432330696,
549
+ "pass@128": 1.0
550
+ },
551
+ "12": {
552
+ "pass@1": 0.9693950688073395,
553
+ "pass@2": 0.9864906149919334,
554
+ "pass@4": 0.9964843422668495,
555
+ "pass@8": 0.999587940904666,
556
+ "pass@16": 0.9999840639525752,
557
+ "pass@32": 0.9999999728189605,
558
+ "pass@64": 0.9999999999999997,
559
+ "pass@128": 1.0
560
+ },
561
+ "13": {
562
+ "pass@1": 0.9416232638888888,
563
+ "pass@2": 0.9657007934772044,
564
+ "pass@4": 0.9807125428765847,
565
+ "pass@8": 0.9889479333237797,
566
+ "pass@16": 0.9935783281704044,
567
+ "pass@32": 0.9965795260843454,
568
+ "pass@64": 0.9983950138936485,
569
+ "pass@128": 1.0
570
+ },
571
+ "14": {
572
+ "pass@1": 0.9647626112759644,
573
+ "pass@2": 0.9797271840463564,
574
+ "pass@4": 0.988019856104782,
575
+ "pass@8": 0.992716483465879,
576
+ "pass@16": 0.9955701659139958,
577
+ "pass@32": 0.9973444053304108,
578
+ "pass@64": 0.9984967309084293,
579
+ "pass@128": 1.0
580
+ },
581
+ "15": {
582
+ "pass@1": 0.9497010030864198,
583
+ "pass@2": 0.9660535597112858,
584
+ "pass@4": 0.9750617191369597,
585
+ "pass@8": 0.9813197913201593,
586
+ "pass@16": 0.9856122764931645,
587
+ "pass@32": 0.9887173282223192,
588
+ "pass@64": 0.991433089630488,
589
+ "pass@128": 0.9938271604938271
590
+ },
591
+ "16": {
592
+ "pass@1": 0.8941970870206489,
593
+ "pass@2": 0.9212493177014375,
594
+ "pass@4": 0.9393702139555561,
595
+ "pass@8": 0.9519523737165061,
596
+ "pass@16": 0.9612349386592156,
597
+ "pass@32": 0.9691753292432682,
598
+ "pass@64": 0.9747878703756769,
599
+ "pass@128": 0.976401179941003
600
+ },
601
+ "17": {
602
+ "pass@1": 0.8594455948795181,
603
+ "pass@2": 0.897720433900958,
604
+ "pass@4": 0.922174053073938,
605
+ "pass@8": 0.9382293341864976,
606
+ "pass@16": 0.9493378639982005,
607
+ "pass@32": 0.959124887388815,
608
+ "pass@64": 0.9681289020289342,
609
+ "pass@128": 0.9759036144578314
610
+ },
611
+ "18": {
612
+ "pass@1": 0.8485887096774194,
613
+ "pass@2": 0.903131746888494,
614
+ "pass@4": 0.9370043603420539,
615
+ "pass@8": 0.9578532946585311,
616
+ "pass@16": 0.9702169368171149,
617
+ "pass@32": 0.9777537348282815,
618
+ "pass@64": 0.9826360654372754,
619
+ "pass@128": 0.9870967741935484
620
+ },
621
+ "19": {
622
+ "pass@1": 0.7076331193353474,
623
+ "pass@2": 0.7887924625924787,
624
+ "pass@4": 0.8411277290300948,
625
+ "pass@8": 0.878659443062788,
626
+ "pass@16": 0.9053831900865986,
627
+ "pass@32": 0.9237568606242907,
628
+ "pass@64": 0.9352225250892545,
629
+ "pass@128": 0.9425981873111783
630
+ },
631
+ "20": {
632
+ "pass@1": 0.626196509009009,
633
+ "pass@2": 0.7125315522215124,
634
+ "pass@4": 0.7734252413268156,
635
+ "pass@8": 0.8190036582565382,
636
+ "pass@16": 0.8555370910100033,
637
+ "pass@32": 0.8847167374444287,
638
+ "pass@64": 0.9059201413232556,
639
+ "pass@128": 0.9219219219219219
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]
Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_id_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc96c6c038c1ffd5920d3659d33c7102aa384e31647ed37d10c1b8001dd287d
3
+ size 1789699126
Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_metrics.json ADDED
@@ -0,0 +1,1897 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "checkpoint-38645",
3
+ "id": {
4
+ "answer_accuracy": 0.9926675347222222,
5
+ "avg_response_len": 200.20069097222222,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.9926675347222222,
11
+ "pass@2": 0.9947181075021866,
12
+ "pass@4": 0.9961613556430446,
13
+ "pass@8": 0.9973026695761072,
14
+ "pass@16": 0.9981802787310782,
15
+ "pass@32": 0.9987948199302888,
16
+ "pass@64": 0.9992436062012987,
17
+ "pass@128": 0.9995555555555555
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.9546875,
22
+ "pass@2": 0.9643489173228345,
23
+ "pass@4": 0.9724239796587925,
24
+ "pass@8": 0.9796451423626065,
25
+ "pass@16": 0.9858481869460654,
26
+ "pass@32": 0.9905653033141515,
27
+ "pass@64": 0.9942351004838736,
28
+ "pass@128": 0.997
29
+ },
30
+ "2": {
31
+ "pass@1": 1.0,
32
+ "pass@2": 1.0,
33
+ "pass@4": 1.0,
34
+ "pass@8": 1.0,
35
+ "pass@16": 1.0,
36
+ "pass@32": 1.0,
37
+ "pass@64": 1.0,
38
+ "pass@128": 1.0
39
+ },
40
+ "3": {
41
+ "pass@1": 0.99915625,
42
+ "pass@2": 0.9997679625984253,
43
+ "pass@4": 0.9999731251406074,
44
+ "pass@8": 0.9999995472606525,
45
+ "pass@16": 0.9999999999231317,
46
+ "pass@32": 1.0,
47
+ "pass@64": 1.0,
48
+ "pass@128": 1.0
49
+ },
50
+ "4": {
51
+ "pass@1": 0.99971875,
52
+ "pass@2": 0.9999778543307086,
53
+ "pass@4": 0.9999998386764155,
54
+ "pass@8": 0.9999999999969994,
55
+ "pass@16": 1.0,
56
+ "pass@32": 1.0,
57
+ "pass@64": 1.0,
58
+ "pass@128": 1.0
59
+ },
60
+ "5": {
61
+ "pass@1": 0.9941953125,
62
+ "pass@2": 0.9956927903543309,
63
+ "pass@4": 0.9968433910761155,
64
+ "pass@8": 0.9977670040034647,
65
+ "pass@16": 0.9983917733914977,
66
+ "pass@32": 0.9987650573014524,
67
+ "pass@64": 0.9989711801510246,
68
+ "pass@128": 0.999
69
+ },
70
+ "6": {
71
+ "pass@1": 0.99975,
72
+ "pass@2": 0.9999803149606299,
73
+ "pass@4": 0.9999997736220472,
74
+ "pass@8": 0.9999999999829965,
75
+ "pass@16": 1.0,
76
+ "pass@32": 1.0,
77
+ "pass@64": 1.0,
78
+ "pass@128": 1.0
79
+ },
80
+ "7": {
81
+ "pass@1": 0.9958359375,
82
+ "pass@2": 0.9972054625984251,
83
+ "pass@4": 0.9982031517622797,
84
+ "pass@8": 0.9990104842344203,
85
+ "pass@16": 0.9995193774344288,
86
+ "pass@32": 0.9998284427302075,
87
+ "pass@64": 0.9999861762904964,
88
+ "pass@128": 1.0
89
+ },
90
+ "8": {
91
+ "pass@1": 0.9950703125,
92
+ "pass@2": 0.997607160433071,
93
+ "pass@4": 0.9989324190101235,
94
+ "pass@8": 0.9996309201327338,
95
+ "pass@16": 0.9999226231371163,
96
+ "pass@32": 0.9999963916027095,
97
+ "pass@64": 0.9999999990502599,
98
+ "pass@128": 1.0
99
+ },
100
+ "9": {
101
+ "pass@1": 0.99559375,
102
+ "pass@2": 0.9978825049212597,
103
+ "pass@4": 0.9990765218410199,
104
+ "pass@8": 0.9996709282110962,
105
+ "pass@16": 0.9999405477474613,
106
+ "pass@32": 0.9999981844240781,
107
+ "pass@64": 0.9999999998360332,
108
+ "pass@128": 1.0
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.9546875,
113
+ "2": 1.0,
114
+ "3": 0.99915625,
115
+ "4": 0.99971875,
116
+ "5": 0.9941953125,
117
+ "6": 0.99975,
118
+ "7": 0.9958359375,
119
+ "8": 0.9950703125,
120
+ "9": 0.99559375
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 281.6347734375,
124
+ "2": 115.6326015625,
125
+ "3": 144.829234375,
126
+ "4": 159.923921875,
127
+ "5": 173.2866484375,
128
+ "6": 198.9441953125,
129
+ "7": 224.1663515625,
130
+ "8": 243.7276171875,
131
+ "9": 259.660875
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 281.6347734375,
136
+ "2": 115.6326015625,
137
+ "3": 144.829234375,
138
+ "4": 159.923921875,
139
+ "5": 173.2866484375,
140
+ "6": 198.9441953125,
141
+ "7": 224.1663515625,
142
+ "8": 243.7276171875,
143
+ "9": 259.660875
144
+ },
145
+ "per_op_loss": {},
146
+ "per_template": {
147
+ "crazy_zootopia": {
148
+ "count": 379008,
149
+ "correct": 376612,
150
+ "answer_accuracy": 0.9936782337048294,
151
+ "avg_response_len": 190.71223826409997,
152
+ "resp_tokens_sum": 72281464,
153
+ "pass_at_k": {
154
+ "pass@1": 0.9936782337048294,
155
+ "pass@2": 0.9956697567059437,
156
+ "pass@4": 0.996967571777692,
157
+ "pass@8": 0.9979938409459532,
158
+ "pass@16": 0.9988097707718845,
159
+ "pass@32": 0.9992490341086927,
160
+ "pass@64": 0.9994945000973269,
161
+ "pass@128": 0.999662276258021
162
+ },
163
+ "per_op_pass_at_k": {
164
+ "10": {
165
+ "pass@1": 0.9615366887905604,
166
+ "pass@2": 0.970145808654449,
167
+ "pass@4": 0.9771259859110534,
168
+ "pass@8": 0.9837142589656627,
169
+ "pass@16": 0.9897806295670789,
170
+ "pass@32": 0.9934434017257641,
171
+ "pass@64": 0.9955847044260153,
172
+ "pass@128": 0.9970501474926253
173
+ },
174
+ "2": {
175
+ "pass@1": 1.0,
176
+ "pass@2": 1.0,
177
+ "pass@4": 1.0,
178
+ "pass@8": 1.0,
179
+ "pass@16": 1.0,
180
+ "pass@32": 1.0,
181
+ "pass@64": 1.0,
182
+ "pass@128": 1.0
183
+ },
184
+ "3": {
185
+ "pass@1": 0.9997610856269113,
186
+ "pass@2": 0.9999864552481399,
187
+ "pass@4": 0.9999999638806617,
188
+ "pass@8": 0.9999999999999809,
189
+ "pass@16": 1.0,
190
+ "pass@32": 1.0,
191
+ "pass@64": 1.0,
192
+ "pass@128": 1.0
193
+ },
194
+ "4": {
195
+ "pass@1": 0.99931640625,
196
+ "pass@2": 0.9999350239911416,
197
+ "pass@4": 0.9999994973284589,
198
+ "pass@8": 0.999999999990623,
199
+ "pass@16": 1.0,
200
+ "pass@32": 1.0,
201
+ "pass@64": 1.0,
202
+ "pass@128": 1.0
203
+ },
204
+ "5": {
205
+ "pass@1": 0.9954861111111111,
206
+ "pass@2": 0.9972468285214349,
207
+ "pass@4": 0.9985486585010207,
208
+ "pass@8": 0.9994671341886722,
209
+ "pass@16": 0.9999236250321564,
210
+ "pass@32": 0.9999990493973,
211
+ "pass@64": 0.9999999999949286,
212
+ "pass@128": 1.0
213
+ },
214
+ "6": {
215
+ "pass@1": 0.9995555763473054,
216
+ "pass@2": 0.9999499033429206,
217
+ "pass@4": 0.9999993320445721,
218
+ "pass@8": 0.9999999999490911,
219
+ "pass@16": 1.0,
220
+ "pass@32": 1.0,
221
+ "pass@64": 1.0,
222
+ "pass@128": 1.0
223
+ },
224
+ "7": {
225
+ "pass@1": 0.9964404585798816,
226
+ "pass@2": 0.9978735207100592,
227
+ "pass@4": 0.9986706386183974,
228
+ "pass@8": 0.9994230191252826,
229
+ "pass@16": 0.9999007629980622,
230
+ "pass@32": 0.9999981593967747,
231
+ "pass@64": 0.99999999996853,
232
+ "pass@128": 1.0
233
+ },
234
+ "8": {
235
+ "pass@1": 0.997245592948718,
236
+ "pass@2": 0.9984009848828992,
237
+ "pass@4": 0.9992322474113812,
238
+ "pass@8": 0.9998262245762686,
239
+ "pass@16": 0.9999926289511722,
240
+ "pass@32": 0.9999999947902106,
241
+ "pass@64": 1.0,
242
+ "pass@128": 1.0
243
+ },
244
+ "9": {
245
+ "pass@1": 0.9950704225352113,
246
+ "pass@2": 0.9983818759010756,
247
+ "pass@4": 0.999779442534472,
248
+ "pass@8": 0.9999935759719568,
249
+ "pass@16": 0.9999999938621692,
250
+ "pass@32": 0.9999999999999997,
251
+ "pass@64": 1.0,
252
+ "pass@128": 1.0
253
+ }
254
+ }
255
+ },
256
+ "teachers_in_school": {
257
+ "count": 390656,
258
+ "correct": 387758,
259
+ "answer_accuracy": 0.9925817087155964,
260
+ "avg_response_len": 198.13595081094365,
261
+ "resp_tokens_sum": 77402998,
262
+ "pass_at_k": {
263
+ "pass@1": 0.9925817087155964,
264
+ "pass@2": 0.9942163103321948,
265
+ "pass@4": 0.9953949149315869,
266
+ "pass@8": 0.9964613581820646,
267
+ "pass@16": 0.9974663333818123,
268
+ "pass@32": 0.9984046891944619,
269
+ "pass@64": 0.999174331646805,
270
+ "pass@128": 0.9996723460026212
271
+ },
272
+ "per_op_pass_at_k": {
273
+ "10": {
274
+ "pass@1": 0.9446654524539877,
275
+ "pass@2": 0.9550259498333415,
276
+ "pass@4": 0.9634138444542589,
277
+ "pass@8": 0.970866877957459,
278
+ "pass@16": 0.9782378206275941,
279
+ "pass@32": 0.9857900637806933,
280
+ "pass@64": 0.9923585282128631,
281
+ "pass@128": 0.9969325153374233
282
+ },
283
+ "2": {
284
+ "pass@1": 1.0,
285
+ "pass@2": 1.0,
286
+ "pass@4": 1.0,
287
+ "pass@8": 1.0,
288
+ "pass@16": 1.0,
289
+ "pass@32": 1.0,
290
+ "pass@64": 1.0,
291
+ "pass@128": 1.0
292
+ },
293
+ "3": {
294
+ "pass@1": 0.9988873106060606,
295
+ "pass@2": 0.9997856269386781,
296
+ "pass@4": 0.9999895822681255,
297
+ "pass@8": 0.9999999777033803,
298
+ "pass@16": 0.9999999999999803,
299
+ "pass@32": 1.0,
300
+ "pass@64": 1.0,
301
+ "pass@128": 1.0
302
+ },
303
+ "4": {
304
+ "pass@1": 0.9999537721893491,
305
+ "pass@2": 0.999999636001491,
306
+ "pass@4": 1.0,
307
+ "pass@8": 1.0,
308
+ "pass@16": 1.0,
309
+ "pass@32": 1.0,
310
+ "pass@64": 1.0,
311
+ "pass@128": 1.0
312
+ },
313
+ "5": {
314
+ "pass@1": 0.9965579710144927,
315
+ "pass@2": 0.9972633515919205,
316
+ "pass@4": 0.9975327839454851,
317
+ "pass@8": 0.9979120550709301,
318
+ "pass@16": 0.9985302315822023,
319
+ "pass@32": 0.9993303337082865,
320
+ "pass@64": 0.9999164669633687,
321
+ "pass@128": 1.0
322
+ },
323
+ "6": {
324
+ "pass@1": 0.9997313753581661,
325
+ "pass@2": 0.9999915393813595,
326
+ "pass@4": 0.9999999905993125,
327
+ "pass@8": 1.0,
328
+ "pass@16": 1.0,
329
+ "pass@32": 1.0,
330
+ "pass@64": 1.0,
331
+ "pass@128": 1.0
332
+ },
333
+ "7": {
334
+ "pass@1": 0.9975162572254336,
335
+ "pass@2": 0.9985822931364069,
336
+ "pass@4": 0.9993384239181086,
337
+ "pass@8": 0.9998572295938166,
338
+ "pass@16": 0.9999945349140869,
339
+ "pass@32": 0.9999999969725001,
340
+ "pass@64": 1.0,
341
+ "pass@128": 1.0
342
+ },
343
+ "8": {
344
+ "pass@1": 0.9966769366197183,
345
+ "pass@2": 0.9978297937229678,
346
+ "pass@4": 0.9984739589769589,
347
+ "pass@8": 0.9991927685739189,
348
+ "pass@16": 0.9997893254704586,
349
+ "pass@32": 0.999989840105361,
350
+ "pass@64": 0.9999999973246758,
351
+ "pass@128": 1.0
352
+ },
353
+ "9": {
354
+ "pass@1": 0.9973100673652695,
355
+ "pass@2": 0.9978701553585743,
356
+ "pass@4": 0.9984959510113631,
357
+ "pass@8": 0.9992628054872507,
358
+ "pass@16": 0.9998367378399854,
359
+ "pass@32": 0.9999945907477397,
360
+ "pass@64": 0.9999999995090815,
361
+ "pass@128": 1.0
362
+ }
363
+ }
364
+ },
365
+ "movie_festival_awards": {
366
+ "count": 382336,
367
+ "correct": 379183,
368
+ "answer_accuracy": 0.9917533269166388,
369
+ "avg_response_len": 211.7162234265149,
370
+ "resp_tokens_sum": 80946734,
371
+ "pass_at_k": {
372
+ "pass@1": 0.9917533269166388,
373
+ "pass@2": 0.9942874585803578,
374
+ "pass@4": 0.996145276324892,
375
+ "pass@8": 0.997477133569582,
376
+ "pass@16": 0.9982857475202078,
377
+ "pass@32": 0.9987431797640651,
378
+ "pass@64": 0.9990656782180966,
379
+ "pass@128": 0.9993304318714429
380
+ },
381
+ "per_op_pass_at_k": {
382
+ "10": {
383
+ "pass@1": 0.9575093283582089,
384
+ "pass@2": 0.9675553090844993,
385
+ "pass@4": 0.9764339019189767,
386
+ "pass@8": 0.9840698697287039,
387
+ "pass@16": 0.9892746985021801,
388
+ "pass@32": 0.9922997890645133,
389
+ "pass@64": 0.9946955387643621,
390
+ "pass@128": 0.9970149253731343
391
+ },
392
+ "2": {
393
+ "pass@1": 1.0,
394
+ "pass@2": 1.0,
395
+ "pass@4": 1.0,
396
+ "pass@8": 1.0,
397
+ "pass@16": 1.0,
398
+ "pass@32": 1.0,
399
+ "pass@64": 1.0,
400
+ "pass@128": 1.0
401
+ },
402
+ "3": {
403
+ "pass@1": 0.9988383746355685,
404
+ "pass@2": 0.9995426671793577,
405
+ "pass@4": 0.9999317049654508,
406
+ "pass@8": 0.999998701511788,
407
+ "pass@16": 0.9999999997759129,
408
+ "pass@32": 1.0,
409
+ "pass@64": 1.0,
410
+ "pass@128": 1.0
411
+ },
412
+ "4": {
413
+ "pass@1": 0.9998629385964912,
414
+ "pass@2": 0.9999964025878345,
415
+ "pass@4": 0.9999999986295574,
416
+ "pass@8": 1.0,
417
+ "pass@16": 1.0,
418
+ "pass@32": 1.0,
419
+ "pass@64": 1.0,
420
+ "pass@128": 1.0
421
+ },
422
+ "5": {
423
+ "pass@1": 0.9906020220588235,
424
+ "pass@2": 0.9926593619731356,
425
+ "pass@4": 0.9945639799620636,
426
+ "pass@8": 0.9960446992193006,
427
+ "pass@16": 0.9968320635603195,
428
+ "pass@32": 0.997048210623365,
429
+ "pass@64": 0.9970588207360587,
430
+ "pass@128": 0.9970588235294118
431
+ },
432
+ "6": {
433
+ "pass@1": 0.9999753548895899,
434
+ "pass@2": 1.0,
435
+ "pass@4": 1.0,
436
+ "pass@8": 1.0,
437
+ "pass@16": 1.0,
438
+ "pass@32": 1.0,
439
+ "pass@64": 1.0,
440
+ "pass@128": 1.0
441
+ },
442
+ "7": {
443
+ "pass@1": 0.9933494857594937,
444
+ "pass@2": 0.9949833518140139,
445
+ "pass@4": 0.9964600671949234,
446
+ "pass@8": 0.9976420959829561,
447
+ "pass@16": 0.9985911723443348,
448
+ "pass@32": 0.9994590693089006,
449
+ "pass@64": 0.9999562541175095,
450
+ "pass@128": 1.0
451
+ },
452
+ "8": {
453
+ "pass@1": 0.9913194444444444,
454
+ "pass@2": 0.9966260551890473,
455
+ "pass@4": 0.9991402473902474,
456
+ "pass@8": 0.9999150306942846,
457
+ "pass@16": 0.9999991362232366,
458
+ "pass@32": 0.9999999999722541,
459
+ "pass@64": 1.0,
460
+ "pass@128": 1.0
461
+ },
462
+ "9": {
463
+ "pass@1": 0.9943478697749196,
464
+ "pass@2": 0.9973257462592097,
465
+ "pass@4": 0.9988976594967428,
466
+ "pass@8": 0.9997409379688414,
467
+ "pass@16": 0.9999841784174797,
468
+ "pass@32": 0.999999971428724,
469
+ "pass@64": 0.9999999999999997,
470
+ "pass@128": 1.0
471
+ }
472
+ }
473
+ }
474
+ }
475
+ },
476
+ "ood": {
477
+ "answer_accuracy": 0.844671875,
478
+ "avg_response_len": 377.0967484375,
479
+ "avg_loss": 0.0,
480
+ "count": 1280000,
481
+ "validation_metrics": {},
482
+ "pass_at_k": {
483
+ "pass@1": 0.844671875,
484
+ "pass@2": 0.8858922244094257,
485
+ "pass@4": 0.9141995808398893,
486
+ "pass@8": 0.9341837080333515,
487
+ "pass@16": 0.9486755484175874,
488
+ "pass@32": 0.9595485287445626,
489
+ "pass@64": 0.9677227239017148,
490
+ "pass@128": 0.9738
491
+ },
492
+ "per_op_pass_at_k": {
493
+ "11": {
494
+ "pass@1": 0.9726171875,
495
+ "pass@2": 0.9828142224409449,
496
+ "pass@4": 0.9897272834645668,
497
+ "pass@8": 0.994115282605061,
498
+ "pass@16": 0.9967868462201568,
499
+ "pass@32": 0.9981416746464655,
500
+ "pass@64": 0.9987367902594374,
501
+ "pass@128": 0.999
502
+ },
503
+ "12": {
504
+ "pass@1": 0.9644375,
505
+ "pass@2": 0.9804958169291337,
506
+ "pass@4": 0.9905623012748407,
507
+ "pass@8": 0.9955742374047644,
508
+ "pass@16": 0.9976946487441701,
509
+ "pass@32": 0.998880341662968,
510
+ "pass@64": 0.9996771390867283,
511
+ "pass@128": 1.0
512
+ },
513
+ "13": {
514
+ "pass@1": 0.94846875,
515
+ "pass@2": 0.9692981053149601,
516
+ "pass@4": 0.9827727335958009,
517
+ "pass@8": 0.9904335216979527,
518
+ "pass@16": 0.9947883099927657,
519
+ "pass@32": 0.9972493649171777,
520
+ "pass@64": 0.9987378705005298,
521
+ "pass@128": 1.0
522
+ },
523
+ "14": {
524
+ "pass@1": 0.9449453125,
525
+ "pass@2": 0.964385088582677,
526
+ "pass@4": 0.9777694221034873,
527
+ "pass@8": 0.9865351007090998,
528
+ "pass@16": 0.9922419706883057,
529
+ "pass@32": 0.9962460277292379,
530
+ "pass@64": 0.9986672351003253,
531
+ "pass@128": 1.0
532
+ },
533
+ "15": {
534
+ "pass@1": 0.952953125,
535
+ "pass@2": 0.9735356791338584,
536
+ "pass@4": 0.9843826020809897,
537
+ "pass@8": 0.9903981612161823,
538
+ "pass@16": 0.9936567666222805,
539
+ "pass@32": 0.9955643444237633,
540
+ "pass@64": 0.9966508344175822,
541
+ "pass@128": 0.997
542
+ },
543
+ "16": {
544
+ "pass@1": 0.8934609375,
545
+ "pass@2": 0.9216697834645677,
546
+ "pass@4": 0.9393977767154105,
547
+ "pass@8": 0.9517931687352534,
548
+ "pass@16": 0.96139777462629,
549
+ "pass@32": 0.9693210349487325,
550
+ "pass@64": 0.9751328706018372,
551
+ "pass@128": 0.979
552
+ },
553
+ "17": {
554
+ "pass@1": 0.8661875,
555
+ "pass@2": 0.9038288631889774,
556
+ "pass@4": 0.9277408284589423,
557
+ "pass@8": 0.9448044024114316,
558
+ "pass@16": 0.9568565852772714,
559
+ "pass@32": 0.9646994651551266,
560
+ "pass@64": 0.9694077197479471,
561
+ "pass@128": 0.972
562
+ },
563
+ "18": {
564
+ "pass@1": 0.788859375,
565
+ "pass@2": 0.8561178641732294,
566
+ "pass@4": 0.8988476714473197,
567
+ "pass@8": 0.9267583655390567,
568
+ "pass@16": 0.9448361294806787,
569
+ "pass@32": 0.9568568515114735,
570
+ "pass@64": 0.9657552890983766,
571
+ "pass@128": 0.973
572
+ },
573
+ "19": {
574
+ "pass@1": 0.625640625,
575
+ "pass@2": 0.7169927411417328,
576
+ "pass@4": 0.7811060572740908,
577
+ "pass@8": 0.8285917496219818,
578
+ "pass@16": 0.8654698909087529,
579
+ "pass@32": 0.8941006950628526,
580
+ "pass@64": 0.9155477279248722,
581
+ "pass@128": 0.932
582
+ },
583
+ "20": {
584
+ "pass@1": 0.4891484375,
585
+ "pass@2": 0.5897840797244098,
586
+ "pass@4": 0.6696891319835014,
587
+ "pass@8": 0.7328330903927104,
588
+ "pass@16": 0.7830265616151493,
589
+ "pass@32": 0.824425487387794,
590
+ "pass@64": 0.8589137622794993,
591
+ "pass@128": 0.886
592
+ }
593
+ },
594
+ "per_op_accuracy": {
595
+ "11": 0.9726171875,
596
+ "12": 0.9644375,
597
+ "13": 0.94846875,
598
+ "14": 0.9449453125,
599
+ "15": 0.952953125,
600
+ "16": 0.8934609375,
601
+ "17": 0.8661875,
602
+ "18": 0.788859375,
603
+ "19": 0.625640625,
604
+ "20": 0.4891484375
605
+ },
606
+ "per_op_avg_response_len": {
607
+ "11": 300.8103125,
608
+ "12": 313.388375,
609
+ "13": 334.3829921875,
610
+ "14": 361.2994765625,
611
+ "15": 381.435625,
612
+ "16": 390.2542265625,
613
+ "17": 410.935984375,
614
+ "18": 425.279296875,
615
+ "19": 422.265296875,
616
+ "20": 430.9158984375
617
+ },
618
+ "per_op_avg_loss": {},
619
+ "per_op_length": {
620
+ "11": 300.8103125,
621
+ "12": 313.388375,
622
+ "13": 334.3829921875,
623
+ "14": 361.2994765625,
624
+ "15": 381.435625,
625
+ "16": 390.2542265625,
626
+ "17": 410.935984375,
627
+ "18": 425.279296875,
628
+ "19": 422.265296875,
629
+ "20": 430.9158984375
630
+ },
631
+ "per_op_loss": {},
632
+ "per_template": {
633
+ "crazy_zootopia": {
634
+ "count": 430720,
635
+ "correct": 361406,
636
+ "answer_accuracy": 0.8390741084695393,
637
+ "avg_response_len": 358.89673569836555,
638
+ "resp_tokens_sum": 154584002,
639
+ "pass_at_k": {
640
+ "pass@1": 0.8390741084695393,
641
+ "pass@2": 0.8810461662435247,
642
+ "pass@4": 0.910567308794798,
643
+ "pass@8": 0.9312514898839028,
644
+ "pass@16": 0.9461738981519632,
645
+ "pass@32": 0.9574585135295627,
646
+ "pass@64": 0.9658631665868088,
647
+ "pass@128": 0.9723625557206538
648
+ },
649
+ "per_op_pass_at_k": {
650
+ "11": {
651
+ "pass@1": 0.9698123229461756,
652
+ "pass@2": 0.981584311079387,
653
+ "pass@4": 0.9891040887948495,
654
+ "pass@8": 0.9937797636155625,
655
+ "pass@16": 0.9970789483598115,
656
+ "pass@32": 0.999223562425918,
657
+ "pass@64": 0.9999570534856826,
658
+ "pass@128": 1.0
659
+ },
660
+ "12": {
661
+ "pass@1": 0.9659030720338984,
662
+ "pass@2": 0.9809874632990792,
663
+ "pass@4": 0.9906215364498931,
664
+ "pass@8": 0.9956137072056146,
665
+ "pass@16": 0.9978803736651605,
666
+ "pass@32": 0.9993246177441057,
667
+ "pass@64": 0.9999568688255516,
668
+ "pass@128": 1.0
669
+ },
670
+ "13": {
671
+ "pass@1": 0.9498922413793104,
672
+ "pass@2": 0.9708758608347934,
673
+ "pass@4": 0.9840897281060871,
674
+ "pass@8": 0.9909108589255634,
675
+ "pass@16": 0.9943999521503089,
676
+ "pass@32": 0.9963005415376021,
677
+ "pass@64": 0.9980499904733999,
678
+ "pass@128": 1.0
679
+ },
680
+ "14": {
681
+ "pass@1": 0.9233839563862928,
682
+ "pass@2": 0.944520460789364,
683
+ "pass@4": 0.9611923819102052,
684
+ "pass@8": 0.9751079976868544,
685
+ "pass@16": 0.9861293435926446,
686
+ "pass@32": 0.9935272719026856,
687
+ "pass@64": 0.9975030863628863,
688
+ "pass@128": 1.0
689
+ },
690
+ "15": {
691
+ "pass@1": 0.9595375722543352,
692
+ "pass@2": 0.9784015719584908,
693
+ "pass@4": 0.987961396353635,
694
+ "pass@8": 0.9923778119086278,
695
+ "pass@16": 0.9938310119401556,
696
+ "pass@32": 0.9941908530213401,
697
+ "pass@64": 0.9942196182961773,
698
+ "pass@128": 0.9942196531791907
699
+ },
700
+ "16": {
701
+ "pass@1": 0.8793850806451613,
702
+ "pass@2": 0.9133687611125221,
703
+ "pass@4": 0.9350571322737883,
704
+ "pass@8": 0.9489252481008612,
705
+ "pass@16": 0.9594660322806725,
706
+ "pass@32": 0.9677192403291304,
707
+ "pass@64": 0.9722136540329196,
708
+ "pass@128": 0.9741935483870968
709
+ },
710
+ "17": {
711
+ "pass@1": 0.8896992413294798,
712
+ "pass@2": 0.9255197191752769,
713
+ "pass@4": 0.9464512051600483,
714
+ "pass@8": 0.9595738090472379,
715
+ "pass@16": 0.9673121876199731,
716
+ "pass@32": 0.9725731938539892,
717
+ "pass@64": 0.9768482847119901,
718
+ "pass@128": 0.9797687861271677
719
+ },
720
+ "18": {
721
+ "pass@1": 0.7444419642857143,
722
+ "pass@2": 0.8136916479190104,
723
+ "pass@4": 0.8625618206652741,
724
+ "pass@8": 0.8958082898451949,
725
+ "pass@16": 0.9174575405950798,
726
+ "pass@32": 0.9337781303810576,
727
+ "pass@64": 0.947397000627292,
728
+ "pass@128": 0.9571428571428572
729
+ },
730
+ "19": {
731
+ "pass@1": 0.6253753753753754,
732
+ "pass@2": 0.7184758577475104,
733
+ "pass@4": 0.7833039738275956,
734
+ "pass@8": 0.8296772377534075,
735
+ "pass@16": 0.8660549147719705,
736
+ "pass@32": 0.8940814351693145,
737
+ "pass@64": 0.9133406551952218,
738
+ "pass@128": 0.9279279279279279
739
+ },
740
+ "20": {
741
+ "pass@1": 0.4760932807807808,
742
+ "pass@2": 0.5768932071835613,
743
+ "pass@4": 0.6601997517765237,
744
+ "pass@8": 0.7265525943478015,
745
+ "pass@16": 0.7789762742387952,
746
+ "pass@32": 0.8215439955324653,
747
+ "pass@64": 0.8572865791166149,
748
+ "pass@128": 0.8888888888888888
749
+ }
750
+ }
751
+ },
752
+ "teachers_in_school": {
753
+ "count": 430464,
754
+ "correct": 365670,
755
+ "answer_accuracy": 0.8494787020517395,
756
+ "avg_response_len": 372.46568586455544,
757
+ "resp_tokens_sum": 160333069,
758
+ "pass_at_k": {
759
+ "pass@1": 0.8494787020517395,
760
+ "pass@2": 0.8895784091467879,
761
+ "pass@4": 0.9172445349438386,
762
+ "pass@8": 0.9367987196255487,
763
+ "pass@16": 0.950993996091102,
764
+ "pass@32": 0.961825739478423,
765
+ "pass@64": 0.9700731776529568,
766
+ "pass@128": 0.976211715730003
767
+ },
768
+ "per_op_pass_at_k": {
769
+ "11": {
770
+ "pass@1": 0.9770566641566265,
771
+ "pass@2": 0.9841648829570252,
772
+ "pass@4": 0.989164249235412,
773
+ "pass@8": 0.9922976666641117,
774
+ "pass@16": 0.9941890352635745,
775
+ "pass@32": 0.9952655846372421,
776
+ "pass@64": 0.9962408325530068,
777
+ "pass@128": 0.9969879518072289
778
+ },
779
+ "12": {
780
+ "pass@1": 0.9620640673981191,
781
+ "pass@2": 0.9773606620097254,
782
+ "pass@4": 0.9866140545127782,
783
+ "pass@8": 0.9920244775588233,
784
+ "pass@16": 0.9951791105256566,
785
+ "pass@32": 0.9972397387226369,
786
+ "pass@64": 0.9990357602586,
787
+ "pass@128": 1.0
788
+ },
789
+ "13": {
790
+ "pass@1": 0.9582020308123249,
791
+ "pass@2": 0.9730195720020293,
792
+ "pass@4": 0.9829933805543213,
793
+ "pass@8": 0.9895737184859488,
794
+ "pass@16": 0.9944316023575817,
795
+ "pass@32": 0.9979028151511814,
796
+ "pass@64": 0.9996096734768417,
797
+ "pass@128": 1.0
798
+ },
799
+ "14": {
800
+ "pass@1": 0.9545869883040936,
801
+ "pass@2": 0.9759829569001243,
802
+ "pass@4": 0.9895990122945156,
803
+ "pass@8": 0.9958761100329401,
804
+ "pass@16": 0.9982192698442767,
805
+ "pass@32": 0.9995253069447078,
806
+ "pass@64": 0.9999798903618302,
807
+ "pass@128": 1.0
808
+ },
809
+ "15": {
810
+ "pass@1": 0.964654356060606,
811
+ "pass@2": 0.9848753280839894,
812
+ "pass@4": 0.994307931394939,
813
+ "pass@8": 0.9984355730943542,
814
+ "pass@16": 0.9997865737709953,
815
+ "pass@32": 0.999996225078149,
816
+ "pass@64": 0.9999999999355342,
817
+ "pass@128": 1.0
818
+ },
819
+ "16": {
820
+ "pass@1": 0.9025106837606838,
821
+ "pass@2": 0.9249840865244409,
822
+ "pass@4": 0.9394740470475377,
823
+ "pass@8": 0.951603221594124,
824
+ "pass@16": 0.9618929894371758,
825
+ "pass@32": 0.9704062836352245,
826
+ "pass@64": 0.9772483460299233,
827
+ "pass@128": 0.9829059829059829
828
+ },
829
+ "17": {
830
+ "pass@1": 0.8692498059006211,
831
+ "pass@2": 0.9090858377757125,
832
+ "pass@4": 0.9353135909447651,
833
+ "pass@8": 0.9535516185363221,
834
+ "pass@16": 0.965466357509199,
835
+ "pass@32": 0.9717789256494813,
836
+ "pass@64": 0.9742932379404277,
837
+ "pass@128": 0.9751552795031055
838
+ },
839
+ "18": {
840
+ "pass@1": 0.8068244485294118,
841
+ "pass@2": 0.8750351001621121,
842
+ "pass@4": 0.9166487397714989,
843
+ "pass@8": 0.9411302798270424,
844
+ "pass@16": 0.9559175964520414,
845
+ "pass@32": 0.9659157855028336,
846
+ "pass@64": 0.9733500817730232,
847
+ "pass@128": 0.9794117647058823
848
+ },
849
+ "19": {
850
+ "pass@1": 0.6194428943452381,
851
+ "pass@2": 0.7078185051087363,
852
+ "pass@4": 0.7742094414537468,
853
+ "pass@8": 0.8272903079106774,
854
+ "pass@16": 0.8697325655416732,
855
+ "pass@32": 0.9032315125581434,
856
+ "pass@64": 0.9280735994123079,
857
+ "pass@128": 0.9464285714285714
858
+ },
859
+ "20": {
860
+ "pass@1": 0.47754491017964074,
861
+ "pass@2": 0.5815400449101793,
862
+ "pass@4": 0.6627141611041132,
863
+ "pass@8": 0.7251319869091699,
864
+ "pass@16": 0.7741932335037112,
865
+ "pass@32": 0.8160539579293532,
866
+ "pass@64": 0.8519449321090409,
867
+ "pass@128": 0.8802395209580839
868
+ }
869
+ }
870
+ },
871
+ "movie_festival_awards": {
872
+ "count": 418816,
873
+ "correct": 354104,
874
+ "answer_accuracy": 0.8454882334963325,
875
+ "avg_response_len": 400.5739202895782,
876
+ "resp_tokens_sum": 167766767,
877
+ "pass_at_k": {
878
+ "pass@1": 0.8454882334963325,
879
+ "pass@2": 0.8870873180698133,
880
+ "pass@4": 0.914805453327734,
881
+ "pass@8": 0.93451152896499,
882
+ "pass@16": 0.9488653753178875,
883
+ "pass@32": 0.9593574045087645,
884
+ "pass@64": 0.967219311432032,
885
+ "pass@128": 0.972799511002445
886
+ },
887
+ "per_op_pass_at_k": {
888
+ "11": {
889
+ "pass@1": 0.9710813492063493,
890
+ "pass@2": 0.9827689507561553,
891
+ "pass@4": 0.9910190773772323,
892
+ "pass@8": 0.9964069864008952,
893
+ "pass@16": 0.9991975166401181,
894
+ "pass@32": 0.9999605809858803,
895
+ "pass@64": 0.9999999808615654,
896
+ "pass@128": 1.0
897
+ },
898
+ "12": {
899
+ "pass@1": 0.9651662844036697,
900
+ "pass@2": 0.9830220297864142,
901
+ "pass@4": 0.9943498286911382,
902
+ "pass@8": 0.9989944241978972,
903
+ "pass@16": 0.9999475847370622,
904
+ "pass@32": 0.9999998481010195,
905
+ "pass@64": 0.9999999999999678,
906
+ "pass@128": 1.0
907
+ },
908
+ "13": {
909
+ "pass@1": 0.9363425925925926,
910
+ "pass@2": 0.9636441929133857,
911
+ "pass@4": 0.9812329428150182,
912
+ "pass@8": 0.9909109265469578,
913
+ "pass@16": 0.995563713627039,
914
+ "pass@32": 0.997463540610219,
915
+ "pass@64": 0.9984545373712423,
916
+ "pass@128": 1.0
917
+ },
918
+ "14": {
919
+ "pass@1": 0.9556982566765578,
920
+ "pass@2": 0.971536645131896,
921
+ "pass@4": 0.9815543184142042,
922
+ "pass@8": 0.9879400706835424,
923
+ "pass@16": 0.9919984009149101,
924
+ "pass@32": 0.9955077699507003,
925
+ "pass@64": 0.9984439818222332,
926
+ "pass@128": 1.0
927
+ },
928
+ "15": {
929
+ "pass@1": 0.9340036651234568,
930
+ "pass@2": 0.9567897437299503,
931
+ "pass@4": 0.9704516715503154,
932
+ "pass@8": 0.9800978369588287,
933
+ "pass@16": 0.9872273677362894,
934
+ "pass@32": 0.9925171450697239,
935
+ "pass@64": 0.9958359460135142,
936
+ "pass@128": 0.9969135802469136
937
+ },
938
+ "16": {
939
+ "pass@1": 0.8969625737463127,
940
+ "pass@2": 0.9258290653380717,
941
+ "pass@4": 0.9432881274243372,
942
+ "pass@8": 0.9546124219600274,
943
+ "pass@16": 0.9626515201381516,
944
+ "pass@32": 0.9696621383207606,
945
+ "pass@64": 0.9756120011655725,
946
+ "pass@128": 0.9793510324483776
947
+ },
948
+ "17": {
949
+ "pass@1": 0.8387142319277109,
950
+ "pass@2": 0.8761247005739499,
951
+ "pass@4": 0.9008967927390097,
952
+ "pass@8": 0.9209284437120231,
953
+ "pass@16": 0.937609642297589,
954
+ "pass@32": 0.9496274880196173,
955
+ "pass@64": 0.9569150319903035,
956
+ "pass@128": 0.9608433734939759
957
+ },
958
+ "18": {
959
+ "pass@1": 0.819304435483871,
960
+ "pass@2": 0.8832704946659896,
961
+ "pass@4": 0.9202918151360103,
962
+ "pass@8": 0.9459392546840153,
963
+ "pass@16": 0.9635935725119584,
964
+ "pass@32": 0.9729778671198072,
965
+ "pass@64": 0.9781526163741832,
966
+ "pass@128": 0.9838709677419355
967
+ },
968
+ "19": {
969
+ "pass@1": 0.6321988293051359,
970
+ "pass@2": 0.7248134827651832,
971
+ "pass@4": 0.7858956545650826,
972
+ "pass@8": 0.828820803601541,
973
+ "pass@16": 0.8605542666697465,
974
+ "pass@32": 0.8848513260783547,
975
+ "pass@64": 0.905053052393738,
976
+ "pass@128": 0.9214501510574018
977
+ },
978
+ "20": {
979
+ "pass@1": 0.5138419669669669,
980
+ "pass@2": 0.6109437439407909,
981
+ "pass@4": 0.6861744289283656,
982
+ "pass@8": 0.7468378163580444,
983
+ "pass@16": 0.7959367036137914,
984
+ "pass@32": 0.8357036484296656,
985
+ "pass@64": 0.8675307030307697,
986
+ "pass@128": 0.8888888888888888
987
+ }
988
+ }
989
+ }
990
+ }
991
+ },
992
+ "total": {
993
+ "answer_accuracy": 0.9147750822368421,
994
+ "avg_loss": 0.0,
995
+ "count": 2432000,
996
+ "validation_metrics": {
997
+ "id": {},
998
+ "ood": {}
999
+ },
1000
+ "pass_at_k": {
1001
+ "pass@1": 0.9147750822368421,
1002
+ "pass@2": 0.9374413269270534,
1003
+ "pass@4": 0.9530235794308524,
1004
+ "pass@8": 0.9640821635009731,
1005
+ "pass@16": 0.9721251575134345,
1006
+ "pass@32": 0.9781388772009632,
1007
+ "pass@64": 0.9826536681488868,
1008
+ "pass@128": 0.986
1009
+ },
1010
+ "per_op_pass_at_k": {
1011
+ "10": {
1012
+ "pass@1": 0.9546875,
1013
+ "pass@2": 0.9643489173228345,
1014
+ "pass@4": 0.9724239796587925,
1015
+ "pass@8": 0.9796451423626065,
1016
+ "pass@16": 0.9858481869460654,
1017
+ "pass@32": 0.9905653033141515,
1018
+ "pass@64": 0.9942351004838736,
1019
+ "pass@128": 0.997
1020
+ },
1021
+ "2": {
1022
+ "pass@1": 1.0,
1023
+ "pass@2": 1.0,
1024
+ "pass@4": 1.0,
1025
+ "pass@8": 1.0,
1026
+ "pass@16": 1.0,
1027
+ "pass@32": 1.0,
1028
+ "pass@64": 1.0,
1029
+ "pass@128": 1.0
1030
+ },
1031
+ "3": {
1032
+ "pass@1": 0.99915625,
1033
+ "pass@2": 0.9997679625984253,
1034
+ "pass@4": 0.9999731251406074,
1035
+ "pass@8": 0.9999995472606525,
1036
+ "pass@16": 0.9999999999231317,
1037
+ "pass@32": 1.0,
1038
+ "pass@64": 1.0,
1039
+ "pass@128": 1.0
1040
+ },
1041
+ "4": {
1042
+ "pass@1": 0.99971875,
1043
+ "pass@2": 0.9999778543307086,
1044
+ "pass@4": 0.9999998386764155,
1045
+ "pass@8": 0.9999999999969994,
1046
+ "pass@16": 1.0,
1047
+ "pass@32": 1.0,
1048
+ "pass@64": 1.0,
1049
+ "pass@128": 1.0
1050
+ },
1051
+ "5": {
1052
+ "pass@1": 0.9941953125,
1053
+ "pass@2": 0.9956927903543309,
1054
+ "pass@4": 0.9968433910761155,
1055
+ "pass@8": 0.9977670040034647,
1056
+ "pass@16": 0.9983917733914977,
1057
+ "pass@32": 0.9987650573014524,
1058
+ "pass@64": 0.9989711801510246,
1059
+ "pass@128": 0.999
1060
+ },
1061
+ "6": {
1062
+ "pass@1": 0.99975,
1063
+ "pass@2": 0.9999803149606299,
1064
+ "pass@4": 0.9999997736220472,
1065
+ "pass@8": 0.9999999999829965,
1066
+ "pass@16": 1.0,
1067
+ "pass@32": 1.0,
1068
+ "pass@64": 1.0,
1069
+ "pass@128": 1.0
1070
+ },
1071
+ "7": {
1072
+ "pass@1": 0.9958359375,
1073
+ "pass@2": 0.9972054625984251,
1074
+ "pass@4": 0.9982031517622797,
1075
+ "pass@8": 0.9990104842344203,
1076
+ "pass@16": 0.9995193774344288,
1077
+ "pass@32": 0.9998284427302075,
1078
+ "pass@64": 0.9999861762904964,
1079
+ "pass@128": 1.0
1080
+ },
1081
+ "8": {
1082
+ "pass@1": 0.9950703125,
1083
+ "pass@2": 0.997607160433071,
1084
+ "pass@4": 0.9989324190101235,
1085
+ "pass@8": 0.9996309201327338,
1086
+ "pass@16": 0.9999226231371163,
1087
+ "pass@32": 0.9999963916027095,
1088
+ "pass@64": 0.9999999990502599,
1089
+ "pass@128": 1.0
1090
+ },
1091
+ "9": {
1092
+ "pass@1": 0.99559375,
1093
+ "pass@2": 0.9978825049212597,
1094
+ "pass@4": 0.9990765218410199,
1095
+ "pass@8": 0.9996709282110962,
1096
+ "pass@16": 0.9999405477474613,
1097
+ "pass@32": 0.9999981844240781,
1098
+ "pass@64": 0.9999999998360332,
1099
+ "pass@128": 1.0
1100
+ },
1101
+ "11": {
1102
+ "pass@1": 0.9726171875,
1103
+ "pass@2": 0.9828142224409449,
1104
+ "pass@4": 0.9897272834645668,
1105
+ "pass@8": 0.994115282605061,
1106
+ "pass@16": 0.9967868462201568,
1107
+ "pass@32": 0.9981416746464655,
1108
+ "pass@64": 0.9987367902594374,
1109
+ "pass@128": 0.999
1110
+ },
1111
+ "12": {
1112
+ "pass@1": 0.9644375,
1113
+ "pass@2": 0.9804958169291337,
1114
+ "pass@4": 0.9905623012748407,
1115
+ "pass@8": 0.9955742374047644,
1116
+ "pass@16": 0.9976946487441701,
1117
+ "pass@32": 0.998880341662968,
1118
+ "pass@64": 0.9996771390867283,
1119
+ "pass@128": 1.0
1120
+ },
1121
+ "13": {
1122
+ "pass@1": 0.94846875,
1123
+ "pass@2": 0.9692981053149601,
1124
+ "pass@4": 0.9827727335958009,
1125
+ "pass@8": 0.9904335216979527,
1126
+ "pass@16": 0.9947883099927657,
1127
+ "pass@32": 0.9972493649171777,
1128
+ "pass@64": 0.9987378705005298,
1129
+ "pass@128": 1.0
1130
+ },
1131
+ "14": {
1132
+ "pass@1": 0.9449453125,
1133
+ "pass@2": 0.964385088582677,
1134
+ "pass@4": 0.9777694221034873,
1135
+ "pass@8": 0.9865351007090998,
1136
+ "pass@16": 0.9922419706883057,
1137
+ "pass@32": 0.9962460277292379,
1138
+ "pass@64": 0.9986672351003253,
1139
+ "pass@128": 1.0
1140
+ },
1141
+ "15": {
1142
+ "pass@1": 0.952953125,
1143
+ "pass@2": 0.9735356791338584,
1144
+ "pass@4": 0.9843826020809897,
1145
+ "pass@8": 0.9903981612161823,
1146
+ "pass@16": 0.9936567666222805,
1147
+ "pass@32": 0.9955643444237633,
1148
+ "pass@64": 0.9966508344175822,
1149
+ "pass@128": 0.997
1150
+ },
1151
+ "16": {
1152
+ "pass@1": 0.8934609375,
1153
+ "pass@2": 0.9216697834645677,
1154
+ "pass@4": 0.9393977767154105,
1155
+ "pass@8": 0.9517931687352534,
1156
+ "pass@16": 0.96139777462629,
1157
+ "pass@32": 0.9693210349487325,
1158
+ "pass@64": 0.9751328706018372,
1159
+ "pass@128": 0.979
1160
+ },
1161
+ "17": {
1162
+ "pass@1": 0.8661875,
1163
+ "pass@2": 0.9038288631889774,
1164
+ "pass@4": 0.9277408284589423,
1165
+ "pass@8": 0.9448044024114316,
1166
+ "pass@16": 0.9568565852772714,
1167
+ "pass@32": 0.9646994651551266,
1168
+ "pass@64": 0.9694077197479471,
1169
+ "pass@128": 0.972
1170
+ },
1171
+ "18": {
1172
+ "pass@1": 0.788859375,
1173
+ "pass@2": 0.8561178641732294,
1174
+ "pass@4": 0.8988476714473197,
1175
+ "pass@8": 0.9267583655390567,
1176
+ "pass@16": 0.9448361294806787,
1177
+ "pass@32": 0.9568568515114735,
1178
+ "pass@64": 0.9657552890983766,
1179
+ "pass@128": 0.973
1180
+ },
1181
+ "19": {
1182
+ "pass@1": 0.625640625,
1183
+ "pass@2": 0.7169927411417328,
1184
+ "pass@4": 0.7811060572740908,
1185
+ "pass@8": 0.8285917496219818,
1186
+ "pass@16": 0.8654698909087529,
1187
+ "pass@32": 0.8941006950628526,
1188
+ "pass@64": 0.9155477279248722,
1189
+ "pass@128": 0.932
1190
+ },
1191
+ "20": {
1192
+ "pass@1": 0.4891484375,
1193
+ "pass@2": 0.5897840797244098,
1194
+ "pass@4": 0.6696891319835014,
1195
+ "pass@8": 0.7328330903927104,
1196
+ "pass@16": 0.7830265616151493,
1197
+ "pass@32": 0.824425487387794,
1198
+ "pass@64": 0.8589137622794993,
1199
+ "pass@128": 0.886
1200
+ }
1201
+ },
1202
+ "per_op_accuracy": {
1203
+ "10": 0.9546875,
1204
+ "2": 1.0,
1205
+ "3": 0.99915625,
1206
+ "4": 0.99971875,
1207
+ "5": 0.9941953125,
1208
+ "6": 0.99975,
1209
+ "7": 0.9958359375,
1210
+ "8": 0.9950703125,
1211
+ "9": 0.99559375,
1212
+ "11": 0.9726171875,
1213
+ "12": 0.9644375,
1214
+ "13": 0.94846875,
1215
+ "14": 0.9449453125,
1216
+ "15": 0.952953125,
1217
+ "16": 0.8934609375,
1218
+ "17": 0.8661875,
1219
+ "18": 0.788859375,
1220
+ "19": 0.625640625,
1221
+ "20": 0.4891484375
1222
+ },
1223
+ "per_op_avg_response_len": {
1224
+ "10": 281.6347734375,
1225
+ "2": 115.6326015625,
1226
+ "3": 144.829234375,
1227
+ "4": 159.923921875,
1228
+ "5": 173.2866484375,
1229
+ "6": 198.9441953125,
1230
+ "7": 224.1663515625,
1231
+ "8": 243.7276171875,
1232
+ "9": 259.660875,
1233
+ "11": 300.8103125,
1234
+ "12": 313.388375,
1235
+ "13": 334.3829921875,
1236
+ "14": 361.2994765625,
1237
+ "15": 381.435625,
1238
+ "16": 390.2542265625,
1239
+ "17": 410.935984375,
1240
+ "18": 425.279296875,
1241
+ "19": 422.265296875,
1242
+ "20": 430.9158984375
1243
+ },
1244
+ "per_op_avg_loss": {},
1245
+ "per_op_length": {
1246
+ "10": 281.6347734375,
1247
+ "2": 115.6326015625,
1248
+ "3": 144.829234375,
1249
+ "4": 159.923921875,
1250
+ "5": 173.2866484375,
1251
+ "6": 198.9441953125,
1252
+ "7": 224.1663515625,
1253
+ "8": 243.7276171875,
1254
+ "9": 259.660875,
1255
+ "11": 300.8103125,
1256
+ "12": 313.388375,
1257
+ "13": 334.3829921875,
1258
+ "14": 361.2994765625,
1259
+ "15": 381.435625,
1260
+ "16": 390.2542265625,
1261
+ "17": 410.935984375,
1262
+ "18": 425.279296875,
1263
+ "19": 422.265296875,
1264
+ "20": 430.9158984375
1265
+ },
1266
+ "per_op_loss": {},
1267
+ "per_template": {
1268
+ "crazy_zootopia": {
1269
+ "count": 809728,
1270
+ "correct": 738018,
1271
+ "answer_accuracy": 0.9114393969332911,
1272
+ "avg_response_len": 280.1749056473285,
1273
+ "resp_tokens_sum": 226865466,
1274
+ "pass_at_k": {
1275
+ "pass@1": 0.9114393969332911,
1276
+ "pass@2": 0.9346978341788974,
1277
+ "pass@4": 0.9510085321100552,
1278
+ "pass@8": 0.9624914679892927,
1279
+ "pass@16": 0.9708110810206952,
1280
+ "pass@32": 0.9770193310184669,
1281
+ "pass@64": 0.981604927339997,
1282
+ "pass@128": 0.9851406892190958
1283
+ },
1284
+ "per_op_pass_at_k": {
1285
+ "10": {
1286
+ "pass@1": 0.9615366887905604,
1287
+ "pass@2": 0.970145808654449,
1288
+ "pass@4": 0.9771259859110534,
1289
+ "pass@8": 0.9837142589656627,
1290
+ "pass@16": 0.9897806295670789,
1291
+ "pass@32": 0.9934434017257641,
1292
+ "pass@64": 0.9955847044260153,
1293
+ "pass@128": 0.9970501474926253
1294
+ },
1295
+ "2": {
1296
+ "pass@1": 1.0,
1297
+ "pass@2": 1.0,
1298
+ "pass@4": 1.0,
1299
+ "pass@8": 1.0,
1300
+ "pass@16": 1.0,
1301
+ "pass@32": 1.0,
1302
+ "pass@64": 1.0,
1303
+ "pass@128": 1.0
1304
+ },
1305
+ "3": {
1306
+ "pass@1": 0.9997610856269113,
1307
+ "pass@2": 0.9999864552481399,
1308
+ "pass@4": 0.9999999638806617,
1309
+ "pass@8": 0.9999999999999809,
1310
+ "pass@16": 1.0,
1311
+ "pass@32": 1.0,
1312
+ "pass@64": 1.0,
1313
+ "pass@128": 1.0
1314
+ },
1315
+ "4": {
1316
+ "pass@1": 0.99931640625,
1317
+ "pass@2": 0.9999350239911416,
1318
+ "pass@4": 0.9999994973284589,
1319
+ "pass@8": 0.999999999990623,
1320
+ "pass@16": 1.0,
1321
+ "pass@32": 1.0,
1322
+ "pass@64": 1.0,
1323
+ "pass@128": 1.0
1324
+ },
1325
+ "5": {
1326
+ "pass@1": 0.9954861111111111,
1327
+ "pass@2": 0.9972468285214349,
1328
+ "pass@4": 0.9985486585010207,
1329
+ "pass@8": 0.9994671341886722,
1330
+ "pass@16": 0.9999236250321564,
1331
+ "pass@32": 0.9999990493973,
1332
+ "pass@64": 0.9999999999949286,
1333
+ "pass@128": 1.0
1334
+ },
1335
+ "6": {
1336
+ "pass@1": 0.9995555763473054,
1337
+ "pass@2": 0.9999499033429206,
1338
+ "pass@4": 0.9999993320445721,
1339
+ "pass@8": 0.9999999999490911,
1340
+ "pass@16": 1.0,
1341
+ "pass@32": 1.0,
1342
+ "pass@64": 1.0,
1343
+ "pass@128": 1.0
1344
+ },
1345
+ "7": {
1346
+ "pass@1": 0.9964404585798816,
1347
+ "pass@2": 0.9978735207100592,
1348
+ "pass@4": 0.9986706386183974,
1349
+ "pass@8": 0.9994230191252826,
1350
+ "pass@16": 0.9999007629980622,
1351
+ "pass@32": 0.9999981593967747,
1352
+ "pass@64": 0.99999999996853,
1353
+ "pass@128": 1.0
1354
+ },
1355
+ "8": {
1356
+ "pass@1": 0.997245592948718,
1357
+ "pass@2": 0.9984009848828992,
1358
+ "pass@4": 0.9992322474113812,
1359
+ "pass@8": 0.9998262245762686,
1360
+ "pass@16": 0.9999926289511722,
1361
+ "pass@32": 0.9999999947902106,
1362
+ "pass@64": 1.0,
1363
+ "pass@128": 1.0
1364
+ },
1365
+ "9": {
1366
+ "pass@1": 0.9950704225352113,
1367
+ "pass@2": 0.9983818759010756,
1368
+ "pass@4": 0.999779442534472,
1369
+ "pass@8": 0.9999935759719568,
1370
+ "pass@16": 0.9999999938621692,
1371
+ "pass@32": 0.9999999999999997,
1372
+ "pass@64": 1.0,
1373
+ "pass@128": 1.0
1374
+ },
1375
+ "11": {
1376
+ "pass@1": 0.9698123229461756,
1377
+ "pass@2": 0.981584311079387,
1378
+ "pass@4": 0.9891040887948495,
1379
+ "pass@8": 0.9937797636155625,
1380
+ "pass@16": 0.9970789483598115,
1381
+ "pass@32": 0.999223562425918,
1382
+ "pass@64": 0.9999570534856826,
1383
+ "pass@128": 1.0
1384
+ },
1385
+ "12": {
1386
+ "pass@1": 0.9659030720338984,
1387
+ "pass@2": 0.9809874632990792,
1388
+ "pass@4": 0.9906215364498931,
1389
+ "pass@8": 0.9956137072056146,
1390
+ "pass@16": 0.9978803736651605,
1391
+ "pass@32": 0.9993246177441057,
1392
+ "pass@64": 0.9999568688255516,
1393
+ "pass@128": 1.0
1394
+ },
1395
+ "13": {
1396
+ "pass@1": 0.9498922413793104,
1397
+ "pass@2": 0.9708758608347934,
1398
+ "pass@4": 0.9840897281060871,
1399
+ "pass@8": 0.9909108589255634,
1400
+ "pass@16": 0.9943999521503089,
1401
+ "pass@32": 0.9963005415376021,
1402
+ "pass@64": 0.9980499904733999,
1403
+ "pass@128": 1.0
1404
+ },
1405
+ "14": {
1406
+ "pass@1": 0.9233839563862928,
1407
+ "pass@2": 0.944520460789364,
1408
+ "pass@4": 0.9611923819102052,
1409
+ "pass@8": 0.9751079976868544,
1410
+ "pass@16": 0.9861293435926446,
1411
+ "pass@32": 0.9935272719026856,
1412
+ "pass@64": 0.9975030863628863,
1413
+ "pass@128": 1.0
1414
+ },
1415
+ "15": {
1416
+ "pass@1": 0.9595375722543352,
1417
+ "pass@2": 0.9784015719584908,
1418
+ "pass@4": 0.987961396353635,
1419
+ "pass@8": 0.9923778119086278,
1420
+ "pass@16": 0.9938310119401556,
1421
+ "pass@32": 0.9941908530213401,
1422
+ "pass@64": 0.9942196182961773,
1423
+ "pass@128": 0.9942196531791907
1424
+ },
1425
+ "16": {
1426
+ "pass@1": 0.8793850806451613,
1427
+ "pass@2": 0.9133687611125221,
1428
+ "pass@4": 0.9350571322737883,
1429
+ "pass@8": 0.9489252481008612,
1430
+ "pass@16": 0.9594660322806725,
1431
+ "pass@32": 0.9677192403291304,
1432
+ "pass@64": 0.9722136540329196,
1433
+ "pass@128": 0.9741935483870968
1434
+ },
1435
+ "17": {
1436
+ "pass@1": 0.8896992413294798,
1437
+ "pass@2": 0.9255197191752769,
1438
+ "pass@4": 0.9464512051600483,
1439
+ "pass@8": 0.9595738090472379,
1440
+ "pass@16": 0.9673121876199731,
1441
+ "pass@32": 0.9725731938539892,
1442
+ "pass@64": 0.9768482847119901,
1443
+ "pass@128": 0.9797687861271677
1444
+ },
1445
+ "18": {
1446
+ "pass@1": 0.7444419642857143,
1447
+ "pass@2": 0.8136916479190104,
1448
+ "pass@4": 0.8625618206652741,
1449
+ "pass@8": 0.8958082898451949,
1450
+ "pass@16": 0.9174575405950798,
1451
+ "pass@32": 0.9337781303810576,
1452
+ "pass@64": 0.947397000627292,
1453
+ "pass@128": 0.9571428571428572
1454
+ },
1455
+ "19": {
1456
+ "pass@1": 0.6253753753753754,
1457
+ "pass@2": 0.7184758577475104,
1458
+ "pass@4": 0.7833039738275956,
1459
+ "pass@8": 0.8296772377534075,
1460
+ "pass@16": 0.8660549147719705,
1461
+ "pass@32": 0.8940814351693145,
1462
+ "pass@64": 0.9133406551952218,
1463
+ "pass@128": 0.9279279279279279
1464
+ },
1465
+ "20": {
1466
+ "pass@1": 0.4760932807807808,
1467
+ "pass@2": 0.5768932071835613,
1468
+ "pass@4": 0.6601997517765237,
1469
+ "pass@8": 0.7265525943478015,
1470
+ "pass@16": 0.7789762742387952,
1471
+ "pass@32": 0.8215439955324653,
1472
+ "pass@64": 0.8572865791166149,
1473
+ "pass@128": 0.8888888888888888
1474
+ }
1475
+ }
1476
+ },
1477
+ "teachers_in_school": {
1478
+ "count": 821120,
1479
+ "correct": 753428,
1480
+ "answer_accuracy": 0.9175613795791114,
1481
+ "avg_response_len": 289.52658198558066,
1482
+ "resp_tokens_sum": 237736067,
1483
+ "pass_at_k": {
1484
+ "pass@1": 0.9175613795791114,
1485
+ "pass@2": 0.9393609304901669,
1486
+ "pass@4": 0.9544253548538294,
1487
+ "pass@8": 0.9651838128249977,
1488
+ "pass@16": 0.9731036723828017,
1489
+ "pass@32": 0.9792285383144879,
1490
+ "pass@64": 0.9839183408625037,
1491
+ "pass@128": 0.987373343725643
1492
+ },
1493
+ "per_op_pass_at_k": {
1494
+ "10": {
1495
+ "pass@1": 0.9446654524539877,
1496
+ "pass@2": 0.9550259498333415,
1497
+ "pass@4": 0.9634138444542589,
1498
+ "pass@8": 0.970866877957459,
1499
+ "pass@16": 0.9782378206275941,
1500
+ "pass@32": 0.9857900637806933,
1501
+ "pass@64": 0.9923585282128631,
1502
+ "pass@128": 0.9969325153374233
1503
+ },
1504
+ "2": {
1505
+ "pass@1": 1.0,
1506
+ "pass@2": 1.0,
1507
+ "pass@4": 1.0,
1508
+ "pass@8": 1.0,
1509
+ "pass@16": 1.0,
1510
+ "pass@32": 1.0,
1511
+ "pass@64": 1.0,
1512
+ "pass@128": 1.0
1513
+ },
1514
+ "3": {
1515
+ "pass@1": 0.9988873106060606,
1516
+ "pass@2": 0.9997856269386781,
1517
+ "pass@4": 0.9999895822681255,
1518
+ "pass@8": 0.9999999777033803,
1519
+ "pass@16": 0.9999999999999803,
1520
+ "pass@32": 1.0,
1521
+ "pass@64": 1.0,
1522
+ "pass@128": 1.0
1523
+ },
1524
+ "4": {
1525
+ "pass@1": 0.9999537721893491,
1526
+ "pass@2": 0.999999636001491,
1527
+ "pass@4": 1.0,
1528
+ "pass@8": 1.0,
1529
+ "pass@16": 1.0,
1530
+ "pass@32": 1.0,
1531
+ "pass@64": 1.0,
1532
+ "pass@128": 1.0
1533
+ },
1534
+ "5": {
1535
+ "pass@1": 0.9965579710144927,
1536
+ "pass@2": 0.9972633515919205,
1537
+ "pass@4": 0.9975327839454851,
1538
+ "pass@8": 0.9979120550709301,
1539
+ "pass@16": 0.9985302315822023,
1540
+ "pass@32": 0.9993303337082865,
1541
+ "pass@64": 0.9999164669633687,
1542
+ "pass@128": 1.0
1543
+ },
1544
+ "6": {
1545
+ "pass@1": 0.9997313753581661,
1546
+ "pass@2": 0.9999915393813595,
1547
+ "pass@4": 0.9999999905993125,
1548
+ "pass@8": 1.0,
1549
+ "pass@16": 1.0,
1550
+ "pass@32": 1.0,
1551
+ "pass@64": 1.0,
1552
+ "pass@128": 1.0
1553
+ },
1554
+ "7": {
1555
+ "pass@1": 0.9975162572254336,
1556
+ "pass@2": 0.9985822931364069,
1557
+ "pass@4": 0.9993384239181086,
1558
+ "pass@8": 0.9998572295938166,
1559
+ "pass@16": 0.9999945349140869,
1560
+ "pass@32": 0.9999999969725001,
1561
+ "pass@64": 1.0,
1562
+ "pass@128": 1.0
1563
+ },
1564
+ "8": {
1565
+ "pass@1": 0.9966769366197183,
1566
+ "pass@2": 0.9978297937229678,
1567
+ "pass@4": 0.9984739589769589,
1568
+ "pass@8": 0.9991927685739189,
1569
+ "pass@16": 0.9997893254704586,
1570
+ "pass@32": 0.999989840105361,
1571
+ "pass@64": 0.9999999973246758,
1572
+ "pass@128": 1.0
1573
+ },
1574
+ "9": {
1575
+ "pass@1": 0.9973100673652695,
1576
+ "pass@2": 0.9978701553585743,
1577
+ "pass@4": 0.9984959510113631,
1578
+ "pass@8": 0.9992628054872507,
1579
+ "pass@16": 0.9998367378399854,
1580
+ "pass@32": 0.9999945907477397,
1581
+ "pass@64": 0.9999999995090815,
1582
+ "pass@128": 1.0
1583
+ },
1584
+ "11": {
1585
+ "pass@1": 0.9770566641566265,
1586
+ "pass@2": 0.9841648829570252,
1587
+ "pass@4": 0.989164249235412,
1588
+ "pass@8": 0.9922976666641117,
1589
+ "pass@16": 0.9941890352635745,
1590
+ "pass@32": 0.9952655846372421,
1591
+ "pass@64": 0.9962408325530068,
1592
+ "pass@128": 0.9969879518072289
1593
+ },
1594
+ "12": {
1595
+ "pass@1": 0.9620640673981191,
1596
+ "pass@2": 0.9773606620097254,
1597
+ "pass@4": 0.9866140545127782,
1598
+ "pass@8": 0.9920244775588233,
1599
+ "pass@16": 0.9951791105256566,
1600
+ "pass@32": 0.9972397387226369,
1601
+ "pass@64": 0.9990357602586,
1602
+ "pass@128": 1.0
1603
+ },
1604
+ "13": {
1605
+ "pass@1": 0.9582020308123249,
1606
+ "pass@2": 0.9730195720020293,
1607
+ "pass@4": 0.9829933805543213,
1608
+ "pass@8": 0.9895737184859488,
1609
+ "pass@16": 0.9944316023575817,
1610
+ "pass@32": 0.9979028151511814,
1611
+ "pass@64": 0.9996096734768417,
1612
+ "pass@128": 1.0
1613
+ },
1614
+ "14": {
1615
+ "pass@1": 0.9545869883040936,
1616
+ "pass@2": 0.9759829569001243,
1617
+ "pass@4": 0.9895990122945156,
1618
+ "pass@8": 0.9958761100329401,
1619
+ "pass@16": 0.9982192698442767,
1620
+ "pass@32": 0.9995253069447078,
1621
+ "pass@64": 0.9999798903618302,
1622
+ "pass@128": 1.0
1623
+ },
1624
+ "15": {
1625
+ "pass@1": 0.964654356060606,
1626
+ "pass@2": 0.9848753280839894,
1627
+ "pass@4": 0.994307931394939,
1628
+ "pass@8": 0.9984355730943542,
1629
+ "pass@16": 0.9997865737709953,
1630
+ "pass@32": 0.999996225078149,
1631
+ "pass@64": 0.9999999999355342,
1632
+ "pass@128": 1.0
1633
+ },
1634
+ "16": {
1635
+ "pass@1": 0.9025106837606838,
1636
+ "pass@2": 0.9249840865244409,
1637
+ "pass@4": 0.9394740470475377,
1638
+ "pass@8": 0.951603221594124,
1639
+ "pass@16": 0.9618929894371758,
1640
+ "pass@32": 0.9704062836352245,
1641
+ "pass@64": 0.9772483460299233,
1642
+ "pass@128": 0.9829059829059829
1643
+ },
1644
+ "17": {
1645
+ "pass@1": 0.8692498059006211,
1646
+ "pass@2": 0.9090858377757125,
1647
+ "pass@4": 0.9353135909447651,
1648
+ "pass@8": 0.9535516185363221,
1649
+ "pass@16": 0.965466357509199,
1650
+ "pass@32": 0.9717789256494813,
1651
+ "pass@64": 0.9742932379404277,
1652
+ "pass@128": 0.9751552795031055
1653
+ },
1654
+ "18": {
1655
+ "pass@1": 0.8068244485294118,
1656
+ "pass@2": 0.8750351001621121,
1657
+ "pass@4": 0.9166487397714989,
1658
+ "pass@8": 0.9411302798270424,
1659
+ "pass@16": 0.9559175964520414,
1660
+ "pass@32": 0.9659157855028336,
1661
+ "pass@64": 0.9733500817730232,
1662
+ "pass@128": 0.9794117647058823
1663
+ },
1664
+ "19": {
1665
+ "pass@1": 0.6194428943452381,
1666
+ "pass@2": 0.7078185051087363,
1667
+ "pass@4": 0.7742094414537468,
1668
+ "pass@8": 0.8272903079106774,
1669
+ "pass@16": 0.8697325655416732,
1670
+ "pass@32": 0.9032315125581434,
1671
+ "pass@64": 0.9280735994123079,
1672
+ "pass@128": 0.9464285714285714
1673
+ },
1674
+ "20": {
1675
+ "pass@1": 0.47754491017964074,
1676
+ "pass@2": 0.5815400449101793,
1677
+ "pass@4": 0.6627141611041132,
1678
+ "pass@8": 0.7251319869091699,
1679
+ "pass@16": 0.7741932335037112,
1680
+ "pass@32": 0.8160539579293532,
1681
+ "pass@64": 0.8519449321090409,
1682
+ "pass@128": 0.8802395209580839
1683
+ }
1684
+ }
1685
+ },
1686
+ "movie_festival_awards": {
1687
+ "count": 801152,
1688
+ "correct": 733287,
1689
+ "answer_accuracy": 0.9152907313468606,
1690
+ "avg_response_len": 310.44483568661127,
1691
+ "resp_tokens_sum": 248713501,
1692
+ "pass_at_k": {
1693
+ "pass@1": 0.9152907313468606,
1694
+ "pass@2": 0.9382467396555126,
1695
+ "pass@4": 0.9536234835709834,
1696
+ "pass@8": 0.9645607797964179,
1697
+ "pass@16": 0.9724503971693556,
1698
+ "pass@32": 0.9781535877149617,
1699
+ "pass@64": 0.9824174417387895,
1700
+ "pass@128": 0.9854609362517974
1701
+ },
1702
+ "per_op_pass_at_k": {
1703
+ "10": {
1704
+ "pass@1": 0.9575093283582089,
1705
+ "pass@2": 0.9675553090844993,
1706
+ "pass@4": 0.9764339019189767,
1707
+ "pass@8": 0.9840698697287039,
1708
+ "pass@16": 0.9892746985021801,
1709
+ "pass@32": 0.9922997890645133,
1710
+ "pass@64": 0.9946955387643621,
1711
+ "pass@128": 0.9970149253731343
1712
+ },
1713
+ "2": {
1714
+ "pass@1": 1.0,
1715
+ "pass@2": 1.0,
1716
+ "pass@4": 1.0,
1717
+ "pass@8": 1.0,
1718
+ "pass@16": 1.0,
1719
+ "pass@32": 1.0,
1720
+ "pass@64": 1.0,
1721
+ "pass@128": 1.0
1722
+ },
1723
+ "3": {
1724
+ "pass@1": 0.9988383746355685,
1725
+ "pass@2": 0.9995426671793577,
1726
+ "pass@4": 0.9999317049654508,
1727
+ "pass@8": 0.999998701511788,
1728
+ "pass@16": 0.9999999997759129,
1729
+ "pass@32": 1.0,
1730
+ "pass@64": 1.0,
1731
+ "pass@128": 1.0
1732
+ },
1733
+ "4": {
1734
+ "pass@1": 0.9998629385964912,
1735
+ "pass@2": 0.9999964025878345,
1736
+ "pass@4": 0.9999999986295574,
1737
+ "pass@8": 1.0,
1738
+ "pass@16": 1.0,
1739
+ "pass@32": 1.0,
1740
+ "pass@64": 1.0,
1741
+ "pass@128": 1.0
1742
+ },
1743
+ "5": {
1744
+ "pass@1": 0.9906020220588235,
1745
+ "pass@2": 0.9926593619731356,
1746
+ "pass@4": 0.9945639799620636,
1747
+ "pass@8": 0.9960446992193006,
1748
+ "pass@16": 0.9968320635603195,
1749
+ "pass@32": 0.997048210623365,
1750
+ "pass@64": 0.9970588207360587,
1751
+ "pass@128": 0.9970588235294118
1752
+ },
1753
+ "6": {
1754
+ "pass@1": 0.9999753548895899,
1755
+ "pass@2": 1.0,
1756
+ "pass@4": 1.0,
1757
+ "pass@8": 1.0,
1758
+ "pass@16": 1.0,
1759
+ "pass@32": 1.0,
1760
+ "pass@64": 1.0,
1761
+ "pass@128": 1.0
1762
+ },
1763
+ "7": {
1764
+ "pass@1": 0.9933494857594937,
1765
+ "pass@2": 0.9949833518140139,
1766
+ "pass@4": 0.9964600671949234,
1767
+ "pass@8": 0.9976420959829561,
1768
+ "pass@16": 0.9985911723443348,
1769
+ "pass@32": 0.9994590693089006,
1770
+ "pass@64": 0.9999562541175095,
1771
+ "pass@128": 1.0
1772
+ },
1773
+ "8": {
1774
+ "pass@1": 0.9913194444444444,
1775
+ "pass@2": 0.9966260551890473,
1776
+ "pass@4": 0.9991402473902474,
1777
+ "pass@8": 0.9999150306942846,
1778
+ "pass@16": 0.9999991362232366,
1779
+ "pass@32": 0.9999999999722541,
1780
+ "pass@64": 1.0,
1781
+ "pass@128": 1.0
1782
+ },
1783
+ "9": {
1784
+ "pass@1": 0.9943478697749196,
1785
+ "pass@2": 0.9973257462592097,
1786
+ "pass@4": 0.9988976594967428,
1787
+ "pass@8": 0.9997409379688414,
1788
+ "pass@16": 0.9999841784174797,
1789
+ "pass@32": 0.999999971428724,
1790
+ "pass@64": 0.9999999999999997,
1791
+ "pass@128": 1.0
1792
+ },
1793
+ "11": {
1794
+ "pass@1": 0.9710813492063493,
1795
+ "pass@2": 0.9827689507561553,
1796
+ "pass@4": 0.9910190773772323,
1797
+ "pass@8": 0.9964069864008952,
1798
+ "pass@16": 0.9991975166401181,
1799
+ "pass@32": 0.9999605809858803,
1800
+ "pass@64": 0.9999999808615654,
1801
+ "pass@128": 1.0
1802
+ },
1803
+ "12": {
1804
+ "pass@1": 0.9651662844036697,
1805
+ "pass@2": 0.9830220297864142,
1806
+ "pass@4": 0.9943498286911382,
1807
+ "pass@8": 0.9989944241978972,
1808
+ "pass@16": 0.9999475847370622,
1809
+ "pass@32": 0.9999998481010195,
1810
+ "pass@64": 0.9999999999999678,
1811
+ "pass@128": 1.0
1812
+ },
1813
+ "13": {
1814
+ "pass@1": 0.9363425925925926,
1815
+ "pass@2": 0.9636441929133857,
1816
+ "pass@4": 0.9812329428150182,
1817
+ "pass@8": 0.9909109265469578,
1818
+ "pass@16": 0.995563713627039,
1819
+ "pass@32": 0.997463540610219,
1820
+ "pass@64": 0.9984545373712423,
1821
+ "pass@128": 1.0
1822
+ },
1823
+ "14": {
1824
+ "pass@1": 0.9556982566765578,
1825
+ "pass@2": 0.971536645131896,
1826
+ "pass@4": 0.9815543184142042,
1827
+ "pass@8": 0.9879400706835424,
1828
+ "pass@16": 0.9919984009149101,
1829
+ "pass@32": 0.9955077699507003,
1830
+ "pass@64": 0.9984439818222332,
1831
+ "pass@128": 1.0
1832
+ },
1833
+ "15": {
1834
+ "pass@1": 0.9340036651234568,
1835
+ "pass@2": 0.9567897437299503,
1836
+ "pass@4": 0.9704516715503154,
1837
+ "pass@8": 0.9800978369588287,
1838
+ "pass@16": 0.9872273677362894,
1839
+ "pass@32": 0.9925171450697239,
1840
+ "pass@64": 0.9958359460135142,
1841
+ "pass@128": 0.9969135802469136
1842
+ },
1843
+ "16": {
1844
+ "pass@1": 0.8969625737463127,
1845
+ "pass@2": 0.9258290653380717,
1846
+ "pass@4": 0.9432881274243372,
1847
+ "pass@8": 0.9546124219600274,
1848
+ "pass@16": 0.9626515201381516,
1849
+ "pass@32": 0.9696621383207606,
1850
+ "pass@64": 0.9756120011655725,
1851
+ "pass@128": 0.9793510324483776
1852
+ },
1853
+ "17": {
1854
+ "pass@1": 0.8387142319277109,
1855
+ "pass@2": 0.8761247005739499,
1856
+ "pass@4": 0.9008967927390097,
1857
+ "pass@8": 0.9209284437120231,
1858
+ "pass@16": 0.937609642297589,
1859
+ "pass@32": 0.9496274880196173,
1860
+ "pass@64": 0.9569150319903035,
1861
+ "pass@128": 0.9608433734939759
1862
+ },
1863
+ "18": {
1864
+ "pass@1": 0.819304435483871,
1865
+ "pass@2": 0.8832704946659896,
1866
+ "pass@4": 0.9202918151360103,
1867
+ "pass@8": 0.9459392546840153,
1868
+ "pass@16": 0.9635935725119584,
1869
+ "pass@32": 0.9729778671198072,
1870
+ "pass@64": 0.9781526163741832,
1871
+ "pass@128": 0.9838709677419355
1872
+ },
1873
+ "19": {
1874
+ "pass@1": 0.6321988293051359,
1875
+ "pass@2": 0.7248134827651832,
1876
+ "pass@4": 0.7858956545650826,
1877
+ "pass@8": 0.828820803601541,
1878
+ "pass@16": 0.8605542666697465,
1879
+ "pass@32": 0.8848513260783547,
1880
+ "pass@64": 0.905053052393738,
1881
+ "pass@128": 0.9214501510574018
1882
+ },
1883
+ "20": {
1884
+ "pass@1": 0.5138419669669669,
1885
+ "pass@2": 0.6109437439407909,
1886
+ "pass@4": 0.6861744289283656,
1887
+ "pass@8": 0.7468378163580444,
1888
+ "pass@16": 0.7959367036137914,
1889
+ "pass@32": 0.8357036484296656,
1890
+ "pass@64": 0.8675307030307697,
1891
+ "pass@128": 0.8888888888888888
1892
+ }
1893
+ }
1894
+ }
1895
+ }
1896
+ }
1897
+ }
Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_ood_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb18d559562580a79812b126ac3310f0999c5cc942f0954d4c7b557696c292e3
3
+ size 2708951048
Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_id_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ab4985f208a74ba69c0cafcd566c44396812b21d93da2410cc3bacad99f1ab
3
+ size 373215241
Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_ood_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8a42cbbf5bba96958a9c3cf17f5ddbfc0a59a3aa61c3da10ef4fa15cd02490
3
+ size 423543596
Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/composition_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/composition/op-difficulty-10B/graphs", "generated_path": "results/Qwen3-100M-midtrain-diff_ar-block8/composition", "results_dir": "results/Qwen3-100M-midtrain-diff_ar-block8/composition/graphs", "per_file": [{"file": "results/Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1024156, "value_mismatch": 9626, "dependency_mismatch": 126467, "answer_mismatch": 8447, "extra_nodes": 11789, "missing_nodes": 9372, "perfect_with_extra": 832, "unused_gold_entries": 10000, "template_stats": {"crazy_zootopia": {"total": 379008, "perfect": 337828, "dependency_mismatch": 40795, "value_mismatch": 2837, "answer_mismatch": 2396, "extra_nodes": 3565, "missing_nodes": 2829, "perfect_with_extra": 194}, "teachers_in_school": {"total": 390656, "perfect": 346878, "value_mismatch": 3053, "dependency_mismatch": 43324, "answer_mismatch": 2898, "extra_nodes": 3875, "perfect_with_extra": 245, "missing_nodes": 3417}, "movie_festival_awards": {"total": 382336, "perfect": 339450, "dependency_mismatch": 42348, "missing_nodes": 3126, "extra_nodes": 4349, "perfect_with_extra": 393, "value_mismatch": 3736, "answer_mismatch": 3153}}, "results_path": "results/Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/Qwen3-100M-midtrain-diff_ar-block8/composition/checkpoint-38645_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 619058, "value_mismatch": 253560, "dependency_mismatch": 638256, "answer_mismatch": 198821, "extra_nodes": 43329, "missing_nodes": 193491, "perfect_with_extra": 424, "unused_gold_entries": 9000, "template_stats": {"crazy_zootopia": {"total": 430720, "perfect": 206999, "extra_nodes": 16615, "perfect_with_extra": 50, "value_mismatch": 87251, "dependency_mismatch": 215764, "answer_mismatch": 69314, "missing_nodes": 70355}, "movie_festival_awards": {"total": 418816, "perfect": 204316, "value_mismatch": 82684, "dependency_mismatch": 206999, "answer_mismatch": 64712, "extra_nodes": 14071, "missing_nodes": 59687, "perfect_with_extra": 220}, "teachers_in_school": {"total": 430464, "perfect": 207743, "value_mismatch": 83625, "dependency_mismatch": 215493, "answer_mismatch": 64795, "missing_nodes": 63449, "extra_nodes": 12643, "perfect_with_extra": 154}}, "results_path": "results/Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/checkpoint-38645_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 1643214, "value_mismatch": 263186, "dependency_mismatch": 764723, "answer_mismatch": 207268, "extra_nodes": 55118, "missing_nodes": 202863, "perfect_with_extra": 1256, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/Qwen3-100M-midtrain-diff_ar-block8/composition/graphs/composition_score_report.jsonl", "template_stats": {"crazy_zootopia": {"total": 809728, "perfect": 544827, "dependency_mismatch": 256559, "value_mismatch": 90088, "answer_mismatch": 71710, "extra_nodes": 20180, "missing_nodes": 73184, "perfect_with_extra": 244}, "teachers_in_school": {"total": 821120, "perfect": 554621, "value_mismatch": 86678, "dependency_mismatch": 258817, "answer_mismatch": 67693, "extra_nodes": 16518, "perfect_with_extra": 399, "missing_nodes": 66866}, "movie_festival_awards": {"total": 801152, "perfect": 543766, "dependency_mismatch": 249347, "missing_nodes": 62813, "extra_nodes": 18420, "perfect_with_extra": 613, "value_mismatch": 86420, "answer_mismatch": 67865}}}}