DatPySci commited on
Commit
6abc6b3
·
verified ·
1 Parent(s): 0df005c

Upload folder using huggingface_hub (part 2)

Browse files
Files changed (34) hide show
  1. .gitattributes +5 -0
  2. results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl +3 -0
  3. results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2_score_report.jsonl +1 -0
  4. results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/results.json +910 -0
  5. results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/summary.csv +2 -0
  6. results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/summary.json +245 -0
  7. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl +3 -0
  8. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_metrics.json +1077 -0
  9. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl +3 -0
  10. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl +3 -0
  11. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl +3 -0
  12. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2_score_report.jsonl +1 -0
  13. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/results.json +910 -0
  14. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/summary.csv +2 -0
  15. results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/summary.json +245 -0
  16. results/context/graphs/op10_1k_graphs.jsonl +0 -0
  17. results/context/graphs/op11_1k_graphs.jsonl +0 -0
  18. results/context/graphs/op12_1k_graphs.jsonl +0 -0
  19. results/context/graphs/op13_1k_graphs.jsonl +0 -0
  20. results/context/graphs/op14_1k_graphs.jsonl +0 -0
  21. results/context/graphs/op15_1k_graphs.jsonl +0 -0
  22. results/context/graphs/op16_1k_graphs.jsonl +0 -0
  23. results/context/graphs/op17_1k_graphs.jsonl +0 -0
  24. results/context/graphs/op18_1k_graphs.jsonl +0 -0
  25. results/context/graphs/op19_1k_graphs.jsonl +0 -0
  26. results/context/graphs/op20_1k_graphs.jsonl +0 -0
  27. results/context/graphs/op2_1k_graphs.jsonl +0 -0
  28. results/context/graphs/op3_1k_graphs.jsonl +0 -0
  29. results/context/graphs/op4_1k_graphs.jsonl +0 -0
  30. results/context/graphs/op5_1k_graphs.jsonl +0 -0
  31. results/context/graphs/op6_1k_graphs.jsonl +0 -0
  32. results/context/graphs/op7_1k_graphs.jsonl +0 -0
  33. results/context/graphs/op8_1k_graphs.jsonl +0 -0
  34. results/context/graphs/op9_1k_graphs.jsonl +0 -0
.gitattributes CHANGED
@@ -195,3 +195,8 @@ results/context/block4/SDAR-100M-0.999zoo_op2-20+0.001teacher_op2/graphs/SDAR-10
195
  results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
196
  results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
197
  results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
195
  results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
196
  results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
197
  results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
198
+ results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
199
+ results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl filter=lfs diff=lfs merge=lfs -text
200
+ results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
201
+ results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
202
+ results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794ea7abc36f93ca354acc38ffea1bfcc2ba70a39534774e509e24b6de2fe92e
3
+ size 453198525
results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/context/graphs", "generated_path": "results/context/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2", "results_dir": "results/context/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs", "per_file": [{"file": "results/context/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 125582, "value_mismatch": 383696, "dependency_mismatch": 799349, "answer_mismatch": 449771, "extra_nodes": 1021505, "missing_nodes": 1024382, "perfect_with_extra": 20, "unused_gold_entries": 10000, "template_stats": {"teachers_in_school": {"total": 1152000, "dependency_mismatch": 799349, "extra_nodes": 1021505, "missing_nodes": 1024382, "answer_mismatch": 449771, "value_mismatch": 383696, "perfect": 125582, "perfect_with_extra": 20}}, "results_path": "results/context/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/context/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 0, "value_mismatch": 793137, "dependency_mismatch": 1010575, "answer_mismatch": 936146, "extra_nodes": 1279339, "missing_nodes": 1280000, "perfect_with_extra": 0, "unused_gold_entries": 9000, "template_stats": {"teachers_in_school": {"total": 1280000, "dependency_mismatch": 1010575, "extra_nodes": 1279339, "missing_nodes": 1280000, "value_mismatch": 793137, "answer_mismatch": 936146}}, "results_path": "results/context/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 125582, "value_mismatch": 1176833, "dependency_mismatch": 1809924, "answer_mismatch": 1385917, "extra_nodes": 2300844, "missing_nodes": 2304382, "perfect_with_extra": 20, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/context/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2_score_report.jsonl", "template_stats": {"teachers_in_school": {"total": 2432000, "dependency_mismatch": 1809924, "extra_nodes": 2300844, "missing_nodes": 2304382, "answer_mismatch": 1385917, "value_mismatch": 1176833, "perfect": 125582, "perfect_with_extra": 20}}}}
results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/graphs/results.json ADDED
@@ -0,0 +1,910 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "teachers_in_school": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 0.987,
9
+ "pass@2": 0.989,
10
+ "pass@4": 0.991,
11
+ "pass@8": 0.995,
12
+ "pass@16": 0.996,
13
+ "pass@32": 0.996,
14
+ "pass@64": 0.997,
15
+ "pass@128": 0.998
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": 0.987,
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": 0.989,
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": 0.991,
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": 0.995,
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": 0.996,
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": 0.996,
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": 0.997,
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": 0.998,
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": 0.10966666666666666,
190
+ "pass@2": 0.10988888888888888,
191
+ "pass@4": 0.11011111111111112,
192
+ "pass@8": 0.11055555555555556,
193
+ "pass@16": 0.11066666666666666,
194
+ "pass@32": 0.11066666666666666,
195
+ "pass@64": 0.11077777777777778,
196
+ "pass@128": 0.11088888888888888
197
+ }
198
+ }
199
+ },
200
+ "total": {
201
+ "per_op_pass_at_k": {
202
+ "2": {
203
+ "pass@1": 0.987,
204
+ "pass@2": 0.989,
205
+ "pass@4": 0.991,
206
+ "pass@8": 0.995,
207
+ "pass@16": 0.996,
208
+ "pass@32": 0.996,
209
+ "pass@64": 0.997,
210
+ "pass@128": 0.998
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": 0.987,
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": 0.989,
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": 0.991,
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": 0.995,
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": 0.996,
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": 0.996,
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": 0.997,
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": 0.998,
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": 0.10966666666666666,
385
+ "pass@2": 0.10988888888888888,
386
+ "pass@4": 0.11011111111111112,
387
+ "pass@8": 0.11055555555555556,
388
+ "pass@16": 0.11066666666666666,
389
+ "pass@32": 0.11066666666666666,
390
+ "pass@64": 0.11077777777777778,
391
+ "pass@128": 0.11088888888888888
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
+ "SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm_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
+ }
results/context/block4/SDAR-100M-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
+ SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm,0.6095842013888889,0.26865078125,0.43014555921052633,0.0,0.0,0.0,188.3091059027778,329.576009375,1152000,1280000,2432000
results/context/block4/SDAR-100M-0.99zoo_op2-20+0.01teacher_op2/summary.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "SDAR-100M-0.99zoo_op2-20+0.01teacher_op2-dlm",
4
+ "id_acc": 0.6095842013888889,
5
+ "ood_acc": 0.26865078125,
6
+ "total_acc": 0.43014555921052633,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 188.3091059027778,
11
+ "ood_avg_resp_len": 329.576009375,
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": 1046114,
28
+ "answer_accuracy": 0.43014555921052633,
29
+ "avg_response_len": 262.6601077302632,
30
+ "resp_tokens_sum": 638789382,
31
+ "pass_at_k": {
32
+ "pass@1": 0.43014555921052633,
33
+ "pass@2": 0.5127499935246315,
34
+ "pass@4": 0.5888443842479902,
35
+ "pass@8": 0.65593384801061,
36
+ "pass@16": 0.7139182433220806,
37
+ "pass@32": 0.7639782330796132,
38
+ "pass@64": 0.8070965045058616,
39
+ "pass@128": 0.8437894736842105
40
+ },
41
+ "per_op_pass_at_k": {
42
+ "10": {
43
+ "pass@1": 0.4126953125,
44
+ "pass@2": 0.507600147637796,
45
+ "pass@4": 0.5959926069553801,
46
+ "pass@8": 0.6732117833496856,
47
+ "pass@16": 0.7380794626965851,
48
+ "pass@32": 0.7922476964440843,
49
+ "pass@64": 0.8373047359451761,
50
+ "pass@128": 0.874
51
+ },
52
+ "2": {
53
+ "pass@1": 0.9961171875,
54
+ "pass@2": 0.9975230068897637,
55
+ "pass@4": 0.9983221306711659,
56
+ "pass@8": 0.9989727756084528,
57
+ "pass@16": 0.9994807207704051,
58
+ "pass@32": 0.9998254611556207,
59
+ "pass@64": 0.999986175351393,
60
+ "pass@128": 1.0
61
+ },
62
+ "3": {
63
+ "pass@1": 0.9103828125,
64
+ "pass@2": 0.9425506889763784,
65
+ "pass@4": 0.9622388740157479,
66
+ "pass@8": 0.975349999295636,
67
+ "pass@16": 0.983853120609227,
68
+ "pass@32": 0.9890244416004188,
69
+ "pass@64": 0.991897819351238,
70
+ "pass@128": 0.993
71
+ },
72
+ "4": {
73
+ "pass@1": 0.569328125,
74
+ "pass@2": 0.6406991879921266,
75
+ "pass@4": 0.6936721926321712,
76
+ "pass@8": 0.7283366374009416,
77
+ "pass@16": 0.7517969322028165,
78
+ "pass@32": 0.7706096514107452,
79
+ "pass@64": 0.7877617326183003,
80
+ "pass@128": 0.804
81
+ },
82
+ "5": {
83
+ "pass@1": 0.611265625,
84
+ "pass@2": 0.6687064468503937,
85
+ "pass@4": 0.7086858456130481,
86
+ "pass@8": 0.7409106477256262,
87
+ "pass@16": 0.7669154169918215,
88
+ "pass@32": 0.7875065182756034,
89
+ "pass@64": 0.804226792081769,
90
+ "pass@128": 0.818
91
+ },
92
+ "6": {
93
+ "pass@1": 0.5552109375,
94
+ "pass@2": 0.6553241879921267,
95
+ "pass@4": 0.7353291125796779,
96
+ "pass@8": 0.7949701863120477,
97
+ "pass@16": 0.8385434166582159,
98
+ "pass@32": 0.8708625833577998,
99
+ "pass@64": 0.8952376000359653,
100
+ "pass@128": 0.915
101
+ },
102
+ "7": {
103
+ "pass@1": 0.51128125,
104
+ "pass@2": 0.6093948080708659,
105
+ "pass@4": 0.6908841087364086,
106
+ "pass@8": 0.756764869841941,
107
+ "pass@16": 0.809663845258288,
108
+ "pass@32": 0.8496598066629238,
109
+ "pass@64": 0.8777094301364703,
110
+ "pass@128": 0.899
111
+ },
112
+ "8": {
113
+ "pass@1": 0.494265625,
114
+ "pass@2": 0.5934778543307095,
115
+ "pass@4": 0.6761844399137602,
116
+ "pass@8": 0.7425982996766892,
117
+ "pass@16": 0.7955701172611106,
118
+ "pass@32": 0.8373145095042487,
119
+ "pass@64": 0.8688134871207882,
120
+ "pass@128": 0.892
121
+ },
122
+ "9": {
123
+ "pass@1": 0.4257109375,
124
+ "pass@2": 0.5289901574803154,
125
+ "pass@4": 0.621674902699662,
126
+ "pass@8": 0.6973594884074764,
127
+ "pass@16": 0.7561953984078553,
128
+ "pass@32": 0.80240550747302,
129
+ "pass@64": 0.8399071477796645,
130
+ "pass@128": 0.873
131
+ },
132
+ "11": {
133
+ "pass@1": 0.3774140625,
134
+ "pass@2": 0.47613705708661475,
135
+ "pass@4": 0.5642286361079859,
136
+ "pass@8": 0.6398687454955166,
137
+ "pass@16": 0.7064828961710622,
138
+ "pass@32": 0.7651126517689707,
139
+ "pass@64": 0.8155510166375527,
140
+ "pass@128": 0.86
141
+ },
142
+ "12": {
143
+ "pass@1": 0.3462890625,
144
+ "pass@2": 0.43872404035433077,
145
+ "pass@4": 0.5239153018372701,
146
+ "pass@8": 0.5990279281078111,
147
+ "pass@16": 0.66361095472774,
148
+ "pass@32": 0.7185271454523737,
149
+ "pass@64": 0.767031490951785,
150
+ "pass@128": 0.81
151
+ },
152
+ "13": {
153
+ "pass@1": 0.3391015625,
154
+ "pass@2": 0.4317790354330709,
155
+ "pass@4": 0.5181833852643416,
156
+ "pass@8": 0.5964838833520059,
157
+ "pass@16": 0.6654815946565797,
158
+ "pass@32": 0.7258743492382231,
159
+ "pass@64": 0.7780189814625351,
160
+ "pass@128": 0.823
161
+ },
162
+ "14": {
163
+ "pass@1": 0.3178984375,
164
+ "pass@2": 0.41741326279527563,
165
+ "pass@4": 0.5151516998500183,
166
+ "pass@8": 0.6058998559790486,
167
+ "pass@16": 0.6868555981134699,
168
+ "pass@32": 0.7566070244002328,
169
+ "pass@64": 0.8129041237583818,
170
+ "pass@128": 0.853
171
+ },
172
+ "15": {
173
+ "pass@1": 0.2464140625,
174
+ "pass@2": 0.33977239173228363,
175
+ "pass@4": 0.4343145795838022,
176
+ "pass@8": 0.5257461444108301,
177
+ "pass@16": 0.6110246382597375,
178
+ "pass@32": 0.6873883168003965,
179
+ "pass@64": 0.7533468237790689,
180
+ "pass@128": 0.807
181
+ },
182
+ "16": {
183
+ "pass@1": 0.303984375,
184
+ "pass@2": 0.40927595964566926,
185
+ "pass@4": 0.5103989389763774,
186
+ "pass@8": 0.6014718394871122,
187
+ "pass@16": 0.6813868600977412,
188
+ "pass@32": 0.7502524053212755,
189
+ "pass@64": 0.8061733769962259,
190
+ "pass@128": 0.847
191
+ },
192
+ "17": {
193
+ "pass@1": 0.226390625,
194
+ "pass@2": 0.31797650098425195,
195
+ "pass@4": 0.4140369549118857,
196
+ "pass@8": 0.505305026834578,
197
+ "pass@16": 0.5872945080924371,
198
+ "pass@32": 0.6601433644830466,
199
+ "pass@64": 0.7246326001567372,
200
+ "pass@128": 0.779
201
+ },
202
+ "18": {
203
+ "pass@1": 0.195859375,
204
+ "pass@2": 0.2821972194881889,
205
+ "pass@4": 0.37402928880764974,
206
+ "pass@8": 0.4643392170092771,
207
+ "pass@16": 0.5504452676774946,
208
+ "pass@32": 0.631118943787985,
209
+ "pass@64": 0.7060759494181154,
210
+ "pass@128": 0.777
211
+ },
212
+ "19": {
213
+ "pass@1": 0.1715546875,
214
+ "pass@2": 0.24920460137795278,
215
+ "pass@4": 0.33425357292838365,
216
+ "pass@8": 0.4190603164372725,
217
+ "pass@16": 0.4990036239598838,
218
+ "pass@32": 0.5745888217956253,
219
+ "pass@64": 0.6477536211565927,
220
+ "pass@128": 0.719
221
+ },
222
+ "20": {
223
+ "pass@1": 0.1616015625,
224
+ "pass@2": 0.23550332185039363,
225
+ "pass@4": 0.3165467286276713,
226
+ "pass@8": 0.39706546746953736,
227
+ "pass@16": 0.47276225050650716,
228
+ "pass@32": 0.5465172295795503,
229
+ "pass@64": 0.6205006808734961,
230
+ "pass@128": 0.689
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
+ ]
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b915ae7f0776b617543d1667800e95057a5356df3f4b42558b3e7ffc2b605e2b
3
+ size 1708183214
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_metrics.json ADDED
@@ -0,0 +1,1077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm",
3
+ "id": {
4
+ "answer_accuracy": 0.7950407986111111,
5
+ "avg_response_len": 191.67480555555557,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.7950407986111111,
11
+ "pass@2": 0.8549200158573753,
12
+ "pass@4": 0.896188728450606,
13
+ "pass@8": 0.9256159452646258,
14
+ "pass@16": 0.9468696290126306,
15
+ "pass@32": 0.9624260879025623,
16
+ "pass@64": 0.9735857436689734,
17
+ "pass@128": 0.981
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.60040625,
22
+ "pass@2": 0.7095417076771655,
23
+ "pass@4": 0.7922922718410202,
24
+ "pass@8": 0.8536646585430178,
25
+ "pass@16": 0.8970646089375027,
26
+ "pass@32": 0.9278957351338625,
27
+ "pass@64": 0.9501738187952159,
28
+ "pass@128": 0.964
29
+ },
30
+ "2": {
31
+ "pass@1": 0.999359375,
32
+ "pass@2": 0.999788877952756,
33
+ "pass@4": 0.9999602164416947,
34
+ "pass@8": 0.9999986593035204,
35
+ "pass@16": 0.9999999991433727,
36
+ "pass@32": 1.0,
37
+ "pass@64": 1.0,
38
+ "pass@128": 1.0
39
+ },
40
+ "3": {
41
+ "pass@1": 0.853296875,
42
+ "pass@2": 0.9059648129921256,
43
+ "pass@4": 0.9374243321147357,
44
+ "pass@8": 0.95700210973271,
45
+ "pass@16": 0.9705665053339986,
46
+ "pass@32": 0.9808741341838165,
47
+ "pass@64": 0.9882856831646993,
48
+ "pass@128": 0.993
49
+ },
50
+ "4": {
51
+ "pass@1": 0.933296875,
52
+ "pass@2": 0.9605745570866148,
53
+ "pass@4": 0.9749672712785896,
54
+ "pass@8": 0.9835223449928111,
55
+ "pass@16": 0.9891968090319382,
56
+ "pass@32": 0.9930382063200087,
57
+ "pass@64": 0.9954544705589414,
58
+ "pass@128": 0.997
59
+ },
60
+ "5": {
61
+ "pass@1": 0.8969609375,
62
+ "pass@2": 0.9238891486220477,
63
+ "pass@4": 0.9422059093550802,
64
+ "pass@8": 0.9569563523578236,
65
+ "pass@16": 0.969469384243192,
66
+ "pass@32": 0.9790453107712829,
67
+ "pass@64": 0.9855235851364291,
68
+ "pass@128": 0.989
69
+ },
70
+ "6": {
71
+ "pass@1": 0.7950390625,
72
+ "pass@2": 0.8500728346456693,
73
+ "pass@4": 0.8884933542369708,
74
+ "pass@8": 0.919191859282107,
75
+ "pass@16": 0.9442962035744217,
76
+ "pass@32": 0.9633178311861345,
77
+ "pass@64": 0.9753459978184749,
78
+ "pass@128": 0.983
79
+ },
80
+ "7": {
81
+ "pass@1": 0.7745390625,
82
+ "pass@2": 0.8443341535433072,
83
+ "pass@4": 0.8893270361829764,
84
+ "pass@8": 0.9198137493815588,
85
+ "pass@16": 0.9415577088491797,
86
+ "pass@32": 0.95791377452376,
87
+ "pass@64": 0.9705372614318992,
88
+ "pass@128": 0.98
89
+ },
90
+ "8": {
91
+ "pass@1": 0.6962109375,
92
+ "pass@2": 0.7824670275590552,
93
+ "pass@4": 0.8416537919947508,
94
+ "pass@8": 0.8825173414680063,
95
+ "pass@16": 0.9106842561584872,
96
+ "pass@32": 0.9317685203443532,
97
+ "pass@64": 0.9487756713205382,
98
+ "pass@128": 0.962
99
+ },
100
+ "9": {
101
+ "pass@1": 0.6062578125,
102
+ "pass@2": 0.7176470226377951,
103
+ "pass@4": 0.7993743726096733,
104
+ "pass@8": 0.857876432320144,
105
+ "pass@16": 0.8989911858415434,
106
+ "pass@32": 0.9279812786598292,
107
+ "pass@64": 0.9481752047945332,
108
+ "pass@128": 0.961
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.60040625,
113
+ "2": 0.999359375,
114
+ "3": 0.853296875,
115
+ "4": 0.933296875,
116
+ "5": 0.8969609375,
117
+ "6": 0.7950390625,
118
+ "7": 0.7745390625,
119
+ "8": 0.6962109375,
120
+ "9": 0.6062578125
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 265.446171875,
124
+ "2": 107.34296875,
125
+ "3": 138.452078125,
126
+ "4": 152.1454453125,
127
+ "5": 177.308921875,
128
+ "6": 195.2357734375,
129
+ "7": 208.0973125,
130
+ "8": 229.4393828125,
131
+ "9": 251.6051953125
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 265.446171875,
136
+ "2": 107.34296875,
137
+ "3": 138.452078125,
138
+ "4": 152.1454453125,
139
+ "5": 177.308921875,
140
+ "6": 195.2357734375,
141
+ "7": 208.0973125,
142
+ "8": 229.4393828125,
143
+ "9": 251.6051953125
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": 915887,
159
+ "answer_accuracy": 0.7950407986111111,
160
+ "avg_response_len": 191.67480555555557,
161
+ "resp_tokens_sum": 220809376,
162
+ "pass_at_k": {
163
+ "pass@1": 0.7950407986111111,
164
+ "pass@2": 0.8549200158573753,
165
+ "pass@4": 0.896188728450606,
166
+ "pass@8": 0.9256159452646258,
167
+ "pass@16": 0.9468696290126306,
168
+ "pass@32": 0.9624260879025623,
169
+ "pass@64": 0.9735857436689734,
170
+ "pass@128": 0.981
171
+ },
172
+ "per_op_pass_at_k": {
173
+ "10": {
174
+ "pass@1": 0.60040625,
175
+ "pass@2": 0.7095417076771655,
176
+ "pass@4": 0.7922922718410202,
177
+ "pass@8": 0.8536646585430178,
178
+ "pass@16": 0.8970646089375027,
179
+ "pass@32": 0.9278957351338625,
180
+ "pass@64": 0.9501738187952159,
181
+ "pass@128": 0.964
182
+ },
183
+ "2": {
184
+ "pass@1": 0.999359375,
185
+ "pass@2": 0.999788877952756,
186
+ "pass@4": 0.9999602164416947,
187
+ "pass@8": 0.9999986593035204,
188
+ "pass@16": 0.9999999991433727,
189
+ "pass@32": 1.0,
190
+ "pass@64": 1.0,
191
+ "pass@128": 1.0
192
+ },
193
+ "3": {
194
+ "pass@1": 0.853296875,
195
+ "pass@2": 0.9059648129921256,
196
+ "pass@4": 0.9374243321147357,
197
+ "pass@8": 0.95700210973271,
198
+ "pass@16": 0.9705665053339986,
199
+ "pass@32": 0.9808741341838165,
200
+ "pass@64": 0.9882856831646993,
201
+ "pass@128": 0.993
202
+ },
203
+ "4": {
204
+ "pass@1": 0.933296875,
205
+ "pass@2": 0.9605745570866148,
206
+ "pass@4": 0.9749672712785896,
207
+ "pass@8": 0.9835223449928111,
208
+ "pass@16": 0.9891968090319382,
209
+ "pass@32": 0.9930382063200087,
210
+ "pass@64": 0.9954544705589414,
211
+ "pass@128": 0.997
212
+ },
213
+ "5": {
214
+ "pass@1": 0.8969609375,
215
+ "pass@2": 0.9238891486220477,
216
+ "pass@4": 0.9422059093550802,
217
+ "pass@8": 0.9569563523578236,
218
+ "pass@16": 0.969469384243192,
219
+ "pass@32": 0.9790453107712829,
220
+ "pass@64": 0.9855235851364291,
221
+ "pass@128": 0.989
222
+ },
223
+ "6": {
224
+ "pass@1": 0.7950390625,
225
+ "pass@2": 0.8500728346456693,
226
+ "pass@4": 0.8884933542369708,
227
+ "pass@8": 0.919191859282107,
228
+ "pass@16": 0.9442962035744217,
229
+ "pass@32": 0.9633178311861345,
230
+ "pass@64": 0.9753459978184749,
231
+ "pass@128": 0.983
232
+ },
233
+ "7": {
234
+ "pass@1": 0.7745390625,
235
+ "pass@2": 0.8443341535433072,
236
+ "pass@4": 0.8893270361829764,
237
+ "pass@8": 0.9198137493815588,
238
+ "pass@16": 0.9415577088491797,
239
+ "pass@32": 0.95791377452376,
240
+ "pass@64": 0.9705372614318992,
241
+ "pass@128": 0.98
242
+ },
243
+ "8": {
244
+ "pass@1": 0.6962109375,
245
+ "pass@2": 0.7824670275590552,
246
+ "pass@4": 0.8416537919947508,
247
+ "pass@8": 0.8825173414680063,
248
+ "pass@16": 0.9106842561584872,
249
+ "pass@32": 0.9317685203443532,
250
+ "pass@64": 0.9487756713205382,
251
+ "pass@128": 0.962
252
+ },
253
+ "9": {
254
+ "pass@1": 0.6062578125,
255
+ "pass@2": 0.7176470226377951,
256
+ "pass@4": 0.7993743726096733,
257
+ "pass@8": 0.857876432320144,
258
+ "pass@16": 0.8989911858415434,
259
+ "pass@32": 0.9279812786598292,
260
+ "pass@64": 0.9481752047945332,
261
+ "pass@128": 0.961
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": 0.35009765625,
278
+ "avg_response_len": 347.2910515625,
279
+ "avg_loss": 0.0,
280
+ "count": 1280000,
281
+ "validation_metrics": {},
282
+ "pass_at_k": {
283
+ "pass@1": 0.35009765625,
284
+ "pass@2": 0.4592879798228353,
285
+ "pass@4": 0.5631615146137859,
286
+ "pass@8": 0.6546591456723665,
287
+ "pass@16": 0.7309985472105498,
288
+ "pass@32": 0.79469004226284,
289
+ "pass@64": 0.8487453146189491,
290
+ "pass@128": 0.893
291
+ },
292
+ "per_op_pass_at_k": {
293
+ "11": {
294
+ "pass@1": 0.55,
295
+ "pass@2": 0.6644686269685045,
296
+ "pass@4": 0.7554949091676033,
297
+ "pass@8": 0.8267174476106581,
298
+ "pass@16": 0.8800008354399814,
299
+ "pass@32": 0.9183316005509333,
300
+ "pass@64": 0.946713590674644,
301
+ "pass@128": 0.965
302
+ },
303
+ "12": {
304
+ "pass@1": 0.6275234375,
305
+ "pass@2": 0.7376862696850398,
306
+ "pass@4": 0.8155612725909257,
307
+ "pass@8": 0.8696673090375664,
308
+ "pass@16": 0.9069490704010332,
309
+ "pass@32": 0.9345824383122423,
310
+ "pass@64": 0.9566355686746477,
311
+ "pass@128": 0.973
312
+ },
313
+ "13": {
314
+ "pass@1": 0.56715625,
315
+ "pass@2": 0.6825030757874021,
316
+ "pass@4": 0.772606745406825,
317
+ "pass@8": 0.8417930717051642,
318
+ "pass@16": 0.8930984286997508,
319
+ "pass@32": 0.9305863285411988,
320
+ "pass@64": 0.957979634084356,
321
+ "pass@128": 0.976
322
+ },
323
+ "14": {
324
+ "pass@1": 0.395359375,
325
+ "pass@2": 0.5176122047244094,
326
+ "pass@4": 0.62899828327709,
327
+ "pass@8": 0.7233866013178575,
328
+ "pass@16": 0.8002926961241378,
329
+ "pass@32": 0.8620897217799554,
330
+ "pass@64": 0.9101993889981667,
331
+ "pass@128": 0.945
332
+ },
333
+ "15": {
334
+ "pass@1": 0.3023984375,
335
+ "pass@2": 0.4241403789370082,
336
+ "pass@4": 0.5439839366329201,
337
+ "pass@8": 0.6498669531400889,
338
+ "pass@16": 0.7388635243222283,
339
+ "pass@32": 0.811690443284991,
340
+ "pass@64": 0.868667672101463,
341
+ "pass@128": 0.91
342
+ },
343
+ "16": {
344
+ "pass@1": 0.28628125,
345
+ "pass@2": 0.4098443651574804,
346
+ "pass@4": 0.53514521616048,
347
+ "pass@8": 0.6481046812551223,
348
+ "pass@16": 0.7400196560843376,
349
+ "pass@32": 0.8094523138499621,
350
+ "pass@64": 0.8630424460190331,
351
+ "pass@128": 0.908
352
+ },
353
+ "17": {
354
+ "pass@1": 0.24675,
355
+ "pass@2": 0.35776919291338577,
356
+ "pass@4": 0.47396416788526324,
357
+ "pass@8": 0.5805913679278526,
358
+ "pass@16": 0.6708496973546186,
359
+ "pass@32": 0.747876572986338,
360
+ "pass@64": 0.8143806632004396,
361
+ "pass@128": 0.87
362
+ },
363
+ "18": {
364
+ "pass@1": 0.193015625,
365
+ "pass@2": 0.29202448326771696,
366
+ "pass@4": 0.40241395856767875,
367
+ "pass@8": 0.509743436064761,
368
+ "pass@16": 0.6061520258445829,
369
+ "pass@32": 0.6915977882757431,
370
+ "pass@64": 0.7662865861840186,
371
+ "pass@128": 0.829
372
+ },
373
+ "19": {
374
+ "pass@1": 0.1789296875,
375
+ "pass@2": 0.271176919291339,
376
+ "pass@4": 0.3740147122234719,
377
+ "pass@8": 0.47313048990847273,
378
+ "pass@16": 0.5621066862281713,
379
+ "pass@32": 0.644930194885751,
380
+ "pass@64": 0.7242095021188344,
381
+ "pass@128": 0.796
382
+ },
383
+ "20": {
384
+ "pass@1": 0.1535625,
385
+ "pass@2": 0.2356542814960631,
386
+ "pass@4": 0.3294319442257221,
387
+ "pass@8": 0.4235900987560518,
388
+ "pass@16": 0.5116528516064207,
389
+ "pass@32": 0.5957630201612798,
390
+ "pass@64": 0.6793380941337777,
391
+ "pass@128": 0.758
392
+ }
393
+ },
394
+ "per_op_accuracy": {
395
+ "11": 0.55,
396
+ "12": 0.6275234375,
397
+ "13": 0.56715625,
398
+ "14": 0.395359375,
399
+ "15": 0.3023984375,
400
+ "16": 0.28628125,
401
+ "17": 0.24675,
402
+ "18": 0.193015625,
403
+ "19": 0.1789296875,
404
+ "20": 0.1535625
405
+ },
406
+ "per_op_avg_response_len": {
407
+ "11": 284.4908984375,
408
+ "12": 291.8610859375,
409
+ "13": 305.328,
410
+ "14": 330.875390625,
411
+ "15": 346.5292890625,
412
+ "16": 368.616109375,
413
+ "17": 375.2890625,
414
+ "18": 381.5163984375,
415
+ "19": 390.989515625,
416
+ "20": 397.414765625
417
+ },
418
+ "per_op_avg_loss": {},
419
+ "per_op_length": {
420
+ "11": 284.4908984375,
421
+ "12": 291.8610859375,
422
+ "13": 305.328,
423
+ "14": 330.875390625,
424
+ "15": 346.5292890625,
425
+ "16": 368.616109375,
426
+ "17": 375.2890625,
427
+ "18": 381.5163984375,
428
+ "19": 390.989515625,
429
+ "20": 397.414765625
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": 448125,
445
+ "answer_accuracy": 0.35009765625,
446
+ "avg_response_len": 347.2910515625,
447
+ "resp_tokens_sum": 444532546,
448
+ "pass_at_k": {
449
+ "pass@1": 0.35009765625,
450
+ "pass@2": 0.4592879798228353,
451
+ "pass@4": 0.5631615146137859,
452
+ "pass@8": 0.6546591456723665,
453
+ "pass@16": 0.7309985472105498,
454
+ "pass@32": 0.79469004226284,
455
+ "pass@64": 0.8487453146189491,
456
+ "pass@128": 0.893
457
+ },
458
+ "per_op_pass_at_k": {
459
+ "11": {
460
+ "pass@1": 0.55,
461
+ "pass@2": 0.6644686269685045,
462
+ "pass@4": 0.7554949091676033,
463
+ "pass@8": 0.8267174476106581,
464
+ "pass@16": 0.8800008354399814,
465
+ "pass@32": 0.9183316005509333,
466
+ "pass@64": 0.946713590674644,
467
+ "pass@128": 0.965
468
+ },
469
+ "12": {
470
+ "pass@1": 0.6275234375,
471
+ "pass@2": 0.7376862696850398,
472
+ "pass@4": 0.8155612725909257,
473
+ "pass@8": 0.8696673090375664,
474
+ "pass@16": 0.9069490704010332,
475
+ "pass@32": 0.9345824383122423,
476
+ "pass@64": 0.9566355686746477,
477
+ "pass@128": 0.973
478
+ },
479
+ "13": {
480
+ "pass@1": 0.56715625,
481
+ "pass@2": 0.6825030757874021,
482
+ "pass@4": 0.772606745406825,
483
+ "pass@8": 0.8417930717051642,
484
+ "pass@16": 0.8930984286997508,
485
+ "pass@32": 0.9305863285411988,
486
+ "pass@64": 0.957979634084356,
487
+ "pass@128": 0.976
488
+ },
489
+ "14": {
490
+ "pass@1": 0.395359375,
491
+ "pass@2": 0.5176122047244094,
492
+ "pass@4": 0.62899828327709,
493
+ "pass@8": 0.7233866013178575,
494
+ "pass@16": 0.8002926961241378,
495
+ "pass@32": 0.8620897217799554,
496
+ "pass@64": 0.9101993889981667,
497
+ "pass@128": 0.945
498
+ },
499
+ "15": {
500
+ "pass@1": 0.3023984375,
501
+ "pass@2": 0.4241403789370082,
502
+ "pass@4": 0.5439839366329201,
503
+ "pass@8": 0.6498669531400889,
504
+ "pass@16": 0.7388635243222283,
505
+ "pass@32": 0.811690443284991,
506
+ "pass@64": 0.868667672101463,
507
+ "pass@128": 0.91
508
+ },
509
+ "16": {
510
+ "pass@1": 0.28628125,
511
+ "pass@2": 0.4098443651574804,
512
+ "pass@4": 0.53514521616048,
513
+ "pass@8": 0.6481046812551223,
514
+ "pass@16": 0.7400196560843376,
515
+ "pass@32": 0.8094523138499621,
516
+ "pass@64": 0.8630424460190331,
517
+ "pass@128": 0.908
518
+ },
519
+ "17": {
520
+ "pass@1": 0.24675,
521
+ "pass@2": 0.35776919291338577,
522
+ "pass@4": 0.47396416788526324,
523
+ "pass@8": 0.5805913679278526,
524
+ "pass@16": 0.6708496973546186,
525
+ "pass@32": 0.747876572986338,
526
+ "pass@64": 0.8143806632004396,
527
+ "pass@128": 0.87
528
+ },
529
+ "18": {
530
+ "pass@1": 0.193015625,
531
+ "pass@2": 0.29202448326771696,
532
+ "pass@4": 0.40241395856767875,
533
+ "pass@8": 0.509743436064761,
534
+ "pass@16": 0.6061520258445829,
535
+ "pass@32": 0.6915977882757431,
536
+ "pass@64": 0.7662865861840186,
537
+ "pass@128": 0.829
538
+ },
539
+ "19": {
540
+ "pass@1": 0.1789296875,
541
+ "pass@2": 0.271176919291339,
542
+ "pass@4": 0.3740147122234719,
543
+ "pass@8": 0.47313048990847273,
544
+ "pass@16": 0.5621066862281713,
545
+ "pass@32": 0.644930194885751,
546
+ "pass@64": 0.7242095021188344,
547
+ "pass@128": 0.796
548
+ },
549
+ "20": {
550
+ "pass@1": 0.1535625,
551
+ "pass@2": 0.2356542814960631,
552
+ "pass@4": 0.3294319442257221,
553
+ "pass@8": 0.4235900987560518,
554
+ "pass@16": 0.5116528516064207,
555
+ "pass@32": 0.5957630201612798,
556
+ "pass@64": 0.6793380941337777,
557
+ "pass@128": 0.758
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": 0.5608601973684211,
574
+ "avg_loss": 0.0,
575
+ "count": 2432000,
576
+ "validation_metrics": {
577
+ "id": {},
578
+ "ood": {}
579
+ },
580
+ "pass_at_k": {
581
+ "pass@1": 0.5608601973684211,
582
+ "pass@2": 0.646692628470746,
583
+ "pass@4": 0.7209112474838338,
584
+ "pass@8": 0.7830071033739708,
585
+ "pass@16": 0.8332532701694395,
586
+ "pass@32": 0.874143958618523,
587
+ "pass@64": 0.9078802546952751,
588
+ "pass@128": 0.9346842105263158
589
+ },
590
+ "per_op_pass_at_k": {
591
+ "10": {
592
+ "pass@1": 0.60040625,
593
+ "pass@2": 0.7095417076771655,
594
+ "pass@4": 0.7922922718410202,
595
+ "pass@8": 0.8536646585430178,
596
+ "pass@16": 0.8970646089375027,
597
+ "pass@32": 0.9278957351338625,
598
+ "pass@64": 0.9501738187952159,
599
+ "pass@128": 0.964
600
+ },
601
+ "2": {
602
+ "pass@1": 0.999359375,
603
+ "pass@2": 0.999788877952756,
604
+ "pass@4": 0.9999602164416947,
605
+ "pass@8": 0.9999986593035204,
606
+ "pass@16": 0.9999999991433727,
607
+ "pass@32": 1.0,
608
+ "pass@64": 1.0,
609
+ "pass@128": 1.0
610
+ },
611
+ "3": {
612
+ "pass@1": 0.853296875,
613
+ "pass@2": 0.9059648129921256,
614
+ "pass@4": 0.9374243321147357,
615
+ "pass@8": 0.95700210973271,
616
+ "pass@16": 0.9705665053339986,
617
+ "pass@32": 0.9808741341838165,
618
+ "pass@64": 0.9882856831646993,
619
+ "pass@128": 0.993
620
+ },
621
+ "4": {
622
+ "pass@1": 0.933296875,
623
+ "pass@2": 0.9605745570866148,
624
+ "pass@4": 0.9749672712785896,
625
+ "pass@8": 0.9835223449928111,
626
+ "pass@16": 0.9891968090319382,
627
+ "pass@32": 0.9930382063200087,
628
+ "pass@64": 0.9954544705589414,
629
+ "pass@128": 0.997
630
+ },
631
+ "5": {
632
+ "pass@1": 0.8969609375,
633
+ "pass@2": 0.9238891486220477,
634
+ "pass@4": 0.9422059093550802,
635
+ "pass@8": 0.9569563523578236,
636
+ "pass@16": 0.969469384243192,
637
+ "pass@32": 0.9790453107712829,
638
+ "pass@64": 0.9855235851364291,
639
+ "pass@128": 0.989
640
+ },
641
+ "6": {
642
+ "pass@1": 0.7950390625,
643
+ "pass@2": 0.8500728346456693,
644
+ "pass@4": 0.8884933542369708,
645
+ "pass@8": 0.919191859282107,
646
+ "pass@16": 0.9442962035744217,
647
+ "pass@32": 0.9633178311861345,
648
+ "pass@64": 0.9753459978184749,
649
+ "pass@128": 0.983
650
+ },
651
+ "7": {
652
+ "pass@1": 0.7745390625,
653
+ "pass@2": 0.8443341535433072,
654
+ "pass@4": 0.8893270361829764,
655
+ "pass@8": 0.9198137493815588,
656
+ "pass@16": 0.9415577088491797,
657
+ "pass@32": 0.95791377452376,
658
+ "pass@64": 0.9705372614318992,
659
+ "pass@128": 0.98
660
+ },
661
+ "8": {
662
+ "pass@1": 0.6962109375,
663
+ "pass@2": 0.7824670275590552,
664
+ "pass@4": 0.8416537919947508,
665
+ "pass@8": 0.8825173414680063,
666
+ "pass@16": 0.9106842561584872,
667
+ "pass@32": 0.9317685203443532,
668
+ "pass@64": 0.9487756713205382,
669
+ "pass@128": 0.962
670
+ },
671
+ "9": {
672
+ "pass@1": 0.6062578125,
673
+ "pass@2": 0.7176470226377951,
674
+ "pass@4": 0.7993743726096733,
675
+ "pass@8": 0.857876432320144,
676
+ "pass@16": 0.8989911858415434,
677
+ "pass@32": 0.9279812786598292,
678
+ "pass@64": 0.9481752047945332,
679
+ "pass@128": 0.961
680
+ },
681
+ "11": {
682
+ "pass@1": 0.55,
683
+ "pass@2": 0.6644686269685045,
684
+ "pass@4": 0.7554949091676033,
685
+ "pass@8": 0.8267174476106581,
686
+ "pass@16": 0.8800008354399814,
687
+ "pass@32": 0.9183316005509333,
688
+ "pass@64": 0.946713590674644,
689
+ "pass@128": 0.965
690
+ },
691
+ "12": {
692
+ "pass@1": 0.6275234375,
693
+ "pass@2": 0.7376862696850398,
694
+ "pass@4": 0.8155612725909257,
695
+ "pass@8": 0.8696673090375664,
696
+ "pass@16": 0.9069490704010332,
697
+ "pass@32": 0.9345824383122423,
698
+ "pass@64": 0.9566355686746477,
699
+ "pass@128": 0.973
700
+ },
701
+ "13": {
702
+ "pass@1": 0.56715625,
703
+ "pass@2": 0.6825030757874021,
704
+ "pass@4": 0.772606745406825,
705
+ "pass@8": 0.8417930717051642,
706
+ "pass@16": 0.8930984286997508,
707
+ "pass@32": 0.9305863285411988,
708
+ "pass@64": 0.957979634084356,
709
+ "pass@128": 0.976
710
+ },
711
+ "14": {
712
+ "pass@1": 0.395359375,
713
+ "pass@2": 0.5176122047244094,
714
+ "pass@4": 0.62899828327709,
715
+ "pass@8": 0.7233866013178575,
716
+ "pass@16": 0.8002926961241378,
717
+ "pass@32": 0.8620897217799554,
718
+ "pass@64": 0.9101993889981667,
719
+ "pass@128": 0.945
720
+ },
721
+ "15": {
722
+ "pass@1": 0.3023984375,
723
+ "pass@2": 0.4241403789370082,
724
+ "pass@4": 0.5439839366329201,
725
+ "pass@8": 0.6498669531400889,
726
+ "pass@16": 0.7388635243222283,
727
+ "pass@32": 0.811690443284991,
728
+ "pass@64": 0.868667672101463,
729
+ "pass@128": 0.91
730
+ },
731
+ "16": {
732
+ "pass@1": 0.28628125,
733
+ "pass@2": 0.4098443651574804,
734
+ "pass@4": 0.53514521616048,
735
+ "pass@8": 0.6481046812551223,
736
+ "pass@16": 0.7400196560843376,
737
+ "pass@32": 0.8094523138499621,
738
+ "pass@64": 0.8630424460190331,
739
+ "pass@128": 0.908
740
+ },
741
+ "17": {
742
+ "pass@1": 0.24675,
743
+ "pass@2": 0.35776919291338577,
744
+ "pass@4": 0.47396416788526324,
745
+ "pass@8": 0.5805913679278526,
746
+ "pass@16": 0.6708496973546186,
747
+ "pass@32": 0.747876572986338,
748
+ "pass@64": 0.8143806632004396,
749
+ "pass@128": 0.87
750
+ },
751
+ "18": {
752
+ "pass@1": 0.193015625,
753
+ "pass@2": 0.29202448326771696,
754
+ "pass@4": 0.40241395856767875,
755
+ "pass@8": 0.509743436064761,
756
+ "pass@16": 0.6061520258445829,
757
+ "pass@32": 0.6915977882757431,
758
+ "pass@64": 0.7662865861840186,
759
+ "pass@128": 0.829
760
+ },
761
+ "19": {
762
+ "pass@1": 0.1789296875,
763
+ "pass@2": 0.271176919291339,
764
+ "pass@4": 0.3740147122234719,
765
+ "pass@8": 0.47313048990847273,
766
+ "pass@16": 0.5621066862281713,
767
+ "pass@32": 0.644930194885751,
768
+ "pass@64": 0.7242095021188344,
769
+ "pass@128": 0.796
770
+ },
771
+ "20": {
772
+ "pass@1": 0.1535625,
773
+ "pass@2": 0.2356542814960631,
774
+ "pass@4": 0.3294319442257221,
775
+ "pass@8": 0.4235900987560518,
776
+ "pass@16": 0.5116528516064207,
777
+ "pass@32": 0.5957630201612798,
778
+ "pass@64": 0.6793380941337777,
779
+ "pass@128": 0.758
780
+ }
781
+ },
782
+ "per_op_accuracy": {
783
+ "10": 0.60040625,
784
+ "2": 0.999359375,
785
+ "3": 0.853296875,
786
+ "4": 0.933296875,
787
+ "5": 0.8969609375,
788
+ "6": 0.7950390625,
789
+ "7": 0.7745390625,
790
+ "8": 0.6962109375,
791
+ "9": 0.6062578125,
792
+ "11": 0.55,
793
+ "12": 0.6275234375,
794
+ "13": 0.56715625,
795
+ "14": 0.395359375,
796
+ "15": 0.3023984375,
797
+ "16": 0.28628125,
798
+ "17": 0.24675,
799
+ "18": 0.193015625,
800
+ "19": 0.1789296875,
801
+ "20": 0.1535625
802
+ },
803
+ "per_op_avg_response_len": {
804
+ "10": 265.446171875,
805
+ "2": 107.34296875,
806
+ "3": 138.452078125,
807
+ "4": 152.1454453125,
808
+ "5": 177.308921875,
809
+ "6": 195.2357734375,
810
+ "7": 208.0973125,
811
+ "8": 229.4393828125,
812
+ "9": 251.6051953125,
813
+ "11": 284.4908984375,
814
+ "12": 291.8610859375,
815
+ "13": 305.328,
816
+ "14": 330.875390625,
817
+ "15": 346.5292890625,
818
+ "16": 368.616109375,
819
+ "17": 375.2890625,
820
+ "18": 381.5163984375,
821
+ "19": 390.989515625,
822
+ "20": 397.414765625
823
+ },
824
+ "per_op_avg_loss": {},
825
+ "per_op_length": {
826
+ "10": 265.446171875,
827
+ "2": 107.34296875,
828
+ "3": 138.452078125,
829
+ "4": 152.1454453125,
830
+ "5": 177.308921875,
831
+ "6": 195.2357734375,
832
+ "7": 208.0973125,
833
+ "8": 229.4393828125,
834
+ "9": 251.6051953125,
835
+ "11": 284.4908984375,
836
+ "12": 291.8610859375,
837
+ "13": 305.328,
838
+ "14": 330.875390625,
839
+ "15": 346.5292890625,
840
+ "16": 368.616109375,
841
+ "17": 375.2890625,
842
+ "18": 381.5163984375,
843
+ "19": 390.989515625,
844
+ "20": 397.414765625
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": 1364012,
860
+ "answer_accuracy": 0.5608601973684211,
861
+ "avg_response_len": 273.5780929276316,
862
+ "resp_tokens_sum": 665341922,
863
+ "pass_at_k": {
864
+ "pass@1": 0.5608601973684211,
865
+ "pass@2": 0.646692628470746,
866
+ "pass@4": 0.7209112474838338,
867
+ "pass@8": 0.7830071033739708,
868
+ "pass@16": 0.8332532701694395,
869
+ "pass@32": 0.874143958618523,
870
+ "pass@64": 0.9078802546952751,
871
+ "pass@128": 0.9346842105263158
872
+ },
873
+ "per_op_pass_at_k": {
874
+ "10": {
875
+ "pass@1": 0.60040625,
876
+ "pass@2": 0.7095417076771655,
877
+ "pass@4": 0.7922922718410202,
878
+ "pass@8": 0.8536646585430178,
879
+ "pass@16": 0.8970646089375027,
880
+ "pass@32": 0.9278957351338625,
881
+ "pass@64": 0.9501738187952159,
882
+ "pass@128": 0.964
883
+ },
884
+ "2": {
885
+ "pass@1": 0.999359375,
886
+ "pass@2": 0.999788877952756,
887
+ "pass@4": 0.9999602164416947,
888
+ "pass@8": 0.9999986593035204,
889
+ "pass@16": 0.9999999991433727,
890
+ "pass@32": 1.0,
891
+ "pass@64": 1.0,
892
+ "pass@128": 1.0
893
+ },
894
+ "3": {
895
+ "pass@1": 0.853296875,
896
+ "pass@2": 0.9059648129921256,
897
+ "pass@4": 0.9374243321147357,
898
+ "pass@8": 0.95700210973271,
899
+ "pass@16": 0.9705665053339986,
900
+ "pass@32": 0.9808741341838165,
901
+ "pass@64": 0.9882856831646993,
902
+ "pass@128": 0.993
903
+ },
904
+ "4": {
905
+ "pass@1": 0.933296875,
906
+ "pass@2": 0.9605745570866148,
907
+ "pass@4": 0.9749672712785896,
908
+ "pass@8": 0.9835223449928111,
909
+ "pass@16": 0.9891968090319382,
910
+ "pass@32": 0.9930382063200087,
911
+ "pass@64": 0.9954544705589414,
912
+ "pass@128": 0.997
913
+ },
914
+ "5": {
915
+ "pass@1": 0.8969609375,
916
+ "pass@2": 0.9238891486220477,
917
+ "pass@4": 0.9422059093550802,
918
+ "pass@8": 0.9569563523578236,
919
+ "pass@16": 0.969469384243192,
920
+ "pass@32": 0.9790453107712829,
921
+ "pass@64": 0.9855235851364291,
922
+ "pass@128": 0.989
923
+ },
924
+ "6": {
925
+ "pass@1": 0.7950390625,
926
+ "pass@2": 0.8500728346456693,
927
+ "pass@4": 0.8884933542369708,
928
+ "pass@8": 0.919191859282107,
929
+ "pass@16": 0.9442962035744217,
930
+ "pass@32": 0.9633178311861345,
931
+ "pass@64": 0.9753459978184749,
932
+ "pass@128": 0.983
933
+ },
934
+ "7": {
935
+ "pass@1": 0.7745390625,
936
+ "pass@2": 0.8443341535433072,
937
+ "pass@4": 0.8893270361829764,
938
+ "pass@8": 0.9198137493815588,
939
+ "pass@16": 0.9415577088491797,
940
+ "pass@32": 0.95791377452376,
941
+ "pass@64": 0.9705372614318992,
942
+ "pass@128": 0.98
943
+ },
944
+ "8": {
945
+ "pass@1": 0.6962109375,
946
+ "pass@2": 0.7824670275590552,
947
+ "pass@4": 0.8416537919947508,
948
+ "pass@8": 0.8825173414680063,
949
+ "pass@16": 0.9106842561584872,
950
+ "pass@32": 0.9317685203443532,
951
+ "pass@64": 0.9487756713205382,
952
+ "pass@128": 0.962
953
+ },
954
+ "9": {
955
+ "pass@1": 0.6062578125,
956
+ "pass@2": 0.7176470226377951,
957
+ "pass@4": 0.7993743726096733,
958
+ "pass@8": 0.857876432320144,
959
+ "pass@16": 0.8989911858415434,
960
+ "pass@32": 0.9279812786598292,
961
+ "pass@64": 0.9481752047945332,
962
+ "pass@128": 0.961
963
+ },
964
+ "11": {
965
+ "pass@1": 0.55,
966
+ "pass@2": 0.6644686269685045,
967
+ "pass@4": 0.7554949091676033,
968
+ "pass@8": 0.8267174476106581,
969
+ "pass@16": 0.8800008354399814,
970
+ "pass@32": 0.9183316005509333,
971
+ "pass@64": 0.946713590674644,
972
+ "pass@128": 0.965
973
+ },
974
+ "12": {
975
+ "pass@1": 0.6275234375,
976
+ "pass@2": 0.7376862696850398,
977
+ "pass@4": 0.8155612725909257,
978
+ "pass@8": 0.8696673090375664,
979
+ "pass@16": 0.9069490704010332,
980
+ "pass@32": 0.9345824383122423,
981
+ "pass@64": 0.9566355686746477,
982
+ "pass@128": 0.973
983
+ },
984
+ "13": {
985
+ "pass@1": 0.56715625,
986
+ "pass@2": 0.6825030757874021,
987
+ "pass@4": 0.772606745406825,
988
+ "pass@8": 0.8417930717051642,
989
+ "pass@16": 0.8930984286997508,
990
+ "pass@32": 0.9305863285411988,
991
+ "pass@64": 0.957979634084356,
992
+ "pass@128": 0.976
993
+ },
994
+ "14": {
995
+ "pass@1": 0.395359375,
996
+ "pass@2": 0.5176122047244094,
997
+ "pass@4": 0.62899828327709,
998
+ "pass@8": 0.7233866013178575,
999
+ "pass@16": 0.8002926961241378,
1000
+ "pass@32": 0.8620897217799554,
1001
+ "pass@64": 0.9101993889981667,
1002
+ "pass@128": 0.945
1003
+ },
1004
+ "15": {
1005
+ "pass@1": 0.3023984375,
1006
+ "pass@2": 0.4241403789370082,
1007
+ "pass@4": 0.5439839366329201,
1008
+ "pass@8": 0.6498669531400889,
1009
+ "pass@16": 0.7388635243222283,
1010
+ "pass@32": 0.811690443284991,
1011
+ "pass@64": 0.868667672101463,
1012
+ "pass@128": 0.91
1013
+ },
1014
+ "16": {
1015
+ "pass@1": 0.28628125,
1016
+ "pass@2": 0.4098443651574804,
1017
+ "pass@4": 0.53514521616048,
1018
+ "pass@8": 0.6481046812551223,
1019
+ "pass@16": 0.7400196560843376,
1020
+ "pass@32": 0.8094523138499621,
1021
+ "pass@64": 0.8630424460190331,
1022
+ "pass@128": 0.908
1023
+ },
1024
+ "17": {
1025
+ "pass@1": 0.24675,
1026
+ "pass@2": 0.35776919291338577,
1027
+ "pass@4": 0.47396416788526324,
1028
+ "pass@8": 0.5805913679278526,
1029
+ "pass@16": 0.6708496973546186,
1030
+ "pass@32": 0.747876572986338,
1031
+ "pass@64": 0.8143806632004396,
1032
+ "pass@128": 0.87
1033
+ },
1034
+ "18": {
1035
+ "pass@1": 0.193015625,
1036
+ "pass@2": 0.29202448326771696,
1037
+ "pass@4": 0.40241395856767875,
1038
+ "pass@8": 0.509743436064761,
1039
+ "pass@16": 0.6061520258445829,
1040
+ "pass@32": 0.6915977882757431,
1041
+ "pass@64": 0.7662865861840186,
1042
+ "pass@128": 0.829
1043
+ },
1044
+ "19": {
1045
+ "pass@1": 0.1789296875,
1046
+ "pass@2": 0.271176919291339,
1047
+ "pass@4": 0.3740147122234719,
1048
+ "pass@8": 0.47313048990847273,
1049
+ "pass@16": 0.5621066862281713,
1050
+ "pass@32": 0.644930194885751,
1051
+ "pass@64": 0.7242095021188344,
1052
+ "pass@128": 0.796
1053
+ },
1054
+ "20": {
1055
+ "pass@1": 0.1535625,
1056
+ "pass@2": 0.2356542814960631,
1057
+ "pass@4": 0.3294319442257221,
1058
+ "pass@8": 0.4235900987560518,
1059
+ "pass@16": 0.5116528516064207,
1060
+ "pass@32": 0.5957630201612798,
1061
+ "pass@64": 0.6793380941337777,
1062
+ "pass@128": 0.758
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
+ }
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9e63e7c4c2269479e996cfc50c12064d5024880c66dddb20a7c5ef157bc9ba
3
+ size 2615189606
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392f84570bc6eb7449e8aa4055d64c221eafb28ff32d1daeebe400dbf054cdcd
3
+ size 382718309
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199a47a7d0d04c8c87aacab974e8aefb268755d1aea5715dc8a0ae6de0d12161
3
+ size 449076903
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2_score_report.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gold_dir": "results/context/graphs", "generated_path": "results/context/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2", "results_dir": "results/context/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs", "per_file": [{"file": "results/context/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl", "total": 1152000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 510449, "value_mismatch": 227269, "dependency_mismatch": 443939, "answer_mismatch": 236113, "extra_nodes": 516832, "missing_nodes": 570721, "perfect_with_extra": 2327, "unused_gold_entries": 10000, "template_stats": {"teachers_in_school": {"total": 1152000, "value_mismatch": 227269, "dependency_mismatch": 443939, "answer_mismatch": 236113, "extra_nodes": 516832, "missing_nodes": 570721, "perfect": 510449, "perfect_with_extra": 2327}}, "results_path": "results/context/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl"}, {"file": "results/context/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl", "total": 1280000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 4600, "value_mismatch": 839930, "dependency_mismatch": 1073527, "answer_mismatch": 831880, "extra_nodes": 1218438, "missing_nodes": 1265282, "perfect_with_extra": 42, "unused_gold_entries": 9000, "template_stats": {"teachers_in_school": {"total": 1280000, "value_mismatch": 839930, "answer_mismatch": 831880, "extra_nodes": 1218438, "missing_nodes": 1265282, "dependency_mismatch": 1073527, "perfect": 4600, "perfect_with_extra": 42}}, "results_path": "results/context/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl"}], "aggregate": {"files": 2, "total": 2432000, "missing_solution": 0, "missing_gold": 0, "parse_fail": 0, "perfect": 515049, "value_mismatch": 1067199, "dependency_mismatch": 1517466, "answer_mismatch": 1067993, "extra_nodes": 1735270, "missing_nodes": 1836003, "perfect_with_extra": 2369, "skipped": 0, "unused_gold_entries": 0, "aggregated": true, "report_path": "results/context/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2_score_report.jsonl", "template_stats": {"teachers_in_school": {"total": 2432000, "value_mismatch": 1067199, "dependency_mismatch": 1517466, "answer_mismatch": 1067993, "extra_nodes": 1735270, "missing_nodes": 1836003, "perfect": 515049, "perfect_with_extra": 2369}}}}
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/graphs/results.json ADDED
@@ -0,0 +1,910 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "teachers_in_school": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 0.999,
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": 0.29,
19
+ "pass@2": 0.331,
20
+ "pass@4": 0.364,
21
+ "pass@8": 0.382,
22
+ "pass@16": 0.411,
23
+ "pass@32": 0.433,
24
+ "pass@64": 0.461,
25
+ "pass@128": 0.486
26
+ },
27
+ "4": {
28
+ "pass@1": 0.787,
29
+ "pass@2": 0.808,
30
+ "pass@4": 0.816,
31
+ "pass@8": 0.825,
32
+ "pass@16": 0.83,
33
+ "pass@32": 0.831,
34
+ "pass@64": 0.838,
35
+ "pass@128": 0.846
36
+ },
37
+ "5": {
38
+ "pass@1": 0.694,
39
+ "pass@2": 0.699,
40
+ "pass@4": 0.701,
41
+ "pass@8": 0.704,
42
+ "pass@16": 0.709,
43
+ "pass@32": 0.711,
44
+ "pass@64": 0.715,
45
+ "pass@128": 0.722
46
+ },
47
+ "6": {
48
+ "pass@1": 0.531,
49
+ "pass@2": 0.573,
50
+ "pass@4": 0.6,
51
+ "pass@8": 0.616,
52
+ "pass@16": 0.631,
53
+ "pass@32": 0.645,
54
+ "pass@64": 0.659,
55
+ "pass@128": 0.674
56
+ },
57
+ "7": {
58
+ "pass@1": 0.394,
59
+ "pass@2": 0.447,
60
+ "pass@4": 0.48,
61
+ "pass@8": 0.501,
62
+ "pass@16": 0.525,
63
+ "pass@32": 0.539,
64
+ "pass@64": 0.559,
65
+ "pass@128": 0.574
66
+ },
67
+ "8": {
68
+ "pass@1": 0.191,
69
+ "pass@2": 0.228,
70
+ "pass@4": 0.254,
71
+ "pass@8": 0.266,
72
+ "pass@16": 0.292,
73
+ "pass@32": 0.32,
74
+ "pass@64": 0.346,
75
+ "pass@128": 0.366
76
+ },
77
+ "9": {
78
+ "pass@1": 0.082,
79
+ "pass@2": 0.116,
80
+ "pass@4": 0.147,
81
+ "pass@8": 0.171,
82
+ "pass@16": 0.185,
83
+ "pass@32": 0.208,
84
+ "pass@64": 0.227,
85
+ "pass@128": 0.249
86
+ },
87
+ "10": {
88
+ "pass@1": 0.027,
89
+ "pass@2": 0.036,
90
+ "pass@4": 0.053,
91
+ "pass@8": 0.068,
92
+ "pass@16": 0.085,
93
+ "pass@32": 0.099,
94
+ "pass@64": 0.114,
95
+ "pass@128": 0.127
96
+ }
97
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 0.999,
101
+ "3": 0.29,
102
+ "4": 0.787,
103
+ "5": 0.694,
104
+ "6": 0.531,
105
+ "7": 0.394,
106
+ "8": 0.191,
107
+ "9": 0.082,
108
+ "10": 0.027
109
+ },
110
+ "pass@2": {
111
+ "2": 1.0,
112
+ "3": 0.331,
113
+ "4": 0.808,
114
+ "5": 0.699,
115
+ "6": 0.573,
116
+ "7": 0.447,
117
+ "8": 0.228,
118
+ "9": 0.116,
119
+ "10": 0.036
120
+ },
121
+ "pass@4": {
122
+ "2": 1.0,
123
+ "3": 0.364,
124
+ "4": 0.816,
125
+ "5": 0.701,
126
+ "6": 0.6,
127
+ "7": 0.48,
128
+ "8": 0.254,
129
+ "9": 0.147,
130
+ "10": 0.053
131
+ },
132
+ "pass@8": {
133
+ "2": 1.0,
134
+ "3": 0.382,
135
+ "4": 0.825,
136
+ "5": 0.704,
137
+ "6": 0.616,
138
+ "7": 0.501,
139
+ "8": 0.266,
140
+ "9": 0.171,
141
+ "10": 0.068
142
+ },
143
+ "pass@16": {
144
+ "2": 1.0,
145
+ "3": 0.411,
146
+ "4": 0.83,
147
+ "5": 0.709,
148
+ "6": 0.631,
149
+ "7": 0.525,
150
+ "8": 0.292,
151
+ "9": 0.185,
152
+ "10": 0.085
153
+ },
154
+ "pass@32": {
155
+ "2": 1.0,
156
+ "3": 0.433,
157
+ "4": 0.831,
158
+ "5": 0.711,
159
+ "6": 0.645,
160
+ "7": 0.539,
161
+ "8": 0.32,
162
+ "9": 0.208,
163
+ "10": 0.099
164
+ },
165
+ "pass@64": {
166
+ "2": 1.0,
167
+ "3": 0.461,
168
+ "4": 0.838,
169
+ "5": 0.715,
170
+ "6": 0.659,
171
+ "7": 0.559,
172
+ "8": 0.346,
173
+ "9": 0.227,
174
+ "10": 0.114
175
+ },
176
+ "pass@128": {
177
+ "2": 1.0,
178
+ "3": 0.486,
179
+ "4": 0.846,
180
+ "5": 0.722,
181
+ "6": 0.674,
182
+ "7": 0.574,
183
+ "8": 0.366,
184
+ "9": 0.249,
185
+ "10": 0.127
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.4438888888888889,
190
+ "pass@2": 0.4708888888888889,
191
+ "pass@4": 0.4905555555555556,
192
+ "pass@8": 0.5036666666666667,
193
+ "pass@16": 0.5186666666666667,
194
+ "pass@32": 0.5317777777777778,
195
+ "pass@64": 0.5465555555555556,
196
+ "pass@128": 0.5604444444444444
197
+ }
198
+ }
199
+ },
200
+ "total": {
201
+ "per_op_pass_at_k": {
202
+ "2": {
203
+ "pass@1": 0.999,
204
+ "pass@2": 1.0,
205
+ "pass@4": 1.0,
206
+ "pass@8": 1.0,
207
+ "pass@16": 1.0,
208
+ "pass@32": 1.0,
209
+ "pass@64": 1.0,
210
+ "pass@128": 1.0
211
+ },
212
+ "3": {
213
+ "pass@1": 0.29,
214
+ "pass@2": 0.331,
215
+ "pass@4": 0.364,
216
+ "pass@8": 0.382,
217
+ "pass@16": 0.411,
218
+ "pass@32": 0.433,
219
+ "pass@64": 0.461,
220
+ "pass@128": 0.486
221
+ },
222
+ "4": {
223
+ "pass@1": 0.787,
224
+ "pass@2": 0.808,
225
+ "pass@4": 0.816,
226
+ "pass@8": 0.825,
227
+ "pass@16": 0.83,
228
+ "pass@32": 0.831,
229
+ "pass@64": 0.838,
230
+ "pass@128": 0.846
231
+ },
232
+ "5": {
233
+ "pass@1": 0.694,
234
+ "pass@2": 0.699,
235
+ "pass@4": 0.701,
236
+ "pass@8": 0.704,
237
+ "pass@16": 0.709,
238
+ "pass@32": 0.711,
239
+ "pass@64": 0.715,
240
+ "pass@128": 0.722
241
+ },
242
+ "6": {
243
+ "pass@1": 0.531,
244
+ "pass@2": 0.573,
245
+ "pass@4": 0.6,
246
+ "pass@8": 0.616,
247
+ "pass@16": 0.631,
248
+ "pass@32": 0.645,
249
+ "pass@64": 0.659,
250
+ "pass@128": 0.674
251
+ },
252
+ "7": {
253
+ "pass@1": 0.394,
254
+ "pass@2": 0.447,
255
+ "pass@4": 0.48,
256
+ "pass@8": 0.501,
257
+ "pass@16": 0.525,
258
+ "pass@32": 0.539,
259
+ "pass@64": 0.559,
260
+ "pass@128": 0.574
261
+ },
262
+ "8": {
263
+ "pass@1": 0.191,
264
+ "pass@2": 0.228,
265
+ "pass@4": 0.254,
266
+ "pass@8": 0.266,
267
+ "pass@16": 0.292,
268
+ "pass@32": 0.32,
269
+ "pass@64": 0.346,
270
+ "pass@128": 0.366
271
+ },
272
+ "9": {
273
+ "pass@1": 0.082,
274
+ "pass@2": 0.116,
275
+ "pass@4": 0.147,
276
+ "pass@8": 0.171,
277
+ "pass@16": 0.185,
278
+ "pass@32": 0.208,
279
+ "pass@64": 0.227,
280
+ "pass@128": 0.249
281
+ },
282
+ "10": {
283
+ "pass@1": 0.027,
284
+ "pass@2": 0.036,
285
+ "pass@4": 0.053,
286
+ "pass@8": 0.068,
287
+ "pass@16": 0.085,
288
+ "pass@32": 0.099,
289
+ "pass@64": 0.114,
290
+ "pass@128": 0.127
291
+ }
292
+ },
293
+ "per_op_pass_at_columns": {
294
+ "pass@1": {
295
+ "2": 0.999,
296
+ "3": 0.29,
297
+ "4": 0.787,
298
+ "5": 0.694,
299
+ "6": 0.531,
300
+ "7": 0.394,
301
+ "8": 0.191,
302
+ "9": 0.082,
303
+ "10": 0.027
304
+ },
305
+ "pass@2": {
306
+ "2": 1.0,
307
+ "3": 0.331,
308
+ "4": 0.808,
309
+ "5": 0.699,
310
+ "6": 0.573,
311
+ "7": 0.447,
312
+ "8": 0.228,
313
+ "9": 0.116,
314
+ "10": 0.036
315
+ },
316
+ "pass@4": {
317
+ "2": 1.0,
318
+ "3": 0.364,
319
+ "4": 0.816,
320
+ "5": 0.701,
321
+ "6": 0.6,
322
+ "7": 0.48,
323
+ "8": 0.254,
324
+ "9": 0.147,
325
+ "10": 0.053
326
+ },
327
+ "pass@8": {
328
+ "2": 1.0,
329
+ "3": 0.382,
330
+ "4": 0.825,
331
+ "5": 0.704,
332
+ "6": 0.616,
333
+ "7": 0.501,
334
+ "8": 0.266,
335
+ "9": 0.171,
336
+ "10": 0.068
337
+ },
338
+ "pass@16": {
339
+ "2": 1.0,
340
+ "3": 0.411,
341
+ "4": 0.83,
342
+ "5": 0.709,
343
+ "6": 0.631,
344
+ "7": 0.525,
345
+ "8": 0.292,
346
+ "9": 0.185,
347
+ "10": 0.085
348
+ },
349
+ "pass@32": {
350
+ "2": 1.0,
351
+ "3": 0.433,
352
+ "4": 0.831,
353
+ "5": 0.711,
354
+ "6": 0.645,
355
+ "7": 0.539,
356
+ "8": 0.32,
357
+ "9": 0.208,
358
+ "10": 0.099
359
+ },
360
+ "pass@64": {
361
+ "2": 1.0,
362
+ "3": 0.461,
363
+ "4": 0.838,
364
+ "5": 0.715,
365
+ "6": 0.659,
366
+ "7": 0.559,
367
+ "8": 0.346,
368
+ "9": 0.227,
369
+ "10": 0.114
370
+ },
371
+ "pass@128": {
372
+ "2": 1.0,
373
+ "3": 0.486,
374
+ "4": 0.846,
375
+ "5": 0.722,
376
+ "6": 0.674,
377
+ "7": 0.574,
378
+ "8": 0.366,
379
+ "9": 0.249,
380
+ "10": 0.127
381
+ }
382
+ },
383
+ "total_pass_at_k": {
384
+ "pass@1": 0.4438888888888889,
385
+ "pass@2": 0.4708888888888889,
386
+ "pass@4": 0.4905555555555556,
387
+ "pass@8": 0.5036666666666667,
388
+ "pass@16": 0.5186666666666667,
389
+ "pass@32": 0.5317777777777778,
390
+ "pass@64": 0.5465555555555556,
391
+ "pass@128": 0.5604444444444444
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
+ "SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm_ood_generations.jsonl.graph_results.jsonl": {
438
+ "per_template": {
439
+ "teachers_in_school": {
440
+ "per_op_pass_at_k": {
441
+ "11": {
442
+ "pass@1": 0.006,
443
+ "pass@2": 0.011,
444
+ "pass@4": 0.024,
445
+ "pass@8": 0.036,
446
+ "pass@16": 0.048,
447
+ "pass@32": 0.062,
448
+ "pass@64": 0.072,
449
+ "pass@128": 0.083
450
+ },
451
+ "12": {
452
+ "pass@1": 0.014,
453
+ "pass@2": 0.019,
454
+ "pass@4": 0.025,
455
+ "pass@8": 0.029,
456
+ "pass@16": 0.036,
457
+ "pass@32": 0.045,
458
+ "pass@64": 0.06,
459
+ "pass@128": 0.076
460
+ },
461
+ "13": {
462
+ "pass@1": 0.007,
463
+ "pass@2": 0.014,
464
+ "pass@4": 0.019,
465
+ "pass@8": 0.026,
466
+ "pass@16": 0.03,
467
+ "pass@32": 0.037,
468
+ "pass@64": 0.047,
469
+ "pass@128": 0.054
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": 0.003,
477
+ "pass@32": 0.004,
478
+ "pass@64": 0.004,
479
+ "pass@128": 0.005
480
+ },
481
+ "15": {
482
+ "pass@1": 0.0,
483
+ "pass@2": 0.001,
484
+ "pass@4": 0.001,
485
+ "pass@8": 0.001,
486
+ "pass@16": 0.001,
487
+ "pass@32": 0.001,
488
+ "pass@64": 0.002,
489
+ "pass@128": 0.003
490
+ },
491
+ "16": {
492
+ "pass@1": 0.0,
493
+ "pass@2": 0.0,
494
+ "pass@4": 0.0,
495
+ "pass@8": 0.001,
496
+ "pass@16": 0.002,
497
+ "pass@32": 0.002,
498
+ "pass@64": 0.003,
499
+ "pass@128": 0.004
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": 0.001,
518
+ "pass@64": 0.001,
519
+ "pass@128": 0.001
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": 0.006,
545
+ "12": 0.014,
546
+ "13": 0.007,
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": 0.011,
557
+ "12": 0.019,
558
+ "13": 0.014,
559
+ "14": 0.0,
560
+ "15": 0.001,
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": 0.024,
569
+ "12": 0.025,
570
+ "13": 0.019,
571
+ "14": 0.0,
572
+ "15": 0.001,
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": 0.036,
581
+ "12": 0.029,
582
+ "13": 0.026,
583
+ "14": 0.0,
584
+ "15": 0.001,
585
+ "16": 0.001,
586
+ "17": 0.0,
587
+ "18": 0.0,
588
+ "19": 0.0,
589
+ "20": 0.0
590
+ },
591
+ "pass@16": {
592
+ "11": 0.048,
593
+ "12": 0.036,
594
+ "13": 0.03,
595
+ "14": 0.003,
596
+ "15": 0.001,
597
+ "16": 0.002,
598
+ "17": 0.0,
599
+ "18": 0.0,
600
+ "19": 0.0,
601
+ "20": 0.0
602
+ },
603
+ "pass@32": {
604
+ "11": 0.062,
605
+ "12": 0.045,
606
+ "13": 0.037,
607
+ "14": 0.004,
608
+ "15": 0.001,
609
+ "16": 0.002,
610
+ "17": 0.0,
611
+ "18": 0.001,
612
+ "19": 0.0,
613
+ "20": 0.0
614
+ },
615
+ "pass@64": {
616
+ "11": 0.072,
617
+ "12": 0.06,
618
+ "13": 0.047,
619
+ "14": 0.004,
620
+ "15": 0.002,
621
+ "16": 0.003,
622
+ "17": 0.0,
623
+ "18": 0.001,
624
+ "19": 0.0,
625
+ "20": 0.0
626
+ },
627
+ "pass@128": {
628
+ "11": 0.083,
629
+ "12": 0.076,
630
+ "13": 0.054,
631
+ "14": 0.005,
632
+ "15": 0.003,
633
+ "16": 0.004,
634
+ "17": 0.0,
635
+ "18": 0.001,
636
+ "19": 0.0,
637
+ "20": 0.0
638
+ }
639
+ },
640
+ "total_pass_at_k": {
641
+ "pass@1": 0.0027,
642
+ "pass@2": 0.0045,
643
+ "pass@4": 0.0069,
644
+ "pass@8": 0.0093,
645
+ "pass@16": 0.012,
646
+ "pass@32": 0.0152,
647
+ "pass@64": 0.0189,
648
+ "pass@128": 0.0226
649
+ }
650
+ }
651
+ },
652
+ "total": {
653
+ "per_op_pass_at_k": {
654
+ "11": {
655
+ "pass@1": 0.006,
656
+ "pass@2": 0.011,
657
+ "pass@4": 0.024,
658
+ "pass@8": 0.036,
659
+ "pass@16": 0.048,
660
+ "pass@32": 0.062,
661
+ "pass@64": 0.072,
662
+ "pass@128": 0.083
663
+ },
664
+ "12": {
665
+ "pass@1": 0.014,
666
+ "pass@2": 0.019,
667
+ "pass@4": 0.025,
668
+ "pass@8": 0.029,
669
+ "pass@16": 0.036,
670
+ "pass@32": 0.045,
671
+ "pass@64": 0.06,
672
+ "pass@128": 0.076
673
+ },
674
+ "13": {
675
+ "pass@1": 0.007,
676
+ "pass@2": 0.014,
677
+ "pass@4": 0.019,
678
+ "pass@8": 0.026,
679
+ "pass@16": 0.03,
680
+ "pass@32": 0.037,
681
+ "pass@64": 0.047,
682
+ "pass@128": 0.054
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": 0.003,
690
+ "pass@32": 0.004,
691
+ "pass@64": 0.004,
692
+ "pass@128": 0.005
693
+ },
694
+ "15": {
695
+ "pass@1": 0.0,
696
+ "pass@2": 0.001,
697
+ "pass@4": 0.001,
698
+ "pass@8": 0.001,
699
+ "pass@16": 0.001,
700
+ "pass@32": 0.001,
701
+ "pass@64": 0.002,
702
+ "pass@128": 0.003
703
+ },
704
+ "16": {
705
+ "pass@1": 0.0,
706
+ "pass@2": 0.0,
707
+ "pass@4": 0.0,
708
+ "pass@8": 0.001,
709
+ "pass@16": 0.002,
710
+ "pass@32": 0.002,
711
+ "pass@64": 0.003,
712
+ "pass@128": 0.004
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": 0.001,
731
+ "pass@64": 0.001,
732
+ "pass@128": 0.001
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": 0.006,
758
+ "12": 0.014,
759
+ "13": 0.007,
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": 0.011,
770
+ "12": 0.019,
771
+ "13": 0.014,
772
+ "14": 0.0,
773
+ "15": 0.001,
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": 0.024,
782
+ "12": 0.025,
783
+ "13": 0.019,
784
+ "14": 0.0,
785
+ "15": 0.001,
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": 0.036,
794
+ "12": 0.029,
795
+ "13": 0.026,
796
+ "14": 0.0,
797
+ "15": 0.001,
798
+ "16": 0.001,
799
+ "17": 0.0,
800
+ "18": 0.0,
801
+ "19": 0.0,
802
+ "20": 0.0
803
+ },
804
+ "pass@16": {
805
+ "11": 0.048,
806
+ "12": 0.036,
807
+ "13": 0.03,
808
+ "14": 0.003,
809
+ "15": 0.001,
810
+ "16": 0.002,
811
+ "17": 0.0,
812
+ "18": 0.0,
813
+ "19": 0.0,
814
+ "20": 0.0
815
+ },
816
+ "pass@32": {
817
+ "11": 0.062,
818
+ "12": 0.045,
819
+ "13": 0.037,
820
+ "14": 0.004,
821
+ "15": 0.001,
822
+ "16": 0.002,
823
+ "17": 0.0,
824
+ "18": 0.001,
825
+ "19": 0.0,
826
+ "20": 0.0
827
+ },
828
+ "pass@64": {
829
+ "11": 0.072,
830
+ "12": 0.06,
831
+ "13": 0.047,
832
+ "14": 0.004,
833
+ "15": 0.002,
834
+ "16": 0.003,
835
+ "17": 0.0,
836
+ "18": 0.001,
837
+ "19": 0.0,
838
+ "20": 0.0
839
+ },
840
+ "pass@128": {
841
+ "11": 0.083,
842
+ "12": 0.076,
843
+ "13": 0.054,
844
+ "14": 0.005,
845
+ "15": 0.003,
846
+ "16": 0.004,
847
+ "17": 0.0,
848
+ "18": 0.001,
849
+ "19": 0.0,
850
+ "20": 0.0
851
+ }
852
+ },
853
+ "total_pass_at_k": {
854
+ "pass@1": 0.0027,
855
+ "pass@2": 0.0045,
856
+ "pass@4": 0.0069,
857
+ "pass@8": 0.0093,
858
+ "pass@16": 0.012,
859
+ "pass@32": 0.0152,
860
+ "pass@64": 0.0189,
861
+ "pass@128": 0.0226
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
+ }
results/context/block4/SDAR-100M-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
+ SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm,0.7950407986111111,0.35009765625,0.5608601973684211,0.0,0.0,0.0,191.67480555555557,347.2910515625,1152000,1280000,2432000
results/context/block4/SDAR-100M-0.9zoo_op2-20+0.1teacher_op2/summary.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "SDAR-100M-0.9zoo_op2-20+0.1teacher_op2-dlm",
4
+ "id_acc": 0.7950407986111111,
5
+ "ood_acc": 0.35009765625,
6
+ "total_acc": 0.5608601973684211,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 191.67480555555557,
11
+ "ood_avg_resp_len": 347.2910515625,
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": 1364012,
28
+ "answer_accuracy": 0.5608601973684211,
29
+ "avg_response_len": 273.5780929276316,
30
+ "resp_tokens_sum": 665341922,
31
+ "pass_at_k": {
32
+ "pass@1": 0.5608601973684211,
33
+ "pass@2": 0.646692628470746,
34
+ "pass@4": 0.7209112474838338,
35
+ "pass@8": 0.7830071033739708,
36
+ "pass@16": 0.8332532701694395,
37
+ "pass@32": 0.874143958618523,
38
+ "pass@64": 0.9078802546952751,
39
+ "pass@128": 0.9346842105263158
40
+ },
41
+ "per_op_pass_at_k": {
42
+ "10": {
43
+ "pass@1": 0.60040625,
44
+ "pass@2": 0.7095417076771655,
45
+ "pass@4": 0.7922922718410202,
46
+ "pass@8": 0.8536646585430178,
47
+ "pass@16": 0.8970646089375027,
48
+ "pass@32": 0.9278957351338625,
49
+ "pass@64": 0.9501738187952159,
50
+ "pass@128": 0.964
51
+ },
52
+ "2": {
53
+ "pass@1": 0.999359375,
54
+ "pass@2": 0.999788877952756,
55
+ "pass@4": 0.9999602164416947,
56
+ "pass@8": 0.9999986593035204,
57
+ "pass@16": 0.9999999991433727,
58
+ "pass@32": 1.0,
59
+ "pass@64": 1.0,
60
+ "pass@128": 1.0
61
+ },
62
+ "3": {
63
+ "pass@1": 0.853296875,
64
+ "pass@2": 0.9059648129921256,
65
+ "pass@4": 0.9374243321147357,
66
+ "pass@8": 0.95700210973271,
67
+ "pass@16": 0.9705665053339986,
68
+ "pass@32": 0.9808741341838165,
69
+ "pass@64": 0.9882856831646993,
70
+ "pass@128": 0.993
71
+ },
72
+ "4": {
73
+ "pass@1": 0.933296875,
74
+ "pass@2": 0.9605745570866148,
75
+ "pass@4": 0.9749672712785896,
76
+ "pass@8": 0.9835223449928111,
77
+ "pass@16": 0.9891968090319382,
78
+ "pass@32": 0.9930382063200087,
79
+ "pass@64": 0.9954544705589414,
80
+ "pass@128": 0.997
81
+ },
82
+ "5": {
83
+ "pass@1": 0.8969609375,
84
+ "pass@2": 0.9238891486220477,
85
+ "pass@4": 0.9422059093550802,
86
+ "pass@8": 0.9569563523578236,
87
+ "pass@16": 0.969469384243192,
88
+ "pass@32": 0.9790453107712829,
89
+ "pass@64": 0.9855235851364291,
90
+ "pass@128": 0.989
91
+ },
92
+ "6": {
93
+ "pass@1": 0.7950390625,
94
+ "pass@2": 0.8500728346456693,
95
+ "pass@4": 0.8884933542369708,
96
+ "pass@8": 0.919191859282107,
97
+ "pass@16": 0.9442962035744217,
98
+ "pass@32": 0.9633178311861345,
99
+ "pass@64": 0.9753459978184749,
100
+ "pass@128": 0.983
101
+ },
102
+ "7": {
103
+ "pass@1": 0.7745390625,
104
+ "pass@2": 0.8443341535433072,
105
+ "pass@4": 0.8893270361829764,
106
+ "pass@8": 0.9198137493815588,
107
+ "pass@16": 0.9415577088491797,
108
+ "pass@32": 0.95791377452376,
109
+ "pass@64": 0.9705372614318992,
110
+ "pass@128": 0.98
111
+ },
112
+ "8": {
113
+ "pass@1": 0.6962109375,
114
+ "pass@2": 0.7824670275590552,
115
+ "pass@4": 0.8416537919947508,
116
+ "pass@8": 0.8825173414680063,
117
+ "pass@16": 0.9106842561584872,
118
+ "pass@32": 0.9317685203443532,
119
+ "pass@64": 0.9487756713205382,
120
+ "pass@128": 0.962
121
+ },
122
+ "9": {
123
+ "pass@1": 0.6062578125,
124
+ "pass@2": 0.7176470226377951,
125
+ "pass@4": 0.7993743726096733,
126
+ "pass@8": 0.857876432320144,
127
+ "pass@16": 0.8989911858415434,
128
+ "pass@32": 0.9279812786598292,
129
+ "pass@64": 0.9481752047945332,
130
+ "pass@128": 0.961
131
+ },
132
+ "11": {
133
+ "pass@1": 0.55,
134
+ "pass@2": 0.6644686269685045,
135
+ "pass@4": 0.7554949091676033,
136
+ "pass@8": 0.8267174476106581,
137
+ "pass@16": 0.8800008354399814,
138
+ "pass@32": 0.9183316005509333,
139
+ "pass@64": 0.946713590674644,
140
+ "pass@128": 0.965
141
+ },
142
+ "12": {
143
+ "pass@1": 0.6275234375,
144
+ "pass@2": 0.7376862696850398,
145
+ "pass@4": 0.8155612725909257,
146
+ "pass@8": 0.8696673090375664,
147
+ "pass@16": 0.9069490704010332,
148
+ "pass@32": 0.9345824383122423,
149
+ "pass@64": 0.9566355686746477,
150
+ "pass@128": 0.973
151
+ },
152
+ "13": {
153
+ "pass@1": 0.56715625,
154
+ "pass@2": 0.6825030757874021,
155
+ "pass@4": 0.772606745406825,
156
+ "pass@8": 0.8417930717051642,
157
+ "pass@16": 0.8930984286997508,
158
+ "pass@32": 0.9305863285411988,
159
+ "pass@64": 0.957979634084356,
160
+ "pass@128": 0.976
161
+ },
162
+ "14": {
163
+ "pass@1": 0.395359375,
164
+ "pass@2": 0.5176122047244094,
165
+ "pass@4": 0.62899828327709,
166
+ "pass@8": 0.7233866013178575,
167
+ "pass@16": 0.8002926961241378,
168
+ "pass@32": 0.8620897217799554,
169
+ "pass@64": 0.9101993889981667,
170
+ "pass@128": 0.945
171
+ },
172
+ "15": {
173
+ "pass@1": 0.3023984375,
174
+ "pass@2": 0.4241403789370082,
175
+ "pass@4": 0.5439839366329201,
176
+ "pass@8": 0.6498669531400889,
177
+ "pass@16": 0.7388635243222283,
178
+ "pass@32": 0.811690443284991,
179
+ "pass@64": 0.868667672101463,
180
+ "pass@128": 0.91
181
+ },
182
+ "16": {
183
+ "pass@1": 0.28628125,
184
+ "pass@2": 0.4098443651574804,
185
+ "pass@4": 0.53514521616048,
186
+ "pass@8": 0.6481046812551223,
187
+ "pass@16": 0.7400196560843376,
188
+ "pass@32": 0.8094523138499621,
189
+ "pass@64": 0.8630424460190331,
190
+ "pass@128": 0.908
191
+ },
192
+ "17": {
193
+ "pass@1": 0.24675,
194
+ "pass@2": 0.35776919291338577,
195
+ "pass@4": 0.47396416788526324,
196
+ "pass@8": 0.5805913679278526,
197
+ "pass@16": 0.6708496973546186,
198
+ "pass@32": 0.747876572986338,
199
+ "pass@64": 0.8143806632004396,
200
+ "pass@128": 0.87
201
+ },
202
+ "18": {
203
+ "pass@1": 0.193015625,
204
+ "pass@2": 0.29202448326771696,
205
+ "pass@4": 0.40241395856767875,
206
+ "pass@8": 0.509743436064761,
207
+ "pass@16": 0.6061520258445829,
208
+ "pass@32": 0.6915977882757431,
209
+ "pass@64": 0.7662865861840186,
210
+ "pass@128": 0.829
211
+ },
212
+ "19": {
213
+ "pass@1": 0.1789296875,
214
+ "pass@2": 0.271176919291339,
215
+ "pass@4": 0.3740147122234719,
216
+ "pass@8": 0.47313048990847273,
217
+ "pass@16": 0.5621066862281713,
218
+ "pass@32": 0.644930194885751,
219
+ "pass@64": 0.7242095021188344,
220
+ "pass@128": 0.796
221
+ },
222
+ "20": {
223
+ "pass@1": 0.1535625,
224
+ "pass@2": 0.2356542814960631,
225
+ "pass@4": 0.3294319442257221,
226
+ "pass@8": 0.4235900987560518,
227
+ "pass@16": 0.5116528516064207,
228
+ "pass@32": 0.5957630201612798,
229
+ "pass@64": 0.6793380941337777,
230
+ "pass@128": 0.758
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
+ ]
results/context/graphs/op10_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op11_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op12_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op13_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op14_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op15_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op16_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op17_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op18_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op19_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op20_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op2_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op3_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op4_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op5_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op6_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op7_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op8_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/context/graphs/op9_1k_graphs.jsonl ADDED
The diff for this file is too large to render. See raw diff