ZachW commited on
Commit
e0bf3a4
·
verified ·
1 Parent(s): 7b17ba0

Upload extrapolation artifact: 020305 pretrain checkpoint-18809 metrics

Browse files
020305/evals/pretrain_ckpt18809/pretrain_ckpt18809_metrics.json ADDED
@@ -0,0 +1,1897 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": "pretrain_ckpt18809",
3
+ "id": {
4
+ "answer_accuracy": 0.3620373263888889,
5
+ "avg_response_len": 204.96420920138888,
6
+ "avg_loss": 0.0,
7
+ "count": 1152000,
8
+ "validation_metrics": {},
9
+ "pass_at_k": {
10
+ "pass@1": 0.3620373263888889,
11
+ "pass@2": 0.4239386756343036,
12
+ "pass@4": 0.48403845929675654,
13
+ "pass@8": 0.5413847569297006,
14
+ "pass@16": 0.5955209111027207,
15
+ "pass@32": 0.64618112939657,
16
+ "pass@64": 0.693051089543297,
17
+ "pass@128": 0.7367777777777778
18
+ },
19
+ "per_op_pass_at_k": {
20
+ "10": {
21
+ "pass@1": 0.153078125,
22
+ "pass@2": 0.20062807578740144,
23
+ "pass@4": 0.24996057695913,
24
+ "pass@8": 0.30092839238317415,
25
+ "pass@16": 0.35337128470273454,
26
+ "pass@32": 0.4057937324821779,
27
+ "pass@64": 0.45745223284049236,
28
+ "pass@128": 0.511
29
+ },
30
+ "2": {
31
+ "pass@1": 0.7223515625,
32
+ "pass@2": 0.7726219242125981,
33
+ "pass@4": 0.816936636670416,
34
+ "pass@8": 0.8547507956069074,
35
+ "pass@16": 0.8857456544394229,
36
+ "pass@32": 0.9118260535213927,
37
+ "pass@64": 0.9343826419291248,
38
+ "pass@128": 0.954
39
+ },
40
+ "3": {
41
+ "pass@1": 0.6634375,
42
+ "pass@2": 0.728427411417323,
43
+ "pass@4": 0.7820601895388077,
44
+ "pass@8": 0.8274680138797387,
45
+ "pass@16": 0.8668559639271197,
46
+ "pass@32": 0.900318968240842,
47
+ "pass@64": 0.9265554947853907,
48
+ "pass@128": 0.947
49
+ },
50
+ "4": {
51
+ "pass@1": 0.49425,
52
+ "pass@2": 0.565187253937008,
53
+ "pass@4": 0.6314227619984999,
54
+ "pass@8": 0.6908256447524266,
55
+ "pass@16": 0.7441946217927244,
56
+ "pass@32": 0.7921254407781363,
57
+ "pass@64": 0.8329447961928805,
58
+ "pass@128": 0.867
59
+ },
60
+ "5": {
61
+ "pass@1": 0.2666875,
62
+ "pass@2": 0.3425367864173231,
63
+ "pass@4": 0.41431873622047216,
64
+ "pass@8": 0.48238861153714807,
65
+ "pass@16": 0.5474928528605428,
66
+ "pass@32": 0.6100132327723347,
67
+ "pass@64": 0.6666898943727598,
68
+ "pass@128": 0.714
69
+ },
70
+ "6": {
71
+ "pass@1": 0.3322109375,
72
+ "pass@2": 0.38863324311023634,
73
+ "pass@4": 0.4494082936820398,
74
+ "pass@8": 0.5135329718566175,
75
+ "pass@16": 0.5766645404957943,
76
+ "pass@32": 0.634882092289773,
77
+ "pass@64": 0.6863767949088386,
78
+ "pass@128": 0.731
79
+ },
80
+ "7": {
81
+ "pass@1": 0.2464765625,
82
+ "pass@2": 0.3143423966535434,
83
+ "pass@4": 0.3799570868016498,
84
+ "pass@8": 0.4408821430672949,
85
+ "pass@16": 0.4967942984254299,
86
+ "pass@32": 0.5486898689322044,
87
+ "pass@64": 0.5979581445148634,
88
+ "pass@128": 0.647
89
+ },
90
+ "8": {
91
+ "pass@1": 0.2124140625,
92
+ "pass@2": 0.2722742372047242,
93
+ "pass@4": 0.33279232649043833,
94
+ "pass@8": 0.3928992314946121,
95
+ "pass@16": 0.4520373656761814,
96
+ "pass@32": 0.5096369501508324,
97
+ "pass@64": 0.5668209754644449,
98
+ "pass@128": 0.624
99
+ },
100
+ "9": {
101
+ "pass@1": 0.1674296875,
102
+ "pass@2": 0.230796751968504,
103
+ "pass@4": 0.29948952530933626,
104
+ "pass@8": 0.36878700778934914,
105
+ "pass@16": 0.43653161760440473,
106
+ "pass@32": 0.5023438254014455,
107
+ "pass@64": 0.5682788308808282,
108
+ "pass@128": 0.636
109
+ }
110
+ },
111
+ "per_op_accuracy": {
112
+ "10": 0.153078125,
113
+ "2": 0.7223515625,
114
+ "3": 0.6634375,
115
+ "4": 0.49425,
116
+ "5": 0.2666875,
117
+ "6": 0.3322109375,
118
+ "7": 0.2464765625,
119
+ "8": 0.2124140625,
120
+ "9": 0.1674296875
121
+ },
122
+ "per_op_avg_response_len": {
123
+ "10": 274.915625,
124
+ "2": 120.882765625,
125
+ "3": 150.5270546875,
126
+ "4": 167.6719453125,
127
+ "5": 181.6410703125,
128
+ "6": 211.30146875,
129
+ "7": 229.0457265625,
130
+ "8": 247.367390625,
131
+ "9": 261.3248359375
132
+ },
133
+ "per_op_avg_loss": {},
134
+ "per_op_length": {
135
+ "10": 274.915625,
136
+ "2": 120.882765625,
137
+ "3": 150.5270546875,
138
+ "4": 167.6719453125,
139
+ "5": 181.6410703125,
140
+ "6": 211.30146875,
141
+ "7": 229.0457265625,
142
+ "8": 247.367390625,
143
+ "9": 261.3248359375
144
+ },
145
+ "per_op_loss": {},
146
+ "per_template": {
147
+ "crazy_zootopia": {
148
+ "count": 379008,
149
+ "correct": 133815,
150
+ "answer_accuracy": 0.3530664260385005,
151
+ "avg_response_len": 195.14912613981764,
152
+ "resp_tokens_sum": 73963080,
153
+ "pass_at_k": {
154
+ "pass@1": 0.3530664260385005,
155
+ "pass@2": 0.41746759713546594,
156
+ "pass@4": 0.48063072919456573,
157
+ "pass@8": 0.5404106216352604,
158
+ "pass@16": 0.5960848866259677,
159
+ "pass@32": 0.6473489272599112,
160
+ "pass@64": 0.6938996560628597,
161
+ "pass@128": 0.7369132049983114
162
+ },
163
+ "per_op_pass_at_k": {
164
+ "10": {
165
+ "pass@1": 0.16118178466076696,
166
+ "pass@2": 0.21100700009290868,
167
+ "pass@4": 0.26204468053219016,
168
+ "pass@8": 0.313965959315187,
169
+ "pass@16": 0.3669307944259261,
170
+ "pass@32": 0.4192929029900247,
171
+ "pass@64": 0.4697690954137164,
172
+ "pass@128": 0.5221238938053098
173
+ },
174
+ "2": {
175
+ "pass@1": 0.6974785825545171,
176
+ "pass@2": 0.7498029962960233,
177
+ "pass@4": 0.7984764164993392,
178
+ "pass@8": 0.8426580781725969,
179
+ "pass@16": 0.8811400390570819,
180
+ "pass@32": 0.9154355567676705,
181
+ "pass@64": 0.9439033477168228,
182
+ "pass@128": 0.9626168224299065
183
+ },
184
+ "3": {
185
+ "pass@1": 0.6284881498470948,
186
+ "pass@2": 0.6921070968479855,
187
+ "pass@4": 0.7454523299266487,
188
+ "pass@8": 0.7916577080236396,
189
+ "pass@16": 0.8325218506692965,
190
+ "pass@32": 0.8683391227625886,
191
+ "pass@64": 0.8968584133079681,
192
+ "pass@128": 0.9174311926605505
193
+ },
194
+ "4": {
195
+ "pass@1": 0.459765625,
196
+ "pass@2": 0.5297778512549212,
197
+ "pass@4": 0.5945688033136481,
198
+ "pass@8": 0.6530113938111209,
199
+ "pass@16": 0.7081231827169705,
200
+ "pass@32": 0.759363772014444,
201
+ "pass@64": 0.8044523643734547,
202
+ "pass@128": 0.84375
203
+ },
204
+ "5": {
205
+ "pass@1": 0.26671626984126984,
206
+ "pass@2": 0.3425470253718283,
207
+ "pass@4": 0.41556439968813413,
208
+ "pass@8": 0.48176800859338753,
209
+ "pass@16": 0.5418400059324522,
210
+ "pass@32": 0.5976897340165899,
211
+ "pass@64": 0.6484423831216877,
212
+ "pass@128": 0.6952380952380952
213
+ },
214
+ "6": {
215
+ "pass@1": 0.33493169910179643,
216
+ "pass@2": 0.3905675361874673,
217
+ "pass@4": 0.449119640078673,
218
+ "pass@8": 0.509693792465805,
219
+ "pass@16": 0.5692551867943821,
220
+ "pass@32": 0.6241793020699291,
221
+ "pass@64": 0.6729702040598893,
222
+ "pass@128": 0.718562874251497
223
+ },
224
+ "7": {
225
+ "pass@1": 0.2567030325443787,
226
+ "pass@2": 0.33237031461119126,
227
+ "pass@4": 0.40505862386654345,
228
+ "pass@8": 0.47228374550038577,
229
+ "pass@16": 0.533299549975349,
230
+ "pass@32": 0.5853612209560378,
231
+ "pass@64": 0.6296383818221275,
232
+ "pass@128": 0.6715976331360947
233
+ },
234
+ "8": {
235
+ "pass@1": 0.22741386217948717,
236
+ "pass@2": 0.29118518763880463,
237
+ "pass@4": 0.3558928727659042,
238
+ "pass@8": 0.41934049330733497,
239
+ "pass@16": 0.4790422934302815,
240
+ "pass@32": 0.5353208860582773,
241
+ "pass@64": 0.5903250480614363,
242
+ "pass@128": 0.6442307692307693
243
+ },
244
+ "9": {
245
+ "pass@1": 0.17086267605633804,
246
+ "pass@2": 0.24369766829322378,
247
+ "pass@4": 0.32428576603980847,
248
+ "pass@8": 0.4026243423547874,
249
+ "pass@16": 0.4743958200381107,
250
+ "pass@32": 0.5415250798666842,
251
+ "pass@64": 0.6075046168962964,
252
+ "pass@128": 0.6732394366197183
253
+ }
254
+ }
255
+ },
256
+ "teachers_in_school": {
257
+ "count": 390656,
258
+ "correct": 134332,
259
+ "answer_accuracy": 0.343862631061599,
260
+ "avg_response_len": 203.14277778915465,
261
+ "resp_tokens_sum": 79358945,
262
+ "pass_at_k": {
263
+ "pass@1": 0.343862631061599,
264
+ "pass@2": 0.4041069058239878,
265
+ "pass@4": 0.4631716250286882,
266
+ "pass@8": 0.5200616651906146,
267
+ "pass@16": 0.574551588816319,
268
+ "pass@32": 0.6266133409455688,
269
+ "pass@64": 0.6765130476593962,
270
+ "pass@128": 0.7250982961992136
271
+ },
272
+ "per_op_pass_at_k": {
273
+ "10": {
274
+ "pass@1": 0.14239838957055215,
275
+ "pass@2": 0.18646215762523552,
276
+ "pass@4": 0.23446961643214842,
277
+ "pass@8": 0.28705840266279736,
278
+ "pass@16": 0.34176712763641864,
279
+ "pass@32": 0.393697107128622,
280
+ "pass@64": 0.4396077946700623,
281
+ "pass@128": 0.4815950920245399
282
+ },
283
+ "2": {
284
+ "pass@1": 0.6969747340425532,
285
+ "pass@2": 0.753928406887969,
286
+ "pass@4": 0.8035614455867784,
287
+ "pass@8": 0.843974271174507,
288
+ "pass@16": 0.8749837921659976,
289
+ "pass@32": 0.8982223777835114,
290
+ "pass@64": 0.9187984833921925,
291
+ "pass@128": 0.9422492401215805
292
+ },
293
+ "3": {
294
+ "pass@1": 0.6451467803030303,
295
+ "pass@2": 0.7162670007158197,
296
+ "pass@4": 0.7793047312267779,
297
+ "pass@8": 0.8333319187968913,
298
+ "pass@16": 0.8770961555446578,
299
+ "pass@32": 0.909542515519656,
300
+ "pass@64": 0.9324872967635861,
301
+ "pass@128": 0.9515151515151515
302
+ },
303
+ "4": {
304
+ "pass@1": 0.522605399408284,
305
+ "pass@2": 0.5892557104086102,
306
+ "pass@4": 0.6476280076676802,
307
+ "pass@8": 0.6990817626466677,
308
+ "pass@16": 0.7463410223529519,
309
+ "pass@32": 0.7917997275040872,
310
+ "pass@64": 0.8345071710379106,
311
+ "pass@128": 0.8727810650887574
312
+ },
313
+ "5": {
314
+ "pass@1": 0.23156702898550724,
315
+ "pass@2": 0.3060135655597396,
316
+ "pass@4": 0.3781115583378164,
317
+ "pass@8": 0.44872429897310967,
318
+ "pass@16": 0.5185551846144103,
319
+ "pass@32": 0.5877484160335491,
320
+ "pass@64": 0.6546433701390305,
321
+ "pass@128": 0.7130434782608696
322
+ },
323
+ "6": {
324
+ "pass@1": 0.3259760028653295,
325
+ "pass@2": 0.3796741392730634,
326
+ "pass@4": 0.4381010783394194,
327
+ "pass@8": 0.49888167562112606,
328
+ "pass@16": 0.5602468122792769,
329
+ "pass@32": 0.6221272504599301,
330
+ "pass@64": 0.6829418759180574,
331
+ "pass@128": 0.7363896848137536
332
+ },
333
+ "7": {
334
+ "pass@1": 0.2296333092485549,
335
+ "pass@2": 0.29712497439807023,
336
+ "pass@4": 0.36502451770840794,
337
+ "pass@8": 0.426388535715249,
338
+ "pass@16": 0.4804327509720443,
339
+ "pass@32": 0.533175386708967,
340
+ "pass@64": 0.587141630247611,
341
+ "pass@128": 0.6416184971098265
342
+ },
343
+ "8": {
344
+ "pass@1": 0.18727992957746478,
345
+ "pass@2": 0.2457202367749805,
346
+ "pass@4": 0.30368673880553654,
347
+ "pass@8": 0.36232621489128214,
348
+ "pass@16": 0.42333938653385483,
349
+ "pass@32": 0.4851196069605558,
350
+ "pass@64": 0.5487500600105882,
351
+ "pass@128": 0.6197183098591549
352
+ },
353
+ "9": {
354
+ "pass@1": 0.13356100299401197,
355
+ "pass@2": 0.18219085942288651,
356
+ "pass@4": 0.23733269989829103,
357
+ "pass@8": 0.29824739855791427,
358
+ "pass@16": 0.36406530154791894,
359
+ "pass@32": 0.43171976382911487,
360
+ "pass@64": 0.5005413019533322,
361
+ "pass@128": 0.5748502994011976
362
+ }
363
+ }
364
+ },
365
+ "movie_festival_awards": {
366
+ "count": 382336,
367
+ "correct": 148920,
368
+ "answer_accuracy": 0.38950033478406426,
369
+ "avg_response_len": 216.5549255105457,
370
+ "resp_tokens_sum": 82796744,
371
+ "pass_at_k": {
372
+ "pass@1": 0.38950033478406426,
373
+ "pass@2": 0.4506167556129071,
374
+ "pass@4": 0.5087374439029585,
375
+ "pass@8": 0.5641375157494188,
376
+ "pass@16": 0.6163874795974066,
377
+ "pass@32": 0.6650170988907378,
378
+ "pass@64": 0.7091078348948805,
379
+ "pass@128": 0.7485771677268162
380
+ },
381
+ "per_op_pass_at_k": {
382
+ "10": {
383
+ "pass@1": 0.1552705223880597,
384
+ "pass@2": 0.20391056528381718,
385
+ "pass@4": 0.2528069710502605,
386
+ "pass@8": 0.30123251614105645,
387
+ "pass@16": 0.35094227397872746,
388
+ "pass@32": 0.40390501923769717,
389
+ "pass@64": 0.4623533386053791,
390
+ "pass@128": 0.5283582089552239
391
+ },
392
+ "2": {
393
+ "pass@1": 0.7690178571428572,
394
+ "pass@2": 0.811122047244094,
395
+ "pass@4": 0.8464399753602228,
396
+ "pass@8": 0.8759714779916868,
397
+ "pass@16": 0.9000858122271072,
398
+ "pass@32": 0.9213030785948414,
399
+ "pass@64": 0.940299903645694,
400
+ "pass@128": 0.9571428571428572
401
+ },
402
+ "3": {
403
+ "pass@1": 0.7143540451895044,
404
+ "pass@2": 0.7747530044076125,
405
+ "pass@4": 0.8196114179240708,
406
+ "pass@8": 0.8559662103586972,
407
+ "pass@16": 0.8897364064971576,
408
+ "pass@32": 0.9219330757317451,
409
+ "pass@64": 0.9491603081682237,
410
+ "pass@128": 0.9708454810495627
411
+ },
412
+ "4": {
413
+ "pass@1": 0.4984923245614035,
414
+ "pass@2": 0.5745319047290139,
415
+ "pass@4": 0.6498902875627387,
416
+ "pass@8": 0.7180478449072955,
417
+ "pass@16": 0.7758243794385915,
418
+ "pass@32": 0.8231015375354785,
419
+ "pass@64": 0.8580602800659657,
420
+ "pass@128": 0.8830409356725146
421
+ },
422
+ "5": {
423
+ "pass@1": 0.30229779411764707,
424
+ "pass@2": 0.379587627373784,
425
+ "pass@4": 0.4499043020357746,
426
+ "pass@8": 0.5171229578956147,
427
+ "pass@16": 0.5820932714701458,
428
+ "pass@32": 0.6440228324280421,
429
+ "pass@64": 0.6958193558572406,
430
+ "pass@128": 0.7323529411764705
431
+ },
432
+ "6": {
433
+ "pass@1": 0.33620859621451105,
434
+ "pass@2": 0.39645871109565534,
435
+ "pass@4": 0.4621610648432353,
436
+ "pass@8": 0.5337083292784405,
437
+ "pass@16": 0.6025462795615276,
438
+ "pass@32": 0.6602012460186194,
439
+ "pass@64": 0.704284012799474,
440
+ "pass@128": 0.7381703470031545
441
+ },
442
+ "7": {
443
+ "pass@1": 0.25398041930379744,
444
+ "pass@2": 0.31391135814312754,
445
+ "pass@4": 0.36945819242926925,
446
+ "pass@8": 0.4231639358566098,
447
+ "pass@16": 0.47566240094124973,
448
+ "pass@32": 0.5264528242017742,
449
+ "pass@64": 0.5759157195990866,
450
+ "pass@128": 0.6265822784810127
451
+ },
452
+ "8": {
453
+ "pass@1": 0.22515484234234234,
454
+ "pass@2": 0.2828641880069045,
455
+ "pass@4": 0.3421770507853185,
456
+ "pass@8": 0.4007182921811377,
457
+ "pass@16": 0.45732939311235854,
458
+ "pass@32": 0.5117098295184779,
459
+ "pass@64": 0.5640639314279801,
460
+ "pass@128": 0.6096096096096096
461
+ },
462
+ "9": {
463
+ "pass@1": 0.1998844453376206,
464
+ "pass@2": 0.2682711661645189,
465
+ "pass@4": 0.33793876719991994,
466
+ "pass@8": 0.4059187624921453,
467
+ "pass@16": 0.47113598319572814,
468
+ "pass@32": 0.5334663052406697,
469
+ "pass@64": 0.5962504727660117,
470
+ "pass@128": 0.6591639871382636
471
+ }
472
+ }
473
+ }
474
+ }
475
+ },
476
+ "ood": {
477
+ "answer_accuracy": 0.1004375,
478
+ "avg_response_len": 293.3315125,
479
+ "avg_loss": 0.0,
480
+ "count": 1280000,
481
+ "validation_metrics": {},
482
+ "pass_at_k": {
483
+ "pass@1": 0.1004375,
484
+ "pass@2": 0.14039777312992213,
485
+ "pass@4": 0.18548175144357115,
486
+ "pass@8": 0.23275793252484883,
487
+ "pass@16": 0.2799445370150923,
488
+ "pass@32": 0.32658746674399247,
489
+ "pass@64": 0.3725404493680912,
490
+ "pass@128": 0.4166
491
+ },
492
+ "per_op_pass_at_k": {
493
+ "11": {
494
+ "pass@1": 0.131390625,
495
+ "pass@2": 0.17717458169291328,
496
+ "pass@4": 0.22935256805399312,
497
+ "pass@8": 0.28690414567159045,
498
+ "pass@16": 0.3484727346081054,
499
+ "pass@32": 0.4136139328033935,
500
+ "pass@64": 0.4807059952733389,
501
+ "pass@128": 0.541
502
+ },
503
+ "12": {
504
+ "pass@1": 0.1196640625,
505
+ "pass@2": 0.16031951279527545,
506
+ "pass@4": 0.20569369722534664,
507
+ "pass@8": 0.2532498672669628,
508
+ "pass@16": 0.30201560584141535,
509
+ "pass@32": 0.35198840183015,
510
+ "pass@64": 0.4024866801172818,
511
+ "pass@128": 0.454
512
+ },
513
+ "13": {
514
+ "pass@1": 0.0911875,
515
+ "pass@2": 0.12641806102362202,
516
+ "pass@4": 0.16787350693663286,
517
+ "pass@8": 0.21486568791025193,
518
+ "pass@16": 0.2662775544931056,
519
+ "pass@32": 0.3211539302060912,
520
+ "pass@64": 0.37813810394040775,
521
+ "pass@128": 0.438
522
+ },
523
+ "14": {
524
+ "pass@1": 0.0923203125,
525
+ "pass@2": 0.1340594242125984,
526
+ "pass@4": 0.18355495913010858,
527
+ "pass@8": 0.23832816771772392,
528
+ "pass@16": 0.29379041445980003,
529
+ "pass@32": 0.3470037731751372,
530
+ "pass@64": 0.39704840454373874,
531
+ "pass@128": 0.444
532
+ },
533
+ "15": {
534
+ "pass@1": 0.097203125,
535
+ "pass@2": 0.14641240157480317,
536
+ "pass@4": 0.20366941732283445,
537
+ "pass@8": 0.26212224223981484,
538
+ "pass@16": 0.31753071976349556,
539
+ "pass@32": 0.370484303913742,
540
+ "pass@64": 0.4217421119565217,
541
+ "pass@128": 0.471
542
+ },
543
+ "16": {
544
+ "pass@1": 0.08975,
545
+ "pass@2": 0.12207874015748027,
546
+ "pass@4": 0.15670591497937744,
547
+ "pass@8": 0.19271137721874232,
548
+ "pass@16": 0.2286799558511221,
549
+ "pass@32": 0.2636580337443535,
550
+ "pass@64": 0.2971672780390768,
551
+ "pass@128": 0.329
552
+ },
553
+ "17": {
554
+ "pass@1": 0.1024765625,
555
+ "pass@2": 0.14214628444881894,
556
+ "pass@4": 0.1862614367266591,
557
+ "pass@8": 0.23049963431960444,
558
+ "pass@16": 0.27301508275497594,
559
+ "pass@32": 0.3149990806667348,
560
+ "pass@64": 0.3573013854679643,
561
+ "pass@128": 0.398
562
+ },
563
+ "18": {
564
+ "pass@1": 0.1019140625,
565
+ "pass@2": 0.14577005413385827,
566
+ "pass@4": 0.19389246644169467,
567
+ "pass@8": 0.24124608140188403,
568
+ "pass@16": 0.2849439772933588,
569
+ "pass@32": 0.3251253436965035,
570
+ "pass@64": 0.3625604521014223,
571
+ "pass@128": 0.398
572
+ },
573
+ "19": {
574
+ "pass@1": 0.0853671875,
575
+ "pass@2": 0.11802571358267713,
576
+ "pass@4": 0.15243764351331066,
577
+ "pass@8": 0.18750068166279207,
578
+ "pass@16": 0.22272310002742723,
579
+ "pass@32": 0.2576774472505532,
580
+ "pass@64": 0.2927042928753672,
581
+ "pass@128": 0.326
582
+ },
583
+ "20": {
584
+ "pass@1": 0.0931015625,
585
+ "pass@2": 0.13157295767716534,
586
+ "pass@4": 0.17537590410573672,
587
+ "pass@8": 0.22015143983909957,
588
+ "pass@16": 0.26199622505809744,
589
+ "pass@32": 0.3001704201532964,
590
+ "pass@64": 0.33554978936583424,
591
+ "pass@128": 0.367
592
+ }
593
+ },
594
+ "per_op_accuracy": {
595
+ "11": 0.131390625,
596
+ "12": 0.1196640625,
597
+ "13": 0.0911875,
598
+ "14": 0.0923203125,
599
+ "15": 0.097203125,
600
+ "16": 0.08975,
601
+ "17": 0.1024765625,
602
+ "18": 0.1019140625,
603
+ "19": 0.0853671875,
604
+ "20": 0.0931015625
605
+ },
606
+ "per_op_avg_response_len": {
607
+ "11": 288.871875,
608
+ "12": 291.25571875,
609
+ "13": 292.0997265625,
610
+ "14": 293.006984375,
611
+ "15": 292.100015625,
612
+ "16": 290.70203125,
613
+ "17": 296.6965078125,
614
+ "18": 296.130765625,
615
+ "19": 293.92978125,
616
+ "20": 298.52171875
617
+ },
618
+ "per_op_avg_loss": {},
619
+ "per_op_length": {
620
+ "11": 288.871875,
621
+ "12": 291.25571875,
622
+ "13": 292.0997265625,
623
+ "14": 293.006984375,
624
+ "15": 292.100015625,
625
+ "16": 290.70203125,
626
+ "17": 296.6965078125,
627
+ "18": 296.130765625,
628
+ "19": 293.92978125,
629
+ "20": 298.52171875
630
+ },
631
+ "per_op_loss": {},
632
+ "per_template": {
633
+ "crazy_zootopia": {
634
+ "count": 430720,
635
+ "correct": 41145,
636
+ "answer_accuracy": 0.09552609583952451,
637
+ "avg_response_len": 279.88689635958394,
638
+ "resp_tokens_sum": 120552884,
639
+ "pass_at_k": {
640
+ "pass@1": 0.09552609583952451,
641
+ "pass@2": 0.13479601268266436,
642
+ "pass@4": 0.1797131049740626,
643
+ "pass@8": 0.2267832250472377,
644
+ "pass@16": 0.2730813366645391,
645
+ "pass@32": 0.3184938057175483,
646
+ "pass@64": 0.3631956770227794,
647
+ "pass@128": 0.4059435364041605
648
+ },
649
+ "per_op_pass_at_k": {
650
+ "11": {
651
+ "pass@1": 0.13493714589235128,
652
+ "pass@2": 0.18312558553233246,
653
+ "pass@4": 0.23801532607645007,
654
+ "pass@8": 0.2983196016544395,
655
+ "pass@16": 0.3600201317791979,
656
+ "pass@32": 0.4206971006327828,
657
+ "pass@64": 0.48044195628551944,
658
+ "pass@128": 0.5325779036827195
659
+ },
660
+ "12": {
661
+ "pass@1": 0.1138771186440678,
662
+ "pass@2": 0.15339073412963222,
663
+ "pass@4": 0.19769429801147728,
664
+ "pass@8": 0.24559352472202536,
665
+ "pass@16": 0.29559038484450695,
666
+ "pass@32": 0.34574248692946935,
667
+ "pass@64": 0.3942527843078104,
668
+ "pass@128": 0.4435028248587571
669
+ },
670
+ "13": {
671
+ "pass@1": 0.08118632445141066,
672
+ "pass@2": 0.11738168921087064,
673
+ "pass@4": 0.16368368471966077,
674
+ "pass@8": 0.21852505040149559,
675
+ "pass@16": 0.27768709595526475,
676
+ "pass@32": 0.3372075681784244,
677
+ "pass@64": 0.39446850776198933,
678
+ "pass@128": 0.4482758620689655
679
+ },
680
+ "14": {
681
+ "pass@1": 0.08464758566978194,
682
+ "pass@2": 0.12638439178747513,
683
+ "pass@4": 0.17817912538970013,
684
+ "pass@8": 0.23636157858881193,
685
+ "pass@16": 0.29483488034710237,
686
+ "pass@32": 0.3511077582240689,
687
+ "pass@64": 0.4042818757611095,
688
+ "pass@128": 0.45482866043613707
689
+ },
690
+ "15": {
691
+ "pass@1": 0.09022760115606937,
692
+ "pass@2": 0.1371285586682445,
693
+ "pass@4": 0.19187320163375532,
694
+ "pass@8": 0.2476590145157713,
695
+ "pass@16": 0.30101540861456305,
696
+ "pass@32": 0.35355459521979815,
697
+ "pass@64": 0.403824523100272,
698
+ "pass@128": 0.4479768786127168
699
+ },
700
+ "16": {
701
+ "pass@1": 0.10040322580645161,
702
+ "pass@2": 0.13670188277876558,
703
+ "pass@4": 0.1743356867689926,
704
+ "pass@8": 0.21140222159109787,
705
+ "pass@16": 0.24659782942071334,
706
+ "pass@32": 0.2791460500839276,
707
+ "pass@64": 0.3108012194942665,
708
+ "pass@128": 0.3419354838709677
709
+ },
710
+ "17": {
711
+ "pass@1": 0.08652456647398844,
712
+ "pass@2": 0.12079666093942017,
713
+ "pass@4": 0.1590196281461927,
714
+ "pass@8": 0.1949001400392914,
715
+ "pass@16": 0.22656725369755437,
716
+ "pass@32": 0.2590803393903783,
717
+ "pass@64": 0.297425501824078,
718
+ "pass@128": 0.34104046242774566
719
+ },
720
+ "18": {
721
+ "pass@1": 0.10104910714285714,
722
+ "pass@2": 0.1401813835770529,
723
+ "pass@4": 0.1825441019872516,
724
+ "pass@8": 0.2248524001219474,
725
+ "pass@16": 0.26573177942206255,
726
+ "pass@32": 0.3046260719649893,
727
+ "pass@64": 0.33970862070908614,
728
+ "pass@128": 0.3742857142857143
729
+ },
730
+ "19": {
731
+ "pass@1": 0.08223066816816817,
732
+ "pass@2": 0.1153045269679128,
733
+ "pass@4": 0.1499320814064909,
734
+ "pass@8": 0.1841899892713908,
735
+ "pass@16": 0.21844240351446248,
736
+ "pass@32": 0.2546023729358134,
737
+ "pass@64": 0.29275972060640304,
738
+ "pass@128": 0.32732732732732733
739
+ },
740
+ "20": {
741
+ "pass@1": 0.07627158408408409,
742
+ "pass@2": 0.11276630961670332,
743
+ "pass@4": 0.15630633980437128,
744
+ "pass@8": 0.20000992403576465,
745
+ "pass@16": 0.2379340644851812,
746
+ "pass@32": 0.27221998927265006,
747
+ "pass@64": 0.3063487387247676,
748
+ "pass@128": 0.33933933933933935
749
+ }
750
+ }
751
+ },
752
+ "teachers_in_school": {
753
+ "count": 430464,
754
+ "correct": 45695,
755
+ "answer_accuracy": 0.106152895480226,
756
+ "avg_response_len": 289.1409525535236,
757
+ "resp_tokens_sum": 124464771,
758
+ "pass_at_k": {
759
+ "pass@1": 0.106152895480226,
760
+ "pass@2": 0.14656625423494693,
761
+ "pass@4": 0.19118884478757728,
762
+ "pass@8": 0.23756264830625287,
763
+ "pass@16": 0.2845009456308184,
764
+ "pass@32": 0.33212048291724083,
765
+ "pass@64": 0.38030515033298923,
766
+ "pass@128": 0.42670234909307164
767
+ },
768
+ "per_op_pass_at_k": {
769
+ "11": {
770
+ "pass@1": 0.13234186746987953,
771
+ "pass@2": 0.17239491924390465,
772
+ "pass@4": 0.2164256291194022,
773
+ "pass@8": 0.2647050388915188,
774
+ "pass@16": 0.31922204405231247,
775
+ "pass@32": 0.38374982547121045,
776
+ "pass@64": 0.4587633082915936,
777
+ "pass@128": 0.5301204819277109
778
+ },
779
+ "12": {
780
+ "pass@1": 0.12056720219435736,
781
+ "pass@2": 0.1622743008417052,
782
+ "pass@4": 0.21015363204991236,
783
+ "pass@8": 0.2612399562037256,
784
+ "pass@16": 0.3142117204345368,
785
+ "pass@32": 0.3682695642944986,
786
+ "pass@64": 0.4245855724775943,
787
+ "pass@128": 0.4827586206896552
788
+ },
789
+ "13": {
790
+ "pass@1": 0.10758053221288516,
791
+ "pass@2": 0.14794037693817685,
792
+ "pass@4": 0.19233156149598946,
793
+ "pass@8": 0.23800085311099878,
794
+ "pass@16": 0.28313717264131943,
795
+ "pass@32": 0.32818330018656916,
796
+ "pass@64": 0.3753651392023757,
797
+ "pass@128": 0.42857142857142855
798
+ },
799
+ "14": {
800
+ "pass@1": 0.09708516081871345,
801
+ "pass@2": 0.1348389222728738,
802
+ "pass@4": 0.1788185881918269,
803
+ "pass@8": 0.22941582349844927,
804
+ "pass@16": 0.28430080687144255,
805
+ "pass@32": 0.33796333333182454,
806
+ "pass@64": 0.3873540833022138,
807
+ "pass@128": 0.43567251461988304
808
+ },
809
+ "15": {
810
+ "pass@1": 0.08759469696969698,
811
+ "pass@2": 0.13447789906943447,
812
+ "pass@4": 0.19098245304564204,
813
+ "pass@8": 0.24954836533037086,
814
+ "pass@16": 0.30737819754532864,
815
+ "pass@32": 0.3662480410675128,
816
+ "pass@64": 0.4255872926643773,
817
+ "pass@128": 0.48484848484848486
818
+ },
819
+ "16": {
820
+ "pass@1": 0.09390580484330484,
821
+ "pass@2": 0.12404624301769973,
822
+ "pass@4": 0.15564786185914797,
823
+ "pass@8": 0.18744827833293884,
824
+ "pass@16": 0.21857473436441932,
825
+ "pass@32": 0.25054869625221565,
826
+ "pass@64": 0.28266009150311744,
827
+ "pass@128": 0.31054131054131057
828
+ },
829
+ "17": {
830
+ "pass@1": 0.11886160714285714,
831
+ "pass@2": 0.16336634041668707,
832
+ "pass@4": 0.2106385201461618,
833
+ "pass@8": 0.25959876270632704,
834
+ "pass@16": 0.3096287586457038,
835
+ "pass@32": 0.359575814368446,
836
+ "pass@64": 0.4078289528773535,
837
+ "pass@128": 0.4503105590062112
838
+ },
839
+ "18": {
840
+ "pass@1": 0.12231158088235294,
841
+ "pass@2": 0.1738916309634089,
842
+ "pass@4": 0.2285186930677783,
843
+ "pass@8": 0.2796158296809389,
844
+ "pass@16": 0.3240335073703519,
845
+ "pass@32": 0.3641409802301815,
846
+ "pass@64": 0.4028805495934675,
847
+ "pass@128": 0.4411764705882353
848
+ },
849
+ "19": {
850
+ "pass@1": 0.09354073660714286,
851
+ "pass@2": 0.12886999964848145,
852
+ "pass@4": 0.1643410748321638,
853
+ "pass@8": 0.19890879493759292,
854
+ "pass@16": 0.23392055005639528,
855
+ "pass@32": 0.2704556352870397,
856
+ "pass@64": 0.3076625384550164,
857
+ "pass@128": 0.3392857142857143
858
+ },
859
+ "20": {
860
+ "pass@1": 0.0893057634730539,
861
+ "pass@2": 0.1258284366306757,
862
+ "pass@4": 0.16724632820972232,
863
+ "pass@8": 0.2114976229939815,
864
+ "pass@16": 0.25636790888869143,
865
+ "pass@32": 0.2994744548504521,
866
+ "pass@64": 0.33952434762294603,
867
+ "pass@128": 0.37425149700598803
868
+ }
869
+ }
870
+ },
871
+ "movie_festival_awards": {
872
+ "count": 418816,
873
+ "correct": 41720,
874
+ "answer_accuracy": 0.09961415036674817,
875
+ "avg_response_len": 311.46537142802566,
876
+ "resp_tokens_sum": 130446681,
877
+ "pass_at_k": {
878
+ "pass@1": 0.09961415036674817,
879
+ "pass@2": 0.13981871504581936,
880
+ "pass@4": 0.18554854253586592,
881
+ "pass@8": 0.23396411574284212,
882
+ "pass@16": 0.2823196797427484,
883
+ "pass@32": 0.32922427480125865,
884
+ "pass@64": 0.3741701772400552,
885
+ "pass@128": 0.4171760391198044
886
+ },
887
+ "per_op_pass_at_k": {
888
+ "11": {
889
+ "pass@1": 0.12641369047619047,
890
+ "pass@2": 0.17554329146356704,
891
+ "pass@4": 0.23326936216306302,
892
+ "pass@8": 0.29750874087488655,
893
+ "pass@16": 0.3663616173481937,
894
+ "pass@32": 0.4371521086462832,
895
+ "pass@64": 0.5041287820690189,
896
+ "pass@128": 0.5619047619047619
897
+ },
898
+ "12": {
899
+ "pass@1": 0.12504778287461774,
900
+ "pass@2": 0.16591342796599964,
901
+ "pass@4": 0.21000277402251305,
902
+ "pass@8": 0.2537437721295953,
903
+ "pass@16": 0.2970736109719961,
904
+ "pass@32": 0.3428671879118418,
905
+ "pass@64": 0.3898421922078423,
906
+ "pass@128": 0.43730886850152906
907
+ },
908
+ "13": {
909
+ "pass@1": 0.08297164351851852,
910
+ "pass@2": 0.11160057900748516,
911
+ "pass@4": 0.14504951869442242,
912
+ "pass@8": 0.1857712724430506,
913
+ "pass@16": 0.2364672847235342,
914
+ "pass@32": 0.2976027092301482,
915
+ "pass@64": 0.365115108855201,
916
+ "pass@128": 0.4382716049382716
917
+ },
918
+ "14": {
919
+ "pass@1": 0.0947932121661721,
920
+ "pass@2": 0.14057900009346028,
921
+ "pass@4": 0.19348220391219642,
922
+ "pass@8": 0.24924596247550668,
923
+ "pass@16": 0.30242594041052445,
924
+ "pass@32": 0.3522692070793088,
925
+ "pass@64": 0.39999651612779025,
926
+ "pass@128": 0.4421364985163205
927
+ },
928
+ "15": {
929
+ "pass@1": 0.11443865740740741,
930
+ "pass@2": 0.16848214068727518,
931
+ "pass@4": 0.22918851868053525,
932
+ "pass@8": 0.29037426746400014,
933
+ "pass@16": 0.3455079728175878,
934
+ "pass@32": 0.39287827288707505,
935
+ "pass@64": 0.436959939458589,
936
+ "pass@128": 0.48148148148148145
937
+ },
938
+ "16": {
939
+ "pass@1": 0.07570519911504425,
940
+ "pass@2": 0.10666939586091562,
941
+ "pass@4": 0.1416798010868111,
942
+ "pass@8": 0.1810688579074944,
943
+ "pass@16": 0.22275780816752133,
944
+ "pass@32": 0.263068335792944,
945
+ "pass@64": 0.2997203772220057,
946
+ "pass@128": 0.336283185840708
947
+ },
948
+ "17": {
949
+ "pass@1": 0.10320971385542169,
950
+ "pass@2": 0.14381529563134418,
951
+ "pass@4": 0.19100916235244686,
952
+ "pass@8": 0.23937766347762857,
953
+ "pass@16": 0.2859107008786314,
954
+ "pass@32": 0.3300417801536873,
955
+ "pass@64": 0.37069650304314794,
956
+ "pass@128": 0.4066265060240964
957
+ },
958
+ "18": {
959
+ "pass@1": 0.08051915322580645,
960
+ "pass@2": 0.1212368237236475,
961
+ "pass@4": 0.16872798420358742,
962
+ "pass@8": 0.21767212666994637,
963
+ "pass@16": 0.26376278061199115,
964
+ "pass@32": 0.3054783394532108,
965
+ "pass@64": 0.34413886448859154,
966
+ "pass@128": 0.3774193548387097
967
+ },
968
+ "19": {
969
+ "pass@1": 0.08022564199395771,
970
+ "pass@2": 0.10975524537907083,
971
+ "pass@4": 0.1428751035085871,
972
+ "pass@8": 0.17925093696793923,
973
+ "pass@16": 0.2156630659763213,
974
+ "pass@32": 0.24779989004979322,
975
+ "pass@64": 0.2774643292826266,
976
+ "pass@128": 0.311178247734139
977
+ },
978
+ "20": {
979
+ "pass@1": 0.11373873873873874,
980
+ "pass@2": 0.15614137759807054,
981
+ "pass@4": 0.20259945744394559,
982
+ "pass@8": 0.24897275992552667,
983
+ "pass@16": 0.2917036036507781,
984
+ "pass@32": 0.32881890632268107,
985
+ "pass@64": 0.3607643461394065,
986
+ "pass@128": 0.38738738738738737
987
+ }
988
+ }
989
+ }
990
+ }
991
+ },
992
+ "total": {
993
+ "answer_accuracy": 0.2243532072368421,
994
+ "avg_loss": 0.0,
995
+ "count": 2432000,
996
+ "validation_metrics": {
997
+ "id": {},
998
+ "ood": {}
999
+ },
1000
+ "pass_at_k": {
1001
+ "pass@1": 0.2243532072368421,
1002
+ "pass@2": 0.27470662168461957,
1003
+ "pass@4": 0.326903349900332,
1004
+ "pass@8": 0.3789495861903045,
1005
+ "pass@16": 0.42942808263555565,
1006
+ "pass@32": 0.47797393852679787,
1007
+ "pass@64": 0.524361278924775,
1008
+ "pass@128": 0.5682631578947368
1009
+ },
1010
+ "per_op_pass_at_k": {
1011
+ "10": {
1012
+ "pass@1": 0.153078125,
1013
+ "pass@2": 0.20062807578740144,
1014
+ "pass@4": 0.24996057695913,
1015
+ "pass@8": 0.30092839238317415,
1016
+ "pass@16": 0.35337128470273454,
1017
+ "pass@32": 0.4057937324821779,
1018
+ "pass@64": 0.45745223284049236,
1019
+ "pass@128": 0.511
1020
+ },
1021
+ "2": {
1022
+ "pass@1": 0.7223515625,
1023
+ "pass@2": 0.7726219242125981,
1024
+ "pass@4": 0.816936636670416,
1025
+ "pass@8": 0.8547507956069074,
1026
+ "pass@16": 0.8857456544394229,
1027
+ "pass@32": 0.9118260535213927,
1028
+ "pass@64": 0.9343826419291248,
1029
+ "pass@128": 0.954
1030
+ },
1031
+ "3": {
1032
+ "pass@1": 0.6634375,
1033
+ "pass@2": 0.728427411417323,
1034
+ "pass@4": 0.7820601895388077,
1035
+ "pass@8": 0.8274680138797387,
1036
+ "pass@16": 0.8668559639271197,
1037
+ "pass@32": 0.900318968240842,
1038
+ "pass@64": 0.9265554947853907,
1039
+ "pass@128": 0.947
1040
+ },
1041
+ "4": {
1042
+ "pass@1": 0.49425,
1043
+ "pass@2": 0.565187253937008,
1044
+ "pass@4": 0.6314227619984999,
1045
+ "pass@8": 0.6908256447524266,
1046
+ "pass@16": 0.7441946217927244,
1047
+ "pass@32": 0.7921254407781363,
1048
+ "pass@64": 0.8329447961928805,
1049
+ "pass@128": 0.867
1050
+ },
1051
+ "5": {
1052
+ "pass@1": 0.2666875,
1053
+ "pass@2": 0.3425367864173231,
1054
+ "pass@4": 0.41431873622047216,
1055
+ "pass@8": 0.48238861153714807,
1056
+ "pass@16": 0.5474928528605428,
1057
+ "pass@32": 0.6100132327723347,
1058
+ "pass@64": 0.6666898943727598,
1059
+ "pass@128": 0.714
1060
+ },
1061
+ "6": {
1062
+ "pass@1": 0.3322109375,
1063
+ "pass@2": 0.38863324311023634,
1064
+ "pass@4": 0.4494082936820398,
1065
+ "pass@8": 0.5135329718566175,
1066
+ "pass@16": 0.5766645404957943,
1067
+ "pass@32": 0.634882092289773,
1068
+ "pass@64": 0.6863767949088386,
1069
+ "pass@128": 0.731
1070
+ },
1071
+ "7": {
1072
+ "pass@1": 0.2464765625,
1073
+ "pass@2": 0.3143423966535434,
1074
+ "pass@4": 0.3799570868016498,
1075
+ "pass@8": 0.4408821430672949,
1076
+ "pass@16": 0.4967942984254299,
1077
+ "pass@32": 0.5486898689322044,
1078
+ "pass@64": 0.5979581445148634,
1079
+ "pass@128": 0.647
1080
+ },
1081
+ "8": {
1082
+ "pass@1": 0.2124140625,
1083
+ "pass@2": 0.2722742372047242,
1084
+ "pass@4": 0.33279232649043833,
1085
+ "pass@8": 0.3928992314946121,
1086
+ "pass@16": 0.4520373656761814,
1087
+ "pass@32": 0.5096369501508324,
1088
+ "pass@64": 0.5668209754644449,
1089
+ "pass@128": 0.624
1090
+ },
1091
+ "9": {
1092
+ "pass@1": 0.1674296875,
1093
+ "pass@2": 0.230796751968504,
1094
+ "pass@4": 0.29948952530933626,
1095
+ "pass@8": 0.36878700778934914,
1096
+ "pass@16": 0.43653161760440473,
1097
+ "pass@32": 0.5023438254014455,
1098
+ "pass@64": 0.5682788308808282,
1099
+ "pass@128": 0.636
1100
+ },
1101
+ "11": {
1102
+ "pass@1": 0.131390625,
1103
+ "pass@2": 0.17717458169291328,
1104
+ "pass@4": 0.22935256805399312,
1105
+ "pass@8": 0.28690414567159045,
1106
+ "pass@16": 0.3484727346081054,
1107
+ "pass@32": 0.4136139328033935,
1108
+ "pass@64": 0.4807059952733389,
1109
+ "pass@128": 0.541
1110
+ },
1111
+ "12": {
1112
+ "pass@1": 0.1196640625,
1113
+ "pass@2": 0.16031951279527545,
1114
+ "pass@4": 0.20569369722534664,
1115
+ "pass@8": 0.2532498672669628,
1116
+ "pass@16": 0.30201560584141535,
1117
+ "pass@32": 0.35198840183015,
1118
+ "pass@64": 0.4024866801172818,
1119
+ "pass@128": 0.454
1120
+ },
1121
+ "13": {
1122
+ "pass@1": 0.0911875,
1123
+ "pass@2": 0.12641806102362202,
1124
+ "pass@4": 0.16787350693663286,
1125
+ "pass@8": 0.21486568791025193,
1126
+ "pass@16": 0.2662775544931056,
1127
+ "pass@32": 0.3211539302060912,
1128
+ "pass@64": 0.37813810394040775,
1129
+ "pass@128": 0.438
1130
+ },
1131
+ "14": {
1132
+ "pass@1": 0.0923203125,
1133
+ "pass@2": 0.1340594242125984,
1134
+ "pass@4": 0.18355495913010858,
1135
+ "pass@8": 0.23832816771772392,
1136
+ "pass@16": 0.29379041445980003,
1137
+ "pass@32": 0.3470037731751372,
1138
+ "pass@64": 0.39704840454373874,
1139
+ "pass@128": 0.444
1140
+ },
1141
+ "15": {
1142
+ "pass@1": 0.097203125,
1143
+ "pass@2": 0.14641240157480317,
1144
+ "pass@4": 0.20366941732283445,
1145
+ "pass@8": 0.26212224223981484,
1146
+ "pass@16": 0.31753071976349556,
1147
+ "pass@32": 0.370484303913742,
1148
+ "pass@64": 0.4217421119565217,
1149
+ "pass@128": 0.471
1150
+ },
1151
+ "16": {
1152
+ "pass@1": 0.08975,
1153
+ "pass@2": 0.12207874015748027,
1154
+ "pass@4": 0.15670591497937744,
1155
+ "pass@8": 0.19271137721874232,
1156
+ "pass@16": 0.2286799558511221,
1157
+ "pass@32": 0.2636580337443535,
1158
+ "pass@64": 0.2971672780390768,
1159
+ "pass@128": 0.329
1160
+ },
1161
+ "17": {
1162
+ "pass@1": 0.1024765625,
1163
+ "pass@2": 0.14214628444881894,
1164
+ "pass@4": 0.1862614367266591,
1165
+ "pass@8": 0.23049963431960444,
1166
+ "pass@16": 0.27301508275497594,
1167
+ "pass@32": 0.3149990806667348,
1168
+ "pass@64": 0.3573013854679643,
1169
+ "pass@128": 0.398
1170
+ },
1171
+ "18": {
1172
+ "pass@1": 0.1019140625,
1173
+ "pass@2": 0.14577005413385827,
1174
+ "pass@4": 0.19389246644169467,
1175
+ "pass@8": 0.24124608140188403,
1176
+ "pass@16": 0.2849439772933588,
1177
+ "pass@32": 0.3251253436965035,
1178
+ "pass@64": 0.3625604521014223,
1179
+ "pass@128": 0.398
1180
+ },
1181
+ "19": {
1182
+ "pass@1": 0.0853671875,
1183
+ "pass@2": 0.11802571358267713,
1184
+ "pass@4": 0.15243764351331066,
1185
+ "pass@8": 0.18750068166279207,
1186
+ "pass@16": 0.22272310002742723,
1187
+ "pass@32": 0.2576774472505532,
1188
+ "pass@64": 0.2927042928753672,
1189
+ "pass@128": 0.326
1190
+ },
1191
+ "20": {
1192
+ "pass@1": 0.0931015625,
1193
+ "pass@2": 0.13157295767716534,
1194
+ "pass@4": 0.17537590410573672,
1195
+ "pass@8": 0.22015143983909957,
1196
+ "pass@16": 0.26199622505809744,
1197
+ "pass@32": 0.3001704201532964,
1198
+ "pass@64": 0.33554978936583424,
1199
+ "pass@128": 0.367
1200
+ }
1201
+ },
1202
+ "per_op_accuracy": {
1203
+ "10": 0.153078125,
1204
+ "2": 0.7223515625,
1205
+ "3": 0.6634375,
1206
+ "4": 0.49425,
1207
+ "5": 0.2666875,
1208
+ "6": 0.3322109375,
1209
+ "7": 0.2464765625,
1210
+ "8": 0.2124140625,
1211
+ "9": 0.1674296875,
1212
+ "11": 0.131390625,
1213
+ "12": 0.1196640625,
1214
+ "13": 0.0911875,
1215
+ "14": 0.0923203125,
1216
+ "15": 0.097203125,
1217
+ "16": 0.08975,
1218
+ "17": 0.1024765625,
1219
+ "18": 0.1019140625,
1220
+ "19": 0.0853671875,
1221
+ "20": 0.0931015625
1222
+ },
1223
+ "per_op_avg_response_len": {
1224
+ "10": 274.915625,
1225
+ "2": 120.882765625,
1226
+ "3": 150.5270546875,
1227
+ "4": 167.6719453125,
1228
+ "5": 181.6410703125,
1229
+ "6": 211.30146875,
1230
+ "7": 229.0457265625,
1231
+ "8": 247.367390625,
1232
+ "9": 261.3248359375,
1233
+ "11": 288.871875,
1234
+ "12": 291.25571875,
1235
+ "13": 292.0997265625,
1236
+ "14": 293.006984375,
1237
+ "15": 292.100015625,
1238
+ "16": 290.70203125,
1239
+ "17": 296.6965078125,
1240
+ "18": 296.130765625,
1241
+ "19": 293.92978125,
1242
+ "20": 298.52171875
1243
+ },
1244
+ "per_op_avg_loss": {},
1245
+ "per_op_length": {
1246
+ "10": 274.915625,
1247
+ "2": 120.882765625,
1248
+ "3": 150.5270546875,
1249
+ "4": 167.6719453125,
1250
+ "5": 181.6410703125,
1251
+ "6": 211.30146875,
1252
+ "7": 229.0457265625,
1253
+ "8": 247.367390625,
1254
+ "9": 261.3248359375,
1255
+ "11": 288.871875,
1256
+ "12": 291.25571875,
1257
+ "13": 292.0997265625,
1258
+ "14": 293.006984375,
1259
+ "15": 292.100015625,
1260
+ "16": 290.70203125,
1261
+ "17": 296.6965078125,
1262
+ "18": 296.130765625,
1263
+ "19": 293.92978125,
1264
+ "20": 298.52171875
1265
+ },
1266
+ "per_op_loss": {},
1267
+ "per_template": {
1268
+ "crazy_zootopia": {
1269
+ "count": 809728,
1270
+ "correct": 174960,
1271
+ "answer_accuracy": 0.2160725576983876,
1272
+ "avg_response_len": 240.2238331884287,
1273
+ "resp_tokens_sum": 194515964,
1274
+ "pass_at_k": {
1275
+ "pass@1": 0.2160725576983876,
1276
+ "pass@2": 0.26710561773558145,
1277
+ "pass@4": 0.32056310265299404,
1278
+ "pass@8": 0.37358226413942236,
1279
+ "pass@16": 0.42426905582922897,
1280
+ "pass@32": 0.47242045998358206,
1281
+ "pass@64": 0.5179877228554772,
1282
+ "pass@128": 0.5608599430920013
1283
+ },
1284
+ "per_op_pass_at_k": {
1285
+ "10": {
1286
+ "pass@1": 0.16118178466076696,
1287
+ "pass@2": 0.21100700009290868,
1288
+ "pass@4": 0.26204468053219016,
1289
+ "pass@8": 0.313965959315187,
1290
+ "pass@16": 0.3669307944259261,
1291
+ "pass@32": 0.4192929029900247,
1292
+ "pass@64": 0.4697690954137164,
1293
+ "pass@128": 0.5221238938053098
1294
+ },
1295
+ "2": {
1296
+ "pass@1": 0.6974785825545171,
1297
+ "pass@2": 0.7498029962960233,
1298
+ "pass@4": 0.7984764164993392,
1299
+ "pass@8": 0.8426580781725969,
1300
+ "pass@16": 0.8811400390570819,
1301
+ "pass@32": 0.9154355567676705,
1302
+ "pass@64": 0.9439033477168228,
1303
+ "pass@128": 0.9626168224299065
1304
+ },
1305
+ "3": {
1306
+ "pass@1": 0.6284881498470948,
1307
+ "pass@2": 0.6921070968479855,
1308
+ "pass@4": 0.7454523299266487,
1309
+ "pass@8": 0.7916577080236396,
1310
+ "pass@16": 0.8325218506692965,
1311
+ "pass@32": 0.8683391227625886,
1312
+ "pass@64": 0.8968584133079681,
1313
+ "pass@128": 0.9174311926605505
1314
+ },
1315
+ "4": {
1316
+ "pass@1": 0.459765625,
1317
+ "pass@2": 0.5297778512549212,
1318
+ "pass@4": 0.5945688033136481,
1319
+ "pass@8": 0.6530113938111209,
1320
+ "pass@16": 0.7081231827169705,
1321
+ "pass@32": 0.759363772014444,
1322
+ "pass@64": 0.8044523643734547,
1323
+ "pass@128": 0.84375
1324
+ },
1325
+ "5": {
1326
+ "pass@1": 0.26671626984126984,
1327
+ "pass@2": 0.3425470253718283,
1328
+ "pass@4": 0.41556439968813413,
1329
+ "pass@8": 0.48176800859338753,
1330
+ "pass@16": 0.5418400059324522,
1331
+ "pass@32": 0.5976897340165899,
1332
+ "pass@64": 0.6484423831216877,
1333
+ "pass@128": 0.6952380952380952
1334
+ },
1335
+ "6": {
1336
+ "pass@1": 0.33493169910179643,
1337
+ "pass@2": 0.3905675361874673,
1338
+ "pass@4": 0.449119640078673,
1339
+ "pass@8": 0.509693792465805,
1340
+ "pass@16": 0.5692551867943821,
1341
+ "pass@32": 0.6241793020699291,
1342
+ "pass@64": 0.6729702040598893,
1343
+ "pass@128": 0.718562874251497
1344
+ },
1345
+ "7": {
1346
+ "pass@1": 0.2567030325443787,
1347
+ "pass@2": 0.33237031461119126,
1348
+ "pass@4": 0.40505862386654345,
1349
+ "pass@8": 0.47228374550038577,
1350
+ "pass@16": 0.533299549975349,
1351
+ "pass@32": 0.5853612209560378,
1352
+ "pass@64": 0.6296383818221275,
1353
+ "pass@128": 0.6715976331360947
1354
+ },
1355
+ "8": {
1356
+ "pass@1": 0.22741386217948717,
1357
+ "pass@2": 0.29118518763880463,
1358
+ "pass@4": 0.3558928727659042,
1359
+ "pass@8": 0.41934049330733497,
1360
+ "pass@16": 0.4790422934302815,
1361
+ "pass@32": 0.5353208860582773,
1362
+ "pass@64": 0.5903250480614363,
1363
+ "pass@128": 0.6442307692307693
1364
+ },
1365
+ "9": {
1366
+ "pass@1": 0.17086267605633804,
1367
+ "pass@2": 0.24369766829322378,
1368
+ "pass@4": 0.32428576603980847,
1369
+ "pass@8": 0.4026243423547874,
1370
+ "pass@16": 0.4743958200381107,
1371
+ "pass@32": 0.5415250798666842,
1372
+ "pass@64": 0.6075046168962964,
1373
+ "pass@128": 0.6732394366197183
1374
+ },
1375
+ "11": {
1376
+ "pass@1": 0.13493714589235128,
1377
+ "pass@2": 0.18312558553233246,
1378
+ "pass@4": 0.23801532607645007,
1379
+ "pass@8": 0.2983196016544395,
1380
+ "pass@16": 0.3600201317791979,
1381
+ "pass@32": 0.4206971006327828,
1382
+ "pass@64": 0.48044195628551944,
1383
+ "pass@128": 0.5325779036827195
1384
+ },
1385
+ "12": {
1386
+ "pass@1": 0.1138771186440678,
1387
+ "pass@2": 0.15339073412963222,
1388
+ "pass@4": 0.19769429801147728,
1389
+ "pass@8": 0.24559352472202536,
1390
+ "pass@16": 0.29559038484450695,
1391
+ "pass@32": 0.34574248692946935,
1392
+ "pass@64": 0.3942527843078104,
1393
+ "pass@128": 0.4435028248587571
1394
+ },
1395
+ "13": {
1396
+ "pass@1": 0.08118632445141066,
1397
+ "pass@2": 0.11738168921087064,
1398
+ "pass@4": 0.16368368471966077,
1399
+ "pass@8": 0.21852505040149559,
1400
+ "pass@16": 0.27768709595526475,
1401
+ "pass@32": 0.3372075681784244,
1402
+ "pass@64": 0.39446850776198933,
1403
+ "pass@128": 0.4482758620689655
1404
+ },
1405
+ "14": {
1406
+ "pass@1": 0.08464758566978194,
1407
+ "pass@2": 0.12638439178747513,
1408
+ "pass@4": 0.17817912538970013,
1409
+ "pass@8": 0.23636157858881193,
1410
+ "pass@16": 0.29483488034710237,
1411
+ "pass@32": 0.3511077582240689,
1412
+ "pass@64": 0.4042818757611095,
1413
+ "pass@128": 0.45482866043613707
1414
+ },
1415
+ "15": {
1416
+ "pass@1": 0.09022760115606937,
1417
+ "pass@2": 0.1371285586682445,
1418
+ "pass@4": 0.19187320163375532,
1419
+ "pass@8": 0.2476590145157713,
1420
+ "pass@16": 0.30101540861456305,
1421
+ "pass@32": 0.35355459521979815,
1422
+ "pass@64": 0.403824523100272,
1423
+ "pass@128": 0.4479768786127168
1424
+ },
1425
+ "16": {
1426
+ "pass@1": 0.10040322580645161,
1427
+ "pass@2": 0.13670188277876558,
1428
+ "pass@4": 0.1743356867689926,
1429
+ "pass@8": 0.21140222159109787,
1430
+ "pass@16": 0.24659782942071334,
1431
+ "pass@32": 0.2791460500839276,
1432
+ "pass@64": 0.3108012194942665,
1433
+ "pass@128": 0.3419354838709677
1434
+ },
1435
+ "17": {
1436
+ "pass@1": 0.08652456647398844,
1437
+ "pass@2": 0.12079666093942017,
1438
+ "pass@4": 0.1590196281461927,
1439
+ "pass@8": 0.1949001400392914,
1440
+ "pass@16": 0.22656725369755437,
1441
+ "pass@32": 0.2590803393903783,
1442
+ "pass@64": 0.297425501824078,
1443
+ "pass@128": 0.34104046242774566
1444
+ },
1445
+ "18": {
1446
+ "pass@1": 0.10104910714285714,
1447
+ "pass@2": 0.1401813835770529,
1448
+ "pass@4": 0.1825441019872516,
1449
+ "pass@8": 0.2248524001219474,
1450
+ "pass@16": 0.26573177942206255,
1451
+ "pass@32": 0.3046260719649893,
1452
+ "pass@64": 0.33970862070908614,
1453
+ "pass@128": 0.3742857142857143
1454
+ },
1455
+ "19": {
1456
+ "pass@1": 0.08223066816816817,
1457
+ "pass@2": 0.1153045269679128,
1458
+ "pass@4": 0.1499320814064909,
1459
+ "pass@8": 0.1841899892713908,
1460
+ "pass@16": 0.21844240351446248,
1461
+ "pass@32": 0.2546023729358134,
1462
+ "pass@64": 0.29275972060640304,
1463
+ "pass@128": 0.32732732732732733
1464
+ },
1465
+ "20": {
1466
+ "pass@1": 0.07627158408408409,
1467
+ "pass@2": 0.11276630961670332,
1468
+ "pass@4": 0.15630633980437128,
1469
+ "pass@8": 0.20000992403576465,
1470
+ "pass@16": 0.2379340644851812,
1471
+ "pass@32": 0.27221998927265006,
1472
+ "pass@64": 0.3063487387247676,
1473
+ "pass@128": 0.33933933933933935
1474
+ }
1475
+ }
1476
+ },
1477
+ "teachers_in_school": {
1478
+ "count": 821120,
1479
+ "correct": 180027,
1480
+ "answer_accuracy": 0.21924566445830085,
1481
+ "avg_response_len": 248.22646628994545,
1482
+ "resp_tokens_sum": 203823716,
1483
+ "pass_at_k": {
1484
+ "pass@1": 0.21924566445830085,
1485
+ "pass@2": 0.2690937785762966,
1486
+ "pass@4": 0.3205873553559144,
1487
+ "pass@8": 0.3719643629642574,
1488
+ "pass@16": 0.42249542154697955,
1489
+ "pass@32": 0.4722283866900299,
1490
+ "pass@64": 0.5212290010952906,
1491
+ "pass@128": 0.5686671862821512
1492
+ },
1493
+ "per_op_pass_at_k": {
1494
+ "10": {
1495
+ "pass@1": 0.14239838957055215,
1496
+ "pass@2": 0.18646215762523552,
1497
+ "pass@4": 0.23446961643214842,
1498
+ "pass@8": 0.28705840266279736,
1499
+ "pass@16": 0.34176712763641864,
1500
+ "pass@32": 0.393697107128622,
1501
+ "pass@64": 0.4396077946700623,
1502
+ "pass@128": 0.4815950920245399
1503
+ },
1504
+ "2": {
1505
+ "pass@1": 0.6969747340425532,
1506
+ "pass@2": 0.753928406887969,
1507
+ "pass@4": 0.8035614455867784,
1508
+ "pass@8": 0.843974271174507,
1509
+ "pass@16": 0.8749837921659976,
1510
+ "pass@32": 0.8982223777835114,
1511
+ "pass@64": 0.9187984833921925,
1512
+ "pass@128": 0.9422492401215805
1513
+ },
1514
+ "3": {
1515
+ "pass@1": 0.6451467803030303,
1516
+ "pass@2": 0.7162670007158197,
1517
+ "pass@4": 0.7793047312267779,
1518
+ "pass@8": 0.8333319187968913,
1519
+ "pass@16": 0.8770961555446578,
1520
+ "pass@32": 0.909542515519656,
1521
+ "pass@64": 0.9324872967635861,
1522
+ "pass@128": 0.9515151515151515
1523
+ },
1524
+ "4": {
1525
+ "pass@1": 0.522605399408284,
1526
+ "pass@2": 0.5892557104086102,
1527
+ "pass@4": 0.6476280076676802,
1528
+ "pass@8": 0.6990817626466677,
1529
+ "pass@16": 0.7463410223529519,
1530
+ "pass@32": 0.7917997275040872,
1531
+ "pass@64": 0.8345071710379106,
1532
+ "pass@128": 0.8727810650887574
1533
+ },
1534
+ "5": {
1535
+ "pass@1": 0.23156702898550724,
1536
+ "pass@2": 0.3060135655597396,
1537
+ "pass@4": 0.3781115583378164,
1538
+ "pass@8": 0.44872429897310967,
1539
+ "pass@16": 0.5185551846144103,
1540
+ "pass@32": 0.5877484160335491,
1541
+ "pass@64": 0.6546433701390305,
1542
+ "pass@128": 0.7130434782608696
1543
+ },
1544
+ "6": {
1545
+ "pass@1": 0.3259760028653295,
1546
+ "pass@2": 0.3796741392730634,
1547
+ "pass@4": 0.4381010783394194,
1548
+ "pass@8": 0.49888167562112606,
1549
+ "pass@16": 0.5602468122792769,
1550
+ "pass@32": 0.6221272504599301,
1551
+ "pass@64": 0.6829418759180574,
1552
+ "pass@128": 0.7363896848137536
1553
+ },
1554
+ "7": {
1555
+ "pass@1": 0.2296333092485549,
1556
+ "pass@2": 0.29712497439807023,
1557
+ "pass@4": 0.36502451770840794,
1558
+ "pass@8": 0.426388535715249,
1559
+ "pass@16": 0.4804327509720443,
1560
+ "pass@32": 0.533175386708967,
1561
+ "pass@64": 0.587141630247611,
1562
+ "pass@128": 0.6416184971098265
1563
+ },
1564
+ "8": {
1565
+ "pass@1": 0.18727992957746478,
1566
+ "pass@2": 0.2457202367749805,
1567
+ "pass@4": 0.30368673880553654,
1568
+ "pass@8": 0.36232621489128214,
1569
+ "pass@16": 0.42333938653385483,
1570
+ "pass@32": 0.4851196069605558,
1571
+ "pass@64": 0.5487500600105882,
1572
+ "pass@128": 0.6197183098591549
1573
+ },
1574
+ "9": {
1575
+ "pass@1": 0.13356100299401197,
1576
+ "pass@2": 0.18219085942288651,
1577
+ "pass@4": 0.23733269989829103,
1578
+ "pass@8": 0.29824739855791427,
1579
+ "pass@16": 0.36406530154791894,
1580
+ "pass@32": 0.43171976382911487,
1581
+ "pass@64": 0.5005413019533322,
1582
+ "pass@128": 0.5748502994011976
1583
+ },
1584
+ "11": {
1585
+ "pass@1": 0.13234186746987953,
1586
+ "pass@2": 0.17239491924390465,
1587
+ "pass@4": 0.2164256291194022,
1588
+ "pass@8": 0.2647050388915188,
1589
+ "pass@16": 0.31922204405231247,
1590
+ "pass@32": 0.38374982547121045,
1591
+ "pass@64": 0.4587633082915936,
1592
+ "pass@128": 0.5301204819277109
1593
+ },
1594
+ "12": {
1595
+ "pass@1": 0.12056720219435736,
1596
+ "pass@2": 0.1622743008417052,
1597
+ "pass@4": 0.21015363204991236,
1598
+ "pass@8": 0.2612399562037256,
1599
+ "pass@16": 0.3142117204345368,
1600
+ "pass@32": 0.3682695642944986,
1601
+ "pass@64": 0.4245855724775943,
1602
+ "pass@128": 0.4827586206896552
1603
+ },
1604
+ "13": {
1605
+ "pass@1": 0.10758053221288516,
1606
+ "pass@2": 0.14794037693817685,
1607
+ "pass@4": 0.19233156149598946,
1608
+ "pass@8": 0.23800085311099878,
1609
+ "pass@16": 0.28313717264131943,
1610
+ "pass@32": 0.32818330018656916,
1611
+ "pass@64": 0.3753651392023757,
1612
+ "pass@128": 0.42857142857142855
1613
+ },
1614
+ "14": {
1615
+ "pass@1": 0.09708516081871345,
1616
+ "pass@2": 0.1348389222728738,
1617
+ "pass@4": 0.1788185881918269,
1618
+ "pass@8": 0.22941582349844927,
1619
+ "pass@16": 0.28430080687144255,
1620
+ "pass@32": 0.33796333333182454,
1621
+ "pass@64": 0.3873540833022138,
1622
+ "pass@128": 0.43567251461988304
1623
+ },
1624
+ "15": {
1625
+ "pass@1": 0.08759469696969698,
1626
+ "pass@2": 0.13447789906943447,
1627
+ "pass@4": 0.19098245304564204,
1628
+ "pass@8": 0.24954836533037086,
1629
+ "pass@16": 0.30737819754532864,
1630
+ "pass@32": 0.3662480410675128,
1631
+ "pass@64": 0.4255872926643773,
1632
+ "pass@128": 0.48484848484848486
1633
+ },
1634
+ "16": {
1635
+ "pass@1": 0.09390580484330484,
1636
+ "pass@2": 0.12404624301769973,
1637
+ "pass@4": 0.15564786185914797,
1638
+ "pass@8": 0.18744827833293884,
1639
+ "pass@16": 0.21857473436441932,
1640
+ "pass@32": 0.25054869625221565,
1641
+ "pass@64": 0.28266009150311744,
1642
+ "pass@128": 0.31054131054131057
1643
+ },
1644
+ "17": {
1645
+ "pass@1": 0.11886160714285714,
1646
+ "pass@2": 0.16336634041668707,
1647
+ "pass@4": 0.2106385201461618,
1648
+ "pass@8": 0.25959876270632704,
1649
+ "pass@16": 0.3096287586457038,
1650
+ "pass@32": 0.359575814368446,
1651
+ "pass@64": 0.4078289528773535,
1652
+ "pass@128": 0.4503105590062112
1653
+ },
1654
+ "18": {
1655
+ "pass@1": 0.12231158088235294,
1656
+ "pass@2": 0.1738916309634089,
1657
+ "pass@4": 0.2285186930677783,
1658
+ "pass@8": 0.2796158296809389,
1659
+ "pass@16": 0.3240335073703519,
1660
+ "pass@32": 0.3641409802301815,
1661
+ "pass@64": 0.4028805495934675,
1662
+ "pass@128": 0.4411764705882353
1663
+ },
1664
+ "19": {
1665
+ "pass@1": 0.09354073660714286,
1666
+ "pass@2": 0.12886999964848145,
1667
+ "pass@4": 0.1643410748321638,
1668
+ "pass@8": 0.19890879493759292,
1669
+ "pass@16": 0.23392055005639528,
1670
+ "pass@32": 0.2704556352870397,
1671
+ "pass@64": 0.3076625384550164,
1672
+ "pass@128": 0.3392857142857143
1673
+ },
1674
+ "20": {
1675
+ "pass@1": 0.0893057634730539,
1676
+ "pass@2": 0.1258284366306757,
1677
+ "pass@4": 0.16724632820972232,
1678
+ "pass@8": 0.2114976229939815,
1679
+ "pass@16": 0.25636790888869143,
1680
+ "pass@32": 0.2994744548504521,
1681
+ "pass@64": 0.33952434762294603,
1682
+ "pass@128": 0.37425149700598803
1683
+ }
1684
+ }
1685
+ },
1686
+ "movie_festival_awards": {
1687
+ "count": 801152,
1688
+ "correct": 190640,
1689
+ "answer_accuracy": 0.23795734142834318,
1690
+ "avg_response_len": 266.17099501717524,
1691
+ "resp_tokens_sum": 213243425,
1692
+ "pass_at_k": {
1693
+ "pass@1": 0.23795734142834318,
1694
+ "pass@2": 0.28814172945289696,
1695
+ "pass@4": 0.3397848819484745,
1696
+ "pass@8": 0.39153368689153495,
1697
+ "pass@16": 0.4417477861760282,
1698
+ "pass@32": 0.4894756193539459,
1699
+ "pass@64": 0.5340134083336696,
1700
+ "pass@128": 0.5753315226074452
1701
+ },
1702
+ "per_op_pass_at_k": {
1703
+ "10": {
1704
+ "pass@1": 0.1552705223880597,
1705
+ "pass@2": 0.20391056528381718,
1706
+ "pass@4": 0.2528069710502605,
1707
+ "pass@8": 0.30123251614105645,
1708
+ "pass@16": 0.35094227397872746,
1709
+ "pass@32": 0.40390501923769717,
1710
+ "pass@64": 0.4623533386053791,
1711
+ "pass@128": 0.5283582089552239
1712
+ },
1713
+ "2": {
1714
+ "pass@1": 0.7690178571428572,
1715
+ "pass@2": 0.811122047244094,
1716
+ "pass@4": 0.8464399753602228,
1717
+ "pass@8": 0.8759714779916868,
1718
+ "pass@16": 0.9000858122271072,
1719
+ "pass@32": 0.9213030785948414,
1720
+ "pass@64": 0.940299903645694,
1721
+ "pass@128": 0.9571428571428572
1722
+ },
1723
+ "3": {
1724
+ "pass@1": 0.7143540451895044,
1725
+ "pass@2": 0.7747530044076125,
1726
+ "pass@4": 0.8196114179240708,
1727
+ "pass@8": 0.8559662103586972,
1728
+ "pass@16": 0.8897364064971576,
1729
+ "pass@32": 0.9219330757317451,
1730
+ "pass@64": 0.9491603081682237,
1731
+ "pass@128": 0.9708454810495627
1732
+ },
1733
+ "4": {
1734
+ "pass@1": 0.4984923245614035,
1735
+ "pass@2": 0.5745319047290139,
1736
+ "pass@4": 0.6498902875627387,
1737
+ "pass@8": 0.7180478449072955,
1738
+ "pass@16": 0.7758243794385915,
1739
+ "pass@32": 0.8231015375354785,
1740
+ "pass@64": 0.8580602800659657,
1741
+ "pass@128": 0.8830409356725146
1742
+ },
1743
+ "5": {
1744
+ "pass@1": 0.30229779411764707,
1745
+ "pass@2": 0.379587627373784,
1746
+ "pass@4": 0.4499043020357746,
1747
+ "pass@8": 0.5171229578956147,
1748
+ "pass@16": 0.5820932714701458,
1749
+ "pass@32": 0.6440228324280421,
1750
+ "pass@64": 0.6958193558572406,
1751
+ "pass@128": 0.7323529411764705
1752
+ },
1753
+ "6": {
1754
+ "pass@1": 0.33620859621451105,
1755
+ "pass@2": 0.39645871109565534,
1756
+ "pass@4": 0.4621610648432353,
1757
+ "pass@8": 0.5337083292784405,
1758
+ "pass@16": 0.6025462795615276,
1759
+ "pass@32": 0.6602012460186194,
1760
+ "pass@64": 0.704284012799474,
1761
+ "pass@128": 0.7381703470031545
1762
+ },
1763
+ "7": {
1764
+ "pass@1": 0.25398041930379744,
1765
+ "pass@2": 0.31391135814312754,
1766
+ "pass@4": 0.36945819242926925,
1767
+ "pass@8": 0.4231639358566098,
1768
+ "pass@16": 0.47566240094124973,
1769
+ "pass@32": 0.5264528242017742,
1770
+ "pass@64": 0.5759157195990866,
1771
+ "pass@128": 0.6265822784810127
1772
+ },
1773
+ "8": {
1774
+ "pass@1": 0.22515484234234234,
1775
+ "pass@2": 0.2828641880069045,
1776
+ "pass@4": 0.3421770507853185,
1777
+ "pass@8": 0.4007182921811377,
1778
+ "pass@16": 0.45732939311235854,
1779
+ "pass@32": 0.5117098295184779,
1780
+ "pass@64": 0.5640639314279801,
1781
+ "pass@128": 0.6096096096096096
1782
+ },
1783
+ "9": {
1784
+ "pass@1": 0.1998844453376206,
1785
+ "pass@2": 0.2682711661645189,
1786
+ "pass@4": 0.33793876719991994,
1787
+ "pass@8": 0.4059187624921453,
1788
+ "pass@16": 0.47113598319572814,
1789
+ "pass@32": 0.5334663052406697,
1790
+ "pass@64": 0.5962504727660117,
1791
+ "pass@128": 0.6591639871382636
1792
+ },
1793
+ "11": {
1794
+ "pass@1": 0.12641369047619047,
1795
+ "pass@2": 0.17554329146356704,
1796
+ "pass@4": 0.23326936216306302,
1797
+ "pass@8": 0.29750874087488655,
1798
+ "pass@16": 0.3663616173481937,
1799
+ "pass@32": 0.4371521086462832,
1800
+ "pass@64": 0.5041287820690189,
1801
+ "pass@128": 0.5619047619047619
1802
+ },
1803
+ "12": {
1804
+ "pass@1": 0.12504778287461774,
1805
+ "pass@2": 0.16591342796599964,
1806
+ "pass@4": 0.21000277402251305,
1807
+ "pass@8": 0.2537437721295953,
1808
+ "pass@16": 0.2970736109719961,
1809
+ "pass@32": 0.3428671879118418,
1810
+ "pass@64": 0.3898421922078423,
1811
+ "pass@128": 0.43730886850152906
1812
+ },
1813
+ "13": {
1814
+ "pass@1": 0.08297164351851852,
1815
+ "pass@2": 0.11160057900748516,
1816
+ "pass@4": 0.14504951869442242,
1817
+ "pass@8": 0.1857712724430506,
1818
+ "pass@16": 0.2364672847235342,
1819
+ "pass@32": 0.2976027092301482,
1820
+ "pass@64": 0.365115108855201,
1821
+ "pass@128": 0.4382716049382716
1822
+ },
1823
+ "14": {
1824
+ "pass@1": 0.0947932121661721,
1825
+ "pass@2": 0.14057900009346028,
1826
+ "pass@4": 0.19348220391219642,
1827
+ "pass@8": 0.24924596247550668,
1828
+ "pass@16": 0.30242594041052445,
1829
+ "pass@32": 0.3522692070793088,
1830
+ "pass@64": 0.39999651612779025,
1831
+ "pass@128": 0.4421364985163205
1832
+ },
1833
+ "15": {
1834
+ "pass@1": 0.11443865740740741,
1835
+ "pass@2": 0.16848214068727518,
1836
+ "pass@4": 0.22918851868053525,
1837
+ "pass@8": 0.29037426746400014,
1838
+ "pass@16": 0.3455079728175878,
1839
+ "pass@32": 0.39287827288707505,
1840
+ "pass@64": 0.436959939458589,
1841
+ "pass@128": 0.48148148148148145
1842
+ },
1843
+ "16": {
1844
+ "pass@1": 0.07570519911504425,
1845
+ "pass@2": 0.10666939586091562,
1846
+ "pass@4": 0.1416798010868111,
1847
+ "pass@8": 0.1810688579074944,
1848
+ "pass@16": 0.22275780816752133,
1849
+ "pass@32": 0.263068335792944,
1850
+ "pass@64": 0.2997203772220057,
1851
+ "pass@128": 0.336283185840708
1852
+ },
1853
+ "17": {
1854
+ "pass@1": 0.10320971385542169,
1855
+ "pass@2": 0.14381529563134418,
1856
+ "pass@4": 0.19100916235244686,
1857
+ "pass@8": 0.23937766347762857,
1858
+ "pass@16": 0.2859107008786314,
1859
+ "pass@32": 0.3300417801536873,
1860
+ "pass@64": 0.37069650304314794,
1861
+ "pass@128": 0.4066265060240964
1862
+ },
1863
+ "18": {
1864
+ "pass@1": 0.08051915322580645,
1865
+ "pass@2": 0.1212368237236475,
1866
+ "pass@4": 0.16872798420358742,
1867
+ "pass@8": 0.21767212666994637,
1868
+ "pass@16": 0.26376278061199115,
1869
+ "pass@32": 0.3054783394532108,
1870
+ "pass@64": 0.34413886448859154,
1871
+ "pass@128": 0.3774193548387097
1872
+ },
1873
+ "19": {
1874
+ "pass@1": 0.08022564199395771,
1875
+ "pass@2": 0.10975524537907083,
1876
+ "pass@4": 0.1428751035085871,
1877
+ "pass@8": 0.17925093696793923,
1878
+ "pass@16": 0.2156630659763213,
1879
+ "pass@32": 0.24779989004979322,
1880
+ "pass@64": 0.2774643292826266,
1881
+ "pass@128": 0.311178247734139
1882
+ },
1883
+ "20": {
1884
+ "pass@1": 0.11373873873873874,
1885
+ "pass@2": 0.15614137759807054,
1886
+ "pass@4": 0.20259945744394559,
1887
+ "pass@8": 0.24897275992552667,
1888
+ "pass@16": 0.2917036036507781,
1889
+ "pass@32": 0.32881890632268107,
1890
+ "pass@64": 0.3607643461394065,
1891
+ "pass@128": 0.38738738738738737
1892
+ }
1893
+ }
1894
+ }
1895
+ }
1896
+ }
1897
+ }