ZachW commited on
Commit
3dd83c7
·
verified ·
1 Parent(s): 2a92446

Upload extrapolation artifact: 050302 OPD Ref-KL step20 summary JSON

Browse files
050302/evals/opd_refkl_sweep/step20/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "opd050302_refkl_s020_merged_hf",
4
+ "id_acc": 0.7176015625,
5
+ "ood_acc": 0.32198828125,
6
+ "total_acc": 0.5093840460526315,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 204.70313541666667,
11
+ "ood_avg_resp_len": 345.2811734375,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 413376,
19
+ "answer_accuracy": 0.5105121719886184,
20
+ "avg_response_len": 266.856698792681,
21
+ "resp_tokens_sum": 216081341,
22
+ "pass_at_k": {
23
+ "pass@1": 0.5105121719886184,
24
+ "pass@2": 0.5951151711720979,
25
+ "pass@4": 0.673061658970826,
26
+ "pass@8": 0.7391676582519209,
27
+ "pass@16": 0.7917103283238716,
28
+ "pass@32": 0.8326173602195277,
29
+ "pass@64": 0.8652732057281426,
30
+ "pass@128": 0.8929813468226367
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.634010877581121,
35
+ "pass@2": 0.7062465159222352,
36
+ "pass@4": 0.7644947741598669,
37
+ "pass@8": 0.8116146694006208,
38
+ "pass@16": 0.8500404109788816,
39
+ "pass@32": 0.8823162461259979,
40
+ "pass@64": 0.9080247505948481,
41
+ "pass@128": 0.9292035398230089
42
+ },
43
+ "2": {
44
+ "pass@1": 0.9585280373831776,
45
+ "pass@2": 0.9780915783599481,
46
+ "pass@4": 0.9890098019289645,
47
+ "pass@8": 0.9938439457645543,
48
+ "pass@16": 0.9957206822087614,
49
+ "pass@32": 0.9965938226565182,
50
+ "pass@64": 0.996875090732355,
51
+ "pass@128": 0.9968847352024922
52
+ },
53
+ "3": {
54
+ "pass@1": 0.9226873088685015,
55
+ "pass@2": 0.9478967257819837,
56
+ "pass@4": 0.9646036410012971,
57
+ "pass@8": 0.9763763418391889,
58
+ "pass@16": 0.9838775300421752,
59
+ "pass@32": 0.9883739662533801,
60
+ "pass@64": 0.9905254743410928,
61
+ "pass@128": 0.9908256880733946
62
+ },
63
+ "4": {
64
+ "pass@1": 0.779443359375,
65
+ "pass@2": 0.8007543368602363,
66
+ "pass@4": 0.8170533909823771,
67
+ "pass@8": 0.8336100776757025,
68
+ "pass@16": 0.8517066617834977,
69
+ "pass@32": 0.870517091875033,
70
+ "pass@64": 0.8889414357337735,
71
+ "pass@128": 0.909375
72
+ },
73
+ "5": {
74
+ "pass@1": 0.6555555555555556,
75
+ "pass@2": 0.7173540807399074,
76
+ "pass@4": 0.7735161667291587,
77
+ "pass@8": 0.8231139681122734,
78
+ "pass@16": 0.8634338014008391,
79
+ "pass@32": 0.8917600229999783,
80
+ "pass@64": 0.9118147405773037,
81
+ "pass@128": 0.926984126984127
82
+ },
83
+ "6": {
84
+ "pass@1": 0.6811845059880239,
85
+ "pass@2": 0.7407247512848321,
86
+ "pass@4": 0.7844679375781617,
87
+ "pass@8": 0.8172012314068267,
88
+ "pass@16": 0.8460112851595776,
89
+ "pass@32": 0.8740303640904294,
90
+ "pass@64": 0.8995094132021609,
91
+ "pass@128": 0.9221556886227545
92
+ },
93
+ "7": {
94
+ "pass@1": 0.6608727810650887,
95
+ "pass@2": 0.7246001840376461,
96
+ "pass@4": 0.7779036412053516,
97
+ "pass@8": 0.8236171565225865,
98
+ "pass@16": 0.8633101431811988,
99
+ "pass@32": 0.8952741365922631,
100
+ "pass@64": 0.9173943244665408,
101
+ "pass@128": 0.9319526627218935
102
+ },
103
+ "8": {
104
+ "pass@1": 0.6062449919871795,
105
+ "pass@2": 0.6804016347415706,
106
+ "pass@4": 0.7420314380774514,
107
+ "pass@8": 0.7933181284445693,
108
+ "pass@16": 0.83194350141597,
109
+ "pass@32": 0.8580632321891963,
110
+ "pass@64": 0.8777923319366682,
111
+ "pass@128": 0.8942307692307693
112
+ },
113
+ "9": {
114
+ "pass@1": 0.6108714788732394,
115
+ "pass@2": 0.6978315265609405,
116
+ "pass@4": 0.7622095322591714,
117
+ "pass@8": 0.811851897609808,
118
+ "pass@16": 0.8510715698732106,
119
+ "pass@32": 0.8821537858218351,
120
+ "pass@64": 0.9064998232796105,
121
+ "pass@128": 0.923943661971831
122
+ },
123
+ "11": {
124
+ "pass@1": 0.5089190864022662,
125
+ "pass@2": 0.6062891051950657,
126
+ "pass@4": 0.6916531293184668,
127
+ "pass@8": 0.7634383715515586,
128
+ "pass@16": 0.8206955390269132,
129
+ "pass@32": 0.8659707722579718,
130
+ "pass@64": 0.9009898863276803,
131
+ "pass@128": 0.9263456090651558
132
+ },
133
+ "12": {
134
+ "pass@1": 0.5751897951977402,
135
+ "pass@2": 0.6838681380399486,
136
+ "pass@4": 0.768881719499045,
137
+ "pass@8": 0.8328009439775966,
138
+ "pass@16": 0.876117849445188,
139
+ "pass@32": 0.9028048634536112,
140
+ "pass@64": 0.9196826824715851,
141
+ "pass@128": 0.9293785310734464
142
+ },
143
+ "13": {
144
+ "pass@1": 0.4440634796238245,
145
+ "pass@2": 0.5752304815738156,
146
+ "pass@4": 0.6911161097025877,
147
+ "pass@8": 0.7815396464162131,
148
+ "pass@16": 0.844326063917765,
149
+ "pass@32": 0.8853661927296426,
150
+ "pass@64": 0.9145425050682329,
151
+ "pass@128": 0.9435736677115988
152
+ },
153
+ "14": {
154
+ "pass@1": 0.40437597352024923,
155
+ "pass@2": 0.5385103913704719,
156
+ "pass@4": 0.6595417044832014,
157
+ "pass@8": 0.7566046763256996,
158
+ "pass@16": 0.8284427243213454,
159
+ "pass@32": 0.8795063735124772,
160
+ "pass@64": 0.914993720240685,
161
+ "pass@128": 0.9345794392523364
162
+ },
163
+ "15": {
164
+ "pass@1": 0.286533598265896,
165
+ "pass@2": 0.41651068453871026,
166
+ "pass@4": 0.5486129427101956,
167
+ "pass@8": 0.6593072826250115,
168
+ "pass@16": 0.7398375649184864,
169
+ "pass@32": 0.7943708348680817,
170
+ "pass@64": 0.8333319766764178,
171
+ "pass@128": 0.8670520231213873
172
+ },
173
+ "16": {
174
+ "pass@1": 0.30032762096774196,
175
+ "pass@2": 0.4287127730505461,
176
+ "pass@4": 0.5535804625228296,
177
+ "pass@8": 0.655508716260921,
178
+ "pass@16": 0.7289271830569366,
179
+ "pass@32": 0.7803989824128693,
180
+ "pass@64": 0.8216763628150855,
181
+ "pass@128": 0.8612903225806452
182
+ },
183
+ "17": {
184
+ "pass@1": 0.20838601878612717,
185
+ "pass@2": 0.3180449512994398,
186
+ "pass@4": 0.4395042797215373,
187
+ "pass@8": 0.5530691990399591,
188
+ "pass@16": 0.6472568259606186,
189
+ "pass@32": 0.7217760010616294,
190
+ "pass@64": 0.7819155489452756,
191
+ "pass@128": 0.8352601156069365
192
+ },
193
+ "18": {
194
+ "pass@1": 0.18993303571428571,
195
+ "pass@2": 0.29062640607424045,
196
+ "pass@4": 0.3997742034924205,
197
+ "pass@8": 0.500520186775815,
198
+ "pass@16": 0.5867660895823849,
199
+ "pass@32": 0.659084762886952,
200
+ "pass@64": 0.7193700865193222,
201
+ "pass@128": 0.7742857142857142
202
+ },
203
+ "19": {
204
+ "pass@1": 0.16185716966966968,
205
+ "pass@2": 0.2467017952992363,
206
+ "pass@4": 0.3430552318347592,
207
+ "pass@8": 0.4401732162122715,
208
+ "pass@16": 0.5321758889017915,
209
+ "pass@32": 0.6200199485717071,
210
+ "pass@64": 0.7053426247426714,
211
+ "pass@128": 0.7867867867867868
212
+ },
213
+ "20": {
214
+ "pass@1": 0.15885416666666666,
215
+ "pass@2": 0.25048990920053915,
216
+ "pass@4": 0.3525427080623933,
217
+ "pass@8": 0.4459922203315133,
218
+ "pass@16": 0.5244571426960978,
219
+ "pass@32": 0.5896622976962845,
220
+ "pass@64": 0.6450423966488273,
221
+ "pass@128": 0.6936936936936937
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 420619,
228
+ "answer_accuracy": 0.5122503409976618,
229
+ "avg_response_len": 274.721155251364,
230
+ "resp_tokens_sum": 225579035,
231
+ "pass_at_k": {
232
+ "pass@1": 0.5122503409976618,
233
+ "pass@2": 0.5957355538201029,
234
+ "pass@4": 0.6726182130487799,
235
+ "pass@8": 0.7375016299564596,
236
+ "pass@16": 0.7892638326045714,
237
+ "pass@32": 0.8304815290220704,
238
+ "pass@64": 0.8628537255335752,
239
+ "pass@128": 0.8868277474668745
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.6506182898773006,
244
+ "pass@2": 0.7176615863967921,
245
+ "pass@4": 0.7720718512563227,
246
+ "pass@8": 0.8198265970704206,
247
+ "pass@16": 0.861991341752906,
248
+ "pass@32": 0.8943046565967563,
249
+ "pass@64": 0.9141776152736006,
250
+ "pass@128": 0.9233128834355828
251
+ },
252
+ "2": {
253
+ "pass@1": 0.9608187689969605,
254
+ "pass@2": 0.9726735454610729,
255
+ "pass@4": 0.9791172930891238,
256
+ "pass@8": 0.9825588269128649,
257
+ "pass@16": 0.9844830232595337,
258
+ "pass@32": 0.9861930722002042,
259
+ "pass@64": 0.9875733192925031,
260
+ "pass@128": 0.9878419452887538
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9261126893939394,
264
+ "pass@2": 0.9463910761154857,
265
+ "pass@4": 0.9590749130790467,
266
+ "pass@8": 0.9666300340479783,
267
+ "pass@16": 0.971635935986462,
268
+ "pass@32": 0.9758338314250654,
269
+ "pass@64": 0.9792772034222585,
270
+ "pass@128": 0.9818181818181818
271
+ },
272
+ "4": {
273
+ "pass@1": 0.7858958949704142,
274
+ "pass@2": 0.8230967245958161,
275
+ "pass@4": 0.8534610428689019,
276
+ "pass@8": 0.8796015929651697,
277
+ "pass@16": 0.900744755081072,
278
+ "pass@32": 0.918047765736321,
279
+ "pass@64": 0.9317715610559824,
280
+ "pass@128": 0.9408284023668639
281
+ },
282
+ "5": {
283
+ "pass@1": 0.6816123188405797,
284
+ "pass@2": 0.7434711286089237,
285
+ "pass@4": 0.7988444531390099,
286
+ "pass@8": 0.8413861734001017,
287
+ "pass@16": 0.8699416234033573,
288
+ "pass@32": 0.8900063926614138,
289
+ "pass@64": 0.906048124196305,
290
+ "pass@128": 0.9188405797101449
291
+ },
292
+ "6": {
293
+ "pass@1": 0.6199856733524355,
294
+ "pass@2": 0.6759748747828442,
295
+ "pass@4": 0.7231290177194897,
296
+ "pass@8": 0.7613813055534532,
297
+ "pass@16": 0.7938218054932149,
298
+ "pass@32": 0.8231796743382198,
299
+ "pass@64": 0.8490627429567635,
300
+ "pass@128": 0.8710601719197708
301
+ },
302
+ "7": {
303
+ "pass@1": 0.6366735910404624,
304
+ "pass@2": 0.7071064556688367,
305
+ "pass@4": 0.7648485828722273,
306
+ "pass@8": 0.8102198093905228,
307
+ "pass@16": 0.8443452952353474,
308
+ "pass@32": 0.8723401644506812,
309
+ "pass@64": 0.8987213707206503,
310
+ "pass@128": 0.9190751445086706
311
+ },
312
+ "8": {
313
+ "pass@1": 0.6105853873239436,
314
+ "pass@2": 0.6901224769879115,
315
+ "pass@4": 0.756373029779728,
316
+ "pass@8": 0.8093177877765341,
317
+ "pass@16": 0.8538397064684654,
318
+ "pass@32": 0.8913871534444084,
319
+ "pass@64": 0.9188407101254693,
320
+ "pass@128": 0.9352112676056338
321
+ },
322
+ "9": {
323
+ "pass@1": 0.5959019461077845,
324
+ "pass@2": 0.67921379190438,
325
+ "pass@4": 0.7434201358250875,
326
+ "pass@8": 0.7930573325580851,
327
+ "pass@16": 0.8347511256953661,
328
+ "pass@32": 0.8697378260545378,
329
+ "pass@64": 0.8947935517788745,
330
+ "pass@128": 0.9101796407185628
331
+ },
332
+ "11": {
333
+ "pass@1": 0.5928557981927711,
334
+ "pass@2": 0.6898350043876293,
335
+ "pass@4": 0.7667176422224327,
336
+ "pass@8": 0.8248438324009825,
337
+ "pass@16": 0.8678618395731594,
338
+ "pass@32": 0.9011761639579507,
339
+ "pass@64": 0.9292217049034485,
340
+ "pass@128": 0.9487951807228916
341
+ },
342
+ "12": {
343
+ "pass@1": 0.49615497648902823,
344
+ "pass@2": 0.5971944962110927,
345
+ "pass@4": 0.6846707511874489,
346
+ "pass@8": 0.7607215499502386,
347
+ "pass@16": 0.8229859766156251,
348
+ "pass@32": 0.871370259836704,
349
+ "pass@64": 0.9072556953181591,
350
+ "pass@128": 0.9341692789968652
351
+ },
352
+ "13": {
353
+ "pass@1": 0.42078081232493,
354
+ "pass@2": 0.5402936765257276,
355
+ "pass@4": 0.6431558274228323,
356
+ "pass@8": 0.726376299146558,
357
+ "pass@16": 0.7916423776651302,
358
+ "pass@32": 0.8415217498495176,
359
+ "pass@64": 0.8759160821633467,
360
+ "pass@128": 0.896358543417367
361
+ },
362
+ "14": {
363
+ "pass@1": 0.40778051900584794,
364
+ "pass@2": 0.5438823128194495,
365
+ "pass@4": 0.6632459722688174,
366
+ "pass@8": 0.7553665898552768,
367
+ "pass@16": 0.8244074116182232,
368
+ "pass@32": 0.8744119785492632,
369
+ "pass@64": 0.9110575940279667,
370
+ "pass@128": 0.9385964912280702
371
+ },
372
+ "15": {
373
+ "pass@1": 0.3119318181818182,
374
+ "pass@2": 0.443738069673109,
375
+ "pass@4": 0.5748387193078138,
376
+ "pass@8": 0.6864163501902052,
377
+ "pass@16": 0.7710248118039731,
378
+ "pass@32": 0.830966887395924,
379
+ "pass@64": 0.8693841103191963,
380
+ "pass@128": 0.8939393939393939
381
+ },
382
+ "16": {
383
+ "pass@1": 0.3003917378917379,
384
+ "pass@2": 0.42690807479193266,
385
+ "pass@4": 0.5492866602144819,
386
+ "pass@8": 0.6527981925031016,
387
+ "pass@16": 0.7340473018719692,
388
+ "pass@32": 0.7956380322952691,
389
+ "pass@64": 0.838446007676813,
390
+ "pass@128": 0.8660968660968661
391
+ },
392
+ "17": {
393
+ "pass@1": 0.23864518633540371,
394
+ "pass@2": 0.35061836699760357,
395
+ "pass@4": 0.47032505991098866,
396
+ "pass@8": 0.5784241127863927,
397
+ "pass@16": 0.6619587190160298,
398
+ "pass@32": 0.7266220386938387,
399
+ "pass@64": 0.7820725850125615,
400
+ "pass@128": 0.8260869565217391
401
+ },
402
+ "18": {
403
+ "pass@1": 0.18972886029411765,
404
+ "pass@2": 0.2931876736915237,
405
+ "pass@4": 0.4118093437768809,
406
+ "pass@8": 0.5257871881146705,
407
+ "pass@16": 0.6205779100931101,
408
+ "pass@32": 0.6958105992825102,
409
+ "pass@64": 0.7551185830094297,
410
+ "pass@128": 0.8029411764705883
411
+ },
412
+ "19": {
413
+ "pass@1": 0.1636904761904762,
414
+ "pass@2": 0.2533156255858642,
415
+ "pass@4": 0.3533762615610551,
416
+ "pass@8": 0.4457775457408718,
417
+ "pass@16": 0.5231843366043224,
418
+ "pass@32": 0.5927289872430728,
419
+ "pass@64": 0.6580693686939435,
420
+ "pass@128": 0.7172619047619048
421
+ },
422
+ "20": {
423
+ "pass@1": 0.14822698353293412,
424
+ "pass@2": 0.22706567671743122,
425
+ "pass@4": 0.31300269736118325,
426
+ "pass@8": 0.39253890561183347,
427
+ "pass@16": 0.46300134160296824,
428
+ "pass@32": 0.5277956760729736,
429
+ "pass@64": 0.587383389834938,
430
+ "pass@128": 0.6377245508982036
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 404827,
437
+ "answer_accuracy": 0.505306109202748,
438
+ "avg_response_len": 294.72252206822174,
439
+ "resp_tokens_sum": 236117538,
440
+ "pass_at_k": {
441
+ "pass@1": 0.505306109202748,
442
+ "pass@2": 0.5907367603249829,
443
+ "pass@4": 0.6697681771095563,
444
+ "pass@8": 0.736101667112531,
445
+ "pass@16": 0.78859637191491,
446
+ "pass@32": 0.8302934249828102,
447
+ "pass@64": 0.8633519265499549,
448
+ "pass@128": 0.8892794376098418
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.5948460820895523,
453
+ "pass@2": 0.6784162357503819,
454
+ "pass@4": 0.7527509082819867,
455
+ "pass@8": 0.8139333357748063,
456
+ "pass@16": 0.8587077364815865,
457
+ "pass@32": 0.8907294438489362,
458
+ "pass@64": 0.9149476777823535,
459
+ "pass@128": 0.9343283582089552
460
+ },
461
+ "2": {
462
+ "pass@1": 0.9541517857142857,
463
+ "pass@2": 0.9774050899887515,
464
+ "pass@4": 0.9884335063474204,
465
+ "pass@8": 0.9934172931025678,
466
+ "pass@16": 0.9960565025775125,
467
+ "pass@32": 0.997019357050945,
468
+ "pass@64": 0.9971419771975655,
469
+ "pass@128": 0.9971428571428571
470
+ },
471
+ "3": {
472
+ "pass@1": 0.9253826530612245,
473
+ "pass@2": 0.9461796388971788,
474
+ "pass@4": 0.9591699097926168,
475
+ "pass@8": 0.968384735252641,
476
+ "pass@16": 0.9752389836001336,
477
+ "pass@32": 0.9808482865428164,
478
+ "pass@64": 0.9857832009109867,
479
+ "pass@128": 0.9883381924198251
480
+ },
481
+ "4": {
482
+ "pass@1": 0.7796966374269005,
483
+ "pass@2": 0.8191163604549434,
484
+ "pass@4": 0.8466034242978397,
485
+ "pass@8": 0.8663928448288716,
486
+ "pass@16": 0.8815232479012405,
487
+ "pass@32": 0.8944119482684968,
488
+ "pass@64": 0.9060526114011204,
489
+ "pass@128": 0.9181286549707602
490
+ },
491
+ "5": {
492
+ "pass@1": 0.6695082720588236,
493
+ "pass@2": 0.7312630268642893,
494
+ "pass@4": 0.7866203938662076,
495
+ "pass@8": 0.8310174321989172,
496
+ "pass@16": 0.8650803824252749,
497
+ "pass@32": 0.8914264018985473,
498
+ "pass@64": 0.912964131105359,
499
+ "pass@128": 0.9323529411764706
500
+ },
501
+ "6": {
502
+ "pass@1": 0.6619923107255521,
503
+ "pass@2": 0.7269356696639262,
504
+ "pass@4": 0.7793254738070992,
505
+ "pass@8": 0.8235025865328549,
506
+ "pass@16": 0.8619444093798664,
507
+ "pass@32": 0.8927568014819741,
508
+ "pass@64": 0.9146422265181665,
509
+ "pass@128": 0.9305993690851735
510
+ },
511
+ "7": {
512
+ "pass@1": 0.605740704113924,
513
+ "pass@2": 0.6755110479168743,
514
+ "pass@4": 0.7341896016953572,
515
+ "pass@8": 0.7820892847021093,
516
+ "pass@16": 0.8196935381560206,
517
+ "pass@32": 0.8504635546967145,
518
+ "pass@64": 0.8760534599864116,
519
+ "pass@128": 0.8955696202531646
520
+ },
521
+ "8": {
522
+ "pass@1": 0.6112518768768769,
523
+ "pass@2": 0.6893310633468112,
524
+ "pass@4": 0.7535754542506511,
525
+ "pass@8": 0.8050629623009855,
526
+ "pass@16": 0.8463752646312165,
527
+ "pass@32": 0.8792931778368894,
528
+ "pass@64": 0.9048188262070532,
529
+ "pass@128": 0.924924924924925
530
+ },
531
+ "9": {
532
+ "pass@1": 0.5930968649517685,
533
+ "pass@2": 0.6749610729928853,
534
+ "pass@4": 0.7411335674077718,
535
+ "pass@8": 0.7921720758648182,
536
+ "pass@16": 0.8312983566558316,
537
+ "pass@32": 0.8633446759630666,
538
+ "pass@64": 0.8919567944681497,
539
+ "pass@128": 0.9196141479099679
540
+ },
541
+ "11": {
542
+ "pass@1": 0.5473462301587302,
543
+ "pass@2": 0.6494848300212477,
544
+ "pass@4": 0.7343210411198594,
545
+ "pass@8": 0.7974897602046568,
546
+ "pass@16": 0.8424830562644234,
547
+ "pass@32": 0.875865621077959,
548
+ "pass@64": 0.9006360458357809,
549
+ "pass@128": 0.9206349206349206
550
+ },
551
+ "12": {
552
+ "pass@1": 0.5713159403669725,
553
+ "pass@2": 0.6815470815574655,
554
+ "pass@4": 0.7616184464900604,
555
+ "pass@8": 0.8206595316798269,
556
+ "pass@16": 0.8658105763587155,
557
+ "pass@32": 0.9010371554194384,
558
+ "pass@64": 0.9275783042200226,
559
+ "pass@128": 0.944954128440367
560
+ },
561
+ "13": {
562
+ "pass@1": 0.4498697916666667,
563
+ "pass@2": 0.5832118207446293,
564
+ "pass@4": 0.7017764746999209,
565
+ "pass@8": 0.7937035612715942,
566
+ "pass@16": 0.8560568592353323,
567
+ "pass@32": 0.8965106791414652,
568
+ "pass@64": 0.9238804793558109,
569
+ "pass@128": 0.941358024691358
570
+ },
571
+ "14": {
572
+ "pass@1": 0.3586795252225519,
573
+ "pass@2": 0.4937754094721838,
574
+ "pass@4": 0.6188754287761504,
575
+ "pass@8": 0.7190848075644879,
576
+ "pass@16": 0.7920581470581497,
577
+ "pass@32": 0.845231223854129,
578
+ "pass@64": 0.8813770225787123,
579
+ "pass@128": 0.9050445103857567
580
+ },
581
+ "15": {
582
+ "pass@1": 0.2952594521604938,
583
+ "pass@2": 0.42206410396617056,
584
+ "pass@4": 0.5520324999884273,
585
+ "pass@8": 0.6643895213028989,
586
+ "pass@16": 0.7476881641100671,
587
+ "pass@32": 0.8059029985025377,
588
+ "pass@64": 0.8489543971908488,
589
+ "pass@128": 0.8765432098765432
590
+ },
591
+ "16": {
592
+ "pass@1": 0.2740366887905605,
593
+ "pass@2": 0.40410293707755535,
594
+ "pass@4": 0.537539763005288,
595
+ "pass@8": 0.6497843098991486,
596
+ "pass@16": 0.7341919950848028,
597
+ "pass@32": 0.7992724608196874,
598
+ "pass@64": 0.8528486688122242,
599
+ "pass@128": 0.8997050147492626
600
+ },
601
+ "17": {
602
+ "pass@1": 0.18138177710843373,
603
+ "pass@2": 0.2810061604686461,
604
+ "pass@4": 0.3914212132557223,
605
+ "pass@8": 0.49728099268818116,
606
+ "pass@16": 0.595006800154788,
607
+ "pass@32": 0.6812210325671828,
608
+ "pass@64": 0.7490418301670095,
609
+ "pass@128": 0.8012048192771084
610
+ },
611
+ "18": {
612
+ "pass@1": 0.16995967741935483,
613
+ "pass@2": 0.2633389954279909,
614
+ "pass@4": 0.36664491484935374,
615
+ "pass@8": 0.46449010141047903,
616
+ "pass@16": 0.5518110378525231,
617
+ "pass@32": 0.6303793049310443,
618
+ "pass@64": 0.6970383011318961,
619
+ "pass@128": 0.7483870967741936
620
+ },
621
+ "19": {
622
+ "pass@1": 0.15794939577039274,
623
+ "pass@2": 0.24761742631491315,
624
+ "pass@4": 0.3478093371825502,
625
+ "pass@8": 0.44223387224279903,
626
+ "pass@16": 0.5251490469009392,
627
+ "pass@32": 0.5973193505438142,
628
+ "pass@64": 0.6595889400853764,
629
+ "pass@128": 0.7129909365558912
630
+ },
631
+ "20": {
632
+ "pass@1": 0.14686561561561562,
633
+ "pass@2": 0.23407314795110054,
634
+ "pass@4": 0.3344437716681814,
635
+ "pass@8": 0.42997645757970976,
636
+ "pass@16": 0.511795734470298,
637
+ "pass@32": 0.5819356163017798,
638
+ "pass@64": 0.6417086542151089,
639
+ "pass@128": 0.6906906906906907
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]