ZachW commited on
Commit
7b17ba0
·
verified ·
1 Parent(s): 4818688

Upload extrapolation artifact: 020305 pretrain checkpoint-18809 summary JSON

Browse files
020305/evals/pretrain_ckpt18809/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "pretrain_ckpt18809",
4
+ "id_acc": 0.3620373263888889,
5
+ "ood_acc": 0.1004375,
6
+ "total_acc": 0.2243532072368421,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 204.96420920138888,
11
+ "ood_avg_resp_len": 293.3315125,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 174960,
19
+ "answer_accuracy": 0.2160725576983876,
20
+ "avg_response_len": 240.2238331884287,
21
+ "resp_tokens_sum": 194515964,
22
+ "pass_at_k": {
23
+ "pass@1": 0.2160725576983876,
24
+ "pass@2": 0.26710561773558145,
25
+ "pass@4": 0.32056310265299404,
26
+ "pass@8": 0.37358226413942236,
27
+ "pass@16": 0.42426905582922897,
28
+ "pass@32": 0.47242045998358206,
29
+ "pass@64": 0.5179877228554772,
30
+ "pass@128": 0.5608599430920013
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.16118178466076696,
35
+ "pass@2": 0.21100700009290868,
36
+ "pass@4": 0.26204468053219016,
37
+ "pass@8": 0.313965959315187,
38
+ "pass@16": 0.3669307944259261,
39
+ "pass@32": 0.4192929029900247,
40
+ "pass@64": 0.4697690954137164,
41
+ "pass@128": 0.5221238938053098
42
+ },
43
+ "2": {
44
+ "pass@1": 0.6974785825545171,
45
+ "pass@2": 0.7498029962960233,
46
+ "pass@4": 0.7984764164993392,
47
+ "pass@8": 0.8426580781725969,
48
+ "pass@16": 0.8811400390570819,
49
+ "pass@32": 0.9154355567676705,
50
+ "pass@64": 0.9439033477168228,
51
+ "pass@128": 0.9626168224299065
52
+ },
53
+ "3": {
54
+ "pass@1": 0.6284881498470948,
55
+ "pass@2": 0.6921070968479855,
56
+ "pass@4": 0.7454523299266487,
57
+ "pass@8": 0.7916577080236396,
58
+ "pass@16": 0.8325218506692965,
59
+ "pass@32": 0.8683391227625886,
60
+ "pass@64": 0.8968584133079681,
61
+ "pass@128": 0.9174311926605505
62
+ },
63
+ "4": {
64
+ "pass@1": 0.459765625,
65
+ "pass@2": 0.5297778512549212,
66
+ "pass@4": 0.5945688033136481,
67
+ "pass@8": 0.6530113938111209,
68
+ "pass@16": 0.7081231827169705,
69
+ "pass@32": 0.759363772014444,
70
+ "pass@64": 0.8044523643734547,
71
+ "pass@128": 0.84375
72
+ },
73
+ "5": {
74
+ "pass@1": 0.26671626984126984,
75
+ "pass@2": 0.3425470253718283,
76
+ "pass@4": 0.41556439968813413,
77
+ "pass@8": 0.48176800859338753,
78
+ "pass@16": 0.5418400059324522,
79
+ "pass@32": 0.5976897340165899,
80
+ "pass@64": 0.6484423831216877,
81
+ "pass@128": 0.6952380952380952
82
+ },
83
+ "6": {
84
+ "pass@1": 0.33493169910179643,
85
+ "pass@2": 0.3905675361874673,
86
+ "pass@4": 0.449119640078673,
87
+ "pass@8": 0.509693792465805,
88
+ "pass@16": 0.5692551867943821,
89
+ "pass@32": 0.6241793020699291,
90
+ "pass@64": 0.6729702040598893,
91
+ "pass@128": 0.718562874251497
92
+ },
93
+ "7": {
94
+ "pass@1": 0.2567030325443787,
95
+ "pass@2": 0.33237031461119126,
96
+ "pass@4": 0.40505862386654345,
97
+ "pass@8": 0.47228374550038577,
98
+ "pass@16": 0.533299549975349,
99
+ "pass@32": 0.5853612209560378,
100
+ "pass@64": 0.6296383818221275,
101
+ "pass@128": 0.6715976331360947
102
+ },
103
+ "8": {
104
+ "pass@1": 0.22741386217948717,
105
+ "pass@2": 0.29118518763880463,
106
+ "pass@4": 0.3558928727659042,
107
+ "pass@8": 0.41934049330733497,
108
+ "pass@16": 0.4790422934302815,
109
+ "pass@32": 0.5353208860582773,
110
+ "pass@64": 0.5903250480614363,
111
+ "pass@128": 0.6442307692307693
112
+ },
113
+ "9": {
114
+ "pass@1": 0.17086267605633804,
115
+ "pass@2": 0.24369766829322378,
116
+ "pass@4": 0.32428576603980847,
117
+ "pass@8": 0.4026243423547874,
118
+ "pass@16": 0.4743958200381107,
119
+ "pass@32": 0.5415250798666842,
120
+ "pass@64": 0.6075046168962964,
121
+ "pass@128": 0.6732394366197183
122
+ },
123
+ "11": {
124
+ "pass@1": 0.13493714589235128,
125
+ "pass@2": 0.18312558553233246,
126
+ "pass@4": 0.23801532607645007,
127
+ "pass@8": 0.2983196016544395,
128
+ "pass@16": 0.3600201317791979,
129
+ "pass@32": 0.4206971006327828,
130
+ "pass@64": 0.48044195628551944,
131
+ "pass@128": 0.5325779036827195
132
+ },
133
+ "12": {
134
+ "pass@1": 0.1138771186440678,
135
+ "pass@2": 0.15339073412963222,
136
+ "pass@4": 0.19769429801147728,
137
+ "pass@8": 0.24559352472202536,
138
+ "pass@16": 0.29559038484450695,
139
+ "pass@32": 0.34574248692946935,
140
+ "pass@64": 0.3942527843078104,
141
+ "pass@128": 0.4435028248587571
142
+ },
143
+ "13": {
144
+ "pass@1": 0.08118632445141066,
145
+ "pass@2": 0.11738168921087064,
146
+ "pass@4": 0.16368368471966077,
147
+ "pass@8": 0.21852505040149559,
148
+ "pass@16": 0.27768709595526475,
149
+ "pass@32": 0.3372075681784244,
150
+ "pass@64": 0.39446850776198933,
151
+ "pass@128": 0.4482758620689655
152
+ },
153
+ "14": {
154
+ "pass@1": 0.08464758566978194,
155
+ "pass@2": 0.12638439178747513,
156
+ "pass@4": 0.17817912538970013,
157
+ "pass@8": 0.23636157858881193,
158
+ "pass@16": 0.29483488034710237,
159
+ "pass@32": 0.3511077582240689,
160
+ "pass@64": 0.4042818757611095,
161
+ "pass@128": 0.45482866043613707
162
+ },
163
+ "15": {
164
+ "pass@1": 0.09022760115606937,
165
+ "pass@2": 0.1371285586682445,
166
+ "pass@4": 0.19187320163375532,
167
+ "pass@8": 0.2476590145157713,
168
+ "pass@16": 0.30101540861456305,
169
+ "pass@32": 0.35355459521979815,
170
+ "pass@64": 0.403824523100272,
171
+ "pass@128": 0.4479768786127168
172
+ },
173
+ "16": {
174
+ "pass@1": 0.10040322580645161,
175
+ "pass@2": 0.13670188277876558,
176
+ "pass@4": 0.1743356867689926,
177
+ "pass@8": 0.21140222159109787,
178
+ "pass@16": 0.24659782942071334,
179
+ "pass@32": 0.2791460500839276,
180
+ "pass@64": 0.3108012194942665,
181
+ "pass@128": 0.3419354838709677
182
+ },
183
+ "17": {
184
+ "pass@1": 0.08652456647398844,
185
+ "pass@2": 0.12079666093942017,
186
+ "pass@4": 0.1590196281461927,
187
+ "pass@8": 0.1949001400392914,
188
+ "pass@16": 0.22656725369755437,
189
+ "pass@32": 0.2590803393903783,
190
+ "pass@64": 0.297425501824078,
191
+ "pass@128": 0.34104046242774566
192
+ },
193
+ "18": {
194
+ "pass@1": 0.10104910714285714,
195
+ "pass@2": 0.1401813835770529,
196
+ "pass@4": 0.1825441019872516,
197
+ "pass@8": 0.2248524001219474,
198
+ "pass@16": 0.26573177942206255,
199
+ "pass@32": 0.3046260719649893,
200
+ "pass@64": 0.33970862070908614,
201
+ "pass@128": 0.3742857142857143
202
+ },
203
+ "19": {
204
+ "pass@1": 0.08223066816816817,
205
+ "pass@2": 0.1153045269679128,
206
+ "pass@4": 0.1499320814064909,
207
+ "pass@8": 0.1841899892713908,
208
+ "pass@16": 0.21844240351446248,
209
+ "pass@32": 0.2546023729358134,
210
+ "pass@64": 0.29275972060640304,
211
+ "pass@128": 0.32732732732732733
212
+ },
213
+ "20": {
214
+ "pass@1": 0.07627158408408409,
215
+ "pass@2": 0.11276630961670332,
216
+ "pass@4": 0.15630633980437128,
217
+ "pass@8": 0.20000992403576465,
218
+ "pass@16": 0.2379340644851812,
219
+ "pass@32": 0.27221998927265006,
220
+ "pass@64": 0.3063487387247676,
221
+ "pass@128": 0.33933933933933935
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 180027,
228
+ "answer_accuracy": 0.21924566445830085,
229
+ "avg_response_len": 248.22646628994545,
230
+ "resp_tokens_sum": 203823716,
231
+ "pass_at_k": {
232
+ "pass@1": 0.21924566445830085,
233
+ "pass@2": 0.2690937785762966,
234
+ "pass@4": 0.3205873553559144,
235
+ "pass@8": 0.3719643629642574,
236
+ "pass@16": 0.42249542154697955,
237
+ "pass@32": 0.4722283866900299,
238
+ "pass@64": 0.5212290010952906,
239
+ "pass@128": 0.5686671862821512
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.14239838957055215,
244
+ "pass@2": 0.18646215762523552,
245
+ "pass@4": 0.23446961643214842,
246
+ "pass@8": 0.28705840266279736,
247
+ "pass@16": 0.34176712763641864,
248
+ "pass@32": 0.393697107128622,
249
+ "pass@64": 0.4396077946700623,
250
+ "pass@128": 0.4815950920245399
251
+ },
252
+ "2": {
253
+ "pass@1": 0.6969747340425532,
254
+ "pass@2": 0.753928406887969,
255
+ "pass@4": 0.8035614455867784,
256
+ "pass@8": 0.843974271174507,
257
+ "pass@16": 0.8749837921659976,
258
+ "pass@32": 0.8982223777835114,
259
+ "pass@64": 0.9187984833921925,
260
+ "pass@128": 0.9422492401215805
261
+ },
262
+ "3": {
263
+ "pass@1": 0.6451467803030303,
264
+ "pass@2": 0.7162670007158197,
265
+ "pass@4": 0.7793047312267779,
266
+ "pass@8": 0.8333319187968913,
267
+ "pass@16": 0.8770961555446578,
268
+ "pass@32": 0.909542515519656,
269
+ "pass@64": 0.9324872967635861,
270
+ "pass@128": 0.9515151515151515
271
+ },
272
+ "4": {
273
+ "pass@1": 0.522605399408284,
274
+ "pass@2": 0.5892557104086102,
275
+ "pass@4": 0.6476280076676802,
276
+ "pass@8": 0.6990817626466677,
277
+ "pass@16": 0.7463410223529519,
278
+ "pass@32": 0.7917997275040872,
279
+ "pass@64": 0.8345071710379106,
280
+ "pass@128": 0.8727810650887574
281
+ },
282
+ "5": {
283
+ "pass@1": 0.23156702898550724,
284
+ "pass@2": 0.3060135655597396,
285
+ "pass@4": 0.3781115583378164,
286
+ "pass@8": 0.44872429897310967,
287
+ "pass@16": 0.5185551846144103,
288
+ "pass@32": 0.5877484160335491,
289
+ "pass@64": 0.6546433701390305,
290
+ "pass@128": 0.7130434782608696
291
+ },
292
+ "6": {
293
+ "pass@1": 0.3259760028653295,
294
+ "pass@2": 0.3796741392730634,
295
+ "pass@4": 0.4381010783394194,
296
+ "pass@8": 0.49888167562112606,
297
+ "pass@16": 0.5602468122792769,
298
+ "pass@32": 0.6221272504599301,
299
+ "pass@64": 0.6829418759180574,
300
+ "pass@128": 0.7363896848137536
301
+ },
302
+ "7": {
303
+ "pass@1": 0.2296333092485549,
304
+ "pass@2": 0.29712497439807023,
305
+ "pass@4": 0.36502451770840794,
306
+ "pass@8": 0.426388535715249,
307
+ "pass@16": 0.4804327509720443,
308
+ "pass@32": 0.533175386708967,
309
+ "pass@64": 0.587141630247611,
310
+ "pass@128": 0.6416184971098265
311
+ },
312
+ "8": {
313
+ "pass@1": 0.18727992957746478,
314
+ "pass@2": 0.2457202367749805,
315
+ "pass@4": 0.30368673880553654,
316
+ "pass@8": 0.36232621489128214,
317
+ "pass@16": 0.42333938653385483,
318
+ "pass@32": 0.4851196069605558,
319
+ "pass@64": 0.5487500600105882,
320
+ "pass@128": 0.6197183098591549
321
+ },
322
+ "9": {
323
+ "pass@1": 0.13356100299401197,
324
+ "pass@2": 0.18219085942288651,
325
+ "pass@4": 0.23733269989829103,
326
+ "pass@8": 0.29824739855791427,
327
+ "pass@16": 0.36406530154791894,
328
+ "pass@32": 0.43171976382911487,
329
+ "pass@64": 0.5005413019533322,
330
+ "pass@128": 0.5748502994011976
331
+ },
332
+ "11": {
333
+ "pass@1": 0.13234186746987953,
334
+ "pass@2": 0.17239491924390465,
335
+ "pass@4": 0.2164256291194022,
336
+ "pass@8": 0.2647050388915188,
337
+ "pass@16": 0.31922204405231247,
338
+ "pass@32": 0.38374982547121045,
339
+ "pass@64": 0.4587633082915936,
340
+ "pass@128": 0.5301204819277109
341
+ },
342
+ "12": {
343
+ "pass@1": 0.12056720219435736,
344
+ "pass@2": 0.1622743008417052,
345
+ "pass@4": 0.21015363204991236,
346
+ "pass@8": 0.2612399562037256,
347
+ "pass@16": 0.3142117204345368,
348
+ "pass@32": 0.3682695642944986,
349
+ "pass@64": 0.4245855724775943,
350
+ "pass@128": 0.4827586206896552
351
+ },
352
+ "13": {
353
+ "pass@1": 0.10758053221288516,
354
+ "pass@2": 0.14794037693817685,
355
+ "pass@4": 0.19233156149598946,
356
+ "pass@8": 0.23800085311099878,
357
+ "pass@16": 0.28313717264131943,
358
+ "pass@32": 0.32818330018656916,
359
+ "pass@64": 0.3753651392023757,
360
+ "pass@128": 0.42857142857142855
361
+ },
362
+ "14": {
363
+ "pass@1": 0.09708516081871345,
364
+ "pass@2": 0.1348389222728738,
365
+ "pass@4": 0.1788185881918269,
366
+ "pass@8": 0.22941582349844927,
367
+ "pass@16": 0.28430080687144255,
368
+ "pass@32": 0.33796333333182454,
369
+ "pass@64": 0.3873540833022138,
370
+ "pass@128": 0.43567251461988304
371
+ },
372
+ "15": {
373
+ "pass@1": 0.08759469696969698,
374
+ "pass@2": 0.13447789906943447,
375
+ "pass@4": 0.19098245304564204,
376
+ "pass@8": 0.24954836533037086,
377
+ "pass@16": 0.30737819754532864,
378
+ "pass@32": 0.3662480410675128,
379
+ "pass@64": 0.4255872926643773,
380
+ "pass@128": 0.48484848484848486
381
+ },
382
+ "16": {
383
+ "pass@1": 0.09390580484330484,
384
+ "pass@2": 0.12404624301769973,
385
+ "pass@4": 0.15564786185914797,
386
+ "pass@8": 0.18744827833293884,
387
+ "pass@16": 0.21857473436441932,
388
+ "pass@32": 0.25054869625221565,
389
+ "pass@64": 0.28266009150311744,
390
+ "pass@128": 0.31054131054131057
391
+ },
392
+ "17": {
393
+ "pass@1": 0.11886160714285714,
394
+ "pass@2": 0.16336634041668707,
395
+ "pass@4": 0.2106385201461618,
396
+ "pass@8": 0.25959876270632704,
397
+ "pass@16": 0.3096287586457038,
398
+ "pass@32": 0.359575814368446,
399
+ "pass@64": 0.4078289528773535,
400
+ "pass@128": 0.4503105590062112
401
+ },
402
+ "18": {
403
+ "pass@1": 0.12231158088235294,
404
+ "pass@2": 0.1738916309634089,
405
+ "pass@4": 0.2285186930677783,
406
+ "pass@8": 0.2796158296809389,
407
+ "pass@16": 0.3240335073703519,
408
+ "pass@32": 0.3641409802301815,
409
+ "pass@64": 0.4028805495934675,
410
+ "pass@128": 0.4411764705882353
411
+ },
412
+ "19": {
413
+ "pass@1": 0.09354073660714286,
414
+ "pass@2": 0.12886999964848145,
415
+ "pass@4": 0.1643410748321638,
416
+ "pass@8": 0.19890879493759292,
417
+ "pass@16": 0.23392055005639528,
418
+ "pass@32": 0.2704556352870397,
419
+ "pass@64": 0.3076625384550164,
420
+ "pass@128": 0.3392857142857143
421
+ },
422
+ "20": {
423
+ "pass@1": 0.0893057634730539,
424
+ "pass@2": 0.1258284366306757,
425
+ "pass@4": 0.16724632820972232,
426
+ "pass@8": 0.2114976229939815,
427
+ "pass@16": 0.25636790888869143,
428
+ "pass@32": 0.2994744548504521,
429
+ "pass@64": 0.33952434762294603,
430
+ "pass@128": 0.37425149700598803
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 190640,
437
+ "answer_accuracy": 0.23795734142834318,
438
+ "avg_response_len": 266.17099501717524,
439
+ "resp_tokens_sum": 213243425,
440
+ "pass_at_k": {
441
+ "pass@1": 0.23795734142834318,
442
+ "pass@2": 0.28814172945289696,
443
+ "pass@4": 0.3397848819484745,
444
+ "pass@8": 0.39153368689153495,
445
+ "pass@16": 0.4417477861760282,
446
+ "pass@32": 0.4894756193539459,
447
+ "pass@64": 0.5340134083336696,
448
+ "pass@128": 0.5753315226074452
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.1552705223880597,
453
+ "pass@2": 0.20391056528381718,
454
+ "pass@4": 0.2528069710502605,
455
+ "pass@8": 0.30123251614105645,
456
+ "pass@16": 0.35094227397872746,
457
+ "pass@32": 0.40390501923769717,
458
+ "pass@64": 0.4623533386053791,
459
+ "pass@128": 0.5283582089552239
460
+ },
461
+ "2": {
462
+ "pass@1": 0.7690178571428572,
463
+ "pass@2": 0.811122047244094,
464
+ "pass@4": 0.8464399753602228,
465
+ "pass@8": 0.8759714779916868,
466
+ "pass@16": 0.9000858122271072,
467
+ "pass@32": 0.9213030785948414,
468
+ "pass@64": 0.940299903645694,
469
+ "pass@128": 0.9571428571428572
470
+ },
471
+ "3": {
472
+ "pass@1": 0.7143540451895044,
473
+ "pass@2": 0.7747530044076125,
474
+ "pass@4": 0.8196114179240708,
475
+ "pass@8": 0.8559662103586972,
476
+ "pass@16": 0.8897364064971576,
477
+ "pass@32": 0.9219330757317451,
478
+ "pass@64": 0.9491603081682237,
479
+ "pass@128": 0.9708454810495627
480
+ },
481
+ "4": {
482
+ "pass@1": 0.4984923245614035,
483
+ "pass@2": 0.5745319047290139,
484
+ "pass@4": 0.6498902875627387,
485
+ "pass@8": 0.7180478449072955,
486
+ "pass@16": 0.7758243794385915,
487
+ "pass@32": 0.8231015375354785,
488
+ "pass@64": 0.8580602800659657,
489
+ "pass@128": 0.8830409356725146
490
+ },
491
+ "5": {
492
+ "pass@1": 0.30229779411764707,
493
+ "pass@2": 0.379587627373784,
494
+ "pass@4": 0.4499043020357746,
495
+ "pass@8": 0.5171229578956147,
496
+ "pass@16": 0.5820932714701458,
497
+ "pass@32": 0.6440228324280421,
498
+ "pass@64": 0.6958193558572406,
499
+ "pass@128": 0.7323529411764705
500
+ },
501
+ "6": {
502
+ "pass@1": 0.33620859621451105,
503
+ "pass@2": 0.39645871109565534,
504
+ "pass@4": 0.4621610648432353,
505
+ "pass@8": 0.5337083292784405,
506
+ "pass@16": 0.6025462795615276,
507
+ "pass@32": 0.6602012460186194,
508
+ "pass@64": 0.704284012799474,
509
+ "pass@128": 0.7381703470031545
510
+ },
511
+ "7": {
512
+ "pass@1": 0.25398041930379744,
513
+ "pass@2": 0.31391135814312754,
514
+ "pass@4": 0.36945819242926925,
515
+ "pass@8": 0.4231639358566098,
516
+ "pass@16": 0.47566240094124973,
517
+ "pass@32": 0.5264528242017742,
518
+ "pass@64": 0.5759157195990866,
519
+ "pass@128": 0.6265822784810127
520
+ },
521
+ "8": {
522
+ "pass@1": 0.22515484234234234,
523
+ "pass@2": 0.2828641880069045,
524
+ "pass@4": 0.3421770507853185,
525
+ "pass@8": 0.4007182921811377,
526
+ "pass@16": 0.45732939311235854,
527
+ "pass@32": 0.5117098295184779,
528
+ "pass@64": 0.5640639314279801,
529
+ "pass@128": 0.6096096096096096
530
+ },
531
+ "9": {
532
+ "pass@1": 0.1998844453376206,
533
+ "pass@2": 0.2682711661645189,
534
+ "pass@4": 0.33793876719991994,
535
+ "pass@8": 0.4059187624921453,
536
+ "pass@16": 0.47113598319572814,
537
+ "pass@32": 0.5334663052406697,
538
+ "pass@64": 0.5962504727660117,
539
+ "pass@128": 0.6591639871382636
540
+ },
541
+ "11": {
542
+ "pass@1": 0.12641369047619047,
543
+ "pass@2": 0.17554329146356704,
544
+ "pass@4": 0.23326936216306302,
545
+ "pass@8": 0.29750874087488655,
546
+ "pass@16": 0.3663616173481937,
547
+ "pass@32": 0.4371521086462832,
548
+ "pass@64": 0.5041287820690189,
549
+ "pass@128": 0.5619047619047619
550
+ },
551
+ "12": {
552
+ "pass@1": 0.12504778287461774,
553
+ "pass@2": 0.16591342796599964,
554
+ "pass@4": 0.21000277402251305,
555
+ "pass@8": 0.2537437721295953,
556
+ "pass@16": 0.2970736109719961,
557
+ "pass@32": 0.3428671879118418,
558
+ "pass@64": 0.3898421922078423,
559
+ "pass@128": 0.43730886850152906
560
+ },
561
+ "13": {
562
+ "pass@1": 0.08297164351851852,
563
+ "pass@2": 0.11160057900748516,
564
+ "pass@4": 0.14504951869442242,
565
+ "pass@8": 0.1857712724430506,
566
+ "pass@16": 0.2364672847235342,
567
+ "pass@32": 0.2976027092301482,
568
+ "pass@64": 0.365115108855201,
569
+ "pass@128": 0.4382716049382716
570
+ },
571
+ "14": {
572
+ "pass@1": 0.0947932121661721,
573
+ "pass@2": 0.14057900009346028,
574
+ "pass@4": 0.19348220391219642,
575
+ "pass@8": 0.24924596247550668,
576
+ "pass@16": 0.30242594041052445,
577
+ "pass@32": 0.3522692070793088,
578
+ "pass@64": 0.39999651612779025,
579
+ "pass@128": 0.4421364985163205
580
+ },
581
+ "15": {
582
+ "pass@1": 0.11443865740740741,
583
+ "pass@2": 0.16848214068727518,
584
+ "pass@4": 0.22918851868053525,
585
+ "pass@8": 0.29037426746400014,
586
+ "pass@16": 0.3455079728175878,
587
+ "pass@32": 0.39287827288707505,
588
+ "pass@64": 0.436959939458589,
589
+ "pass@128": 0.48148148148148145
590
+ },
591
+ "16": {
592
+ "pass@1": 0.07570519911504425,
593
+ "pass@2": 0.10666939586091562,
594
+ "pass@4": 0.1416798010868111,
595
+ "pass@8": 0.1810688579074944,
596
+ "pass@16": 0.22275780816752133,
597
+ "pass@32": 0.263068335792944,
598
+ "pass@64": 0.2997203772220057,
599
+ "pass@128": 0.336283185840708
600
+ },
601
+ "17": {
602
+ "pass@1": 0.10320971385542169,
603
+ "pass@2": 0.14381529563134418,
604
+ "pass@4": 0.19100916235244686,
605
+ "pass@8": 0.23937766347762857,
606
+ "pass@16": 0.2859107008786314,
607
+ "pass@32": 0.3300417801536873,
608
+ "pass@64": 0.37069650304314794,
609
+ "pass@128": 0.4066265060240964
610
+ },
611
+ "18": {
612
+ "pass@1": 0.08051915322580645,
613
+ "pass@2": 0.1212368237236475,
614
+ "pass@4": 0.16872798420358742,
615
+ "pass@8": 0.21767212666994637,
616
+ "pass@16": 0.26376278061199115,
617
+ "pass@32": 0.3054783394532108,
618
+ "pass@64": 0.34413886448859154,
619
+ "pass@128": 0.3774193548387097
620
+ },
621
+ "19": {
622
+ "pass@1": 0.08022564199395771,
623
+ "pass@2": 0.10975524537907083,
624
+ "pass@4": 0.1428751035085871,
625
+ "pass@8": 0.17925093696793923,
626
+ "pass@16": 0.2156630659763213,
627
+ "pass@32": 0.24779989004979322,
628
+ "pass@64": 0.2774643292826266,
629
+ "pass@128": 0.311178247734139
630
+ },
631
+ "20": {
632
+ "pass@1": 0.11373873873873874,
633
+ "pass@2": 0.15614137759807054,
634
+ "pass@4": 0.20259945744394559,
635
+ "pass@8": 0.24897275992552667,
636
+ "pass@16": 0.2917036036507781,
637
+ "pass@32": 0.32881890632268107,
638
+ "pass@64": 0.3607643461394065,
639
+ "pass@128": 0.38738738738738737
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]