ZachW commited on
Commit
f76a04b
·
verified ·
1 Parent(s): 306e6b7

Upload extrapolation artifact: 050302 pretrain checkpoint-18586 summary JSON

Browse files
050302/evals/pretrain_050302_ckpt18586/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "pretrain_050302_ckpt18586",
4
+ "id_acc": 0.6591371527777777,
5
+ "ood_acc": 0.1743203125,
6
+ "total_acc": 0.4039703947368421,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 202.56687413194445,
11
+ "ood_avg_resp_len": 301.8644203125,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 326673,
19
+ "answer_accuracy": 0.40343547462851725,
20
+ "avg_response_len": 243.4344248932975,
21
+ "resp_tokens_sum": 197115670,
22
+ "pass_at_k": {
23
+ "pass@1": 0.40343547462851725,
24
+ "pass@2": 0.46300600835572403,
25
+ "pass@4": 0.5211690059747147,
26
+ "pass@8": 0.5776619983204903,
27
+ "pass@16": 0.6303095820829564,
28
+ "pass@32": 0.6763947073834303,
29
+ "pass@64": 0.7152368285303596,
30
+ "pass@128": 0.7492886500158078
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.5485342920353983,
35
+ "pass@2": 0.6212945381274241,
36
+ "pass@4": 0.6798927465372133,
37
+ "pass@8": 0.7329713189633855,
38
+ "pass@16": 0.7809185330850646,
39
+ "pass@32": 0.8214210274584312,
40
+ "pass@64": 0.8545478788781176,
41
+ "pass@128": 0.8820058997050148
42
+ },
43
+ "2": {
44
+ "pass@1": 0.9669976635514018,
45
+ "pass@2": 0.9762200431721738,
46
+ "pass@4": 0.9828518164201436,
47
+ "pass@8": 0.988660768625104,
48
+ "pass@16": 0.9928562993950985,
49
+ "pass@32": 0.9949676562841662,
50
+ "pass@64": 0.9961110638984689,
51
+ "pass@128": 0.9968847352024922
52
+ },
53
+ "3": {
54
+ "pass@1": 0.9523604740061162,
55
+ "pass@2": 0.965793481663416,
56
+ "pass@4": 0.9743357550489675,
57
+ "pass@8": 0.9804021050148144,
58
+ "pass@16": 0.9847239199729213,
59
+ "pass@32": 0.9876441175361615,
60
+ "pass@64": 0.9896933766236177,
61
+ "pass@128": 0.9908256880733946
62
+ },
63
+ "4": {
64
+ "pass@1": 0.7410400390625,
65
+ "pass@2": 0.7776855468750001,
66
+ "pass@4": 0.804752966816648,
67
+ "pass@8": 0.8265181231781614,
68
+ "pass@16": 0.8441561704150973,
69
+ "pass@32": 0.8584107299081515,
70
+ "pass@64": 0.8725424263973889,
71
+ "pass@128": 0.890625
72
+ },
73
+ "5": {
74
+ "pass@1": 0.5860615079365079,
75
+ "pass@2": 0.6280289182602176,
76
+ "pass@4": 0.6568151829235631,
77
+ "pass@8": 0.6784618285484385,
78
+ "pass@16": 0.6985429050145969,
79
+ "pass@32": 0.7172269713114492,
80
+ "pass@64": 0.7336378808087067,
81
+ "pass@128": 0.7523809523809524
82
+ },
83
+ "6": {
84
+ "pass@1": 0.6110357410179641,
85
+ "pass@2": 0.6640256642227358,
86
+ "pass@4": 0.7050190184872099,
87
+ "pass@8": 0.7401048358206398,
88
+ "pass@16": 0.7712992571383563,
89
+ "pass@32": 0.7976646629926885,
90
+ "pass@64": 0.8199997055863216,
91
+ "pass@128": 0.8383233532934131
92
+ },
93
+ "7": {
94
+ "pass@1": 0.5465051775147929,
95
+ "pass@2": 0.597871919116619,
96
+ "pass@4": 0.6383466158815945,
97
+ "pass@8": 0.6704945279926731,
98
+ "pass@16": 0.6982883012525174,
99
+ "pass@32": 0.7252874533852414,
100
+ "pass@64": 0.7523146294968283,
101
+ "pass@128": 0.7810650887573964
102
+ },
103
+ "8": {
104
+ "pass@1": 0.5412159455128205,
105
+ "pass@2": 0.6090149751413282,
106
+ "pass@4": 0.6620202931364347,
107
+ "pass@8": 0.7088100090850898,
108
+ "pass@16": 0.7524414216865002,
109
+ "pass@32": 0.7903939600021158,
110
+ "pass@64": 0.8223663408035892,
111
+ "pass@128": 0.8557692307692307
112
+ },
113
+ "9": {
114
+ "pass@1": 0.5105413732394366,
115
+ "pass@2": 0.5978214761006982,
116
+ "pass@4": 0.6684741905501246,
117
+ "pass@8": 0.7256541935888985,
118
+ "pass@16": 0.7724577522280122,
119
+ "pass@32": 0.8116780331865703,
120
+ "pass@64": 0.8476223526429457,
121
+ "pass@128": 0.8845070422535212
122
+ },
123
+ "11": {
124
+ "pass@1": 0.41977248583569404,
125
+ "pass@2": 0.5152966836563977,
126
+ "pass@4": 0.5988550168835131,
127
+ "pass@8": 0.6740992829329473,
128
+ "pass@16": 0.7422318681552861,
129
+ "pass@32": 0.8019395682288849,
130
+ "pass@64": 0.8536206281446311,
131
+ "pass@128": 0.8980169971671388
132
+ },
133
+ "12": {
134
+ "pass@1": 0.3938912429378531,
135
+ "pass@2": 0.5104100632812844,
136
+ "pass@4": 0.6080495266481519,
137
+ "pass@8": 0.68796901487411,
138
+ "pass@16": 0.7544555654168367,
139
+ "pass@32": 0.8096660100272961,
140
+ "pass@64": 0.8520104842456188,
141
+ "pass@128": 0.884180790960452
142
+ },
143
+ "13": {
144
+ "pass@1": 0.17650372257053293,
145
+ "pass@2": 0.26551083911337076,
146
+ "pass@4": 0.3665973341302558,
147
+ "pass@8": 0.4710679392988577,
148
+ "pass@16": 0.5713484839319661,
149
+ "pass@32": 0.6590817812645573,
150
+ "pass@64": 0.7304700839844447,
151
+ "pass@128": 0.7899686520376176
152
+ },
153
+ "14": {
154
+ "pass@1": 0.11207651869158879,
155
+ "pass@2": 0.17378371292957537,
156
+ "pass@4": 0.25215351060089447,
157
+ "pass@8": 0.3400416779501758,
158
+ "pass@16": 0.42831800765620487,
159
+ "pass@32": 0.5089598246736358,
160
+ "pass@64": 0.5781006993506586,
161
+ "pass@128": 0.6386292834890965
162
+ },
163
+ "15": {
164
+ "pass@1": 0.0994400289017341,
165
+ "pass@2": 0.15031248577670558,
166
+ "pass@4": 0.21217345971204465,
167
+ "pass@8": 0.2830047929574361,
168
+ "pass@16": 0.35940929952555856,
169
+ "pass@32": 0.4361782265948589,
170
+ "pass@64": 0.5084135452231018,
171
+ "pass@128": 0.5751445086705202
172
+ },
173
+ "16": {
174
+ "pass@1": 0.09947076612903226,
175
+ "pass@2": 0.15187325374650743,
176
+ "pass@4": 0.2179497756328846,
177
+ "pass@8": 0.2926177158647718,
178
+ "pass@16": 0.3690935358079865,
179
+ "pass@32": 0.4399879447067403,
180
+ "pass@64": 0.49926141465739254,
181
+ "pass@128": 0.5451612903225806
182
+ },
183
+ "17": {
184
+ "pass@1": 0.10357207369942197,
185
+ "pass@2": 0.1580094215101725,
186
+ "pass@4": 0.22143721648233278,
187
+ "pass@8": 0.2883468654318178,
188
+ "pass@16": 0.35307511467549146,
189
+ "pass@32": 0.4110660972285916,
190
+ "pass@64": 0.45948745382879763,
191
+ "pass@128": 0.5
192
+ },
193
+ "18": {
194
+ "pass@1": 0.11919642857142858,
195
+ "pass@2": 0.17823186164229474,
196
+ "pass@4": 0.24767612941239495,
197
+ "pass@8": 0.32057904558995565,
198
+ "pass@16": 0.3888781464313517,
199
+ "pass@32": 0.44704524193215434,
200
+ "pass@64": 0.4943156741255045,
201
+ "pass@128": 0.5314285714285715
202
+ },
203
+ "19": {
204
+ "pass@1": 0.08955048798798798,
205
+ "pass@2": 0.14224620782199515,
206
+ "pass@4": 0.21036005099587773,
207
+ "pass@8": 0.2858482595544025,
208
+ "pass@16": 0.3575037208007843,
209
+ "pass@32": 0.4184082663584716,
210
+ "pass@64": 0.4677929962465217,
211
+ "pass@128": 0.5075075075075075
212
+ },
213
+ "20": {
214
+ "pass@1": 0.09365615615615616,
215
+ "pass@2": 0.14956861388948,
216
+ "pass@4": 0.22208081000010135,
217
+ "pass@8": 0.301411696925859,
218
+ "pass@16": 0.37289719680717975,
219
+ "pass@32": 0.4278229117854127,
220
+ "pass@64": 0.4672031815887534,
221
+ "pass@128": 0.5015015015015015
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 330878,
228
+ "answer_accuracy": 0.4029593725643024,
229
+ "avg_response_len": 251.9685551441933,
230
+ "resp_tokens_sum": 206896420,
231
+ "pass_at_k": {
232
+ "pass@1": 0.4029593725643024,
233
+ "pass@2": 0.4616005946937903,
234
+ "pass@4": 0.5196187779187411,
235
+ "pass@8": 0.5766667464711145,
236
+ "pass@16": 0.6305522390571069,
237
+ "pass@32": 0.6785554152113233,
238
+ "pass@64": 0.7189738431394698,
239
+ "pass@128": 0.751987529228371
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.5434240797546013,
244
+ "pass@2": 0.6273198607555187,
245
+ "pass@4": 0.6973762240609492,
246
+ "pass@8": 0.7554670303495753,
247
+ "pass@16": 0.8036698672416946,
248
+ "pass@32": 0.8436957147979897,
249
+ "pass@64": 0.877881304694098,
250
+ "pass@128": 0.9049079754601227
251
+ },
252
+ "2": {
253
+ "pass@1": 0.9736892097264438,
254
+ "pass@2": 0.9847328758107362,
255
+ "pass@4": 0.9901901966851409,
256
+ "pass@8": 0.9927113374191188,
257
+ "pass@16": 0.993648342971609,
258
+ "pass@32": 0.9939055659835022,
259
+ "pass@64": 0.9939209658267383,
260
+ "pass@128": 0.993920972644377
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9402225378787878,
264
+ "pass@2": 0.9562224111190645,
265
+ "pass@4": 0.966675997602572,
266
+ "pass@8": 0.9732372569438384,
267
+ "pass@16": 0.9772623665321553,
268
+ "pass@32": 0.979753273368313,
269
+ "pass@64": 0.9813605854303431,
270
+ "pass@128": 0.9818181818181818
271
+ },
272
+ "4": {
273
+ "pass@1": 0.7226100221893491,
274
+ "pass@2": 0.7654976005218281,
275
+ "pass@4": 0.7946490924026508,
276
+ "pass@8": 0.8150740090995962,
277
+ "pass@16": 0.8315740698722591,
278
+ "pass@32": 0.8478944811913116,
279
+ "pass@64": 0.8650704580299757,
280
+ "pass@128": 0.878698224852071
281
+ },
282
+ "5": {
283
+ "pass@1": 0.6107789855072464,
284
+ "pass@2": 0.6436579938377267,
285
+ "pass@4": 0.670637732783402,
286
+ "pass@8": 0.6953935801960935,
287
+ "pass@16": 0.7181272383034838,
288
+ "pass@32": 0.7399590031087759,
289
+ "pass@64": 0.7619561041686341,
290
+ "pass@128": 0.7855072463768116
291
+ },
292
+ "6": {
293
+ "pass@1": 0.5464272922636103,
294
+ "pass@2": 0.5969523441554045,
295
+ "pass@4": 0.6346913039881474,
296
+ "pass@8": 0.6666373773924721,
297
+ "pass@16": 0.6975353973976225,
298
+ "pass@32": 0.7284124145362817,
299
+ "pass@64": 0.756892771403926,
300
+ "pass@128": 0.7822349570200573
301
+ },
302
+ "7": {
303
+ "pass@1": 0.5512779985549133,
304
+ "pass@2": 0.5971500785125847,
305
+ "pass@4": 0.6349748599885993,
306
+ "pass@8": 0.6696253642996941,
307
+ "pass@16": 0.7024347855609688,
308
+ "pass@32": 0.7341433776297595,
309
+ "pass@64": 0.7661180630503324,
310
+ "pass@128": 0.8034682080924855
311
+ },
312
+ "8": {
313
+ "pass@1": 0.5112676056338028,
314
+ "pass@2": 0.5702083564378394,
315
+ "pass@4": 0.6210338083619829,
316
+ "pass@8": 0.6679787729679809,
317
+ "pass@16": 0.7144538059651695,
318
+ "pass@32": 0.7619468940389942,
319
+ "pass@64": 0.8071898332537814,
320
+ "pass@128": 0.847887323943662
321
+ },
322
+ "9": {
323
+ "pass@1": 0.4994620134730539,
324
+ "pass@2": 0.5715450251072656,
325
+ "pass@4": 0.6303960414379337,
326
+ "pass@8": 0.6812784051466028,
327
+ "pass@16": 0.7264440386053771,
328
+ "pass@32": 0.7696312332548112,
329
+ "pass@64": 0.8130165993358162,
330
+ "pass@128": 0.8562874251497006
331
+ },
332
+ "11": {
333
+ "pass@1": 0.4587019954819277,
334
+ "pass@2": 0.5552945047908173,
335
+ "pass@4": 0.6409966999606971,
336
+ "pass@8": 0.7148040088201414,
337
+ "pass@16": 0.7767393045658387,
338
+ "pass@32": 0.8297072308383238,
339
+ "pass@64": 0.8746833656520376,
340
+ "pass@128": 0.9126506024096386
341
+ },
342
+ "12": {
343
+ "pass@1": 0.3535952194357367,
344
+ "pass@2": 0.46705609927677505,
345
+ "pass@4": 0.5703037878494028,
346
+ "pass@8": 0.6629286050294428,
347
+ "pass@16": 0.7478458624123885,
348
+ "pass@32": 0.8187617469065239,
349
+ "pass@64": 0.8679221722274657,
350
+ "pass@128": 0.9028213166144201
351
+ },
352
+ "13": {
353
+ "pass@1": 0.20017069327731093,
354
+ "pass@2": 0.29245896193122883,
355
+ "pass@4": 0.39196500384930894,
356
+ "pass@8": 0.49107469341212867,
357
+ "pass@16": 0.5849278755630151,
358
+ "pass@32": 0.66909629091827,
359
+ "pass@64": 0.7394157298961205,
360
+ "pass@128": 0.7927170868347339
361
+ },
362
+ "14": {
363
+ "pass@1": 0.12148209064327485,
364
+ "pass@2": 0.18374897833494486,
365
+ "pass@4": 0.2576632594719518,
366
+ "pass@8": 0.33923709003618235,
367
+ "pass@16": 0.42476920910139276,
368
+ "pass@32": 0.5074564490761422,
369
+ "pass@64": 0.5803711048868923,
370
+ "pass@128": 0.6403508771929824
371
+ },
372
+ "15": {
373
+ "pass@1": 0.09886363636363636,
374
+ "pass@2": 0.15513675137198757,
375
+ "pass@4": 0.22539836440899438,
376
+ "pass@8": 0.3055976387358603,
377
+ "pass@16": 0.38618518854570155,
378
+ "pass@32": 0.45698552030349504,
379
+ "pass@64": 0.5147245657272281,
380
+ "pass@128": 0.5575757575757576
381
+ },
382
+ "16": {
383
+ "pass@1": 0.10803952991452992,
384
+ "pass@2": 0.15944531372680978,
385
+ "pass@4": 0.22162470449740793,
386
+ "pass@8": 0.29181218523663216,
387
+ "pass@16": 0.36106886230415675,
388
+ "pass@32": 0.42176417751644407,
389
+ "pass@64": 0.47626160158795905,
390
+ "pass@128": 0.5299145299145299
391
+ },
392
+ "17": {
393
+ "pass@1": 0.12783870341614906,
394
+ "pass@2": 0.19124290849513367,
395
+ "pass@4": 0.2656787292116435,
396
+ "pass@8": 0.3460024308333159,
397
+ "pass@16": 0.42595468112596735,
398
+ "pass@32": 0.4986195373338599,
399
+ "pass@64": 0.5599232484124532,
400
+ "pass@128": 0.6118012422360248
401
+ },
402
+ "18": {
403
+ "pass@1": 0.11353400735294118,
404
+ "pass@2": 0.17243262216303845,
405
+ "pass@4": 0.2442672787225127,
406
+ "pass@8": 0.3239806135278011,
407
+ "pass@16": 0.39993769990663836,
408
+ "pass@32": 0.4633629313271958,
409
+ "pass@64": 0.5111777845425836,
410
+ "pass@128": 0.5441176470588235
411
+ },
412
+ "19": {
413
+ "pass@1": 0.10014415922619048,
414
+ "pass@2": 0.1556139711051743,
415
+ "pass@4": 0.22348070581579088,
416
+ "pass@8": 0.29794332466542117,
417
+ "pass@16": 0.37017448624899146,
418
+ "pass@32": 0.43114841416760863,
419
+ "pass@64": 0.4765716994613993,
420
+ "pass@128": 0.5059523809523809
421
+ },
422
+ "20": {
423
+ "pass@1": 0.09110684880239521,
424
+ "pass@2": 0.14313720000942995,
425
+ "pass@4": 0.21076069402252862,
426
+ "pass@8": 0.28671310390061244,
427
+ "pass@16": 0.3586706072592117,
428
+ "pass@32": 0.4163128162045844,
429
+ "pass@64": 0.4539123901453239,
430
+ "pass@128": 0.47005988023952094
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 324905,
437
+ "answer_accuracy": 0.4055472619428024,
438
+ "avg_response_len": 269.2765005891516,
439
+ "resp_tokens_sum": 215731407,
440
+ "pass_at_k": {
441
+ "pass@1": 0.4055472619428024,
442
+ "pass@2": 0.4655933644528339,
443
+ "pass@4": 0.5247422408095355,
444
+ "pass@8": 0.5828397968172885,
445
+ "pass@16": 0.6377283837264522,
446
+ "pass@32": 0.6864299272395259,
447
+ "pass@64": 0.726849277721629,
448
+ "pass@128": 0.7598657932577089
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.4935401119402985,
453
+ "pass@2": 0.5670470237395698,
454
+ "pass@4": 0.6367358320881525,
455
+ "pass@8": 0.7042430815093631,
456
+ "pass@16": 0.7680596090454958,
457
+ "pass@32": 0.8246740921435434,
458
+ "pass@64": 0.8697867463781164,
459
+ "pass@128": 0.9044776119402985
460
+ },
461
+ "2": {
462
+ "pass@1": 0.9596875,
463
+ "pass@2": 0.9764113470191226,
464
+ "pass@4": 0.9854286804328029,
465
+ "pass@8": 0.991061509280679,
466
+ "pass@16": 0.9942260504228976,
467
+ "pass@32": 0.9956652788647895,
468
+ "pass@64": 0.9971427773528576,
469
+ "pass@128": 1.0
470
+ },
471
+ "3": {
472
+ "pass@1": 0.9397093658892128,
473
+ "pass@2": 0.9562255371777508,
474
+ "pass@4": 0.9668405375166294,
475
+ "pass@8": 0.9747146666399417,
476
+ "pass@16": 0.9801107267765427,
477
+ "pass@32": 0.9832217992096687,
478
+ "pass@64": 0.984688404960452,
479
+ "pass@128": 0.9854227405247813
480
+ },
481
+ "4": {
482
+ "pass@1": 0.7007264254385965,
483
+ "pass@2": 0.7445909310678271,
484
+ "pass@4": 0.7808669256255251,
485
+ "pass@8": 0.8129850113269721,
486
+ "pass@16": 0.842129991729984,
487
+ "pass@32": 0.8674656215356255,
488
+ "pass@64": 0.8884742826156206,
489
+ "pass@128": 0.9064327485380117
490
+ },
491
+ "5": {
492
+ "pass@1": 0.5817784926470588,
493
+ "pass@2": 0.6204282943492355,
494
+ "pass@4": 0.6536405768212797,
495
+ "pass@8": 0.68463428746883,
496
+ "pass@16": 0.7157901961439006,
497
+ "pass@32": 0.7474912605697788,
498
+ "pass@64": 0.7777573616250464,
499
+ "pass@128": 0.8029411764705883
500
+ },
501
+ "6": {
502
+ "pass@1": 0.5934296135646687,
503
+ "pass@2": 0.64594756762463,
504
+ "pass@4": 0.6914165587345744,
505
+ "pass@8": 0.7364669504842055,
506
+ "pass@16": 0.778883156850051,
507
+ "pass@32": 0.8167598694063396,
508
+ "pass@64": 0.8509370624044789,
509
+ "pass@128": 0.8801261829652997
510
+ },
511
+ "7": {
512
+ "pass@1": 0.5463558148734177,
513
+ "pass@2": 0.6027772413535332,
514
+ "pass@4": 0.6477394363481457,
515
+ "pass@8": 0.6858369916354995,
516
+ "pass@16": 0.7205188747595422,
517
+ "pass@32": 0.7560440209344339,
518
+ "pass@64": 0.7912034540169977,
519
+ "pass@128": 0.8259493670886076
520
+ },
521
+ "8": {
522
+ "pass@1": 0.5558370870870871,
523
+ "pass@2": 0.6316111879596129,
524
+ "pass@4": 0.6897773594742097,
525
+ "pass@8": 0.736390876197389,
526
+ "pass@16": 0.7772959628816623,
527
+ "pass@32": 0.8148386053479606,
528
+ "pass@64": 0.8483111557392278,
529
+ "pass@128": 0.8738738738738738
530
+ },
531
+ "9": {
532
+ "pass@1": 0.5287630627009646,
533
+ "pass@2": 0.6127898163151629,
534
+ "pass@4": 0.680057331961318,
535
+ "pass@8": 0.7337678523669866,
536
+ "pass@16": 0.7759801527561564,
537
+ "pass@32": 0.8104190136847873,
538
+ "pass@64": 0.841157580846551,
539
+ "pass@128": 0.8713826366559485
540
+ },
541
+ "11": {
542
+ "pass@1": 0.4311011904761905,
543
+ "pass@2": 0.5327611392325959,
544
+ "pass@4": 0.6226473205730233,
545
+ "pass@8": 0.699414827225559,
546
+ "pass@16": 0.7632510144163813,
547
+ "pass@32": 0.8149524603297097,
548
+ "pass@64": 0.8541162619127182,
549
+ "pass@128": 0.8825396825396825
550
+ },
551
+ "12": {
552
+ "pass@1": 0.37994552752293576,
553
+ "pass@2": 0.49269373510077263,
554
+ "pass@4": 0.5890112603470439,
555
+ "pass@8": 0.673374303865433,
556
+ "pass@16": 0.7488352151511932,
557
+ "pass@32": 0.8150540013464985,
558
+ "pass@64": 0.8687804600398654,
559
+ "pass@128": 0.9051987767584098
560
+ },
561
+ "13": {
562
+ "pass@1": 0.18453414351851852,
563
+ "pass@2": 0.26992616591328855,
564
+ "pass@4": 0.36343596575891,
565
+ "pass@8": 0.45878259248561787,
566
+ "pass@16": 0.5525191150433114,
567
+ "pass@32": 0.6384739274316215,
568
+ "pass@64": 0.709316108372,
569
+ "pass@128": 0.7685185185185185
570
+ },
571
+ "14": {
572
+ "pass@1": 0.12685459940652818,
573
+ "pass@2": 0.18879712434869975,
574
+ "pass@4": 0.2624856972626196,
575
+ "pass@8": 0.3443412391690488,
576
+ "pass@16": 0.4263202019821751,
577
+ "pass@32": 0.5005275143900397,
578
+ "pass@64": 0.5643824971967146,
579
+ "pass@128": 0.6201780415430267
580
+ },
581
+ "15": {
582
+ "pass@1": 0.10570987654320987,
583
+ "pass@2": 0.16320697543015447,
584
+ "pass@4": 0.23749303125303775,
585
+ "pass@8": 0.32504223382366393,
586
+ "pass@16": 0.41559522972860385,
587
+ "pass@32": 0.49623847142737515,
588
+ "pass@64": 0.5606971462894773,
589
+ "pass@128": 0.6141975308641975
590
+ },
591
+ "16": {
592
+ "pass@1": 0.10893713126843659,
593
+ "pass@2": 0.1652998919935893,
594
+ "pass@4": 0.23209237285604775,
595
+ "pass@8": 0.3033054579667241,
596
+ "pass@16": 0.3727492867250306,
597
+ "pass@32": 0.43483766239548877,
598
+ "pass@64": 0.48846237984478985,
599
+ "pass@128": 0.5309734513274337
600
+ },
601
+ "17": {
602
+ "pass@1": 0.11794051204819277,
603
+ "pass@2": 0.17528430651740828,
604
+ "pass@4": 0.24250910644829024,
605
+ "pass@8": 0.31225596159268304,
606
+ "pass@16": 0.37914528287600097,
607
+ "pass@32": 0.44015855587538144,
608
+ "pass@64": 0.49245703153300757,
609
+ "pass@128": 0.536144578313253
610
+ },
611
+ "18": {
612
+ "pass@1": 0.08644153225806452,
613
+ "pass@2": 0.1351381921513843,
614
+ "pass@4": 0.19537179505787589,
615
+ "pass@8": 0.2640087960618504,
616
+ "pass@16": 0.3364805754908361,
617
+ "pass@32": 0.40511059898611057,
618
+ "pass@64": 0.4606336256185126,
619
+ "pass@128": 0.5
620
+ },
621
+ "19": {
622
+ "pass@1": 0.08657477341389729,
623
+ "pass@2": 0.13416194364488426,
624
+ "pass@4": 0.19288663416695273,
625
+ "pass@8": 0.25911399140930275,
626
+ "pass@16": 0.32694205872241794,
627
+ "pass@32": 0.3880784900568889,
628
+ "pass@64": 0.43832121607177427,
629
+ "pass@128": 0.48338368580060426
630
+ },
631
+ "20": {
632
+ "pass@1": 0.11606137387387387,
633
+ "pass@2": 0.17806019602279444,
634
+ "pass@4": 0.2542757329883313,
635
+ "pass@8": 0.33586454124686205,
636
+ "pass@16": 0.41006388289722623,
637
+ "pass@32": 0.4660912695451911,
638
+ "pass@64": 0.5023665080660694,
639
+ "pass@128": 0.5285285285285285
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]