ZachW commited on
Commit
a719983
·
verified ·
1 Parent(s): 6632fc0

Upload extrapolation artifact: 020305 OPD Ref-KL OP11-14 step200 summary JSON

Browse files
020305/evals/opd_ckpt18809_refkl_op11_14_s200_merged_hf/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "opd_ckpt18809_refkl_op11_14_s200_merged_hf",
4
+ "id_acc": 0.8010920138888888,
5
+ "ood_acc": 0.36564453125,
6
+ "total_acc": 0.5719091282894737,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 205.78523958333332,
11
+ "ood_avg_resp_len": 344.5203296875,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 460053,
19
+ "answer_accuracy": 0.5681574553430287,
20
+ "avg_response_len": 266.3477649284698,
21
+ "resp_tokens_sum": 215669243,
22
+ "pass_at_k": {
23
+ "pass@1": 0.5681574553430287,
24
+ "pass@2": 0.6169756858957353,
25
+ "pass@4": 0.6581813570529466,
26
+ "pass@8": 0.6935122948467095,
27
+ "pass@16": 0.7237400430515766,
28
+ "pass@32": 0.7501031577105949,
29
+ "pass@64": 0.7739264444569264,
30
+ "pass@128": 0.7956054378754347
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.7424640486725663,
35
+ "pass@2": 0.771093913316145,
36
+ "pass@4": 0.7885841147622034,
37
+ "pass@8": 0.8017946844801921,
38
+ "pass@16": 0.8130353070960848,
39
+ "pass@32": 0.8229444919183865,
40
+ "pass@64": 0.832212669613431,
41
+ "pass@128": 0.8407079646017699
42
+ },
43
+ "2": {
44
+ "pass@1": 0.9816734813084113,
45
+ "pass@2": 0.9876991500478329,
46
+ "pass@4": 0.9918240424386205,
47
+ "pass@8": 0.9948639305932367,
48
+ "pass@16": 0.9967587675729006,
49
+ "pass@32": 0.9980964222823148,
50
+ "pass@64": 0.9992252360339792,
51
+ "pass@128": 1.0
52
+ },
53
+ "3": {
54
+ "pass@1": 0.9375955657492355,
55
+ "pass@2": 0.9566485166991741,
56
+ "pass@4": 0.9687080178624461,
57
+ "pass@8": 0.9778343309167599,
58
+ "pass@16": 0.9855564988603678,
59
+ "pass@32": 0.9923726621122694,
60
+ "pass@64": 0.9972910996660891,
61
+ "pass@128": 1.0
62
+ },
63
+ "4": {
64
+ "pass@1": 0.932373046875,
65
+ "pass@2": 0.9477269931102363,
66
+ "pass@4": 0.9545166007569368,
67
+ "pass@8": 0.9575423541577935,
68
+ "pass@16": 0.9587791556559628,
69
+ "pass@32": 0.9592927175576857,
70
+ "pass@64": 0.9593745674301918,
71
+ "pass@128": 0.959375
72
+ },
73
+ "5": {
74
+ "pass@1": 0.7174603174603175,
75
+ "pass@2": 0.7450810836145483,
76
+ "pass@4": 0.7633263288517506,
77
+ "pass@8": 0.7766124482499086,
78
+ "pass@16": 0.7868052561888605,
79
+ "pass@32": 0.7956232833438782,
80
+ "pass@64": 0.8044412657876658,
81
+ "pass@128": 0.8126984126984127
82
+ },
83
+ "6": {
84
+ "pass@1": 0.8066757110778443,
85
+ "pass@2": 0.8357662136357202,
86
+ "pass@4": 0.8554475958095056,
87
+ "pass@8": 0.8700010853025604,
88
+ "pass@16": 0.8785844044766294,
89
+ "pass@32": 0.8823649494633435,
90
+ "pass@64": 0.8843617970414702,
91
+ "pass@128": 0.8862275449101796
92
+ },
93
+ "7": {
94
+ "pass@1": 0.7186575443786982,
95
+ "pass@2": 0.7438167573265619,
96
+ "pass@4": 0.7602309963658388,
97
+ "pass@8": 0.7710314253324705,
98
+ "pass@16": 0.7775229423282789,
99
+ "pass@32": 0.7829284928793798,
100
+ "pass@64": 0.7897352859886067,
101
+ "pass@128": 0.7988165680473372
102
+ },
103
+ "8": {
104
+ "pass@1": 0.6887269631410257,
105
+ "pass@2": 0.7218151404451849,
106
+ "pass@4": 0.7408405803240937,
107
+ "pass@8": 0.7535949017243314,
108
+ "pass@16": 0.7632645642295485,
109
+ "pass@32": 0.7717595427726075,
110
+ "pass@64": 0.781937679584112,
111
+ "pass@128": 0.7948717948717948
112
+ },
113
+ "9": {
114
+ "pass@1": 0.7055677816901409,
115
+ "pass@2": 0.7412048075856714,
116
+ "pass@4": 0.7638972454147457,
117
+ "pass@8": 0.781629254361862,
118
+ "pass@16": 0.7987463901892804,
119
+ "pass@32": 0.8163050405604395,
120
+ "pass@64": 0.8325055410683851,
121
+ "pass@128": 0.847887323943662
122
+ },
123
+ "11": {
124
+ "pass@1": 0.6466890934844193,
125
+ "pass@2": 0.6912474069282414,
126
+ "pass@4": 0.7249314990902338,
127
+ "pass@8": 0.7530619746343751,
128
+ "pass@16": 0.7767906766703255,
129
+ "pass@32": 0.7957860838634074,
130
+ "pass@64": 0.8099464722387654,
131
+ "pass@128": 0.8215297450424929
132
+ },
133
+ "12": {
134
+ "pass@1": 0.6203213276836158,
135
+ "pass@2": 0.6652862115752477,
136
+ "pass@4": 0.6947977472095646,
137
+ "pass@8": 0.7183483304960792,
138
+ "pass@16": 0.7403059790102484,
139
+ "pass@32": 0.7621004117887317,
140
+ "pass@64": 0.7823689549630459,
141
+ "pass@128": 0.7994350282485876
142
+ },
143
+ "13": {
144
+ "pass@1": 0.5518221003134797,
145
+ "pass@2": 0.6244720058993405,
146
+ "pass@4": 0.6838731447753984,
147
+ "pass@8": 0.7350646918810027,
148
+ "pass@16": 0.7782374932819416,
149
+ "pass@32": 0.8124714323376914,
150
+ "pass@64": 0.8401573879537731,
151
+ "pass@128": 0.8652037617554859
152
+ },
153
+ "14": {
154
+ "pass@1": 0.4788259345794392,
155
+ "pass@2": 0.5704617858807368,
156
+ "pass@4": 0.6435874470130484,
157
+ "pass@8": 0.7019642515080833,
158
+ "pass@16": 0.7500828597068995,
159
+ "pass@32": 0.7915480266112919,
160
+ "pass@64": 0.8291789821042072,
161
+ "pass@128": 0.8566978193146417
162
+ },
163
+ "15": {
164
+ "pass@1": 0.395479588150289,
165
+ "pass@2": 0.49345088411997684,
166
+ "pass@4": 0.5803387016109977,
167
+ "pass@8": 0.6546763774712369,
168
+ "pass@16": 0.7146283327663748,
169
+ "pass@32": 0.7633529080597558,
170
+ "pass@64": 0.8055683940288247,
171
+ "pass@128": 0.8410404624277457
172
+ },
173
+ "16": {
174
+ "pass@1": 0.30463709677419354,
175
+ "pass@2": 0.39736791973583935,
176
+ "pass@4": 0.4838570234164276,
177
+ "pass@8": 0.560171896794669,
178
+ "pass@16": 0.6259420568008504,
179
+ "pass@32": 0.6826416370167399,
180
+ "pass@64": 0.7330660197942794,
181
+ "pass@128": 0.7838709677419354
182
+ },
183
+ "17": {
184
+ "pass@1": 0.1865065028901734,
185
+ "pass@2": 0.2576165741204313,
186
+ "pass@4": 0.33118188532069326,
187
+ "pass@8": 0.40501942940750135,
188
+ "pass@16": 0.47777948573225826,
189
+ "pass@32": 0.5432131121358732,
190
+ "pass@64": 0.5990578766366198,
191
+ "pass@128": 0.6473988439306358
192
+ },
193
+ "18": {
194
+ "pass@1": 0.16359375,
195
+ "pass@2": 0.23147778402699662,
196
+ "pass@4": 0.3019324468370022,
197
+ "pass@8": 0.3664561842792813,
198
+ "pass@16": 0.4239151851388876,
199
+ "pass@32": 0.47703502162589173,
200
+ "pass@64": 0.5304555482144475,
201
+ "pass@128": 0.5857142857142857
202
+ },
203
+ "19": {
204
+ "pass@1": 0.12901182432432431,
205
+ "pass@2": 0.18813658638953917,
206
+ "pass@4": 0.25000342946996496,
207
+ "pass@8": 0.30734962570947605,
208
+ "pass@16": 0.36104940546688785,
209
+ "pass@32": 0.4146789996350884,
210
+ "pass@64": 0.4671837563626336,
211
+ "pass@128": 0.5165165165165165
212
+ },
213
+ "20": {
214
+ "pass@1": 0.13534628378378377,
215
+ "pass@2": 0.19904537904045783,
216
+ "pass@4": 0.2683787491090641,
217
+ "pass@8": 0.33199490474801735,
218
+ "pass@16": 0.38259119119235185,
219
+ "pass@32": 0.4236190233585821,
220
+ "pass@64": 0.45986092700105347,
221
+ "pass@128": 0.4894894894894895
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 470777,
228
+ "answer_accuracy": 0.5733352007014809,
229
+ "avg_response_len": 275.2089913776305,
230
+ "resp_tokens_sum": 225979607,
231
+ "pass_at_k": {
232
+ "pass@1": 0.5733352007014809,
233
+ "pass@2": 0.6204956663761795,
234
+ "pass@4": 0.6613293853954154,
235
+ "pass@8": 0.6969568807478189,
236
+ "pass@16": 0.7276117041763569,
237
+ "pass@32": 0.7534820513784004,
238
+ "pass@64": 0.7756554075274653,
239
+ "pass@128": 0.7962587685113016
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.6941382285276073,
244
+ "pass@2": 0.7169124529008262,
245
+ "pass@4": 0.7325675896149484,
246
+ "pass@8": 0.7465744310859458,
247
+ "pass@16": 0.7597846970927132,
248
+ "pass@32": 0.7718304058990098,
249
+ "pass@64": 0.7825067415218101,
250
+ "pass@128": 0.7914110429447853
251
+ },
252
+ "2": {
253
+ "pass@1": 0.9884593465045592,
254
+ "pass@2": 0.9938308492688415,
255
+ "pass@4": 0.9963562869610904,
256
+ "pass@8": 0.9979561058343865,
257
+ "pass@16": 0.9989800473532323,
258
+ "pass@32": 0.9997180881458465,
259
+ "pass@64": 0.999990590078186,
260
+ "pass@128": 1.0
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9420217803030303,
264
+ "pass@2": 0.9601116976855169,
265
+ "pass@4": 0.9727987419186237,
266
+ "pass@8": 0.981870428852454,
267
+ "pass@16": 0.9871837322982397,
268
+ "pass@32": 0.9904988444828229,
269
+ "pass@64": 0.9928072163491805,
270
+ "pass@128": 0.9939393939393939
271
+ },
272
+ "4": {
273
+ "pass@1": 0.9240708210059172,
274
+ "pass@2": 0.9393782323067603,
275
+ "pass@4": 0.9470039566984598,
276
+ "pass@8": 0.9520202606379223,
277
+ "pass@16": 0.9563486248166372,
278
+ "pass@32": 0.9602347588314415,
279
+ "pass@64": 0.9643112265926712,
280
+ "pass@128": 0.9704142011834319
281
+ },
282
+ "5": {
283
+ "pass@1": 0.7742980072463768,
284
+ "pass@2": 0.7911791766518318,
285
+ "pass@4": 0.8002917034827165,
286
+ "pass@8": 0.8076305584698334,
287
+ "pass@16": 0.8154755022818414,
288
+ "pass@32": 0.8234288212540828,
289
+ "pass@64": 0.8300067880501992,
290
+ "pass@128": 0.8347826086956521
291
+ },
292
+ "6": {
293
+ "pass@1": 0.7923755372492837,
294
+ "pass@2": 0.8100037649752954,
295
+ "pass@4": 0.8205033933795525,
296
+ "pass@8": 0.8287238327511557,
297
+ "pass@16": 0.8352207608631064,
298
+ "pass@32": 0.8401888180209954,
299
+ "pass@64": 0.8441842989037608,
300
+ "pass@128": 0.8481375358166189
301
+ },
302
+ "7": {
303
+ "pass@1": 0.7284140173410405,
304
+ "pass@2": 0.7450527826453051,
305
+ "pass@4": 0.756333304344905,
306
+ "pass@8": 0.7670722174014459,
307
+ "pass@16": 0.7776457966176703,
308
+ "pass@32": 0.7862487711301089,
309
+ "pass@64": 0.7936717180406007,
310
+ "pass@128": 0.8034682080924855
311
+ },
312
+ "8": {
313
+ "pass@1": 0.6920774647887324,
314
+ "pass@2": 0.7218004879671733,
315
+ "pass@4": 0.7422890933527669,
316
+ "pass@8": 0.7611340680222076,
317
+ "pass@16": 0.7811552948334626,
318
+ "pass@32": 0.8003676932497851,
319
+ "pass@64": 0.8157911805780659,
320
+ "pass@128": 0.8309859154929577
321
+ },
322
+ "9": {
323
+ "pass@1": 0.6940727919161677,
324
+ "pass@2": 0.7248043283511716,
325
+ "pass@4": 0.7457611413842727,
326
+ "pass@8": 0.7624813315258454,
327
+ "pass@16": 0.7761188208246117,
328
+ "pass@32": 0.7890762281069109,
329
+ "pass@64": 0.802726380242553,
330
+ "pass@128": 0.8143712574850299
331
+ },
332
+ "11": {
333
+ "pass@1": 0.7183028990963856,
334
+ "pass@2": 0.7547463475951047,
335
+ "pass@4": 0.778843663461495,
336
+ "pass@8": 0.8001833180576524,
337
+ "pass@16": 0.8210950896880099,
338
+ "pass@32": 0.8388310686977585,
339
+ "pass@64": 0.8521677729294844,
340
+ "pass@128": 0.8644578313253012
341
+ },
342
+ "12": {
343
+ "pass@1": 0.6392045454545454,
344
+ "pass@2": 0.6809673746698593,
345
+ "pass@4": 0.7114183330923758,
346
+ "pass@8": 0.7354809272101315,
347
+ "pass@16": 0.7552831404797815,
348
+ "pass@32": 0.7736660117584646,
349
+ "pass@64": 0.7943748812610173,
350
+ "pass@128": 0.8181818181818182
351
+ },
352
+ "13": {
353
+ "pass@1": 0.515515581232493,
354
+ "pass@2": 0.5916474365336687,
355
+ "pass@4": 0.6541928824023043,
356
+ "pass@8": 0.7090663341112685,
357
+ "pass@16": 0.7575139403928042,
358
+ "pass@32": 0.7969721460716788,
359
+ "pass@64": 0.827320248252286,
360
+ "pass@128": 0.8515406162464986
361
+ },
362
+ "14": {
363
+ "pass@1": 0.5028554459064327,
364
+ "pass@2": 0.5943345794769074,
365
+ "pass@4": 0.6694795044807993,
366
+ "pass@8": 0.7286993424163887,
367
+ "pass@16": 0.7738064705013502,
368
+ "pass@32": 0.8074243425728098,
369
+ "pass@64": 0.8344422052000626,
370
+ "pass@128": 0.8567251461988304
371
+ },
372
+ "15": {
373
+ "pass@1": 0.3809659090909091,
374
+ "pass@2": 0.48800070090670433,
375
+ "pass@4": 0.5794779112838165,
376
+ "pass@8": 0.655881428491387,
377
+ "pass@16": 0.7197720112082253,
378
+ "pass@32": 0.772857260531611,
379
+ "pass@64": 0.8142473639388284,
380
+ "pass@128": 0.8424242424242424
381
+ },
382
+ "16": {
383
+ "pass@1": 0.2588586182336182,
384
+ "pass@2": 0.3582789330820826,
385
+ "pass@4": 0.4504977286493035,
386
+ "pass@8": 0.527422399996188,
387
+ "pass@16": 0.5925210670613872,
388
+ "pass@32": 0.6497134851869707,
389
+ "pass@64": 0.7010039904486145,
390
+ "pass@128": 0.7464387464387464
391
+ },
392
+ "17": {
393
+ "pass@1": 0.2038286102484472,
394
+ "pass@2": 0.28597868880520366,
395
+ "pass@4": 0.3738453955871977,
396
+ "pass@8": 0.45652316123650455,
397
+ "pass@16": 0.5265870333919532,
398
+ "pass@32": 0.5819561915712852,
399
+ "pass@64": 0.6257082136677266,
400
+ "pass@128": 0.6645962732919255
401
+ },
402
+ "18": {
403
+ "pass@1": 0.19016544117647058,
404
+ "pass@2": 0.263053279874942,
405
+ "pass@4": 0.3404500567943713,
406
+ "pass@8": 0.41273929223917083,
407
+ "pass@16": 0.4748584080239207,
408
+ "pass@32": 0.5284791511884555,
409
+ "pass@64": 0.5784465188199855,
410
+ "pass@128": 0.638235294117647
411
+ },
412
+ "19": {
413
+ "pass@1": 0.12053571428571429,
414
+ "pass@2": 0.17115365462129736,
415
+ "pass@4": 0.22653255536138342,
416
+ "pass@8": 0.28174911979378237,
417
+ "pass@16": 0.33318653864249986,
418
+ "pass@32": 0.37810474381002396,
419
+ "pass@64": 0.41829601349017753,
420
+ "pass@128": 0.45535714285714285
421
+ },
422
+ "20": {
423
+ "pass@1": 0.13255520209580837,
424
+ "pass@2": 0.19633837639681267,
425
+ "pass@4": 0.26445615265531924,
426
+ "pass@8": 0.32675204052635204,
427
+ "pass@16": 0.3794958485367521,
428
+ "pass@32": 0.42349892224034347,
429
+ "pass@64": 0.46216467566216196,
430
+ "pass@128": 0.5
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 460053,
437
+ "answer_accuracy": 0.5742393453427065,
438
+ "avg_response_len": 295.07729868988656,
439
+ "resp_tokens_sum": 236401768,
440
+ "pass_at_k": {
441
+ "pass@1": 0.5742393453427065,
442
+ "pass@2": 0.6239584289961095,
443
+ "pass@4": 0.6666958063178703,
444
+ "pass@8": 0.7028775947967277,
445
+ "pass@16": 0.7331856661779317,
446
+ "pass@32": 0.7589928649714469,
447
+ "pass@64": 0.7819899066152834,
448
+ "pass@128": 0.8030036747084198
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.6966884328358209,
453
+ "pass@2": 0.7254671524268425,
454
+ "pass@4": 0.7452860190050866,
455
+ "pass@8": 0.7630148686937185,
456
+ "pass@16": 0.7822015409812071,
457
+ "pass@32": 0.801441945154566,
458
+ "pass@64": 0.8197128932028365,
459
+ "pass@128": 0.835820895522388
460
+ },
461
+ "2": {
462
+ "pass@1": 0.9757366071428571,
463
+ "pass@2": 0.9844678008998877,
464
+ "pass@4": 0.9889769950184799,
465
+ "pass@8": 0.991142491681806,
466
+ "pass@16": 0.9920860456550812,
467
+ "pass@32": 0.9928567333726679,
468
+ "pass@64": 0.9942857142850705,
469
+ "pass@128": 0.9971428571428571
470
+ },
471
+ "3": {
472
+ "pass@1": 0.9559948979591837,
473
+ "pass@2": 0.9725055095153923,
474
+ "pass@4": 0.9808652912555023,
475
+ "pass@8": 0.9864905641207768,
476
+ "pass@16": 0.9911096990647493,
477
+ "pass@32": 0.9939737573126675,
478
+ "pass@64": 0.9955404450370899,
479
+ "pass@128": 0.9970845481049563
480
+ },
481
+ "4": {
482
+ "pass@1": 0.9099506578947368,
483
+ "pass@2": 0.9203432218998941,
484
+ "pass@4": 0.9284361009150172,
485
+ "pass@8": 0.935410510962043,
486
+ "pass@16": 0.939848383703258,
487
+ "pass@32": 0.9413484384818201,
488
+ "pass@64": 0.9415196517783105,
489
+ "pass@128": 0.9415204678362573
490
+ },
491
+ "5": {
492
+ "pass@1": 0.75546875,
493
+ "pass@2": 0.780877648795739,
494
+ "pass@4": 0.7965669936478528,
495
+ "pass@8": 0.8067648972270169,
496
+ "pass@16": 0.8132321266409782,
497
+ "pass@32": 0.8192865122573731,
498
+ "pass@64": 0.8267881425482179,
499
+ "pass@128": 0.8352941176470589
500
+ },
501
+ "6": {
502
+ "pass@1": 0.7910833990536278,
503
+ "pass@2": 0.8183573859261287,
504
+ "pass@4": 0.8383415817108033,
505
+ "pass@8": 0.8527606250641574,
506
+ "pass@16": 0.8610393527942269,
507
+ "pass@32": 0.8654213076464958,
508
+ "pass@64": 0.8687027213585333,
509
+ "pass@128": 0.8706624605678234
510
+ },
511
+ "7": {
512
+ "pass@1": 0.686387460443038,
513
+ "pass@2": 0.7061451117562048,
514
+ "pass@4": 0.7210873436113207,
515
+ "pass@8": 0.7322503029787266,
516
+ "pass@16": 0.7410873795801756,
517
+ "pass@32": 0.7478464786416772,
518
+ "pass@64": 0.7531605356373143,
519
+ "pass@128": 0.759493670886076
520
+ },
521
+ "8": {
522
+ "pass@1": 0.706128003003003,
523
+ "pass@2": 0.7367765156889171,
524
+ "pass@4": 0.7584327336335209,
525
+ "pass@8": 0.7760591544495503,
526
+ "pass@16": 0.7921301299301136,
527
+ "pass@32": 0.8063975878774187,
528
+ "pass@64": 0.8183995687804435,
529
+ "pass@128": 0.8288288288288288
530
+ },
531
+ "9": {
532
+ "pass@1": 0.6841840836012861,
533
+ "pass@2": 0.7126937647163075,
534
+ "pass@4": 0.7311196296403464,
535
+ "pass@8": 0.7456370648483638,
536
+ "pass@16": 0.758084258899627,
537
+ "pass@32": 0.7686180196201899,
538
+ "pass@64": 0.7770365116596999,
539
+ "pass@128": 0.7845659163987139
540
+ },
541
+ "11": {
542
+ "pass@1": 0.6542410714285715,
543
+ "pass@2": 0.7034226190476196,
544
+ "pass@4": 0.7421287035549127,
545
+ "pass@8": 0.7713736357086015,
546
+ "pass@16": 0.7933978654743874,
547
+ "pass@32": 0.812370724344478,
548
+ "pass@64": 0.8284308675159244,
549
+ "pass@128": 0.8380952380952381
550
+ },
551
+ "12": {
552
+ "pass@1": 0.660980504587156,
553
+ "pass@2": 0.7064547514989525,
554
+ "pass@4": 0.7416728367669632,
555
+ "pass@8": 0.771262457210244,
556
+ "pass@16": 0.7970504799514619,
557
+ "pass@32": 0.8194293208619524,
558
+ "pass@64": 0.8397135967490932,
559
+ "pass@128": 0.8623853211009175
560
+ },
561
+ "13": {
562
+ "pass@1": 0.5504436728395061,
563
+ "pass@2": 0.6252384684553316,
564
+ "pass@4": 0.6787703524906605,
565
+ "pass@8": 0.7194007733197777,
566
+ "pass@16": 0.7551278725908533,
567
+ "pass@32": 0.7889391054259809,
568
+ "pass@64": 0.8228371217447265,
569
+ "pass@128": 0.8549382716049383
570
+ },
571
+ "14": {
572
+ "pass@1": 0.4782084569732938,
573
+ "pass@2": 0.5734753586532397,
574
+ "pass@4": 0.6481680605020811,
575
+ "pass@8": 0.7028333090553421,
576
+ "pass@16": 0.7441566918393214,
577
+ "pass@32": 0.7786413556423193,
578
+ "pass@64": 0.8099070209833706,
579
+ "pass@128": 0.8397626112759644
580
+ },
581
+ "15": {
582
+ "pass@1": 0.4148582175925926,
583
+ "pass@2": 0.5159439705453481,
584
+ "pass@4": 0.6012471027927059,
585
+ "pass@8": 0.6729046096132648,
586
+ "pass@16": 0.7313953058257493,
587
+ "pass@32": 0.774479621602295,
588
+ "pass@64": 0.8024911635264447,
589
+ "pass@128": 0.8209876543209876
590
+ },
591
+ "16": {
592
+ "pass@1": 0.3055862831858407,
593
+ "pass@2": 0.4155993049264857,
594
+ "pass@4": 0.5233688064987452,
595
+ "pass@8": 0.61649192420964,
596
+ "pass@16": 0.6877108315436323,
597
+ "pass@32": 0.7411285331916613,
598
+ "pass@64": 0.7833701645353189,
599
+ "pass@128": 0.8141592920353983
600
+ },
601
+ "17": {
602
+ "pass@1": 0.20783132530120482,
603
+ "pass@2": 0.28941936545394154,
604
+ "pass@4": 0.37251450571690553,
605
+ "pass@8": 0.4498245481792572,
606
+ "pass@16": 0.5198675183713172,
607
+ "pass@32": 0.5854354584449748,
608
+ "pass@64": 0.6483419372761501,
609
+ "pass@128": 0.7018072289156626
610
+ },
611
+ "18": {
612
+ "pass@1": 0.1850554435483871,
613
+ "pass@2": 0.2636965805181609,
614
+ "pass@4": 0.3436965849026936,
615
+ "pass@8": 0.4168114472153046,
616
+ "pass@16": 0.47926210493149596,
617
+ "pass@32": 0.5322981106756975,
618
+ "pass@64": 0.579410041121762,
619
+ "pass@128": 0.6258064516129033
620
+ },
621
+ "19": {
622
+ "pass@1": 0.11293901057401813,
623
+ "pass@2": 0.16683777089230925,
624
+ "pass@4": 0.2275661126762477,
625
+ "pass@8": 0.28925043953870366,
626
+ "pass@16": 0.34857112085394526,
627
+ "pass@32": 0.4056005496629237,
628
+ "pass@64": 0.46160284801836204,
629
+ "pass@128": 0.5166163141993958
630
+ },
631
+ "20": {
632
+ "pass@1": 0.13278903903903905,
633
+ "pass@2": 0.1947211729445982,
634
+ "pass@4": 0.25905214325686776,
635
+ "pass@8": 0.31757959622018117,
636
+ "pass@16": 0.36798408324022314,
637
+ "pass@32": 0.4120717727332606,
638
+ "pass@64": 0.4547245540517399,
639
+ "pass@128": 0.5015015015015015
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]