ZachW commited on
Commit
0e7c75c
·
verified ·
1 Parent(s): e546e6e

Upload extrapolation artifact: 050302 RL OP11-14 step200 summary JSON

Browse files
050302/evals/rl050302_op11_14_step200_merged_hf/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "rl050302_op11_14_step200_merged_hf",
4
+ "id_acc": 0.7564635416666666,
5
+ "ood_acc": 0.34808203125,
6
+ "total_acc": 0.5415259046052632,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 208.0127170138889,
11
+ "ood_avg_resp_len": 342.315659375,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 438889,
19
+ "answer_accuracy": 0.5420202833544103,
20
+ "avg_response_len": 266.6312070226051,
21
+ "resp_tokens_sum": 215898754,
22
+ "pass_at_k": {
23
+ "pass@1": 0.5420202833544103,
24
+ "pass@2": 0.6053215925837938,
25
+ "pass@4": 0.6601015812845192,
26
+ "pass@8": 0.7063449522824156,
27
+ "pass@16": 0.7442708953088986,
28
+ "pass@32": 0.7752375894022824,
29
+ "pass@64": 0.8011639131735242,
30
+ "pass@128": 0.8239013594688587
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.7018805309734514,
35
+ "pass@2": 0.7549985628179221,
36
+ "pass@4": 0.794857199542535,
37
+ "pass@8": 0.8246423155165492,
38
+ "pass@16": 0.8477130887947533,
39
+ "pass@32": 0.8687864891718109,
40
+ "pass@64": 0.8890464019643919,
41
+ "pass@128": 0.9085545722713865
42
+ },
43
+ "2": {
44
+ "pass@1": 0.9495716510903427,
45
+ "pass@2": 0.9728514331444554,
46
+ "pass@4": 0.9851647276567062,
47
+ "pass@8": 0.992077485746166,
48
+ "pass@16": 0.9954145881797847,
49
+ "pass@32": 0.996585667661237,
50
+ "pass@64": 0.9968750895206262,
51
+ "pass@128": 0.9968847352024922
52
+ },
53
+ "3": {
54
+ "pass@1": 0.9074445718654435,
55
+ "pass@2": 0.9352523236774299,
56
+ "pass@4": 0.953601489034054,
57
+ "pass@8": 0.9679758338381604,
58
+ "pass@16": 0.9790672679207248,
59
+ "pass@32": 0.9871383226541847,
60
+ "pass@64": 0.9930782875203557,
61
+ "pass@128": 0.9969418960244648
62
+ },
63
+ "4": {
64
+ "pass@1": 0.8296630859375,
65
+ "pass@2": 0.8626487912155513,
66
+ "pass@4": 0.8834582688882635,
67
+ "pass@8": 0.895808641913504,
68
+ "pass@16": 0.9041949013259944,
69
+ "pass@32": 0.9123519155789825,
70
+ "pass@64": 0.9217296599331064,
71
+ "pass@128": 0.93125
72
+ },
73
+ "5": {
74
+ "pass@1": 0.6723710317460317,
75
+ "pass@2": 0.7115751156105488,
76
+ "pass@4": 0.7433334842073313,
77
+ "pass@8": 0.768306546362202,
78
+ "pass@16": 0.7871896199409257,
79
+ "pass@32": 0.8020106421329306,
80
+ "pass@64": 0.8145428062453238,
81
+ "pass@128": 0.8285714285714286
82
+ },
83
+ "6": {
84
+ "pass@1": 0.6831259356287425,
85
+ "pass@2": 0.7225941817153095,
86
+ "pass@4": 0.7511133829079745,
87
+ "pass@8": 0.7732136904251459,
88
+ "pass@16": 0.7908965515084061,
89
+ "pass@32": 0.8059498542595275,
90
+ "pass@64": 0.8190138601274597,
91
+ "pass@128": 0.8323353293413174
92
+ },
93
+ "7": {
94
+ "pass@1": 0.7232572115384616,
95
+ "pass@2": 0.7591458265386947,
96
+ "pass@4": 0.7840269109297723,
97
+ "pass@8": 0.8025467115547503,
98
+ "pass@16": 0.8182715609954336,
99
+ "pass@32": 0.8323267215314273,
100
+ "pass@64": 0.8455724214427237,
101
+ "pass@128": 0.8579881656804734
102
+ },
103
+ "8": {
104
+ "pass@1": 0.6790364583333334,
105
+ "pass@2": 0.7368809780688469,
106
+ "pass@4": 0.7800951419534093,
107
+ "pass@8": 0.8111498024624929,
108
+ "pass@16": 0.8340518273159697,
109
+ "pass@32": 0.851499152999998,
110
+ "pass@64": 0.8652018097269851,
111
+ "pass@128": 0.8782051282051282
112
+ },
113
+ "9": {
114
+ "pass@1": 0.7028389084507042,
115
+ "pass@2": 0.7644043889320176,
116
+ "pass@4": 0.808012754743685,
117
+ "pass@8": 0.8407312628937469,
118
+ "pass@16": 0.8654983711299619,
119
+ "pass@32": 0.8838276379384431,
120
+ "pass@64": 0.8988843924487747,
121
+ "pass@128": 0.9126760563380282
122
+ },
123
+ "11": {
124
+ "pass@1": 0.607471671388102,
125
+ "pass@2": 0.6684865801565879,
126
+ "pass@4": 0.7145608326933632,
127
+ "pass@8": 0.751410226301821,
128
+ "pass@16": 0.7813128542866512,
129
+ "pass@32": 0.8077145164088809,
130
+ "pass@64": 0.8342378682376506,
131
+ "pass@128": 0.8611898016997167
132
+ },
133
+ "12": {
134
+ "pass@1": 0.6359242584745762,
135
+ "pass@2": 0.7010140019573821,
136
+ "pass@4": 0.7524318914584823,
137
+ "pass@8": 0.7966960762341885,
138
+ "pass@16": 0.8349907268657351,
139
+ "pass@32": 0.8675260403092755,
140
+ "pass@64": 0.8927480390421706,
141
+ "pass@128": 0.9124293785310734
142
+ },
143
+ "13": {
144
+ "pass@1": 0.5220905172413793,
145
+ "pass@2": 0.620534226667983,
146
+ "pass@4": 0.7027034552695014,
147
+ "pass@8": 0.770057213759952,
148
+ "pass@16": 0.8241495227282288,
149
+ "pass@32": 0.8631455967014058,
150
+ "pass@64": 0.8879219996985025,
151
+ "pass@128": 0.9090909090909091
152
+ },
153
+ "14": {
154
+ "pass@1": 0.4550963785046729,
155
+ "pass@2": 0.5581134097431748,
156
+ "pass@4": 0.647930787565105,
157
+ "pass@8": 0.7233182340799785,
158
+ "pass@16": 0.7833892226203504,
159
+ "pass@32": 0.8279559428456201,
160
+ "pass@64": 0.8590417122874536,
161
+ "pass@128": 0.881619937694704
162
+ },
163
+ "15": {
164
+ "pass@1": 0.34934971098265893,
165
+ "pass@2": 0.45711498964544184,
166
+ "pass@4": 0.5511690342356048,
167
+ "pass@8": 0.6290683831435004,
168
+ "pass@16": 0.6933893369608615,
169
+ "pass@32": 0.7435434683159998,
170
+ "pass@64": 0.7816914947898684,
171
+ "pass@128": 0.8179190751445087
172
+ },
173
+ "16": {
174
+ "pass@1": 0.2809475806451613,
175
+ "pass@2": 0.38555094297688597,
176
+ "pass@4": 0.4893392721071152,
177
+ "pass@8": 0.5826136332644718,
178
+ "pass@16": 0.6611631758264305,
179
+ "pass@32": 0.7266388086540002,
180
+ "pass@64": 0.7824484578306036,
181
+ "pass@128": 0.832258064516129
182
+ },
183
+ "17": {
184
+ "pass@1": 0.1666365606936416,
185
+ "pass@2": 0.2457618138682809,
186
+ "pass@4": 0.33538570187758293,
187
+ "pass@8": 0.42521167689535794,
188
+ "pass@16": 0.5048829056797672,
189
+ "pass@32": 0.5706106820406163,
190
+ "pass@64": 0.6265261197812971,
191
+ "pass@128": 0.6734104046242775
192
+ },
193
+ "18": {
194
+ "pass@1": 0.15660714285714286,
195
+ "pass@2": 0.2282670134983126,
196
+ "pass@4": 0.3032608698912637,
197
+ "pass@8": 0.37353183319352135,
198
+ "pass@16": 0.43836449791082005,
199
+ "pass@32": 0.4984786995754745,
200
+ "pass@64": 0.5524853165212575,
201
+ "pass@128": 0.5942857142857143
202
+ },
203
+ "19": {
204
+ "pass@1": 0.16272522522522523,
205
+ "pass@2": 0.23145808209784588,
206
+ "pass@4": 0.30189558653141335,
207
+ "pass@8": 0.36420667880460095,
208
+ "pass@16": 0.4138035379213277,
209
+ "pass@32": 0.4535217258277585,
210
+ "pass@64": 0.48873324942873747,
211
+ "pass@128": 0.5225225225225225
212
+ },
213
+ "20": {
214
+ "pass@1": 0.15388044294294295,
215
+ "pass@2": 0.2248661062637441,
216
+ "pass@4": 0.29865429462083,
217
+ "pass@8": 0.3650207487197481,
218
+ "pass@16": 0.41781596055733294,
219
+ "pass@32": 0.4613199772361069,
220
+ "pass@64": 0.5005061369851226,
221
+ "pass@128": 0.5315315315315315
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 445920,
228
+ "answer_accuracy": 0.5430631332813718,
229
+ "avg_response_len": 274.84728297934527,
230
+ "resp_tokens_sum": 225682601,
231
+ "pass_at_k": {
232
+ "pass@1": 0.5430631332813718,
233
+ "pass@2": 0.6044259310118462,
234
+ "pass@4": 0.6581722536728921,
235
+ "pass@8": 0.7037834676975927,
236
+ "pass@16": 0.7411931274105865,
237
+ "pass@32": 0.771978422134926,
238
+ "pass@64": 0.7981625962635988,
239
+ "pass@128": 0.8202650038971161
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.7098590874233128,
244
+ "pass@2": 0.7535682907830544,
245
+ "pass@4": 0.7864975527407232,
246
+ "pass@8": 0.8135336785898025,
247
+ "pass@16": 0.8366857190055628,
248
+ "pass@32": 0.8580710264821365,
249
+ "pass@64": 0.8776973706717127,
250
+ "pass@128": 0.8957055214723927
251
+ },
252
+ "2": {
253
+ "pass@1": 0.9405395136778115,
254
+ "pass@2": 0.9620412308833738,
255
+ "pass@4": 0.9758225314920738,
256
+ "pass@8": 0.9849524204535265,
257
+ "pass@16": 0.9900649654565532,
258
+ "pass@32": 0.9921000445202469,
259
+ "pass@64": 0.9931668037952412,
260
+ "pass@128": 0.993920972644377
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9234375,
264
+ "pass@2": 0.9456786119064663,
265
+ "pass@4": 0.9617405105611796,
266
+ "pass@8": 0.9726108401727136,
267
+ "pass@16": 0.9779520922364761,
268
+ "pass@32": 0.9803488524936297,
269
+ "pass@64": 0.9825398325449198,
270
+ "pass@128": 0.9848484848484849
271
+ },
272
+ "4": {
273
+ "pass@1": 0.8384106878698225,
274
+ "pass@2": 0.8696401219540603,
275
+ "pass@4": 0.8919865230418679,
276
+ "pass@8": 0.9109039824674823,
277
+ "pass@16": 0.9268934190930932,
278
+ "pass@32": 0.939480395901062,
279
+ "pass@64": 0.9475861428402855,
280
+ "pass@128": 0.9526627218934911
281
+ },
282
+ "5": {
283
+ "pass@1": 0.7247509057971014,
284
+ "pass@2": 0.7569896154285061,
285
+ "pass@4": 0.7794320843046791,
286
+ "pass@8": 0.7960690607966524,
287
+ "pass@16": 0.8107549025408636,
288
+ "pass@32": 0.8248985765960865,
289
+ "pass@64": 0.8371374039094492,
290
+ "pass@128": 0.8463768115942029
291
+ },
292
+ "6": {
293
+ "pass@1": 0.6351181948424068,
294
+ "pass@2": 0.6731091927441734,
295
+ "pass@4": 0.7035691777782792,
296
+ "pass@8": 0.7284657829447492,
297
+ "pass@16": 0.7492790741526567,
298
+ "pass@32": 0.7669448136688961,
299
+ "pass@64": 0.7842548351421045,
300
+ "pass@128": 0.8022922636103151
301
+ },
302
+ "7": {
303
+ "pass@1": 0.6782649927745664,
304
+ "pass@2": 0.7190959816348825,
305
+ "pass@4": 0.7507817206555822,
306
+ "pass@8": 0.7737670955280236,
307
+ "pass@16": 0.7898595118415901,
308
+ "pass@32": 0.8002346239143221,
309
+ "pass@64": 0.8076964146996783,
310
+ "pass@128": 0.815028901734104
311
+ },
312
+ "8": {
313
+ "pass@1": 0.6978653169014084,
314
+ "pass@2": 0.7489800515692578,
315
+ "pass@4": 0.7882377675501828,
316
+ "pass@8": 0.8181867244335217,
317
+ "pass@16": 0.8403183790454402,
318
+ "pass@32": 0.8589868896024869,
319
+ "pass@64": 0.876235649537859,
320
+ "pass@128": 0.8901408450704226
321
+ },
322
+ "9": {
323
+ "pass@1": 0.6945172155688623,
324
+ "pass@2": 0.7500011050733182,
325
+ "pass@4": 0.7906428624752743,
326
+ "pass@8": 0.82085154021908,
327
+ "pass@16": 0.8423189279171873,
328
+ "pass@32": 0.8580696456086162,
329
+ "pass@64": 0.8721121926305166,
330
+ "pass@128": 0.8862275449101796
331
+ },
332
+ "11": {
333
+ "pass@1": 0.6834525602409639,
334
+ "pass@2": 0.7452788516269804,
335
+ "pass@4": 0.7915516082891745,
336
+ "pass@8": 0.8261539846629206,
337
+ "pass@16": 0.8526640250865961,
338
+ "pass@32": 0.8738063302776092,
339
+ "pass@64": 0.8889842536640941,
340
+ "pass@128": 0.9006024096385542
341
+ },
342
+ "12": {
343
+ "pass@1": 0.5999706112852664,
344
+ "pass@2": 0.6710307493890849,
345
+ "pass@4": 0.7270021304155156,
346
+ "pass@8": 0.7740386863781831,
347
+ "pass@16": 0.8163447617758682,
348
+ "pass@32": 0.8558721662357881,
349
+ "pass@64": 0.8879737897637945,
350
+ "pass@128": 0.9059561128526645
351
+ },
352
+ "13": {
353
+ "pass@1": 0.5011160714285714,
354
+ "pass@2": 0.5872255398222277,
355
+ "pass@4": 0.6574135097608591,
356
+ "pass@8": 0.7164654558518686,
357
+ "pass@16": 0.7646393709776641,
358
+ "pass@32": 0.8049812812395852,
359
+ "pass@64": 0.8421836892633574,
360
+ "pass@128": 0.8739495798319328
361
+ },
362
+ "14": {
363
+ "pass@1": 0.46562043128654973,
364
+ "pass@2": 0.5736181620389555,
365
+ "pass@4": 0.6658962851683015,
366
+ "pass@8": 0.7406709774148201,
367
+ "pass@16": 0.7999165548996432,
368
+ "pass@32": 0.8459800566229854,
369
+ "pass@64": 0.8804301429076689,
370
+ "pass@128": 0.9035087719298246
371
+ },
372
+ "15": {
373
+ "pass@1": 0.34005681818181815,
374
+ "pass@2": 0.4530862264376045,
375
+ "pass@4": 0.5587200136914704,
376
+ "pass@8": 0.6492672106221214,
377
+ "pass@16": 0.7203189663183454,
378
+ "pass@32": 0.772011087327161,
379
+ "pass@64": 0.8109608705247362,
380
+ "pass@128": 0.8454545454545455
381
+ },
382
+ "16": {
383
+ "pass@1": 0.2512686965811966,
384
+ "pass@2": 0.3525497313637072,
385
+ "pass@4": 0.4530276642770078,
386
+ "pass@8": 0.5447819490663908,
387
+ "pass@16": 0.6222232974153704,
388
+ "pass@32": 0.6833052014073985,
389
+ "pass@64": 0.7317438177167213,
390
+ "pass@128": 0.7663817663817664
391
+ },
392
+ "17": {
393
+ "pass@1": 0.18800951086956522,
394
+ "pass@2": 0.2707564068078446,
395
+ "pass@4": 0.3571127275627813,
396
+ "pass@8": 0.4376570004492196,
397
+ "pass@16": 0.5083689377646803,
398
+ "pass@32": 0.5709991978812625,
399
+ "pass@64": 0.6318509335752782,
400
+ "pass@128": 0.6956521739130435
401
+ },
402
+ "18": {
403
+ "pass@1": 0.16176470588235295,
404
+ "pass@2": 0.23503285664659573,
405
+ "pass@4": 0.31124803204746476,
406
+ "pass@8": 0.3828673713583056,
407
+ "pass@16": 0.44741521106430404,
408
+ "pass@32": 0.5054273561599129,
409
+ "pass@64": 0.5568983926229338,
410
+ "pass@128": 0.6029411764705882
411
+ },
412
+ "19": {
413
+ "pass@1": 0.13955543154761904,
414
+ "pass@2": 0.2029613241704161,
415
+ "pass@4": 0.26906566143517774,
416
+ "pass@8": 0.3307801388013955,
417
+ "pass@16": 0.3853507519948162,
418
+ "pass@32": 0.4335818215143217,
419
+ "pass@64": 0.4757266113676575,
420
+ "pass@128": 0.5089285714285714
421
+ },
422
+ "20": {
423
+ "pass@1": 0.14794629491017963,
424
+ "pass@2": 0.21578361485690029,
425
+ "pass@4": 0.2874044784446853,
426
+ "pass@8": 0.3515917933178076,
427
+ "pass@16": 0.4031600034659726,
428
+ "pass@32": 0.44477466635709534,
429
+ "pass@64": 0.4826415676427111,
430
+ "pass@128": 0.5179640718562875
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 432182,
437
+ "answer_accuracy": 0.5394506910049529,
438
+ "avg_response_len": 294.8421011243809,
439
+ "resp_tokens_sum": 236213339,
440
+ "pass_at_k": {
441
+ "pass@1": 0.5394506910049529,
442
+ "pass@2": 0.6024841157866588,
443
+ "pass@4": 0.6570925329542748,
444
+ "pass@8": 0.702453429392051,
445
+ "pass@16": 0.7392179408263716,
446
+ "pass@32": 0.7691243901857652,
447
+ "pass@64": 0.7942040520267212,
448
+ "pass@128": 0.8167438888001278
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.6880130597014925,
453
+ "pass@2": 0.7406323451639437,
454
+ "pass@4": 0.7818289239964403,
455
+ "pass@8": 0.8151739980189773,
456
+ "pass@16": 0.8430100482640915,
457
+ "pass@32": 0.867084488200749,
458
+ "pass@64": 0.8868682888268872,
459
+ "pass@128": 0.9014925373134328
460
+ },
461
+ "2": {
462
+ "pass@1": 0.9149553571428571,
463
+ "pass@2": 0.941519966254218,
464
+ "pass@4": 0.9592815978359845,
465
+ "pass@8": 0.9720824428768929,
466
+ "pass@16": 0.9815546352101394,
467
+ "pass@32": 0.9888944721407834,
468
+ "pass@64": 0.9941924652953058,
469
+ "pass@128": 0.9971428571428571
470
+ },
471
+ "3": {
472
+ "pass@1": 0.9182990160349854,
473
+ "pass@2": 0.9425432152613579,
474
+ "pass@4": 0.9584297378279611,
475
+ "pass@8": 0.9694135789962994,
476
+ "pass@16": 0.9775193399166878,
477
+ "pass@32": 0.9840654128206252,
478
+ "pass@64": 0.9897341365354874,
479
+ "pass@128": 0.9941690962099126
480
+ },
481
+ "4": {
482
+ "pass@1": 0.8101014254385965,
483
+ "pass@2": 0.8437654688723117,
484
+ "pass@4": 0.8667262329599149,
485
+ "pass@8": 0.8819389004252276,
486
+ "pass@16": 0.8935276816111616,
487
+ "pass@32": 0.9023627399160156,
488
+ "pass@64": 0.9084794471295793,
489
+ "pass@128": 0.9152046783625731
490
+ },
491
+ "5": {
492
+ "pass@1": 0.6963924632352941,
493
+ "pass@2": 0.7404263403195928,
494
+ "pass@4": 0.775511439378901,
495
+ "pass@8": 0.8009202199644325,
496
+ "pass@16": 0.8186978396026182,
497
+ "pass@32": 0.8326293582229927,
498
+ "pass@64": 0.8445105409346427,
499
+ "pass@128": 0.8529411764705882
500
+ },
501
+ "6": {
502
+ "pass@1": 0.714067429022082,
503
+ "pass@2": 0.7500981923296656,
504
+ "pass@4": 0.7762405075942792,
505
+ "pass@8": 0.7969962762271371,
506
+ "pass@16": 0.8134959942735189,
507
+ "pass@32": 0.8282404219834616,
508
+ "pass@64": 0.8447793342621057,
509
+ "pass@128": 0.8643533123028391
510
+ },
511
+ "7": {
512
+ "pass@1": 0.6639141613924051,
513
+ "pass@2": 0.7005717071165156,
514
+ "pass@4": 0.727557464237065,
515
+ "pass@8": 0.7484945090138806,
516
+ "pass@16": 0.7665431737280053,
517
+ "pass@32": 0.7839673099388944,
518
+ "pass@64": 0.8011938587351172,
519
+ "pass@128": 0.8164556962025317
520
+ },
521
+ "8": {
522
+ "pass@1": 0.672461524024024,
523
+ "pass@2": 0.7206985528835925,
524
+ "pass@4": 0.7604853731684436,
525
+ "pass@8": 0.7941016876636111,
526
+ "pass@16": 0.8204262635068897,
527
+ "pass@32": 0.8417859674818847,
528
+ "pass@64": 0.8614391726749312,
529
+ "pass@128": 0.8798798798798799
530
+ },
531
+ "9": {
532
+ "pass@1": 0.6519041398713826,
533
+ "pass@2": 0.7069915911335041,
534
+ "pass@4": 0.7506053654466821,
535
+ "pass@8": 0.7822037981653261,
536
+ "pass@16": 0.8028926727335497,
537
+ "pass@32": 0.8190772373135783,
538
+ "pass@64": 0.8360786694468839,
539
+ "pass@128": 0.8553054662379421
540
+ },
541
+ "11": {
542
+ "pass@1": 0.6475694444444444,
543
+ "pass@2": 0.720068975753031,
544
+ "pass@4": 0.7730891477850979,
545
+ "pass@8": 0.8109217151768221,
546
+ "pass@16": 0.8391620142013038,
547
+ "pass@32": 0.8621038165828088,
548
+ "pass@64": 0.8830074431961632,
549
+ "pass@128": 0.9015873015873016
550
+ },
551
+ "12": {
552
+ "pass@1": 0.6413417431192661,
553
+ "pass@2": 0.704082538707891,
554
+ "pass@4": 0.7513502354636861,
555
+ "pass@8": 0.7928136020002462,
556
+ "pass@16": 0.8301661693801712,
557
+ "pass@32": 0.8624397252433138,
558
+ "pass@64": 0.8888217834671825,
559
+ "pass@128": 0.9113149847094801
560
+ },
561
+ "13": {
562
+ "pass@1": 0.5245225694444444,
563
+ "pass@2": 0.613710341328862,
564
+ "pass@4": 0.6886929619908626,
565
+ "pass@8": 0.7532199740619856,
566
+ "pass@16": 0.8060972428317466,
567
+ "pass@32": 0.8465569697048755,
568
+ "pass@64": 0.8768956451569085,
569
+ "pass@128": 0.9012345679012346
570
+ },
571
+ "14": {
572
+ "pass@1": 0.43209847922848665,
573
+ "pass@2": 0.5442581164279539,
574
+ "pass@4": 0.6390545526208331,
575
+ "pass@8": 0.7148531736292517,
576
+ "pass@16": 0.7709069487836203,
577
+ "pass@32": 0.8091193075610889,
578
+ "pass@64": 0.8354907283201769,
579
+ "pass@128": 0.8545994065281899
580
+ },
581
+ "15": {
582
+ "pass@1": 0.3362750771604938,
583
+ "pass@2": 0.4498217562214446,
584
+ "pass@4": 0.5492879258148281,
585
+ "pass@8": 0.6259151063045518,
586
+ "pass@16": 0.6838288104673347,
587
+ "pass@32": 0.7271659788130399,
588
+ "pass@64": 0.7591946543896418,
589
+ "pass@128": 0.7901234567901234
590
+ },
591
+ "16": {
592
+ "pass@1": 0.24073561946902655,
593
+ "pass@2": 0.345844075906441,
594
+ "pass@4": 0.4501511309980055,
595
+ "pass@8": 0.5388695636519144,
596
+ "pass@16": 0.61091142935178,
597
+ "pass@32": 0.6711357145149186,
598
+ "pass@64": 0.7212133899833834,
599
+ "pass@128": 0.7640117994100295
600
+ },
601
+ "17": {
602
+ "pass@1": 0.1878059111445783,
603
+ "pass@2": 0.264661870908832,
604
+ "pass@4": 0.34510003455893307,
605
+ "pass@8": 0.4229141069156303,
606
+ "pass@16": 0.49251404650709835,
607
+ "pass@32": 0.5519003412110756,
608
+ "pass@64": 0.6045042867269972,
609
+ "pass@128": 0.6536144578313253
610
+ },
611
+ "18": {
612
+ "pass@1": 0.16849798387096773,
613
+ "pass@2": 0.23845488315976635,
614
+ "pass@4": 0.3089043291967536,
615
+ "pass@8": 0.3740905690365366,
616
+ "pass@16": 0.4314242151887938,
617
+ "pass@32": 0.4816503235844736,
618
+ "pass@64": 0.5280348641946153,
619
+ "pass@128": 0.5741935483870968
620
+ },
621
+ "19": {
622
+ "pass@1": 0.15211952416918428,
623
+ "pass@2": 0.22327800509075332,
624
+ "pass@4": 0.2960748354340905,
625
+ "pass@8": 0.3635955512217954,
626
+ "pass@16": 0.4228344210461176,
627
+ "pass@32": 0.4702218209493226,
628
+ "pass@64": 0.5066129236272973,
629
+ "pass@128": 0.5347432024169184
630
+ },
631
+ "20": {
632
+ "pass@1": 0.14806212462462462,
633
+ "pass@2": 0.2182563961599395,
634
+ "pass@4": 0.29120600127686735,
635
+ "pass@8": 0.3549176070341172,
636
+ "pass@16": 0.40818890086199433,
637
+ "pass@32": 0.45330992297920386,
638
+ "pass@64": 0.4915266997620285,
639
+ "pass@128": 0.5315315315315315
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]