ZachW commited on
Commit
f10612f
·
verified ·
1 Parent(s): e6c678b

Upload extrapolation artifact: 020305 RL OP11-14 step200 summary JSON

Browse files
020305/evals/rl_ckpt18809_op11_14_step200_merged_hf/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "rl_ckpt18809_op11_14_step200_merged_hf",
4
+ "id_acc": 0.8007092013888889,
5
+ "ood_acc": 0.3696015625,
6
+ "total_acc": 0.5738104440789473,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 205.96150868055557,
11
+ "ood_avg_resp_len": 344.95646328125,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 462000,
19
+ "answer_accuracy": 0.5705619664875119,
20
+ "avg_response_len": 266.65483841487514,
21
+ "resp_tokens_sum": 215917889,
22
+ "pass_at_k": {
23
+ "pass@1": 0.5705619664875119,
24
+ "pass@2": 0.6188662400641347,
25
+ "pass@4": 0.6598397585991788,
26
+ "pass@8": 0.6947804888680269,
27
+ "pass@16": 0.7245472702197145,
28
+ "pass@32": 0.750087405725655,
29
+ "pass@64": 0.7725793814253182,
30
+ "pass@128": 0.7941827379070503
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.7438928834808259,
35
+ "pass@2": 0.7712075087682627,
36
+ "pass@4": 0.788484906477398,
37
+ "pass@8": 0.8018591228191637,
38
+ "pass@16": 0.8135185053075238,
39
+ "pass@32": 0.8235877070408618,
40
+ "pass@64": 0.8328438858320545,
41
+ "pass@128": 0.8436578171091446
42
+ },
43
+ "2": {
44
+ "pass@1": 0.9810893691588785,
45
+ "pass@2": 0.9871046894547059,
46
+ "pass@4": 0.9915101111776916,
47
+ "pass@8": 0.9953947938305675,
48
+ "pass@16": 0.9983396076986927,
49
+ "pass@32": 0.9997843988181119,
50
+ "pass@64": 0.9999987690221049,
51
+ "pass@128": 1.0
52
+ },
53
+ "3": {
54
+ "pass@1": 0.9368310397553516,
55
+ "pass@2": 0.9563964338173326,
56
+ "pass@4": 0.9680231226830587,
57
+ "pass@8": 0.9768358309888281,
58
+ "pass@16": 0.9847138767567563,
59
+ "pass@32": 0.9918844396490281,
60
+ "pass@64": 0.9975721293132904,
61
+ "pass@128": 1.0
62
+ },
63
+ "4": {
64
+ "pass@1": 0.9338623046875,
65
+ "pass@2": 0.9479572926919291,
66
+ "pass@4": 0.9543002273153357,
67
+ "pass@8": 0.9576982049569731,
68
+ "pass@16": 0.9598406165703117,
69
+ "pass@32": 0.9613712620341444,
70
+ "pass@64": 0.9623117912794369,
71
+ "pass@128": 0.9625
72
+ },
73
+ "5": {
74
+ "pass@1": 0.7163938492063492,
75
+ "pass@2": 0.7431762435945508,
76
+ "pass@4": 0.7610682679546008,
77
+ "pass@8": 0.7744309131768377,
78
+ "pass@16": 0.7855329207880001,
79
+ "pass@32": 0.7959439326927594,
80
+ "pass@64": 0.8064402639496288,
81
+ "pass@128": 0.8158730158730159
82
+ },
83
+ "6": {
84
+ "pass@1": 0.8067458832335329,
85
+ "pass@2": 0.8348232177377528,
86
+ "pass@4": 0.8542045804341821,
87
+ "pass@8": 0.8686333407624491,
88
+ "pass@16": 0.877690076530578,
89
+ "pass@32": 0.882081764599347,
90
+ "pass@64": 0.8847282872785166,
91
+ "pass@128": 0.8892215568862275
92
+ },
93
+ "7": {
94
+ "pass@1": 0.7201830621301775,
95
+ "pass@2": 0.7443889629828077,
96
+ "pass@4": 0.7612230119718763,
97
+ "pass@8": 0.772818887181291,
98
+ "pass@16": 0.7804307509727729,
99
+ "pass@32": 0.7864785589968171,
100
+ "pass@64": 0.7926751149015483,
101
+ "pass@128": 0.8017751479289941
102
+ },
103
+ "8": {
104
+ "pass@1": 0.6916065705128205,
105
+ "pass@2": 0.7239855422218857,
106
+ "pass@4": 0.7439738713550229,
107
+ "pass@8": 0.7577231502892088,
108
+ "pass@16": 0.7674194594515328,
109
+ "pass@32": 0.7748075486795403,
110
+ "pass@64": 0.7828620374894698,
111
+ "pass@128": 0.7948717948717948
112
+ },
113
+ "9": {
114
+ "pass@1": 0.707350352112676,
115
+ "pass@2": 0.7420930603304866,
116
+ "pass@4": 0.7648698249866656,
117
+ "pass@8": 0.7829245962703245,
118
+ "pass@16": 0.8003575087424837,
119
+ "pass@32": 0.817165216063856,
120
+ "pass@64": 0.8313477644994759,
121
+ "pass@128": 0.8450704225352113
122
+ },
123
+ "11": {
124
+ "pass@1": 0.6469768059490085,
125
+ "pass@2": 0.6894238919497665,
126
+ "pass@4": 0.7225725194407352,
127
+ "pass@8": 0.7506833646760649,
128
+ "pass@16": 0.7752962941660689,
129
+ "pass@32": 0.7955695698104521,
130
+ "pass@64": 0.8083750436737148,
131
+ "pass@128": 0.8158640226628895
132
+ },
133
+ "12": {
134
+ "pass@1": 0.6252206920903954,
135
+ "pass@2": 0.6677412807509228,
136
+ "pass@4": 0.6967321915798657,
137
+ "pass@8": 0.7201610143145252,
138
+ "pass@16": 0.7414216037107215,
139
+ "pass@32": 0.7607308684395971,
140
+ "pass@64": 0.7777975420332491,
141
+ "pass@128": 0.7966101694915254
142
+ },
143
+ "13": {
144
+ "pass@1": 0.5582876175548589,
145
+ "pass@2": 0.6307076586527781,
146
+ "pass@4": 0.6898986407067453,
147
+ "pass@8": 0.7401920690613091,
148
+ "pass@16": 0.781177587303372,
149
+ "pass@32": 0.8124884487216828,
150
+ "pass@64": 0.837256590036622,
151
+ "pass@128": 0.8620689655172413
152
+ },
153
+ "14": {
154
+ "pass@1": 0.48286604361370716,
155
+ "pass@2": 0.5730945065862094,
156
+ "pass@4": 0.6440937543437903,
157
+ "pass@8": 0.7008695491861001,
158
+ "pass@16": 0.7489996821068052,
159
+ "pass@32": 0.793426622007421,
160
+ "pass@64": 0.8373514686633189,
161
+ "pass@128": 0.881619937694704
162
+ },
163
+ "15": {
164
+ "pass@1": 0.40144057080924855,
165
+ "pass@2": 0.4994538254972468,
166
+ "pass@4": 0.5848411843208899,
167
+ "pass@8": 0.6554678454383086,
168
+ "pass@16": 0.7107067733225267,
169
+ "pass@32": 0.7537745872542576,
170
+ "pass@64": 0.7895387686905707,
171
+ "pass@128": 0.8208092485549133
172
+ },
173
+ "16": {
174
+ "pass@1": 0.31827116935483873,
175
+ "pass@2": 0.41254564071628147,
176
+ "pass@4": 0.49882131487596315,
177
+ "pass@8": 0.5724213742846472,
178
+ "pass@16": 0.6329779076851179,
179
+ "pass@32": 0.6810765298643525,
180
+ "pass@64": 0.7216800879849797,
181
+ "pass@128": 0.7612903225806451
182
+ },
183
+ "17": {
184
+ "pass@1": 0.1868451950867052,
185
+ "pass@2": 0.2578249453825496,
186
+ "pass@4": 0.3316976206189544,
187
+ "pass@8": 0.40456114782269115,
188
+ "pass@16": 0.47415657485832746,
189
+ "pass@32": 0.5347902610222496,
190
+ "pass@64": 0.5831630010253005,
191
+ "pass@128": 0.6242774566473989
192
+ },
193
+ "18": {
194
+ "pass@1": 0.16613839285714285,
195
+ "pass@2": 0.23395563835770522,
196
+ "pass@4": 0.30313604611923506,
197
+ "pass@8": 0.3660359856781646,
198
+ "pass@16": 0.4214320981910954,
199
+ "pass@32": 0.4705896465101359,
200
+ "pass@64": 0.5180082011947298,
201
+ "pass@128": 0.5714285714285714
202
+ },
203
+ "19": {
204
+ "pass@1": 0.13004410660660662,
205
+ "pass@2": 0.19119279220165045,
206
+ "pass@4": 0.25605800429225645,
207
+ "pass@8": 0.31673822881978403,
208
+ "pass@16": 0.37397659010763834,
209
+ "pass@32": 0.43082063885624244,
210
+ "pass@64": 0.48459265031392806,
211
+ "pass@128": 0.5285285285285285
212
+ },
213
+ "20": {
214
+ "pass@1": 0.1356981981981982,
215
+ "pass@2": 0.1991983371166442,
216
+ "pass@4": 0.2672903291367859,
217
+ "pass@8": 0.32875387960123914,
218
+ "pass@16": 0.3788539821643221,
219
+ "pass@32": 0.4227763457485307,
220
+ "pass@64": 0.46578029037145013,
221
+ "pass@128": 0.5075075075075075
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 472238,
228
+ "answer_accuracy": 0.575114477786438,
229
+ "avg_response_len": 275.4818784099766,
230
+ "resp_tokens_sum": 226203680,
231
+ "pass_at_k": {
232
+ "pass@1": 0.575114477786438,
233
+ "pass@2": 0.6221049912238239,
234
+ "pass@4": 0.6626993699150835,
235
+ "pass@8": 0.6981689197435018,
236
+ "pass@16": 0.7287409506013075,
237
+ "pass@32": 0.7546056580741782,
238
+ "pass@64": 0.7766700850622523,
239
+ "pass@128": 0.7956352299298519
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.6954083588957055,
244
+ "pass@2": 0.7170739789140622,
245
+ "pass@4": 0.7329163909150924,
246
+ "pass@8": 0.7477619068736169,
247
+ "pass@16": 0.7617628934452398,
248
+ "pass@32": 0.7746740516744463,
249
+ "pass@64": 0.7877749262392024,
250
+ "pass@128": 0.8006134969325154
251
+ },
252
+ "2": {
253
+ "pass@1": 0.9869395896656535,
254
+ "pass@2": 0.9929883265921545,
255
+ "pass@4": 0.9955688064637815,
256
+ "pass@8": 0.9969614600133562,
257
+ "pass@16": 0.9978973254755057,
258
+ "pass@32": 0.9987269274383682,
259
+ "pass@64": 0.9996290357273802,
260
+ "pass@128": 1.0
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9388494318181818,
264
+ "pass@2": 0.9576495764733951,
265
+ "pass@4": 0.9700690839781392,
266
+ "pass@8": 0.9792017114235083,
267
+ "pass@16": 0.9851169756005151,
268
+ "pass@32": 0.9888510307730042,
269
+ "pass@64": 0.9922342590379635,
270
+ "pass@128": 0.996969696969697
271
+ },
272
+ "4": {
273
+ "pass@1": 0.9231462647928994,
274
+ "pass@2": 0.9390877614965292,
275
+ "pass@4": 0.9471584942414742,
276
+ "pass@8": 0.9516894661683994,
277
+ "pass@16": 0.9552994076522564,
278
+ "pass@32": 0.958891828651015,
279
+ "pass@64": 0.9635868259368569,
280
+ "pass@128": 0.9704142011834319
281
+ },
282
+ "5": {
283
+ "pass@1": 0.773143115942029,
284
+ "pass@2": 0.7890758729887023,
285
+ "pass@4": 0.7981308879868274,
286
+ "pass@8": 0.8053525497479244,
287
+ "pass@16": 0.8126639880173377,
288
+ "pass@32": 0.8207655283254122,
289
+ "pass@64": 0.8286104178655256,
290
+ "pass@128": 0.8347826086956521
291
+ },
292
+ "6": {
293
+ "pass@1": 0.7913458094555874,
294
+ "pass@2": 0.8091837900187264,
295
+ "pass@4": 0.8204427986974405,
296
+ "pass@8": 0.8288401072601427,
297
+ "pass@16": 0.8348953079946777,
298
+ "pass@32": 0.83994109778685,
299
+ "pass@64": 0.844719198337771,
300
+ "pass@128": 0.8481375358166189
301
+ },
302
+ "7": {
303
+ "pass@1": 0.7280301661849711,
304
+ "pass@2": 0.7447068010104231,
305
+ "pass@4": 0.7566849998157742,
306
+ "pass@8": 0.768125478484118,
307
+ "pass@16": 0.7796628201212392,
308
+ "pass@32": 0.7896973555485508,
309
+ "pass@64": 0.7973812506567756,
310
+ "pass@128": 0.8034682080924855
311
+ },
312
+ "8": {
313
+ "pass@1": 0.6912632042253521,
314
+ "pass@2": 0.7211960740822889,
315
+ "pass@4": 0.7417804496268952,
316
+ "pass@8": 0.7603288659541085,
317
+ "pass@16": 0.7799359510901296,
318
+ "pass@32": 0.7985567000588119,
319
+ "pass@64": 0.8133141668091959,
320
+ "pass@128": 0.8253521126760563
321
+ },
322
+ "9": {
323
+ "pass@1": 0.6947043413173652,
324
+ "pass@2": 0.7243516166485926,
325
+ "pass@4": 0.7447599095958812,
326
+ "pass@8": 0.7611772608863101,
327
+ "pass@16": 0.7749424132577151,
328
+ "pass@32": 0.787756834877791,
329
+ "pass@64": 0.8009645563474614,
330
+ "pass@128": 0.8143712574850299
331
+ },
332
+ "11": {
333
+ "pass@1": 0.719761859939759,
334
+ "pass@2": 0.7545540182383076,
335
+ "pass@4": 0.7766598887112005,
336
+ "pass@8": 0.7958815814944958,
337
+ "pass@16": 0.8145204171314886,
338
+ "pass@32": 0.83108645177137,
339
+ "pass@64": 0.8461287735301839,
340
+ "pass@128": 0.8614457831325302
341
+ },
342
+ "12": {
343
+ "pass@1": 0.6426577194357367,
344
+ "pass@2": 0.6845044337620024,
345
+ "pass@4": 0.7144401497226636,
346
+ "pass@8": 0.7381820842468224,
347
+ "pass@16": 0.7587407212036311,
348
+ "pass@32": 0.7773578918155365,
349
+ "pass@64": 0.7949070026169126,
350
+ "pass@128": 0.8087774294670846
351
+ },
352
+ "13": {
353
+ "pass@1": 0.5179227941176471,
354
+ "pass@2": 0.592116472573281,
355
+ "pass@4": 0.6527041089401636,
356
+ "pass@8": 0.7051737089817524,
357
+ "pass@16": 0.7505252952001717,
358
+ "pass@32": 0.7862346164756925,
359
+ "pass@64": 0.8145135669391687,
360
+ "pass@128": 0.8403361344537815
361
+ },
362
+ "14": {
363
+ "pass@1": 0.5042489035087719,
364
+ "pass@2": 0.5965203671087165,
365
+ "pass@4": 0.6717821086508918,
366
+ "pass@8": 0.731039743629001,
367
+ "pass@16": 0.7764892779355719,
368
+ "pass@32": 0.8115057709727133,
369
+ "pass@64": 0.8394287056389972,
370
+ "pass@128": 0.8567251461988304
371
+ },
372
+ "15": {
373
+ "pass@1": 0.3880208333333333,
374
+ "pass@2": 0.4910850632307325,
375
+ "pass@4": 0.5783466799604597,
376
+ "pass@8": 0.652028689156891,
377
+ "pass@16": 0.7147778441388816,
378
+ "pass@32": 0.7676559272017957,
379
+ "pass@64": 0.810757437605825,
380
+ "pass@128": 0.8454545454545455
381
+ },
382
+ "16": {
383
+ "pass@1": 0.27212428774928776,
384
+ "pass@2": 0.37392987134620964,
385
+ "pass@4": 0.4669545561612491,
386
+ "pass@8": 0.5448438968632648,
387
+ "pass@16": 0.6103403097484277,
388
+ "pass@32": 0.6673280227215023,
389
+ "pass@64": 0.7148452194035275,
390
+ "pass@128": 0.7492877492877493
391
+ },
392
+ "17": {
393
+ "pass@1": 0.21037946428571427,
394
+ "pass@2": 0.294130862718247,
395
+ "pass@4": 0.3831649325084362,
396
+ "pass@8": 0.46734675329115166,
397
+ "pass@16": 0.5396657014484697,
398
+ "pass@32": 0.5969152996425363,
399
+ "pass@64": 0.6389955885732296,
400
+ "pass@128": 0.6739130434782609
401
+ },
402
+ "18": {
403
+ "pass@1": 0.1936810661764706,
404
+ "pass@2": 0.2662510132005558,
405
+ "pass@4": 0.34283214588985195,
406
+ "pass@8": 0.415028674038425,
407
+ "pass@16": 0.47770510724170956,
408
+ "pass@32": 0.5320951966458943,
409
+ "pass@64": 0.5805753034657143,
410
+ "pass@128": 0.6235294117647059
411
+ },
412
+ "19": {
413
+ "pass@1": 0.12307012648809523,
414
+ "pass@2": 0.174551301204537,
415
+ "pass@4": 0.23128027188565717,
416
+ "pass@8": 0.2887166315698561,
417
+ "pass@16": 0.3430794574693393,
418
+ "pass@32": 0.3911214036223261,
419
+ "pass@64": 0.43416213016969346,
420
+ "pass@128": 0.47619047619047616
421
+ },
422
+ "20": {
423
+ "pass@1": 0.13185348053892215,
424
+ "pass@2": 0.19517583926634913,
425
+ "pass@4": 0.26337315666754224,
426
+ "pass@8": 0.32530800932044945,
427
+ "pass@16": 0.37575661954220857,
428
+ "pass@32": 0.41584968083444784,
429
+ "pass@64": 0.45164321538822744,
430
+ "pass@128": 0.48502994011976047
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 461269,
437
+ "answer_accuracy": 0.5757571596900464,
438
+ "avg_response_len": 295.4375224676466,
439
+ "resp_tokens_sum": 236690362,
440
+ "pass_at_k": {
441
+ "pass@1": 0.5757571596900464,
442
+ "pass@2": 0.6253407494782381,
443
+ "pass@4": 0.6677879306816599,
444
+ "pass@8": 0.7037064898603441,
445
+ "pass@16": 0.7339471954953904,
446
+ "pass@32": 0.7598035729171354,
447
+ "pass@64": 0.7824824890408728,
448
+ "pass@128": 0.8025243649145231
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.6960354477611941,
453
+ "pass@2": 0.7238379950640498,
454
+ "pass@4": 0.7423029629691805,
455
+ "pass@8": 0.7576169957553247,
456
+ "pass@16": 0.7726389852880216,
457
+ "pass@32": 0.7863790210748294,
458
+ "pass@64": 0.7994778779127665,
459
+ "pass@128": 0.8149253731343283
460
+ },
461
+ "2": {
462
+ "pass@1": 0.9747544642857143,
463
+ "pass@2": 0.9834810883014625,
464
+ "pass@4": 0.9882808693556165,
465
+ "pass@8": 0.9909076205852885,
466
+ "pass@16": 0.9917476146105553,
467
+ "pass@32": 0.9921427799664233,
468
+ "pass@64": 0.9928571428571391,
469
+ "pass@128": 0.9942857142857143
470
+ },
471
+ "3": {
472
+ "pass@1": 0.9504828717201166,
473
+ "pass@2": 0.9693805812538737,
474
+ "pass@4": 0.9795335058336364,
475
+ "pass@8": 0.9853107407409318,
476
+ "pass@16": 0.9895631581379157,
477
+ "pass@32": 0.9928231863043651,
478
+ "pass@64": 0.9952751458679432,
479
+ "pass@128": 0.9970845481049563
480
+ },
481
+ "4": {
482
+ "pass@1": 0.9078262061403509,
483
+ "pass@2": 0.9193186789151357,
484
+ "pass@4": 0.9287385326834146,
485
+ "pass@8": 0.9361250054268393,
486
+ "pass@16": 0.9400296541281903,
487
+ "pass@32": 0.9412396935692159,
488
+ "pass@64": 0.9415114151979437,
489
+ "pass@128": 0.9415204678362573
490
+ },
491
+ "5": {
492
+ "pass@1": 0.7563419117647059,
493
+ "pass@2": 0.7814931681333954,
494
+ "pass@4": 0.7967286588257347,
495
+ "pass@8": 0.8070400369112668,
496
+ "pass@16": 0.8144193388363633,
497
+ "pass@32": 0.8208420255625952,
498
+ "pass@64": 0.8274708458398427,
499
+ "pass@128": 0.8323529411764706
500
+ },
501
+ "6": {
502
+ "pass@1": 0.7924881703470031,
503
+ "pass@2": 0.8193792847562037,
504
+ "pass@4": 0.8383779743423239,
505
+ "pass@8": 0.852569147899649,
506
+ "pass@16": 0.8620630820365194,
507
+ "pass@32": 0.8678772726237286,
508
+ "pass@64": 0.871323340222345,
509
+ "pass@128": 0.8738170347003155
510
+ },
511
+ "7": {
512
+ "pass@1": 0.6859177215189873,
513
+ "pass@2": 0.7062159716684938,
514
+ "pass@4": 0.7212405864219503,
515
+ "pass@8": 0.732065631859019,
516
+ "pass@16": 0.7404568279563857,
517
+ "pass@32": 0.7478833720913393,
518
+ "pass@64": 0.7545295063099178,
519
+ "pass@128": 0.759493670886076
520
+ },
521
+ "8": {
522
+ "pass@1": 0.7048376501501501,
523
+ "pass@2": 0.7349794430257027,
524
+ "pass@4": 0.7565591801024869,
525
+ "pass@8": 0.7736097281322789,
526
+ "pass@16": 0.7884783753864796,
527
+ "pass@32": 0.8015966774787675,
528
+ "pass@64": 0.8119617421409818,
529
+ "pass@128": 0.8198198198198198
530
+ },
531
+ "9": {
532
+ "pass@1": 0.6833048633440515,
533
+ "pass@2": 0.7121656391624681,
534
+ "pass@4": 0.7305123864139167,
535
+ "pass@8": 0.7459425734694044,
536
+ "pass@16": 0.760025552880257,
537
+ "pass@32": 0.7718879767534061,
538
+ "pass@64": 0.7796528337298139,
539
+ "pass@128": 0.7845659163987139
540
+ },
541
+ "11": {
542
+ "pass@1": 0.6568452380952381,
543
+ "pass@2": 0.7056821022372203,
544
+ "pass@4": 0.7431196210592722,
545
+ "pass@8": 0.7705931577714318,
546
+ "pass@16": 0.79038056488924,
547
+ "pass@32": 0.8084641334754845,
548
+ "pass@64": 0.8274574489507331,
549
+ "pass@128": 0.8476190476190476
550
+ },
551
+ "12": {
552
+ "pass@1": 0.6635607798165137,
553
+ "pass@2": 0.7084574935587181,
554
+ "pass@4": 0.7437457230116872,
555
+ "pass@8": 0.7729424088332045,
556
+ "pass@16": 0.7969976917080968,
557
+ "pass@32": 0.8164971474877366,
558
+ "pass@64": 0.835704647252489,
559
+ "pass@128": 0.8593272171253823
560
+ },
561
+ "13": {
562
+ "pass@1": 0.5529996141975309,
563
+ "pass@2": 0.6263772692475942,
564
+ "pass@4": 0.6793599344642102,
565
+ "pass@8": 0.7195496215300607,
566
+ "pass@16": 0.7548327336564407,
567
+ "pass@32": 0.7890015797359309,
568
+ "pass@64": 0.8235018610625873,
569
+ "pass@128": 0.8549382716049383
570
+ },
571
+ "14": {
572
+ "pass@1": 0.4823813056379822,
573
+ "pass@2": 0.5738948339914481,
574
+ "pass@4": 0.6444869272646553,
575
+ "pass@8": 0.6972942761680696,
576
+ "pass@16": 0.7395782537628437,
577
+ "pass@32": 0.775611194879585,
578
+ "pass@64": 0.8055311048866189,
579
+ "pass@128": 0.827893175074184
580
+ },
581
+ "15": {
582
+ "pass@1": 0.4196807484567901,
583
+ "pass@2": 0.5195058083017399,
584
+ "pass@4": 0.6036365474570303,
585
+ "pass@8": 0.6746719455491015,
586
+ "pass@16": 0.7341197467832548,
587
+ "pass@32": 0.7805278247535845,
588
+ "pass@64": 0.8135251080800728,
589
+ "pass@128": 0.8364197530864198
590
+ },
591
+ "16": {
592
+ "pass@1": 0.31789269911504425,
593
+ "pass@2": 0.42899848732957047,
594
+ "pass@4": 0.5372952689542123,
595
+ "pass@8": 0.6288929476048137,
596
+ "pass@16": 0.6958904288850537,
597
+ "pass@32": 0.7441631561971844,
598
+ "pass@64": 0.7828683092822873,
599
+ "pass@128": 0.8171091445427728
600
+ },
601
+ "17": {
602
+ "pass@1": 0.21110222138554216,
603
+ "pass@2": 0.2928724000332035,
604
+ "pass@4": 0.3764271286495813,
605
+ "pass@8": 0.45583031118438067,
606
+ "pass@16": 0.5288069128891959,
607
+ "pass@32": 0.5950390473854048,
608
+ "pass@64": 0.6539334718972685,
609
+ "pass@128": 0.7018072289156626
610
+ },
611
+ "18": {
612
+ "pass@1": 0.18515625,
613
+ "pass@2": 0.2632278702057403,
614
+ "pass@4": 0.3424678979643676,
615
+ "pass@8": 0.41591608139508307,
616
+ "pass@16": 0.48108409580956335,
617
+ "pass@32": 0.5383369439239621,
618
+ "pass@64": 0.589541064336965,
619
+ "pass@128": 0.6387096774193548
620
+ },
621
+ "19": {
622
+ "pass@1": 0.11407194108761329,
623
+ "pass@2": 0.16886165758736352,
624
+ "pass@4": 0.23095301757975129,
625
+ "pass@8": 0.29505347686633454,
626
+ "pass@16": 0.35727112677654543,
627
+ "pass@32": 0.41468769168700353,
628
+ "pass@64": 0.46779849325669914,
629
+ "pass@128": 0.5196374622356495
630
+ },
631
+ "20": {
632
+ "pass@1": 0.13778622372372373,
633
+ "pass@2": 0.20051104253860164,
634
+ "pass@4": 0.26402179429147926,
635
+ "pass@8": 0.3208415663337511,
636
+ "pass@16": 0.3715229105982221,
637
+ "pass@32": 0.41867352679412273,
638
+ "pass@64": 0.4628762515726032,
639
+ "pass@128": 0.4984984984984985
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]