ZachW commited on
Commit
4f37c12
·
verified ·
1 Parent(s): 655ba99

Upload extrapolation artifact: 020305 RL OP13-20 step200 summary JSON

Browse files
020305/evals/rl_ckpt18809_op13_20_step200_merged_hf/summary.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "checkpoint": "rl_ckpt18809_op13_20_step200_merged_hf",
4
+ "id_acc": 0.6831440972222222,
5
+ "ood_acc": 0.28934609375,
6
+ "total_acc": 0.47588199013157895,
7
+ "id_avg_loss": 0.0,
8
+ "ood_avg_loss": 0.0,
9
+ "total_avg_loss": 0.0,
10
+ "id_avg_resp_len": 199.82384895833334,
11
+ "ood_avg_resp_len": 313.83307109375,
12
+ "count_id": 1152000,
13
+ "count_ood": 1280000,
14
+ "count_total": 2432000,
15
+ "template_metrics": {
16
+ "crazy_zootopia": {
17
+ "count": 809728,
18
+ "correct": 381241,
19
+ "answer_accuracy": 0.47082600576983874,
20
+ "avg_response_len": 248.62063680643377,
21
+ "resp_tokens_sum": 201315091,
22
+ "pass_at_k": {
23
+ "pass@1": 0.47082600576983874,
24
+ "pass@2": 0.5420628659438301,
25
+ "pass@4": 0.60205425237215,
26
+ "pass@8": 0.651081216510764,
27
+ "pass@16": 0.6908459763141861,
28
+ "pass@32": 0.7243716711064014,
29
+ "pass@64": 0.7542292077612036,
30
+ "pass@128": 0.7809042048687954
31
+ },
32
+ "per_op_pass_at_k": {
33
+ "10": {
34
+ "pass@1": 0.5741380899705014,
35
+ "pass@2": 0.6374345283720061,
36
+ "pass@4": 0.6877484625815574,
37
+ "pass@8": 0.7339820506256319,
38
+ "pass@16": 0.7768820473639336,
39
+ "pass@32": 0.8134513625208626,
40
+ "pass@64": 0.8442222274966321,
41
+ "pass@128": 0.8672566371681416
42
+ },
43
+ "2": {
44
+ "pass@1": 0.9447770638629284,
45
+ "pass@2": 0.9496820344886795,
46
+ "pass@4": 0.9534258314089241,
47
+ "pass@8": 0.9564988072518206,
48
+ "pass@16": 0.9596533365254536,
49
+ "pass@32": 0.9640128309589705,
50
+ "pass@64": 0.9696471858423932,
51
+ "pass@128": 0.9750778816199377
52
+ },
53
+ "3": {
54
+ "pass@1": 0.890075496941896,
55
+ "pass@2": 0.9153731428640232,
56
+ "pass@4": 0.9288290752646745,
57
+ "pass@8": 0.9363709567903885,
58
+ "pass@16": 0.9418395773507783,
59
+ "pass@32": 0.9473595562005767,
60
+ "pass@64": 0.9545467492115126,
61
+ "pass@128": 0.963302752293578
62
+ },
63
+ "4": {
64
+ "pass@1": 0.7752197265625,
65
+ "pass@2": 0.8222317913385826,
66
+ "pass@4": 0.8546887019005436,
67
+ "pass@8": 0.8798078050264433,
68
+ "pass@16": 0.8987486358045697,
69
+ "pass@32": 0.9141457607856986,
70
+ "pass@64": 0.9275849795438009,
71
+ "pass@128": 0.940625
72
+ },
73
+ "5": {
74
+ "pass@1": 0.5919642857142857,
75
+ "pass@2": 0.6483459098862642,
76
+ "pass@4": 0.6903727599526247,
77
+ "pass@8": 0.721324081648959,
78
+ "pass@16": 0.7452422640151924,
79
+ "pass@32": 0.7649371701462218,
80
+ "pass@64": 0.784241095420447,
81
+ "pass@128": 0.8063492063492064
82
+ },
83
+ "6": {
84
+ "pass@1": 0.6101936751497006,
85
+ "pass@2": 0.6852625948889624,
86
+ "pass@4": 0.737672784633208,
87
+ "pass@8": 0.772938922756174,
88
+ "pass@16": 0.798958840272014,
89
+ "pass@32": 0.8201741899475089,
90
+ "pass@64": 0.8383901021445377,
91
+ "pass@128": 0.8532934131736527
92
+ },
93
+ "7": {
94
+ "pass@1": 0.6123104659763313,
95
+ "pass@2": 0.6833205691189485,
96
+ "pass@4": 0.7293244864362364,
97
+ "pass@8": 0.7616322923990702,
98
+ "pass@16": 0.7878927447570453,
99
+ "pass@32": 0.8115178358283376,
100
+ "pass@64": 0.8346118917446502,
101
+ "pass@128": 0.8579881656804734
102
+ },
103
+ "8": {
104
+ "pass@1": 0.5609475160256411,
105
+ "pass@2": 0.6446952919947505,
106
+ "pass@4": 0.7031014176112595,
107
+ "pass@8": 0.7419600517349403,
108
+ "pass@16": 0.7673220278771473,
109
+ "pass@32": 0.7887273838182889,
110
+ "pass@64": 0.8099674098488452,
111
+ "pass@128": 0.8269230769230769
112
+ },
113
+ "9": {
114
+ "pass@1": 0.5545994718309859,
115
+ "pass@2": 0.6576068121326386,
116
+ "pass@4": 0.7359780795006251,
117
+ "pass@8": 0.790439971280655,
118
+ "pass@16": 0.8279563910100225,
119
+ "pass@32": 0.8539518807147877,
120
+ "pass@64": 0.8742415789463832,
121
+ "pass@128": 0.8929577464788733
122
+ },
123
+ "11": {
124
+ "pass@1": 0.5319360835694051,
125
+ "pass@2": 0.6215784696973076,
126
+ "pass@4": 0.6907830577480926,
127
+ "pass@8": 0.7432213329841176,
128
+ "pass@16": 0.7828037516289943,
129
+ "pass@32": 0.8150725689730364,
130
+ "pass@64": 0.8445493457746914,
131
+ "pass@128": 0.8725212464589235
132
+ },
133
+ "12": {
134
+ "pass@1": 0.519332627118644,
135
+ "pass@2": 0.6027417256105698,
136
+ "pass@4": 0.6637228021285474,
137
+ "pass@8": 0.7114096130410679,
138
+ "pass@16": 0.7524092343759183,
139
+ "pass@32": 0.7890026535707286,
140
+ "pass@64": 0.8212713564382537,
141
+ "pass@128": 0.847457627118644
142
+ },
143
+ "13": {
144
+ "pass@1": 0.4448961598746082,
145
+ "pass@2": 0.5568930034803646,
146
+ "pass@4": 0.6451671588661135,
147
+ "pass@8": 0.7110854193688476,
148
+ "pass@16": 0.7608013473487977,
149
+ "pass@32": 0.8014909701103228,
150
+ "pass@64": 0.8384952651641907,
151
+ "pass@128": 0.8683385579937304
152
+ },
153
+ "14": {
154
+ "pass@1": 0.34197332554517135,
155
+ "pass@2": 0.4501220349792721,
156
+ "pass@4": 0.5494017024157026,
157
+ "pass@8": 0.6321989976492106,
158
+ "pass@16": 0.6955289358403063,
159
+ "pass@32": 0.7459415528358541,
160
+ "pass@64": 0.7887735797886692,
161
+ "pass@128": 0.822429906542056
162
+ },
163
+ "15": {
164
+ "pass@1": 0.23803287572254336,
165
+ "pass@2": 0.33669275692958894,
166
+ "pass@4": 0.44012880236068747,
167
+ "pass@8": 0.5341238336228396,
168
+ "pass@16": 0.6110083221314118,
169
+ "pass@32": 0.6745370889577138,
170
+ "pass@64": 0.7290513406818961,
171
+ "pass@128": 0.7745664739884393
172
+ },
173
+ "16": {
174
+ "pass@1": 0.20163810483870967,
175
+ "pass@2": 0.2788862077724155,
176
+ "pass@4": 0.3585027432054865,
177
+ "pass@8": 0.43076881842449627,
178
+ "pass@16": 0.4919829537899595,
179
+ "pass@32": 0.5441670943646694,
180
+ "pass@64": 0.5902012441068575,
181
+ "pass@128": 0.6290322580645161
182
+ },
183
+ "17": {
184
+ "pass@1": 0.156882225433526,
185
+ "pass@2": 0.21556575997906322,
186
+ "pass@4": 0.2771691409780425,
187
+ "pass@8": 0.341674925379861,
188
+ "pass@16": 0.4072087355948067,
189
+ "pass@32": 0.4670126441556912,
190
+ "pass@64": 0.5169342900561144,
191
+ "pass@128": 0.5606936416184971
192
+ },
193
+ "18": {
194
+ "pass@1": 0.14910714285714285,
195
+ "pass@2": 0.21308176321709787,
196
+ "pass@4": 0.280601617654936,
197
+ "pass@8": 0.34355741540217244,
198
+ "pass@16": 0.3985258710428493,
199
+ "pass@32": 0.4461388543379518,
200
+ "pass@64": 0.4872909465164243,
201
+ "pass@128": 0.5285714285714286
202
+ },
203
+ "19": {
204
+ "pass@1": 0.14057807807807807,
205
+ "pass@2": 0.20221685760563707,
206
+ "pass@4": 0.2649557811467261,
207
+ "pass@8": 0.3198520926064229,
208
+ "pass@16": 0.365459672897077,
209
+ "pass@32": 0.4061949642563818,
210
+ "pass@64": 0.44616338763451124,
211
+ "pass@128": 0.4864864864864865
212
+ },
213
+ "20": {
214
+ "pass@1": 0.15261355105105104,
215
+ "pass@2": 0.2182194497647254,
216
+ "pass@4": 0.2835954342981902,
217
+ "pass@8": 0.33920423135788597,
218
+ "pass@16": 0.3826292663379262,
219
+ "pass@32": 0.41802288691041456,
220
+ "pass@64": 0.4501180597103666,
221
+ "pass@128": 0.4804804804804805
222
+ }
223
+ }
224
+ },
225
+ "teachers_in_school": {
226
+ "count": 821120,
227
+ "correct": 385295,
228
+ "answer_accuracy": 0.46923105027279816,
229
+ "avg_response_len": 256.39123148869834,
230
+ "resp_tokens_sum": 210527968,
231
+ "pass_at_k": {
232
+ "pass@1": 0.46923105027279816,
233
+ "pass@2": 0.537744087583857,
234
+ "pass@4": 0.5969630008787917,
235
+ "pass@8": 0.646551698886574,
236
+ "pass@16": 0.6869019578091474,
237
+ "pass@32": 0.720059532777375,
238
+ "pass@64": 0.7484124289105339,
239
+ "pass@128": 0.7730319563522993
240
+ },
241
+ "per_op_pass_at_k": {
242
+ "10": {
243
+ "pass@1": 0.6025929831288344,
244
+ "pass@2": 0.6655788820588381,
245
+ "pass@4": 0.712638290708293,
246
+ "pass@8": 0.7520765879868826,
247
+ "pass@16": 0.7863821934536588,
248
+ "pass@32": 0.8153207950273516,
249
+ "pass@64": 0.8387030964952171,
250
+ "pass@128": 0.8588957055214724
251
+ },
252
+ "2": {
253
+ "pass@1": 0.9505841565349544,
254
+ "pass@2": 0.9532843052198261,
255
+ "pass@4": 0.9558882856208325,
256
+ "pass@8": 0.9587953989382784,
257
+ "pass@16": 0.961782530755302,
258
+ "pass@32": 0.9643643890269245,
259
+ "pass@64": 0.9665359573547208,
260
+ "pass@128": 0.9696048632218845
261
+ },
262
+ "3": {
263
+ "pass@1": 0.9034327651515152,
264
+ "pass@2": 0.9192156555714627,
265
+ "pass@4": 0.9302861139516647,
266
+ "pass@8": 0.9386739269294071,
267
+ "pass@16": 0.9438559355563287,
268
+ "pass@32": 0.9468557193564537,
269
+ "pass@64": 0.9492044725881807,
270
+ "pass@128": 0.9515151515151515
271
+ },
272
+ "4": {
273
+ "pass@1": 0.7489367603550295,
274
+ "pass@2": 0.7910608518147509,
275
+ "pass@4": 0.8231998353201413,
276
+ "pass@8": 0.8477757288644923,
277
+ "pass@16": 0.8653097885880157,
278
+ "pass@32": 0.877466942076976,
279
+ "pass@64": 0.8870172256269219,
280
+ "pass@128": 0.893491124260355
281
+ },
282
+ "5": {
283
+ "pass@1": 0.6153532608695652,
284
+ "pass@2": 0.6656110920917495,
285
+ "pass@4": 0.7047145457361306,
286
+ "pass@8": 0.734960864574528,
287
+ "pass@16": 0.7579012844461602,
288
+ "pass@32": 0.7753412883276696,
289
+ "pass@64": 0.7880631576774196,
290
+ "pass@128": 0.8
291
+ },
292
+ "6": {
293
+ "pass@1": 0.6086138968481375,
294
+ "pass@2": 0.6848056454887982,
295
+ "pass@4": 0.7375910427027563,
296
+ "pass@8": 0.7741764834993599,
297
+ "pass@16": 0.8002319395512839,
298
+ "pass@32": 0.8218286879890876,
299
+ "pass@64": 0.8432342376670118,
300
+ "pass@128": 0.8653295128939829
301
+ },
302
+ "7": {
303
+ "pass@1": 0.603888186416185,
304
+ "pass@2": 0.6690694551909333,
305
+ "pass@4": 0.7135883215103886,
306
+ "pass@8": 0.7469629249550308,
307
+ "pass@16": 0.7763369658056625,
308
+ "pass@32": 0.8021818464035171,
309
+ "pass@64": 0.8246229458789898,
310
+ "pass@128": 0.8439306358381503
311
+ },
312
+ "8": {
313
+ "pass@1": 0.5481294014084507,
314
+ "pass@2": 0.6296779693911498,
315
+ "pass@4": 0.6941487652951831,
316
+ "pass@8": 0.7432917081970493,
317
+ "pass@16": 0.7800826825934518,
318
+ "pass@32": 0.8083199455882679,
319
+ "pass@64": 0.8310643932196761,
320
+ "pass@128": 0.8507042253521127
321
+ },
322
+ "9": {
323
+ "pass@1": 0.5193207335329342,
324
+ "pass@2": 0.6124250023574895,
325
+ "pass@4": 0.6825153814979706,
326
+ "pass@8": 0.7339480753308065,
327
+ "pass@16": 0.7732788025060358,
328
+ "pass@32": 0.8077219918528098,
329
+ "pass@64": 0.8375948255424386,
330
+ "pass@128": 0.8622754491017964
331
+ },
332
+ "11": {
333
+ "pass@1": 0.5750894201807228,
334
+ "pass@2": 0.6621766346883593,
335
+ "pass@4": 0.7284196917026932,
336
+ "pass@8": 0.7780922038504625,
337
+ "pass@16": 0.813405098694823,
338
+ "pass@32": 0.8392815462756775,
339
+ "pass@64": 0.8604137867079064,
340
+ "pass@128": 0.8765060240963856
341
+ },
342
+ "12": {
343
+ "pass@1": 0.5449647335423198,
344
+ "pass@2": 0.6343681349196552,
345
+ "pass@4": 0.7027254673103162,
346
+ "pass@8": 0.7573112125137871,
347
+ "pass@16": 0.7986891262756064,
348
+ "pass@32": 0.8283058253225973,
349
+ "pass@64": 0.8514306286603033,
350
+ "pass@128": 0.8714733542319749
351
+ },
352
+ "13": {
353
+ "pass@1": 0.41474089635854344,
354
+ "pass@2": 0.5216235608416595,
355
+ "pass@4": 0.609166683208716,
356
+ "pass@8": 0.6811120686409082,
357
+ "pass@16": 0.7386794715073752,
358
+ "pass@32": 0.7834822105451329,
359
+ "pass@64": 0.8176940029791813,
360
+ "pass@128": 0.8403361344537815
361
+ },
362
+ "14": {
363
+ "pass@1": 0.31992415935672514,
364
+ "pass@2": 0.4319049448588662,
365
+ "pass@4": 0.5384300460249487,
366
+ "pass@8": 0.6301912311847001,
367
+ "pass@16": 0.7053491688109808,
368
+ "pass@32": 0.7645782124873614,
369
+ "pass@64": 0.8085707748135609,
370
+ "pass@128": 0.8391812865497076
371
+ },
372
+ "15": {
373
+ "pass@1": 0.2126657196969697,
374
+ "pass@2": 0.30765442316869457,
375
+ "pass@4": 0.40781750747065687,
376
+ "pass@8": 0.49642400822735633,
377
+ "pass@16": 0.5680396411962745,
378
+ "pass@32": 0.626610399902073,
379
+ "pass@64": 0.676446573867005,
380
+ "pass@128": 0.7212121212121212
381
+ },
382
+ "16": {
383
+ "pass@1": 0.15422453703703703,
384
+ "pass@2": 0.2157730584157749,
385
+ "pass@4": 0.2825862648579184,
386
+ "pass@8": 0.350729859385697,
387
+ "pass@16": 0.41576288513575577,
388
+ "pass@32": 0.4756244133047699,
389
+ "pass@64": 0.5334865753499802,
390
+ "pass@128": 0.5868945868945868
391
+ },
392
+ "17": {
393
+ "pass@1": 0.1774310947204969,
394
+ "pass@2": 0.24994039467892606,
395
+ "pass@4": 0.32356567764045,
396
+ "pass@8": 0.39138325498864096,
397
+ "pass@16": 0.4512251459100479,
398
+ "pass@32": 0.5049210552230611,
399
+ "pass@64": 0.5575395956365649,
400
+ "pass@128": 0.6086956521739131
401
+ },
402
+ "18": {
403
+ "pass@1": 0.1604779411764706,
404
+ "pass@2": 0.2271639069013432,
405
+ "pass@4": 0.29349490863274436,
406
+ "pass@8": 0.35195918625723943,
407
+ "pass@16": 0.4028748773367787,
408
+ "pass@32": 0.44786918936674186,
409
+ "pass@64": 0.4874247416201932,
410
+ "pass@128": 0.5264705882352941
411
+ },
412
+ "19": {
413
+ "pass@1": 0.13846261160714285,
414
+ "pass@2": 0.19192473987626552,
415
+ "pass@4": 0.24761419108325744,
416
+ "pass@8": 0.3012326120456533,
417
+ "pass@16": 0.3485993171013056,
418
+ "pass@32": 0.38909940621048456,
419
+ "pass@64": 0.4246445731793099,
420
+ "pass@128": 0.45535714285714285
421
+ },
422
+ "20": {
423
+ "pass@1": 0.12930389221556887,
424
+ "pass@2": 0.1930537301381488,
425
+ "pass@4": 0.26072267753581696,
426
+ "pass@8": 0.32056687148160085,
427
+ "pass@16": 0.36709700781450916,
428
+ "pass@32": 0.4044418838960831,
429
+ "pass@64": 0.4377505306516329,
430
+ "pass@128": 0.46706586826347307
431
+ }
432
+ }
433
+ },
434
+ "movie_festival_awards": {
435
+ "count": 801152,
436
+ "correct": 390809,
437
+ "answer_accuracy": 0.4878088053203387,
438
+ "avg_response_len": 274.67989345342704,
439
+ "resp_tokens_sum": 220060346,
440
+ "pass_at_k": {
441
+ "pass@1": 0.4878088053203387,
442
+ "pass@2": 0.5543622105428079,
443
+ "pass@4": 0.6110727703213531,
444
+ "pass@8": 0.6581146455552732,
445
+ "pass@16": 0.6963855810057189,
446
+ "pass@32": 0.728310310639796,
447
+ "pass@64": 0.7563010233507497,
448
+ "pass@128": 0.7823933535708579
449
+ },
450
+ "per_op_pass_at_k": {
451
+ "10": {
452
+ "pass@1": 0.5937966417910447,
453
+ "pass@2": 0.6551361058878838,
454
+ "pass@4": 0.7051956306767619,
455
+ "pass@8": 0.7468369195114555,
456
+ "pass@16": 0.7804752311309393,
457
+ "pass@32": 0.8087134368953917,
458
+ "pass@64": 0.8337175398407523,
459
+ "pass@128": 0.8567164179104477
460
+ },
461
+ "2": {
462
+ "pass@1": 0.9383258928571429,
463
+ "pass@2": 0.9434167604049495,
464
+ "pass@4": 0.94656041726927,
465
+ "pass@8": 0.9493516710403994,
466
+ "pass@16": 0.9522428421965253,
467
+ "pass@32": 0.9551417367243559,
468
+ "pass@64": 0.9585785148501862,
469
+ "pass@128": 0.9628571428571429
470
+ },
471
+ "3": {
472
+ "pass@1": 0.9290041909620991,
473
+ "pass@2": 0.9421074039852161,
474
+ "pass@4": 0.9482759917400994,
475
+ "pass@8": 0.9517019733337934,
476
+ "pass@16": 0.9544241083697254,
477
+ "pass@32": 0.9571684872177765,
478
+ "pass@64": 0.9597425063031881,
479
+ "pass@128": 0.9620991253644315
480
+ },
481
+ "4": {
482
+ "pass@1": 0.78812591374269,
483
+ "pass@2": 0.8241577738637934,
484
+ "pass@4": 0.852643570047165,
485
+ "pass@8": 0.8747651744721673,
486
+ "pass@16": 0.8891099109783571,
487
+ "pass@32": 0.8973778497351624,
488
+ "pass@64": 0.9027188391175657,
489
+ "pass@128": 0.9064327485380117
490
+ },
491
+ "5": {
492
+ "pass@1": 0.63125,
493
+ "pass@2": 0.6775536272579896,
494
+ "pass@4": 0.7143841425152739,
495
+ "pass@8": 0.7485260162723093,
496
+ "pass@16": 0.7803454382627247,
497
+ "pass@32": 0.807788639056809,
498
+ "pass@64": 0.8313754642783288,
499
+ "pass@128": 0.8558823529411764
500
+ },
501
+ "6": {
502
+ "pass@1": 0.6381851340694006,
503
+ "pass@2": 0.7121715020243922,
504
+ "pass@4": 0.762374902269708,
505
+ "pass@8": 0.7922977576259308,
506
+ "pass@16": 0.8089222960611702,
507
+ "pass@32": 0.8209672814519965,
508
+ "pass@64": 0.8330832507873658,
509
+ "pass@128": 0.8485804416403786
510
+ },
511
+ "7": {
512
+ "pass@1": 0.586209454113924,
513
+ "pass@2": 0.6469638474284858,
514
+ "pass@4": 0.6919879344591413,
515
+ "pass@8": 0.7262357119718345,
516
+ "pass@16": 0.7534570153581185,
517
+ "pass@32": 0.7767155482073544,
518
+ "pass@64": 0.7974375799700597,
519
+ "pass@128": 0.8164556962025317
520
+ },
521
+ "8": {
522
+ "pass@1": 0.5848817567567568,
523
+ "pass@2": 0.6611343134473057,
524
+ "pass@4": 0.7184318649358015,
525
+ "pass@8": 0.760785210854063,
526
+ "pass@16": 0.792235311124261,
527
+ "pass@32": 0.817320900160503,
528
+ "pass@64": 0.840135828610614,
529
+ "pass@128": 0.8588588588588588
530
+ },
531
+ "9": {
532
+ "pass@1": 0.5386605707395499,
533
+ "pass@2": 0.623377250170899,
534
+ "pass@4": 0.690221168093538,
535
+ "pass@8": 0.7437001781767524,
536
+ "pass@16": 0.785990838389334,
537
+ "pass@32": 0.8204628776025612,
538
+ "pass@64": 0.8473274870019281,
539
+ "pass@128": 0.8681672025723473
540
+ },
541
+ "11": {
542
+ "pass@1": 0.5563988095238095,
543
+ "pass@2": 0.6334466004249469,
544
+ "pass@4": 0.6941237378065835,
545
+ "pass@8": 0.7429034659555144,
546
+ "pass@16": 0.7827518992619408,
547
+ "pass@32": 0.8154297168836708,
548
+ "pass@64": 0.8419106667537043,
549
+ "pass@128": 0.8603174603174604
550
+ },
551
+ "12": {
552
+ "pass@1": 0.5823776758409785,
553
+ "pass@2": 0.6666839738495992,
554
+ "pass@4": 0.7254627030566131,
555
+ "pass@8": 0.7695897334090223,
556
+ "pass@16": 0.8047491960850638,
557
+ "pass@32": 0.834408106008233,
558
+ "pass@64": 0.8606880098450249,
559
+ "pass@128": 0.8837920489296636
560
+ },
561
+ "13": {
562
+ "pass@1": 0.4772135416666667,
563
+ "pass@2": 0.5970475478759603,
564
+ "pass@4": 0.6904258828178885,
565
+ "pass@8": 0.7572986267977532,
566
+ "pass@16": 0.8032741648980943,
567
+ "pass@32": 0.8354083891204626,
568
+ "pass@64": 0.8585825436762666,
569
+ "pass@128": 0.8765432098765432
570
+ },
571
+ "14": {
572
+ "pass@1": 0.3507047477744807,
573
+ "pass@2": 0.4661104815533072,
574
+ "pass@4": 0.5706216789666868,
575
+ "pass@8": 0.6573077164830237,
576
+ "pass@16": 0.7214616991407049,
577
+ "pass@32": 0.7662439064344672,
578
+ "pass@64": 0.799782035575084,
579
+ "pass@128": 0.8308605341246291
580
+ },
581
+ "15": {
582
+ "pass@1": 0.2552806712962963,
583
+ "pass@2": 0.36104465891416354,
584
+ "pass@4": 0.4626344218546755,
585
+ "pass@8": 0.5513210557967552,
586
+ "pass@16": 0.6246323075214912,
587
+ "pass@32": 0.6817829884376061,
588
+ "pass@64": 0.7263914166598042,
589
+ "pass@128": 0.7623456790123457
590
+ },
591
+ "16": {
592
+ "pass@1": 0.17998709439528024,
593
+ "pass@2": 0.24949589749843215,
594
+ "pass@4": 0.3208747200294653,
595
+ "pass@8": 0.3905123632054533,
596
+ "pass@16": 0.45808979050548,
597
+ "pass@32": 0.5216974250103424,
598
+ "pass@64": 0.5777479204581456,
599
+ "pass@128": 0.6283185840707964
600
+ },
601
+ "17": {
602
+ "pass@1": 0.1477315512048193,
603
+ "pass@2": 0.20808739386680566,
604
+ "pass@4": 0.2728240309381508,
605
+ "pass@8": 0.33414692797749634,
606
+ "pass@16": 0.3896587103250072,
607
+ "pass@32": 0.4444444909179926,
608
+ "pass@64": 0.5021505710532824,
609
+ "pass@128": 0.5662650602409639
610
+ },
611
+ "18": {
612
+ "pass@1": 0.15836693548387096,
613
+ "pass@2": 0.22317079946659896,
614
+ "pass@4": 0.29047785871524134,
615
+ "pass@8": 0.3546420062759032,
616
+ "pass@16": 0.4109804893627079,
617
+ "pass@32": 0.4607381281207391,
618
+ "pass@64": 0.509965745745279,
619
+ "pass@128": 0.5645161290322581
620
+ },
621
+ "19": {
622
+ "pass@1": 0.1345591012084592,
623
+ "pass@2": 0.18974541772724032,
624
+ "pass@4": 0.24514280560096152,
625
+ "pass@8": 0.29660860366263314,
626
+ "pass@16": 0.3445860926332715,
627
+ "pass@32": 0.3910334531819703,
628
+ "pass@64": 0.4355684959185234,
629
+ "pass@128": 0.4743202416918429
630
+ },
631
+ "20": {
632
+ "pass@1": 0.14503566066066065,
633
+ "pass@2": 0.20958359934737886,
634
+ "pass@4": 0.27287071435890325,
635
+ "pass@8": 0.3263658967186459,
636
+ "pass@16": 0.3687061510490307,
637
+ "pass@32": 0.4030540866987888,
638
+ "pass@64": 0.43363749885506614,
639
+ "pass@128": 0.46546546546546547
640
+ }
641
+ }
642
+ }
643
+ }
644
+ }
645
+ ]