eyad-silx commited on
Commit
0c3ede0
·
verified ·
1 Parent(s): a955a08

push artifacts/logs/measure.log

Browse files
Files changed (1) hide show
  1. artifacts/logs/measure.log +34 -34
artifacts/logs/measure.log CHANGED
@@ -1,23 +1,23 @@
1
- 2026-10-26 02:28:38.058 | INFO | eval_service.servers:serve:505 - starting the teacher on GPUs (0,): /root/models/teacher
2
- 2026-10-26 02:29:38.237 | INFO | eval_service.servers:serve:514 - the teacher is ready, 60s into serve
3
  teacher 1/16: affine/train/math_prealgebra-4363603/en p73 a130
4
  teacher 2/16: affine/train/math_algebra-7595820/en p86 a378
5
  teacher 3/16: affine/train/math_geometry-2333548/en p110 a242
6
- teacher 4/16: affine/train/math_algebra-15977093/en p95 a231
7
  teacher 5/16: affine/train/math_prealgebra-6982828/en p87 a199
8
  teacher 6/16: affine/train/math_algebra-15278704/en p90 a266
9
  teacher 7/16: affine/train/math_number_theory-5402571/en p85 a278
10
- teacher 8/16: affine/train/math_algebra-10810849/en p118 a454
11
- teacher 9/16: affine/train/math_geometry-3090335/en p93 a620
12
- teacher 10/16: affine/train/math_intermediate_algebra-5570402/en p71 a508
13
- teacher 11/16: affine/train/math_intermediate_algebra-8535128/en p99 a359
14
- teacher 12/16: affine/train/math_intermediate_algebra-11925264/en p94 a504
15
  teacher 13/16: affine/train/math_algebra-7745671/en p96 a435
16
- teacher 14/16: affine/train/math_precalculus-2471323/en p86 a792
17
- teacher 15/16: affine/train/math_prealgebra-7667387/en p86 a1681
18
- teacher 16/16: affine/train/math_precalculus-9027392/en p158 a1013
19
- 2026-10-26 02:30:27.254 | INFO | eval_service.servers:serve:505 - starting the king on GPUs (0,): /root/models/king-ix
20
- 2026-10-26 02:30:29.326 | INFO | eval_service.servers:serve:514 - the king is ready, 2s into serve
21
  king 1/16: affine/train/math_prealgebra-4363603/en
22
  king 2/16: affine/train/math_algebra-7595820/en
23
  king 3/16: affine/train/math_geometry-2333548/en
@@ -34,8 +34,8 @@ king 13/16: affine/train/math_algebra-7745671/en
34
  king 14/16: affine/train/math_precalculus-2471323/en
35
  king 15/16: affine/train/math_prealgebra-7667387/en
36
  king 16/16: affine/train/math_precalculus-9027392/en
37
- 2026-10-26 02:30:37.740 | INFO | eval_service.servers:serve:505 - starting the challenger on GPUs (0,): /root/models/chal-identity
38
- 2026-10-26 02:30:39.972 | INFO | eval_service.servers:serve:514 - the challenger is ready, 2s into serve
39
  challenger 1/16: affine/train/math_prealgebra-4363603/en
40
  challenger 2/16: affine/train/math_algebra-7595820/en
41
  challenger 3/16: affine/train/math_geometry-2333548/en
@@ -52,23 +52,23 @@ challenger 13/16: affine/train/math_algebra-7745671/en
52
  challenger 14/16: affine/train/math_precalculus-2471323/en
53
  challenger 15/16: affine/train/math_prealgebra-7667387/en
54
  challenger 16/16: affine/train/math_precalculus-9027392/en
55
- scored affine/train/math_prealgebra-4363603/en: king KL 0.0097 challenger KL 0.0097
56
- scored affine/train/math_algebra-7595820/en: king KL 0.0239 challenger KL 0.0239
57
- scored affine/train/math_geometry-2333548/en: king KL 0.0153 challenger KL 0.0153
58
- scored affine/train/math_algebra-15977093/en: king KL 0.0128 challenger KL 0.0128
59
- scored affine/train/math_prealgebra-6982828/en: king KL 0.0243 challenger KL 0.0243
60
- scored affine/train/math_algebra-15278704/en: king KL 0.0126 challenger KL 0.0126
61
- scored affine/train/math_number_theory-5402571/en: king KL 0.0290 challenger KL 0.0290
62
- scored affine/train/math_algebra-10810849/en: king KL 0.0385 challenger KL 0.0385
63
- scored affine/train/math_geometry-3090335/en: king KL 0.0298 challenger KL 0.0298
64
- scored affine/train/math_intermediate_algebra-5570402/en: king KL 0.0223 challenger KL 0.0223
65
- scored affine/train/math_intermediate_algebra-8535128/en: king KL 0.0225 challenger KL 0.0225
66
- scored affine/train/math_intermediate_algebra-11925264/en: king KL 0.0297 challenger KL 0.0297
67
- scored affine/train/math_algebra-7745671/en: king KL 0.0204 challenger KL 0.0204
68
- scored affine/train/math_precalculus-2471323/en: king KL 0.0118 challenger KL 0.0118
69
- scored affine/train/math_prealgebra-7667387/en: king KL 0.0198 challenger KL 0.0198
70
- scored affine/train/math_precalculus-9027392/en: king KL 0.0282 challenger KL 0.0282
71
  teacher KL 0.000000 distance 0.00000
72
- king KL 0.022700 distance 0.29762
73
- challenger KL 0.022700 distance 0.29762
74
- margin needed: KL 0.000340 dist 0.002500 ; challenger leads by KL 0.000000 (0.000%) dist 0.000000 (0.000%)
 
1
+ 2026-10-26 09:54:57.449 | INFO | eval_service.servers:serve:505 - starting the teacher on GPUs (0,): /root/models/teacher
2
+ 2026-10-26 09:55:57.630 | INFO | eval_service.servers:serve:514 - the teacher is ready, 60s into serve
3
  teacher 1/16: affine/train/math_prealgebra-4363603/en p73 a130
4
  teacher 2/16: affine/train/math_algebra-7595820/en p86 a378
5
  teacher 3/16: affine/train/math_geometry-2333548/en p110 a242
6
+ teacher 4/16: affine/train/math_algebra-15977093/en p95 a253
7
  teacher 5/16: affine/train/math_prealgebra-6982828/en p87 a199
8
  teacher 6/16: affine/train/math_algebra-15278704/en p90 a266
9
  teacher 7/16: affine/train/math_number_theory-5402571/en p85 a278
10
+ teacher 8/16: affine/train/math_algebra-10810849/en p118 a508
11
+ teacher 9/16: affine/train/math_geometry-3090335/en p93 a785
12
+ teacher 10/16: affine/train/math_intermediate_algebra-5570402/en p71 a536
13
+ teacher 11/16: affine/train/math_intermediate_algebra-8535128/en p99 a377
14
+ teacher 12/16: affine/train/math_intermediate_algebra-11925264/en p94 a456
15
  teacher 13/16: affine/train/math_algebra-7745671/en p96 a435
16
+ teacher 14/16: affine/train/math_precalculus-2471323/en p86 a691
17
+ teacher 15/16: affine/train/math_prealgebra-7667387/en p86 a1209
18
+ teacher 16/16: affine/train/math_precalculus-9027392/en p158 a1382
19
+ 2026-10-26 09:56:45.487 | INFO | eval_service.servers:serve:505 - starting the king on GPUs (0,): /root/models/king-xii
20
+ 2026-10-26 09:56:47.931 | INFO | eval_service.servers:serve:514 - the king is ready, 2s into serve
21
  king 1/16: affine/train/math_prealgebra-4363603/en
22
  king 2/16: affine/train/math_algebra-7595820/en
23
  king 3/16: affine/train/math_geometry-2333548/en
 
34
  king 14/16: affine/train/math_precalculus-2471323/en
35
  king 15/16: affine/train/math_prealgebra-7667387/en
36
  king 16/16: affine/train/math_precalculus-9027392/en
37
+ 2026-10-26 09:56:56.583 | INFO | eval_service.servers:serve:505 - starting the challenger on GPUs (0,): /root/models/chal-norms
38
+ 2026-10-26 09:56:58.359 | INFO | eval_service.servers:serve:514 - the challenger is ready, 2s into serve
39
  challenger 1/16: affine/train/math_prealgebra-4363603/en
40
  challenger 2/16: affine/train/math_algebra-7595820/en
41
  challenger 3/16: affine/train/math_geometry-2333548/en
 
52
  challenger 14/16: affine/train/math_precalculus-2471323/en
53
  challenger 15/16: affine/train/math_prealgebra-7667387/en
54
  challenger 16/16: affine/train/math_precalculus-9027392/en
55
+ scored affine/train/math_prealgebra-4363603/en: king KL 0.0088 challenger KL 0.0626
56
+ scored affine/train/math_algebra-7595820/en: king KL 0.0239 challenger KL 0.0727
57
+ scored affine/train/math_geometry-2333548/en: king KL 0.0159 challenger KL 0.0642
58
+ scored affine/train/math_algebra-15977093/en: king KL 0.0126 challenger KL 0.0854
59
+ scored affine/train/math_prealgebra-6982828/en: king KL 0.0253 challenger KL 0.0667
60
+ scored affine/train/math_algebra-15278704/en: king KL 0.0130 challenger KL 0.0555
61
+ scored affine/train/math_number_theory-5402571/en: king KL 0.0286 challenger KL 0.1200
62
+ scored affine/train/math_algebra-10810849/en: king KL 0.0421 challenger KL 0.1682
63
+ scored affine/train/math_geometry-3090335/en: king KL 0.0232 challenger KL 0.0757
64
+ scored affine/train/math_intermediate_algebra-5570402/en: king KL 0.0298 challenger KL 0.0979
65
+ scored affine/train/math_intermediate_algebra-8535128/en: king KL 0.0213 challenger KL 0.0584
66
+ scored affine/train/math_intermediate_algebra-11925264/en: king KL 0.0326 challenger KL 0.0895
67
+ scored affine/train/math_algebra-7745671/en: king KL 0.0203 challenger KL 0.0663
68
+ scored affine/train/math_precalculus-2471323/en: king KL 0.0104 challenger KL 0.0491
69
+ scored affine/train/math_prealgebra-7667387/en: king KL 0.0180 challenger KL 0.0764
70
+ scored affine/train/math_precalculus-9027392/en: king KL 0.0295 challenger KL 0.0901
71
  teacher KL 0.000000 distance 0.00000
72
+ king KL 0.023454 distance 0.28739
73
+ challenger KL 0.082946 distance 0.28774
74
+ margin needed: KL 0.000352 dist 0.002414 ; challenger leads by KL -0.059493 (-253.659%) dist -0.000354 (-0.123%)