Hugging Face's logo

Asilarkness
/
testgeniy

Text Generation
Transformers
Safetensors
English
testgeniy
causal-lm
reasoning
mathematics
logic
long-context
4k-context
small-language-model
Model card Files
xet
 Community
Asilarkness commited on
Commit
24faea4
·
verified ·
1 Parent(s): 7b717c3

Add v3 evaluation artifact v3_fixed_scores.json

Browse files
Files changed (1) hide show
  1. candidates/budgie-alignment-v2/reasoning-sft-then-rl-v3/recovery/v3_fixed_scores.json +131 -0
candidates/budgie-alignment-v2/reasoning-sft-then-rl-v3/recovery/v3_fixed_scores.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "gsm8k": {
3
+ "correct": 4,
4
+ "total": 30,
5
+ "items": [
6
+ true,
7
+ false,
8
+ false,
9
+ false,
10
+ false,
11
+ false,
12
+ true,
13
+ false,
14
+ false,
15
+ true,
16
+ false,
17
+ false,
18
+ false,
19
+ false,
20
+ false,
21
+ false,
22
+ false,
23
+ false,
24
+ false,
25
+ false,
26
+ false,
27
+ false,
28
+ false,
29
+ false,
30
+ false,
31
+ false,
32
+ false,
33
+ false,
34
+ false,
35
+ true
36
+ ]
37
+ },
38
+ "math500": {
39
+ "correct": 2,
40
+ "total": 15,
41
+ "items": [
42
+ false,
43
+ false,
44
+ false,
45
+ false,
46
+ false,
47
+ false,
48
+ true,
49
+ false,
50
+ false,
51
+ false,
52
+ false,
53
+ false,
54
+ false,
55
+ true,
56
+ false
57
+ ]
58
+ },
59
+ "arc_challenge": {
60
+ "correct": 11,
61
+ "total": 30,
62
+ "items": [
63
+ true,
64
+ false,
65
+ false,
66
+ false,
67
+ false,
68
+ false,
69
+ false,
70
+ true,
71
+ false,
72
+ false,
73
+ true,
74
+ true,
75
+ true,
76
+ false,
77
+ false,
78
+ false,
79
+ true,
80
+ false,
81
+ false,
82
+ true,
83
+ false,
84
+ true,
85
+ true,
86
+ false,
87
+ false,
88
+ true,
89
+ false,
90
+ true,
91
+ false,
92
+ false
93
+ ]
94
+ },
95
+ "folio": {
96
+ "correct": 13,
97
+ "total": 30,
98
+ "items": [
99
+ true,
100
+ true,
101
+ true,
102
+ true,
103
+ true,
104
+ false,
105
+ false,
106
+ true,
107
+ false,
108
+ true,
109
+ false,
110
+ true,
111
+ true,
112
+ false,
113
+ false,
114
+ false,
115
+ false,
116
+ true,
117
+ false,
118
+ false,
119
+ true,
120
+ false,
121
+ false,
122
+ true,
123
+ false,
124
+ true,
125
+ false,
126
+ false,
127
+ false,
128
+ false
129
+ ]
130
+ }
131
+ }