karimouda commited on
Commit
9f9498d
·
verified ·
1 Parent(s): 9bb0a31

Add results file for gemma-3n-e4b-it

Browse files
results/google/gemma-3n-e4b-it_results_2025-05-21_14-55-15.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 7.123404255319149,
4
+ "speed": 4.84039644690807,
5
+ "contamination_score": 0,
6
+ "execution_time": 5315.886887,
7
+ "errors": [
8
+ {
9
+ "error": "503 UNAVAILABLE. {'error': {'code': 503, 'message': 'The service is currently unavailable.', 'status': 'UNAVAILABLE'}}",
10
+ "prompt": "{'role': 'user', 'content': '\u0623\u0639\u062f \u0635\u064a\u0627\u063a\u0629 \u0627\u0644\u0646\u0635 \u0627\u0644\u062a\u0627\u0644\u064a \u0628\u0627\u0644\u0644\u063a\u0629 \u0627\u0644\u0639\u0631\u0628\u064a\u0629 \u0645\u0639 \u0627\u0644\u062d\u0641\u0627\u0638 \u0639\u0644\u0649 \u0627\u0644\u0645\u0639\u0646\u0649 \u0627\u0644\u0623\u0635\u0644\u064a. \\n\u0630\u0647\u0628 \u0627\u0644\u0623\u0648\u0644\u0627\u062f \u0625\u0644\u0649 \u0627\u0644\u062d\u062f\u064a\u0642\u0629 \u0644\u0644\u0627\u0633\u062a\u0645\u062a\u0627\u0639 \u0628\u0648\u0642\u062a\u0647\u0645 \u0648\u0644\u0639\u0628\u0648\u0627 \u0623\u0644\u0639\u0627\u0628\u064b\u0627 \u0645\u062e\u062a\u0644\u0641\u0629. \\n\u0627\u0644\u0625\u062c\u0627\u0628\u0629:'}"
11
+ }
12
+ ],
13
+ "scores_by_category": [
14
+ {
15
+ "category": "Sentiment Analysis",
16
+ "average_score": 10.0,
17
+ "count": 9
18
+ },
19
+ {
20
+ "category": "Reading Comprehension",
21
+ "average_score": 10.0,
22
+ "count": 17
23
+ },
24
+ {
25
+ "category": "Coding",
26
+ "average_score": 10.0,
27
+ "count": 3
28
+ },
29
+ {
30
+ "category": "Function Calling",
31
+ "average_score": 9.333333333333334,
32
+ "count": 3
33
+ },
34
+ {
35
+ "category": "Entity Extraction",
36
+ "average_score": 8.6,
37
+ "count": 5
38
+ },
39
+ {
40
+ "category": "Paraphrasing",
41
+ "average_score": 8.333333333333334,
42
+ "count": 6
43
+ },
44
+ {
45
+ "category": "Instruction Following",
46
+ "average_score": 7.857142857142857,
47
+ "count": 7
48
+ },
49
+ {
50
+ "category": "Summarization",
51
+ "average_score": 7.625,
52
+ "count": 8
53
+ },
54
+ {
55
+ "category": "MMLU",
56
+ "average_score": 7.520661157024794,
57
+ "count": 121
58
+ },
59
+ {
60
+ "category": "Transliteration",
61
+ "average_score": 7.5,
62
+ "count": 6
63
+ },
64
+ {
65
+ "category": "Writing (incl Dialects)",
66
+ "average_score": 7.454545454545454,
67
+ "count": 22
68
+ },
69
+ {
70
+ "category": "RAG QA",
71
+ "average_score": 7.365853658536586,
72
+ "count": 41
73
+ },
74
+ {
75
+ "category": "Translation (incl Dialects)",
76
+ "average_score": 6.916666666666667,
77
+ "count": 36
78
+ },
79
+ {
80
+ "category": "Reasoning & Math",
81
+ "average_score": 6.906976744186046,
82
+ "count": 43
83
+ },
84
+ {
85
+ "category": "General Knowledge",
86
+ "average_score": 6.904761904761905,
87
+ "count": 63
88
+ },
89
+ {
90
+ "category": "Trust & Safety",
91
+ "average_score": 6.666666666666667,
92
+ "count": 30
93
+ },
94
+ {
95
+ "category": "Long Context",
96
+ "average_score": 6.0,
97
+ "count": 4
98
+ },
99
+ {
100
+ "category": "Arabic Language & Grammar",
101
+ "average_score": 5.588235294117647,
102
+ "count": 17
103
+ },
104
+ {
105
+ "category": "Dialect Detection",
106
+ "average_score": 4.7272727272727275,
107
+ "count": 11
108
+ },
109
+ {
110
+ "category": "Diacritization",
111
+ "average_score": 3.75,
112
+ "count": 12
113
+ },
114
+ {
115
+ "category": "Structuring",
116
+ "average_score": 1.0,
117
+ "count": 3
118
+ },
119
+ {
120
+ "category": "Hallucination",
121
+ "average_score": 0.0,
122
+ "count": 3
123
+ }
124
+ ],
125
+ "scores_by_format": [
126
+ {
127
+ "format": "Short Answer",
128
+ "average_score": 10.0,
129
+ "count": 5
130
+ },
131
+ {
132
+ "format": "MCQ",
133
+ "average_score": 7.262008733624454,
134
+ "count": 229
135
+ },
136
+ {
137
+ "format": "Generation",
138
+ "average_score": 6.951754385964913,
139
+ "count": 228
140
+ },
141
+ {
142
+ "format": "Fill-in-the-blank",
143
+ "average_score": 6.25,
144
+ "count": 8
145
+ }
146
+ ]
147
+ },
148
+ "config": {
149
+ "model": "google/gemma-3n-e4b-it",
150
+ "model_sha": "na",
151
+ "submitted_time": "2025-05-21 13:26:34",
152
+ "likes": -1,
153
+ "params": 4,
154
+ "license": "closed",
155
+ "model_source": "API",
156
+ "model_category": "Small"
157
+ }
158
+ }