Upload ./Qwen2-7B-Q2_K.mmlu.pro.txt with huggingface_hub
Browse files- Qwen2-7B-Q2_K.mmlu.pro.txt +80 -0
Qwen2-7B-Q2_K.mmlu.pro.txt
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
multiple_choice_score: there are 70 tasks in prompt
|
2 |
+
multiple_choice_score: reading tasks......................................................................done
|
3 |
+
multiple_choice_score: preparing task data......................................................................done
|
4 |
+
multiple_choice_score : calculating TruthfulQA score over 70 tasks.
|
5 |
+
|
6 |
+
task acc_norm
|
7 |
+
1 0.00000000
|
8 |
+
2 0.00000000
|
9 |
+
3 0.00000000
|
10 |
+
4 0.00000000
|
11 |
+
5 0.00000000
|
12 |
+
6 0.00000000
|
13 |
+
7 0.00000000
|
14 |
+
8 0.00000000
|
15 |
+
9 0.00000000
|
16 |
+
10 0.00000000
|
17 |
+
11 0.00000000
|
18 |
+
12 0.00000000
|
19 |
+
13 0.00000000
|
20 |
+
14 0.00000000
|
21 |
+
15 6.66666667
|
22 |
+
16 6.25000000
|
23 |
+
17 5.88235294
|
24 |
+
18 5.55555556
|
25 |
+
19 5.26315789
|
26 |
+
20 5.00000000
|
27 |
+
21 4.76190476
|
28 |
+
22 4.54545455
|
29 |
+
23 4.34782609
|
30 |
+
24 4.16666667
|
31 |
+
25 4.00000000
|
32 |
+
26 3.84615385
|
33 |
+
27 3.70370370
|
34 |
+
28 3.57142857
|
35 |
+
29 3.44827586
|
36 |
+
30 6.66666667
|
37 |
+
31 6.45161290
|
38 |
+
32 6.25000000
|
39 |
+
33 9.09090909
|
40 |
+
34 8.82352941
|
41 |
+
35 8.57142857
|
42 |
+
36 8.33333333
|
43 |
+
37 8.10810811
|
44 |
+
38 7.89473684
|
45 |
+
39 7.69230769
|
46 |
+
40 7.50000000
|
47 |
+
41 7.31707317
|
48 |
+
42 7.14285714
|
49 |
+
43 6.97674419
|
50 |
+
44 6.81818182
|
51 |
+
45 6.66666667
|
52 |
+
46 8.69565217
|
53 |
+
47 8.51063830
|
54 |
+
48 10.41666667
|
55 |
+
49 10.20408163
|
56 |
+
50 12.00000000
|
57 |
+
51 11.76470588
|
58 |
+
52 11.53846154
|
59 |
+
53 13.20754717
|
60 |
+
54 14.81481481
|
61 |
+
55 16.36363636
|
62 |
+
56 16.07142857
|
63 |
+
57 15.78947368
|
64 |
+
58 15.51724138
|
65 |
+
59 15.25423729
|
66 |
+
60 15.00000000
|
67 |
+
61 14.75409836
|
68 |
+
62 14.51612903
|
69 |
+
63 14.28571429
|
70 |
+
64 15.62500000
|
71 |
+
65 15.38461538
|
72 |
+
66 15.15151515
|
73 |
+
67 14.92537313
|
74 |
+
68 14.70588235
|
75 |
+
69 14.49275362
|
76 |
+
70 14.28571429
|
77 |
+
|
78 |
+
Final result: 14.2857 +/- 4.2126
|
79 |
+
Random chance: 10.0000 +/- 3.6116
|
80 |
+
|