Upload attention_entropies.jsonl with huggingface_hub
Browse files- attention_entropies.jsonl +144 -0
attention_entropies.jsonl
ADDED
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"layer":0,"head":0,"avg_attn_entropy":6.1600648546}
|
2 |
+
{"layer":0,"head":1,"avg_attn_entropy":6.1584506788}
|
3 |
+
{"layer":0,"head":2,"avg_attn_entropy":6.1870868464}
|
4 |
+
{"layer":0,"head":3,"avg_attn_entropy":6.0735976958}
|
5 |
+
{"layer":0,"head":4,"avg_attn_entropy":6.1231322632}
|
6 |
+
{"layer":0,"head":5,"avg_attn_entropy":6.1623747745}
|
7 |
+
{"layer":0,"head":6,"avg_attn_entropy":6.1639594169}
|
8 |
+
{"layer":0,"head":7,"avg_attn_entropy":6.146125165}
|
9 |
+
{"layer":0,"head":8,"avg_attn_entropy":6.1052541461}
|
10 |
+
{"layer":0,"head":9,"avg_attn_entropy":6.1374521623}
|
11 |
+
{"layer":0,"head":10,"avg_attn_entropy":6.118777566}
|
12 |
+
{"layer":0,"head":11,"avg_attn_entropy":6.1617808399}
|
13 |
+
{"layer":1,"head":0,"avg_attn_entropy":6.1494196639}
|
14 |
+
{"layer":1,"head":1,"avg_attn_entropy":6.0499497714}
|
15 |
+
{"layer":1,"head":2,"avg_attn_entropy":6.0912573204}
|
16 |
+
{"layer":1,"head":3,"avg_attn_entropy":5.9151432519}
|
17 |
+
{"layer":1,"head":4,"avg_attn_entropy":6.1039670753}
|
18 |
+
{"layer":1,"head":5,"avg_attn_entropy":6.1303987584}
|
19 |
+
{"layer":1,"head":6,"avg_attn_entropy":6.1378704433}
|
20 |
+
{"layer":1,"head":7,"avg_attn_entropy":6.1732876511}
|
21 |
+
{"layer":1,"head":8,"avg_attn_entropy":6.0844343901}
|
22 |
+
{"layer":1,"head":9,"avg_attn_entropy":6.0224072151}
|
23 |
+
{"layer":1,"head":10,"avg_attn_entropy":6.1575298805}
|
24 |
+
{"layer":1,"head":11,"avg_attn_entropy":6.0931021695}
|
25 |
+
{"layer":2,"head":0,"avg_attn_entropy":5.8973599391}
|
26 |
+
{"layer":2,"head":1,"avg_attn_entropy":6.0091449938}
|
27 |
+
{"layer":2,"head":2,"avg_attn_entropy":6.0747294588}
|
28 |
+
{"layer":2,"head":3,"avg_attn_entropy":6.1213797913}
|
29 |
+
{"layer":2,"head":4,"avg_attn_entropy":6.1024243207}
|
30 |
+
{"layer":2,"head":5,"avg_attn_entropy":6.1493336368}
|
31 |
+
{"layer":2,"head":6,"avg_attn_entropy":6.1045174026}
|
32 |
+
{"layer":2,"head":7,"avg_attn_entropy":5.9014663444}
|
33 |
+
{"layer":2,"head":8,"avg_attn_entropy":6.1138490577}
|
34 |
+
{"layer":2,"head":9,"avg_attn_entropy":6.063114234}
|
35 |
+
{"layer":2,"head":10,"avg_attn_entropy":5.9123973575}
|
36 |
+
{"layer":2,"head":11,"avg_attn_entropy":6.0291404247}
|
37 |
+
{"layer":3,"head":0,"avg_attn_entropy":6.0902112989}
|
38 |
+
{"layer":3,"head":1,"avg_attn_entropy":5.957479712}
|
39 |
+
{"layer":3,"head":2,"avg_attn_entropy":6.0550741978}
|
40 |
+
{"layer":3,"head":3,"avg_attn_entropy":5.8173761544}
|
41 |
+
{"layer":3,"head":4,"avg_attn_entropy":5.8348281069}
|
42 |
+
{"layer":3,"head":5,"avg_attn_entropy":6.1080144997}
|
43 |
+
{"layer":3,"head":6,"avg_attn_entropy":5.7191191387}
|
44 |
+
{"layer":3,"head":7,"avg_attn_entropy":6.065710546}
|
45 |
+
{"layer":3,"head":8,"avg_attn_entropy":5.7916838818}
|
46 |
+
{"layer":3,"head":9,"avg_attn_entropy":6.0804467278}
|
47 |
+
{"layer":3,"head":10,"avg_attn_entropy":5.7831644416}
|
48 |
+
{"layer":3,"head":11,"avg_attn_entropy":5.8379818053}
|
49 |
+
{"layer":4,"head":0,"avg_attn_entropy":5.8622342019}
|
50 |
+
{"layer":4,"head":1,"avg_attn_entropy":6.0836263485}
|
51 |
+
{"layer":4,"head":2,"avg_attn_entropy":6.0946244893}
|
52 |
+
{"layer":4,"head":3,"avg_attn_entropy":5.9619548087}
|
53 |
+
{"layer":4,"head":4,"avg_attn_entropy":6.1173812771}
|
54 |
+
{"layer":4,"head":5,"avg_attn_entropy":6.1273642006}
|
55 |
+
{"layer":4,"head":6,"avg_attn_entropy":5.6209671931}
|
56 |
+
{"layer":4,"head":7,"avg_attn_entropy":5.7213881693}
|
57 |
+
{"layer":4,"head":8,"avg_attn_entropy":5.760812582}
|
58 |
+
{"layer":4,"head":9,"avg_attn_entropy":6.0715985699}
|
59 |
+
{"layer":4,"head":10,"avg_attn_entropy":6.0334770617}
|
60 |
+
{"layer":4,"head":11,"avg_attn_entropy":5.7757602422}
|
61 |
+
{"layer":5,"head":0,"avg_attn_entropy":6.0019089279}
|
62 |
+
{"layer":5,"head":1,"avg_attn_entropy":5.8313751068}
|
63 |
+
{"layer":5,"head":2,"avg_attn_entropy":5.989206809}
|
64 |
+
{"layer":5,"head":3,"avg_attn_entropy":6.0627046595}
|
65 |
+
{"layer":5,"head":4,"avg_attn_entropy":5.7283513236}
|
66 |
+
{"layer":5,"head":5,"avg_attn_entropy":5.9491969538}
|
67 |
+
{"layer":5,"head":6,"avg_attn_entropy":5.9316726594}
|
68 |
+
{"layer":5,"head":7,"avg_attn_entropy":5.9880246181}
|
69 |
+
{"layer":5,"head":8,"avg_attn_entropy":5.9817439265}
|
70 |
+
{"layer":5,"head":9,"avg_attn_entropy":5.7653453698}
|
71 |
+
{"layer":5,"head":10,"avg_attn_entropy":5.7180798602}
|
72 |
+
{"layer":5,"head":11,"avg_attn_entropy":6.0889825735}
|
73 |
+
{"layer":6,"head":0,"avg_attn_entropy":5.8790088012}
|
74 |
+
{"layer":6,"head":1,"avg_attn_entropy":5.7733275442}
|
75 |
+
{"layer":6,"head":2,"avg_attn_entropy":5.8709836962}
|
76 |
+
{"layer":6,"head":3,"avg_attn_entropy":5.8874621382}
|
77 |
+
{"layer":6,"head":4,"avg_attn_entropy":5.8479917793}
|
78 |
+
{"layer":6,"head":5,"avg_attn_entropy":5.9794743543}
|
79 |
+
{"layer":6,"head":6,"avg_attn_entropy":5.9015631943}
|
80 |
+
{"layer":6,"head":7,"avg_attn_entropy":5.8486342669}
|
81 |
+
{"layer":6,"head":8,"avg_attn_entropy":5.7872277117}
|
82 |
+
{"layer":6,"head":9,"avg_attn_entropy":5.7529757719}
|
83 |
+
{"layer":6,"head":10,"avg_attn_entropy":5.857016542}
|
84 |
+
{"layer":6,"head":11,"avg_attn_entropy":5.9148236213}
|
85 |
+
{"layer":7,"head":0,"avg_attn_entropy":5.7042275209}
|
86 |
+
{"layer":7,"head":1,"avg_attn_entropy":5.959549922}
|
87 |
+
{"layer":7,"head":2,"avg_attn_entropy":5.7165108323}
|
88 |
+
{"layer":7,"head":3,"avg_attn_entropy":5.8884048076}
|
89 |
+
{"layer":7,"head":4,"avg_attn_entropy":5.7545999279}
|
90 |
+
{"layer":7,"head":5,"avg_attn_entropy":5.8268059106}
|
91 |
+
{"layer":7,"head":6,"avg_attn_entropy":5.8753777838}
|
92 |
+
{"layer":7,"head":7,"avg_attn_entropy":5.7040046787}
|
93 |
+
{"layer":7,"head":8,"avg_attn_entropy":5.8114910622}
|
94 |
+
{"layer":7,"head":9,"avg_attn_entropy":5.8918173699}
|
95 |
+
{"layer":7,"head":10,"avg_attn_entropy":5.6642464123}
|
96 |
+
{"layer":7,"head":11,"avg_attn_entropy":5.9899081182}
|
97 |
+
{"layer":8,"head":0,"avg_attn_entropy":5.8113057551}
|
98 |
+
{"layer":8,"head":1,"avg_attn_entropy":5.9751627235}
|
99 |
+
{"layer":8,"head":2,"avg_attn_entropy":5.870235693}
|
100 |
+
{"layer":8,"head":3,"avg_attn_entropy":6.00851261}
|
101 |
+
{"layer":8,"head":4,"avg_attn_entropy":5.874881382}
|
102 |
+
{"layer":8,"head":5,"avg_attn_entropy":5.9173713131}
|
103 |
+
{"layer":8,"head":6,"avg_attn_entropy":5.7487669768}
|
104 |
+
{"layer":8,"head":7,"avg_attn_entropy":5.9151715322}
|
105 |
+
{"layer":8,"head":8,"avg_attn_entropy":5.9416119189}
|
106 |
+
{"layer":8,"head":9,"avg_attn_entropy":6.0304414339}
|
107 |
+
{"layer":8,"head":10,"avg_attn_entropy":5.9463654428}
|
108 |
+
{"layer":8,"head":11,"avg_attn_entropy":5.7552012491}
|
109 |
+
{"layer":9,"head":0,"avg_attn_entropy":5.8410833721}
|
110 |
+
{"layer":9,"head":1,"avg_attn_entropy":5.8150470786}
|
111 |
+
{"layer":9,"head":2,"avg_attn_entropy":5.9479796762}
|
112 |
+
{"layer":9,"head":3,"avg_attn_entropy":5.9216109166}
|
113 |
+
{"layer":9,"head":4,"avg_attn_entropy":5.8009545419}
|
114 |
+
{"layer":9,"head":5,"avg_attn_entropy":5.8589636931}
|
115 |
+
{"layer":9,"head":6,"avg_attn_entropy":5.8163571286}
|
116 |
+
{"layer":9,"head":7,"avg_attn_entropy":5.8836691439}
|
117 |
+
{"layer":9,"head":8,"avg_attn_entropy":5.9429277472}
|
118 |
+
{"layer":9,"head":9,"avg_attn_entropy":5.8739997783}
|
119 |
+
{"layer":9,"head":10,"avg_attn_entropy":5.8936929183}
|
120 |
+
{"layer":9,"head":11,"avg_attn_entropy":5.94838977}
|
121 |
+
{"layer":10,"head":0,"avg_attn_entropy":5.8806723328}
|
122 |
+
{"layer":10,"head":1,"avg_attn_entropy":5.8968573709}
|
123 |
+
{"layer":10,"head":2,"avg_attn_entropy":5.6110674973}
|
124 |
+
{"layer":10,"head":3,"avg_attn_entropy":5.8375773864}
|
125 |
+
{"layer":10,"head":4,"avg_attn_entropy":5.885481719}
|
126 |
+
{"layer":10,"head":5,"avg_attn_entropy":5.8896907644}
|
127 |
+
{"layer":10,"head":6,"avg_attn_entropy":5.9586319361}
|
128 |
+
{"layer":10,"head":7,"avg_attn_entropy":5.9226288447}
|
129 |
+
{"layer":10,"head":8,"avg_attn_entropy":5.8263332944}
|
130 |
+
{"layer":10,"head":9,"avg_attn_entropy":5.766307528}
|
131 |
+
{"layer":10,"head":10,"avg_attn_entropy":5.8988998795}
|
132 |
+
{"layer":10,"head":11,"avg_attn_entropy":5.7453649101}
|
133 |
+
{"layer":11,"head":0,"avg_attn_entropy":5.8651043029}
|
134 |
+
{"layer":11,"head":1,"avg_attn_entropy":5.9354231782}
|
135 |
+
{"layer":11,"head":2,"avg_attn_entropy":5.826529108}
|
136 |
+
{"layer":11,"head":3,"avg_attn_entropy":5.9480430651}
|
137 |
+
{"layer":11,"head":4,"avg_attn_entropy":5.970781518}
|
138 |
+
{"layer":11,"head":5,"avg_attn_entropy":5.8623771658}
|
139 |
+
{"layer":11,"head":6,"avg_attn_entropy":5.8123741412}
|
140 |
+
{"layer":11,"head":7,"avg_attn_entropy":5.8292103839}
|
141 |
+
{"layer":11,"head":8,"avg_attn_entropy":5.9031762438}
|
142 |
+
{"layer":11,"head":9,"avg_attn_entropy":5.8772822061}
|
143 |
+
{"layer":11,"head":10,"avg_attn_entropy":5.928469512}
|
144 |
+
{"layer":11,"head":11,"avg_attn_entropy":5.9718926072}
|