bigscience-bloom-1b1
Find this model in the BLOOM model summary
bigscience-bloom-1b1 Model Summary Plots
bigscience-bloom-1b1 Model Selected Details
layer_type
N
M
Q
alpha
D
alpha-hat
log_SN
% Rand
num_traps
num_fingers
rank_loss
layer_id
7
DENSE
4608
1536
3.00
3.55
0.02
5.09
1.43
84.01
0
0
0
8
DENSE
1536
1536
1.00
3.84
0.06
4.42
1.15
83.70
1
0
3
12
DENSE
6144
1536
4.00
4.45
0.05
8.28
1.86
87.85
1
0
0
14
DENSE
6144
1536
4.00
3.72
0.02
5.79
1.56
84.67
4
0
0
18
DENSE
4608
1536
3.00
4.67
0.02
5.98
1.28
88.21
0
0
0
19
DENSE
1536
1536
1.00
4.11
0.02
4.23
1.03
84.97
2
0
2
23
DENSE
6144
1536
4.00
3.28
0.05
6.41
1.95
86.92
1
0
0
25
DENSE
6144
1536
4.00
4.56
0.02
6.96
1.53
90.60
0
0
0
29
DENSE
4608
1536
3.00
4.78
0.03
6.05
1.26
89.25
0
0
0
30
DENSE
1536
1536
1.00
3.46
0.04
3.27
0.94
86.33
1
0
3
34
DENSE
6144
1536
4.00
3.17
0.04
5.98
1.89
86.15
1
0
0
36
DENSE
6144
1536
4.00
4.16
0.05
5.62
1.35
88.08
0
0
0
40
DENSE
4608
1536
3.00
4.66
0.03
5.89
1.27
88.33
0
0
0
41
DENSE
1536
1536
1.00
4.33
0.06
4.63
1.07
87.44
1
0
3
45
DENSE
6144
1536
4.00
3.80
0.01
6.79
1.79
89.61
1
0
0
47
DENSE
6144
1536
4.00
3.26
0.09
4.51
1.38
89.09
1
6
0
51
DENSE
4608
1536
3.00
4.28
0.03
5.54
1.29
87.14
0
0
0
52
DENSE
1536
1536
1.00
4.11
0.04
4.54
1.10
87.51
2
0
3
56
DENSE
6144
1536
4.00
3.64
0.01
5.73
1.57
86.08
1
0
0
58
DENSE
6144
1536
4.00
4.22
0.03
5.83
1.38
87.46
7
0
0
62
DENSE
4608
1536
3.00
4.02
0.03
5.55
1.38
87.55
0
0
0
63
DENSE
1536
1536
1.00
4.44
0.04
4.08
0.92
87.83
0
0
4
67
DENSE
6144
1536
4.00
3.33
0.01
6.46
1.94
79.93
0
0
0
69
DENSE
6144
1536
4.00
3.67
0.04
6.42
1.75
84.66
7
0
0
73
DENSE
4608
1536
3.00
3.49
0.05
4.54
1.30
86.46
0
0
0
74
DENSE
1536
1536
1.00
4.24
0.08
2.79
0.66
90.69
0
2
3
78
DENSE
6144
1536
4.00
3.42
0.02
6.70
1.96
81.01
0
0
0
80
DENSE
6144
1536
4.00
3.68
0.03
5.93
1.61
86.55
5
0
0
84
DENSE
4608
1536
3.00
2.48
0.08
3.29
1.33
82.12
0
1
0
85
DENSE
1536
1536
1.00
3.81
0.09
1.75
0.46
87.73
0
1
3
89
DENSE
6144
1536
4.00
3.66
0.01
6.57
1.79
86.07
2
0
0
91
DENSE
6144
1536
4.00
4.03
0.02
5.84
1.45
87.65
2
0
0
95
DENSE
4608
1536
3.00
2.31
0.08
2.99
1.30
80.61
0
1
0
96
DENSE
1536
1536
1.00
3.64
0.05
1.25
0.34
87.95
0
0
3
100
DENSE
6144
1536
4.00
3.70
0.02
5.31
1.44
81.83
0
0
0
102
DENSE
6144
1536
4.00
3.63
0.04
3.69
1.02
82.38
0
0
0
106
DENSE
4608
1536
3.00
3.25
0.09
4.23
1.30
82.65
0
1
0
107
DENSE
1536
1536
1.00
3.93
0.08
1.86
0.47
89.51
0
0
4
111
DENSE
6144
1536
4.00
3.40
0.03
5.10
1.50
80.95
0
0
0
113
DENSE
6144
1536
4.00
3.27
0.05
3.34
1.02
84.63
0
0
0
117
DENSE
4608
1536
3.00
3.97
0.06
4.82
1.21
84.75
0
0
0
118
DENSE
1536
1536
1.00
6.91
0.04
3.65
0.53
90.79
0
0
4
122
DENSE
6144
1536
4.00
3.15
0.06
4.78
1.52
81.59
0
1
0
124
DENSE
6144
1536
4.00
3.97
0.04
3.71
0.94
87.00
0
0
0
128
DENSE
4608
1536
3.00
2.73
0.07
3.54
1.30
80.62
0
0
0
129
DENSE
1536
1536
1.00
3.26
0.10
1.03
0.32
89.20
0
0
3
133
DENSE
6144
1536
4.00
3.82
0.03
6.57
1.72
85.82
0
0
0
135
DENSE
6144
1536
4.00
5.02
0.05
4.69
0.93
92.62
0
0
0
139
DENSE
4608
1536
3.00
3.51
0.05
4.55
1.30
85.46
0
0
0
140
DENSE
1536
1536
1.00
3.85
0.09
1.54
0.40
91.13
0
1
3
144
DENSE
6144
1536
4.00
3.87
0.03
6.72
1.74
86.03
0
0
0
146
DENSE
6144
1536
4.00
4.56
0.05
4.58
1.00
91.48
0
0
0
150
DENSE
4608
1536
3.00
3.64
0.05
4.46
1.22
85.37
0
0
0
151
DENSE
1536
1536
1.00
3.14
0.08
1.41
0.45
88.80
0
0
3
155
DENSE
6144
1536
4.00
3.60
0.03
6.28
1.75
85.32
0
0
0
157
DENSE
6144
1536
4.00
4.47
0.05
4.44
0.99
90.58
0
0
0
161
DENSE
4608
1536
3.00
3.81
0.06
4.62
1.21
85.01
0
0
0
162
DENSE
1536
1536
1.00
5.04
0.12
3.54
0.70
87.69
0
5
3
166
DENSE
6144
1536
4.00
3.86
0.04
6.69
1.73
86.20
0
0
0
168
DENSE
6144
1536
4.00
4.12
0.04
4.38
1.06
89.47
0
0
0
172
DENSE
4608
1536
3.00
3.52
0.06
4.64
1.32
85.74
0
1
0
173
DENSE
1536
1536
1.00
5.79
0.08
2.19
0.38
89.52
0
0
3
177
DENSE
6144
1536
4.00
3.82
0.03
6.60
1.73
86.94
0
0
0
179
DENSE
6144
1536
4.00
4.29
0.04
4.85
1.13
89.41
0
0
0
183
DENSE
4608
1536
3.00
3.65
0.07
4.53
1.24
87.02
0
1
0
184
DENSE
1536
1536
1.00
3.72
0.04
2.40
0.64
87.37
0
0
4
188
DENSE
6144
1536
4.00
3.78
0.02
6.61
1.75
87.57
0
0
0
190
DENSE
6144
1536
4.00
4.43
0.04
5.30
1.20
89.74
0
0
0
194
DENSE
4608
1536
3.00
3.58
0.07
4.34
1.21
88.14
0
1
0
195
DENSE
1536
1536
1.00
4.18
0.09
2.36
0.56
89.23
0
1
3
199
DENSE
6144
1536
4.00
3.87
0.02
6.87
1.78
87.67
0
0
0
201
DENSE
6144
1536
4.00
4.69
0.03
6.06
1.29
89.80
0
0
0
205
DENSE
4608
1536
3.00
4.35
0.06
5.08
1.17
88.78
0
0
0
206
DENSE
1536
1536
1.00
8.54
0.04
4.52
0.53
93.21
0
0
4
210
DENSE
6144
1536
4.00
3.93
0.01
7.08
1.80
87.50
0
0
0
212
DENSE
6144
1536
4.00
5.33
0.03
7.11
1.33
91.03
0
0
0
216
DENSE
4608
1536
3.00
4.25
0.07
5.44
1.28
90.37
0
1
0
217
DENSE
1536
1536
1.00
6.19
0.06
5.94
0.96
92.81
0
0
2
221
DENSE
6144
1536
4.00
3.73
0.01
6.90
1.85
86.29
0
0
0
223
DENSE
6144
1536
4.00
4.87
0.04
6.21
1.27
92.22
0
0
0
227
DENSE
4608
1536
3.00
4.03
0.05
5.23
1.30
89.89
0
0
0
228
DENSE
1536
1536
1.00
4.71
0.07
4.44
0.94
91.02
0
0
2
232
DENSE
6144
1536
4.00
3.31
0.01
6.71
2.03
82.57
1
0
0
234
DENSE
6144
1536
4.00
4.99
0.02
6.44
1.29
93.01
1
0
0
238
DENSE
4608
1536
3.00
3.64
0.03
5.10
1.40
88.47
0
0
0
239
DENSE
1536
1536
1.00
2.70
0.09
4.75
1.76
77.16
18
0
3
243
DENSE
6144
1536
4.00
3.28
0.02
6.40
1.95
83.15
1
0
0
245
DENSE
6144
1536
4.00
4.08
0.03
7.65
1.87
90.48
8
0
0
249
DENSE
4608
1536
3.00
3.39
0.02
4.94
1.46
87.90
0
0
0
250
DENSE
1536
1536
1.00
2.69
0.08
5.32
1.98
70.46
25
0
3
254
DENSE
6144
1536
4.00
3.07
0.01
6.95
2.26
78.99
3
0
0
256
DENSE
6144
1536
4.00
4.69
0.03
8.36
1.78
91.46
4
0
0
260
DENSE
4608
1536
3.00
3.41
0.01
5.06
1.48
87.16
0
0
0
261
DENSE
1536
1536
1.00
2.42
0.02
4.44
1.84
73.47
6
0
3
265
DENSE
6144
1536
4.00
3.30
0.01
6.63
2.01
82.90
3
0
0
267
DENSE
6144
1536
4.00
4.72
0.04
8.24
1.75
90.96
5
0
0
bigscience-bloom-1b1 Layer Plots
Layer 7
Layer=7 | N=4608 | M=1536 | Q=3.00 | alpha=3.55 | D_ks=0.02 | alpha-hat=5.09 | num traps=0
Layer 8
Layer=8 | N=1536 | M=1536 | Q=1.00 | alpha=3.84 | D_ks=0.06 | alpha-hat=4.42 | num traps=1
Layer 12
Layer=12 | N=6144 | M=1536 | Q=4.00 | alpha=4.45 | D_ks=0.05 | alpha-hat=8.28 | num traps=1
Layer 14
Layer=14 | N=6144 | M=1536 | Q=4.00 | alpha=3.72 | D_ks=0.02 | alpha-hat=5.79 | num traps=4
Layer 18
Layer=18 | N=4608 | M=1536 | Q=3.00 | alpha=4.67 | D_ks=0.02 | alpha-hat=5.98 | num traps=0
Layer 19
Layer=19 | N=1536 | M=1536 | Q=1.00 | alpha=4.11 | D_ks=0.02 | alpha-hat=4.23 | num traps=2
Layer 23
Layer=23 | N=6144 | M=1536 | Q=4.00 | alpha=3.28 | D_ks=0.05 | alpha-hat=6.41 | num traps=1
Layer 25
Layer=25 | N=6144 | M=1536 | Q=4.00 | alpha=4.56 | D_ks=0.02 | alpha-hat=6.96 | num traps=0
Layer 29
Layer=29 | N=4608 | M=1536 | Q=3.00 | alpha=4.78 | D_ks=0.03 | alpha-hat=6.05 | num traps=0
Layer 30
Layer=30 | N=1536 | M=1536 | Q=1.00 | alpha=3.46 | D_ks=0.04 | alpha-hat=3.27 | num traps=1
Layer 34
Layer=34 | N=6144 | M=1536 | Q=4.00 | alpha=3.17 | D_ks=0.04 | alpha-hat=5.98 | num traps=1
Layer 36
Layer=36 | N=6144 | M=1536 | Q=4.00 | alpha=4.16 | D_ks=0.05 | alpha-hat=5.62 | num traps=0
Layer 40
Layer=40 | N=4608 | M=1536 | Q=3.00 | alpha=4.66 | D_ks=0.03 | alpha-hat=5.89 | num traps=0
Layer 41
Layer=41 | N=1536 | M=1536 | Q=1.00 | alpha=4.33 | D_ks=0.06 | alpha-hat=4.63 | num traps=1
Layer 45
Layer=45 | N=6144 | M=1536 | Q=4.00 | alpha=3.80 | D_ks=0.01 | alpha-hat=6.79 | num traps=1
Layer 47
Layer=47 | N=6144 | M=1536 | Q=4.00 | alpha=3.26 | D_ks=0.09 | alpha-hat=4.51 | num traps=1
Layer 51
Layer=51 | N=4608 | M=1536 | Q=3.00 | alpha=4.28 | D_ks=0.03 | alpha-hat=5.54 | num traps=0
Layer 52
Layer=52 | N=1536 | M=1536 | Q=1.00 | alpha=4.11 | D_ks=0.04 | alpha-hat=4.54 | num traps=2
Layer 56
Layer=56 | N=6144 | M=1536 | Q=4.00 | alpha=3.64 | D_ks=0.01 | alpha-hat=5.73 | num traps=1
Layer 58
Layer=58 | N=6144 | M=1536 | Q=4.00 | alpha=4.22 | D_ks=0.03 | alpha-hat=5.83 | num traps=7
Layer 62
Layer=62 | N=4608 | M=1536 | Q=3.00 | alpha=4.02 | D_ks=0.03 | alpha-hat=5.55 | num traps=0
Layer 63
Layer=63 | N=1536 | M=1536 | Q=1.00 | alpha=4.44 | D_ks=0.04 | alpha-hat=4.08 | num traps=0
Layer 67
Layer=67 | N=6144 | M=1536 | Q=4.00 | alpha=3.33 | D_ks=0.01 | alpha-hat=6.46 | num traps=0
Layer 69
Layer=69 | N=6144 | M=1536 | Q=4.00 | alpha=3.67 | D_ks=0.04 | alpha-hat=6.42 | num traps=7
Layer 73
Layer=73 | N=4608 | M=1536 | Q=3.00 | alpha=3.49 | D_ks=0.05 | alpha-hat=4.54 | num traps=0
Layer 74
Layer=74 | N=1536 | M=1536 | Q=1.00 | alpha=4.24 | D_ks=0.08 | alpha-hat=2.79 | num traps=0
Layer 78
Layer=78 | N=6144 | M=1536 | Q=4.00 | alpha=3.42 | D_ks=0.02 | alpha-hat=6.70 | num traps=0
Layer 80
Layer=80 | N=6144 | M=1536 | Q=4.00 | alpha=3.68 | D_ks=0.03 | alpha-hat=5.93 | num traps=5
Layer 84
Layer=84 | N=4608 | M=1536 | Q=3.00 | alpha=2.48 | D_ks=0.08 | alpha-hat=3.29 | num traps=0
Layer 85
Layer=85 | N=1536 | M=1536 | Q=1.00 | alpha=3.81 | D_ks=0.09 | alpha-hat=1.75 | num traps=0
Layer 89
Layer=89 | N=6144 | M=1536 | Q=4.00 | alpha=3.66 | D_ks=0.01 | alpha-hat=6.57 | num traps=2
Layer 91
Layer=91 | N=6144 | M=1536 | Q=4.00 | alpha=4.03 | D_ks=0.02 | alpha-hat=5.84 | num traps=2
Layer 95
Layer=95 | N=4608 | M=1536 | Q=3.00 | alpha=2.31 | D_ks=0.08 | alpha-hat=2.99 | num traps=0
Layer 96
Layer=96 | N=1536 | M=1536 | Q=1.00 | alpha=3.64 | D_ks=0.05 | alpha-hat=1.25 | num traps=0
Layer 100
Layer=100 | N=6144 | M=1536 | Q=4.00 | alpha=3.70 | D_ks=0.02 | alpha-hat=5.31 | num traps=0
Layer 102
Layer=102 | N=6144 | M=1536 | Q=4.00 | alpha=3.63 | D_ks=0.04 | alpha-hat=3.69 | num traps=0
Layer 106
Layer=106 | N=4608 | M=1536 | Q=3.00 | alpha=3.25 | D_ks=0.09 | alpha-hat=4.23 | num traps=0
Layer 107
Layer=107 | N=1536 | M=1536 | Q=1.00 | alpha=3.93 | D_ks=0.08 | alpha-hat=1.86 | num traps=0
Layer 111
Layer=111 | N=6144 | M=1536 | Q=4.00 | alpha=3.40 | D_ks=0.03 | alpha-hat=5.10 | num traps=0
Layer 113
Layer=113 | N=6144 | M=1536 | Q=4.00 | alpha=3.27 | D_ks=0.05 | alpha-hat=3.34 | num traps=0
Layer 117
Layer=117 | N=4608 | M=1536 | Q=3.00 | alpha=3.97 | D_ks=0.06 | alpha-hat=4.82 | num traps=0
Layer 118
Layer=118 | N=1536 | M=1536 | Q=1.00 | alpha=6.91 | D_ks=0.04 | alpha-hat=3.65 | num traps=0
Layer 122
Layer=122 | N=6144 | M=1536 | Q=4.00 | alpha=3.15 | D_ks=0.06 | alpha-hat=4.78 | num traps=0
Layer 124
Layer=124 | N=6144 | M=1536 | Q=4.00 | alpha=3.97 | D_ks=0.04 | alpha-hat=3.71 | num traps=0
Layer 128
Layer=128 | N=4608 | M=1536 | Q=3.00 | alpha=2.73 | D_ks=0.07 | alpha-hat=3.54 | num traps=0
Layer 129
Layer=129 | N=1536 | M=1536 | Q=1.00 | alpha=3.26 | D_ks=0.10 | alpha-hat=1.03 | num traps=0
Layer 133
Layer=133 | N=6144 | M=1536 | Q=4.00 | alpha=3.82 | D_ks=0.03 | alpha-hat=6.57 | num traps=0
Layer 135
Layer=135 | N=6144 | M=1536 | Q=4.00 | alpha=5.02 | D_ks=0.05 | alpha-hat=4.69 | num traps=0
Layer 139
Layer=139 | N=4608 | M=1536 | Q=3.00 | alpha=3.51 | D_ks=0.05 | alpha-hat=4.55 | num traps=0
Layer 140
Layer=140 | N=1536 | M=1536 | Q=1.00 | alpha=3.85 | D_ks=0.09 | alpha-hat=1.54 | num traps=0
Layer 144
Layer=144 | N=6144 | M=1536 | Q=4.00 | alpha=3.87 | D_ks=0.03 | alpha-hat=6.72 | num traps=0
Layer 146
Layer=146 | N=6144 | M=1536 | Q=4.00 | alpha=4.56 | D_ks=0.05 | alpha-hat=4.58 | num traps=0
Layer 150
Layer=150 | N=4608 | M=1536 | Q=3.00 | alpha=3.64 | D_ks=0.05 | alpha-hat=4.46 | num traps=0
Layer 151
Layer=151 | N=1536 | M=1536 | Q=1.00 | alpha=3.14 | D_ks=0.08 | alpha-hat=1.41 | num traps=0
Layer 155
Layer=155 | N=6144 | M=1536 | Q=4.00 | alpha=3.60 | D_ks=0.03 | alpha-hat=6.28 | num traps=0
Layer 157
Layer=157 | N=6144 | M=1536 | Q=4.00 | alpha=4.47 | D_ks=0.05 | alpha-hat=4.44 | num traps=0
Layer 161
Layer=161 | N=4608 | M=1536 | Q=3.00 | alpha=3.81 | D_ks=0.06 | alpha-hat=4.62 | num traps=0
Layer 162
Layer=162 | N=1536 | M=1536 | Q=1.00 | alpha=5.04 | D_ks=0.12 | alpha-hat=3.54 | num traps=0
Layer 166
Layer=166 | N=6144 | M=1536 | Q=4.00 | alpha=3.86 | D_ks=0.04 | alpha-hat=6.69 | num traps=0
Layer 168
Layer=168 | N=6144 | M=1536 | Q=4.00 | alpha=4.12 | D_ks=0.04 | alpha-hat=4.38 | num traps=0
Layer 172
Layer=172 | N=4608 | M=1536 | Q=3.00 | alpha=3.52 | D_ks=0.06 | alpha-hat=4.64 | num traps=0
Layer 173
Layer=173 | N=1536 | M=1536 | Q=1.00 | alpha=5.79 | D_ks=0.08 | alpha-hat=2.19 | num traps=0
Layer 177
Layer=177 | N=6144 | M=1536 | Q=4.00 | alpha=3.82 | D_ks=0.03 | alpha-hat=6.60 | num traps=0
Layer 179
Layer=179 | N=6144 | M=1536 | Q=4.00 | alpha=4.29 | D_ks=0.04 | alpha-hat=4.85 | num traps=0
Layer 183
Layer=183 | N=4608 | M=1536 | Q=3.00 | alpha=3.65 | D_ks=0.07 | alpha-hat=4.53 | num traps=0
Layer 184
Layer=184 | N=1536 | M=1536 | Q=1.00 | alpha=3.72 | D_ks=0.04 | alpha-hat=2.40 | num traps=0
Layer 188
Layer=188 | N=6144 | M=1536 | Q=4.00 | alpha=3.78 | D_ks=0.02 | alpha-hat=6.61 | num traps=0
Layer 190
Layer=190 | N=6144 | M=1536 | Q=4.00 | alpha=4.43 | D_ks=0.04 | alpha-hat=5.30 | num traps=0
Layer 194
Layer=194 | N=4608 | M=1536 | Q=3.00 | alpha=3.58 | D_ks=0.07 | alpha-hat=4.34 | num traps=0
Layer 195
Layer=195 | N=1536 | M=1536 | Q=1.00 | alpha=4.18 | D_ks=0.09 | alpha-hat=2.36 | num traps=0
Layer 199
Layer=199 | N=6144 | M=1536 | Q=4.00 | alpha=3.87 | D_ks=0.02 | alpha-hat=6.87 | num traps=0
Layer 201
Layer=201 | N=6144 | M=1536 | Q=4.00 | alpha=4.69 | D_ks=0.03 | alpha-hat=6.06 | num traps=0
Layer 205
Layer=205 | N=4608 | M=1536 | Q=3.00 | alpha=4.35 | D_ks=0.06 | alpha-hat=5.08 | num traps=0
Layer 206
Layer=206 | N=1536 | M=1536 | Q=1.00 | alpha=8.54 | D_ks=0.04 | alpha-hat=4.52 | num traps=0
Layer 210
Layer=210 | N=6144 | M=1536 | Q=4.00 | alpha=3.93 | D_ks=0.01 | alpha-hat=7.08 | num traps=0
Layer 212
Layer=212 | N=6144 | M=1536 | Q=4.00 | alpha=5.33 | D_ks=0.03 | alpha-hat=7.11 | num traps=0
Layer 216
Layer=216 | N=4608 | M=1536 | Q=3.00 | alpha=4.25 | D_ks=0.07 | alpha-hat=5.44 | num traps=0
Layer 217
Layer=217 | N=1536 | M=1536 | Q=1.00 | alpha=6.19 | D_ks=0.06 | alpha-hat=5.94 | num traps=0
Layer 221
Layer=221 | N=6144 | M=1536 | Q=4.00 | alpha=3.73 | D_ks=0.01 | alpha-hat=6.90 | num traps=0
Layer 223
Layer=223 | N=6144 | M=1536 | Q=4.00 | alpha=4.87 | D_ks=0.04 | alpha-hat=6.21 | num traps=0
Layer 227
Layer=227 | N=4608 | M=1536 | Q=3.00 | alpha=4.03 | D_ks=0.05 | alpha-hat=5.23 | num traps=0
Layer 228
Layer=228 | N=1536 | M=1536 | Q=1.00 | alpha=4.71 | D_ks=0.07 | alpha-hat=4.44 | num traps=0
Layer 232
Layer=232 | N=6144 | M=1536 | Q=4.00 | alpha=3.31 | D_ks=0.01 | alpha-hat=6.71 | num traps=1
Layer 234
Layer=234 | N=6144 | M=1536 | Q=4.00 | alpha=4.99 | D_ks=0.02 | alpha-hat=6.44 | num traps=1
Layer 238
Layer=238 | N=4608 | M=1536 | Q=3.00 | alpha=3.64 | D_ks=0.03 | alpha-hat=5.10 | num traps=0
Layer 239
Layer=239 | N=1536 | M=1536 | Q=1.00 | alpha=2.70 | D_ks=0.09 | alpha-hat=4.75 | num traps=18
Layer 243
Layer=243 | N=6144 | M=1536 | Q=4.00 | alpha=3.28 | D_ks=0.02 | alpha-hat=6.40 | num traps=1
Layer 245
Layer=245 | N=6144 | M=1536 | Q=4.00 | alpha=4.08 | D_ks=0.03 | alpha-hat=7.65 | num traps=8
Layer 249
Layer=249 | N=4608 | M=1536 | Q=3.00 | alpha=3.39 | D_ks=0.02 | alpha-hat=4.94 | num traps=0
Layer 250
Layer=250 | N=1536 | M=1536 | Q=1.00 | alpha=2.69 | D_ks=0.08 | alpha-hat=5.32 | num traps=25
Layer 254
Layer=254 | N=6144 | M=1536 | Q=4.00 | alpha=3.07 | D_ks=0.01 | alpha-hat=6.95 | num traps=3
Layer 256
Layer=256 | N=6144 | M=1536 | Q=4.00 | alpha=4.69 | D_ks=0.03 | alpha-hat=8.36 | num traps=4
Layer 260
Layer=260 | N=4608 | M=1536 | Q=3.00 | alpha=3.41 | D_ks=0.01 | alpha-hat=5.06 | num traps=0
Layer 261
Layer=261 | N=1536 | M=1536 | Q=1.00 | alpha=2.42 | D_ks=0.02 | alpha-hat=4.44 | num traps=6
Layer 265
Layer=265 | N=6144 | M=1536 | Q=4.00 | alpha=3.30 | D_ks=0.01 | alpha-hat=6.63 | num traps=3
Layer 267
Layer=267 | N=6144 | M=1536 | Q=4.00 | alpha=4.72 | D_ks=0.04 | alpha-hat=8.24 | num traps=5
bigscience-bloom-1b1 Model Summary Plots
bigscience-bloom-1b1 Model Selected Details
| layer_type | N | M | Q | alpha | D | alpha-hat | log_SN | % Rand | num_traps | num_fingers | rank_loss | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| layer_id | ||||||||||||
| 7 | DENSE | 4608 | 1536 | 3.00 | 3.55 | 0.02 | 5.09 | 1.43 | 84.01 | 0 | 0 | 0 |
| 8 | DENSE | 1536 | 1536 | 1.00 | 3.84 | 0.06 | 4.42 | 1.15 | 83.70 | 1 | 0 | 3 |
| 12 | DENSE | 6144 | 1536 | 4.00 | 4.45 | 0.05 | 8.28 | 1.86 | 87.85 | 1 | 0 | 0 |
| 14 | DENSE | 6144 | 1536 | 4.00 | 3.72 | 0.02 | 5.79 | 1.56 | 84.67 | 4 | 0 | 0 |
| 18 | DENSE | 4608 | 1536 | 3.00 | 4.67 | 0.02 | 5.98 | 1.28 | 88.21 | 0 | 0 | 0 |
| 19 | DENSE | 1536 | 1536 | 1.00 | 4.11 | 0.02 | 4.23 | 1.03 | 84.97 | 2 | 0 | 2 |
| 23 | DENSE | 6144 | 1536 | 4.00 | 3.28 | 0.05 | 6.41 | 1.95 | 86.92 | 1 | 0 | 0 |
| 25 | DENSE | 6144 | 1536 | 4.00 | 4.56 | 0.02 | 6.96 | 1.53 | 90.60 | 0 | 0 | 0 |
| 29 | DENSE | 4608 | 1536 | 3.00 | 4.78 | 0.03 | 6.05 | 1.26 | 89.25 | 0 | 0 | 0 |
| 30 | DENSE | 1536 | 1536 | 1.00 | 3.46 | 0.04 | 3.27 | 0.94 | 86.33 | 1 | 0 | 3 |
| 34 | DENSE | 6144 | 1536 | 4.00 | 3.17 | 0.04 | 5.98 | 1.89 | 86.15 | 1 | 0 | 0 |
| 36 | DENSE | 6144 | 1536 | 4.00 | 4.16 | 0.05 | 5.62 | 1.35 | 88.08 | 0 | 0 | 0 |
| 40 | DENSE | 4608 | 1536 | 3.00 | 4.66 | 0.03 | 5.89 | 1.27 | 88.33 | 0 | 0 | 0 |
| 41 | DENSE | 1536 | 1536 | 1.00 | 4.33 | 0.06 | 4.63 | 1.07 | 87.44 | 1 | 0 | 3 |
| 45 | DENSE | 6144 | 1536 | 4.00 | 3.80 | 0.01 | 6.79 | 1.79 | 89.61 | 1 | 0 | 0 |
| 47 | DENSE | 6144 | 1536 | 4.00 | 3.26 | 0.09 | 4.51 | 1.38 | 89.09 | 1 | 6 | 0 |
| 51 | DENSE | 4608 | 1536 | 3.00 | 4.28 | 0.03 | 5.54 | 1.29 | 87.14 | 0 | 0 | 0 |
| 52 | DENSE | 1536 | 1536 | 1.00 | 4.11 | 0.04 | 4.54 | 1.10 | 87.51 | 2 | 0 | 3 |
| 56 | DENSE | 6144 | 1536 | 4.00 | 3.64 | 0.01 | 5.73 | 1.57 | 86.08 | 1 | 0 | 0 |
| 58 | DENSE | 6144 | 1536 | 4.00 | 4.22 | 0.03 | 5.83 | 1.38 | 87.46 | 7 | 0 | 0 |
| 62 | DENSE | 4608 | 1536 | 3.00 | 4.02 | 0.03 | 5.55 | 1.38 | 87.55 | 0 | 0 | 0 |
| 63 | DENSE | 1536 | 1536 | 1.00 | 4.44 | 0.04 | 4.08 | 0.92 | 87.83 | 0 | 0 | 4 |
| 67 | DENSE | 6144 | 1536 | 4.00 | 3.33 | 0.01 | 6.46 | 1.94 | 79.93 | 0 | 0 | 0 |
| 69 | DENSE | 6144 | 1536 | 4.00 | 3.67 | 0.04 | 6.42 | 1.75 | 84.66 | 7 | 0 | 0 |
| 73 | DENSE | 4608 | 1536 | 3.00 | 3.49 | 0.05 | 4.54 | 1.30 | 86.46 | 0 | 0 | 0 |
| 74 | DENSE | 1536 | 1536 | 1.00 | 4.24 | 0.08 | 2.79 | 0.66 | 90.69 | 0 | 2 | 3 |
| 78 | DENSE | 6144 | 1536 | 4.00 | 3.42 | 0.02 | 6.70 | 1.96 | 81.01 | 0 | 0 | 0 |
| 80 | DENSE | 6144 | 1536 | 4.00 | 3.68 | 0.03 | 5.93 | 1.61 | 86.55 | 5 | 0 | 0 |
| 84 | DENSE | 4608 | 1536 | 3.00 | 2.48 | 0.08 | 3.29 | 1.33 | 82.12 | 0 | 1 | 0 |
| 85 | DENSE | 1536 | 1536 | 1.00 | 3.81 | 0.09 | 1.75 | 0.46 | 87.73 | 0 | 1 | 3 |
| 89 | DENSE | 6144 | 1536 | 4.00 | 3.66 | 0.01 | 6.57 | 1.79 | 86.07 | 2 | 0 | 0 |
| 91 | DENSE | 6144 | 1536 | 4.00 | 4.03 | 0.02 | 5.84 | 1.45 | 87.65 | 2 | 0 | 0 |
| 95 | DENSE | 4608 | 1536 | 3.00 | 2.31 | 0.08 | 2.99 | 1.30 | 80.61 | 0 | 1 | 0 |
| 96 | DENSE | 1536 | 1536 | 1.00 | 3.64 | 0.05 | 1.25 | 0.34 | 87.95 | 0 | 0 | 3 |
| 100 | DENSE | 6144 | 1536 | 4.00 | 3.70 | 0.02 | 5.31 | 1.44 | 81.83 | 0 | 0 | 0 |
| 102 | DENSE | 6144 | 1536 | 4.00 | 3.63 | 0.04 | 3.69 | 1.02 | 82.38 | 0 | 0 | 0 |
| 106 | DENSE | 4608 | 1536 | 3.00 | 3.25 | 0.09 | 4.23 | 1.30 | 82.65 | 0 | 1 | 0 |
| 107 | DENSE | 1536 | 1536 | 1.00 | 3.93 | 0.08 | 1.86 | 0.47 | 89.51 | 0 | 0 | 4 |
| 111 | DENSE | 6144 | 1536 | 4.00 | 3.40 | 0.03 | 5.10 | 1.50 | 80.95 | 0 | 0 | 0 |
| 113 | DENSE | 6144 | 1536 | 4.00 | 3.27 | 0.05 | 3.34 | 1.02 | 84.63 | 0 | 0 | 0 |
| 117 | DENSE | 4608 | 1536 | 3.00 | 3.97 | 0.06 | 4.82 | 1.21 | 84.75 | 0 | 0 | 0 |
| 118 | DENSE | 1536 | 1536 | 1.00 | 6.91 | 0.04 | 3.65 | 0.53 | 90.79 | 0 | 0 | 4 |
| 122 | DENSE | 6144 | 1536 | 4.00 | 3.15 | 0.06 | 4.78 | 1.52 | 81.59 | 0 | 1 | 0 |
| 124 | DENSE | 6144 | 1536 | 4.00 | 3.97 | 0.04 | 3.71 | 0.94 | 87.00 | 0 | 0 | 0 |
| 128 | DENSE | 4608 | 1536 | 3.00 | 2.73 | 0.07 | 3.54 | 1.30 | 80.62 | 0 | 0 | 0 |
| 129 | DENSE | 1536 | 1536 | 1.00 | 3.26 | 0.10 | 1.03 | 0.32 | 89.20 | 0 | 0 | 3 |
| 133 | DENSE | 6144 | 1536 | 4.00 | 3.82 | 0.03 | 6.57 | 1.72 | 85.82 | 0 | 0 | 0 |
| 135 | DENSE | 6144 | 1536 | 4.00 | 5.02 | 0.05 | 4.69 | 0.93 | 92.62 | 0 | 0 | 0 |
| 139 | DENSE | 4608 | 1536 | 3.00 | 3.51 | 0.05 | 4.55 | 1.30 | 85.46 | 0 | 0 | 0 |
| 140 | DENSE | 1536 | 1536 | 1.00 | 3.85 | 0.09 | 1.54 | 0.40 | 91.13 | 0 | 1 | 3 |
| 144 | DENSE | 6144 | 1536 | 4.00 | 3.87 | 0.03 | 6.72 | 1.74 | 86.03 | 0 | 0 | 0 |
| 146 | DENSE | 6144 | 1536 | 4.00 | 4.56 | 0.05 | 4.58 | 1.00 | 91.48 | 0 | 0 | 0 |
| 150 | DENSE | 4608 | 1536 | 3.00 | 3.64 | 0.05 | 4.46 | 1.22 | 85.37 | 0 | 0 | 0 |
| 151 | DENSE | 1536 | 1536 | 1.00 | 3.14 | 0.08 | 1.41 | 0.45 | 88.80 | 0 | 0 | 3 |
| 155 | DENSE | 6144 | 1536 | 4.00 | 3.60 | 0.03 | 6.28 | 1.75 | 85.32 | 0 | 0 | 0 |
| 157 | DENSE | 6144 | 1536 | 4.00 | 4.47 | 0.05 | 4.44 | 0.99 | 90.58 | 0 | 0 | 0 |
| 161 | DENSE | 4608 | 1536 | 3.00 | 3.81 | 0.06 | 4.62 | 1.21 | 85.01 | 0 | 0 | 0 |
| 162 | DENSE | 1536 | 1536 | 1.00 | 5.04 | 0.12 | 3.54 | 0.70 | 87.69 | 0 | 5 | 3 |
| 166 | DENSE | 6144 | 1536 | 4.00 | 3.86 | 0.04 | 6.69 | 1.73 | 86.20 | 0 | 0 | 0 |
| 168 | DENSE | 6144 | 1536 | 4.00 | 4.12 | 0.04 | 4.38 | 1.06 | 89.47 | 0 | 0 | 0 |
| 172 | DENSE | 4608 | 1536 | 3.00 | 3.52 | 0.06 | 4.64 | 1.32 | 85.74 | 0 | 1 | 0 |
| 173 | DENSE | 1536 | 1536 | 1.00 | 5.79 | 0.08 | 2.19 | 0.38 | 89.52 | 0 | 0 | 3 |
| 177 | DENSE | 6144 | 1536 | 4.00 | 3.82 | 0.03 | 6.60 | 1.73 | 86.94 | 0 | 0 | 0 |
| 179 | DENSE | 6144 | 1536 | 4.00 | 4.29 | 0.04 | 4.85 | 1.13 | 89.41 | 0 | 0 | 0 |
| 183 | DENSE | 4608 | 1536 | 3.00 | 3.65 | 0.07 | 4.53 | 1.24 | 87.02 | 0 | 1 | 0 |
| 184 | DENSE | 1536 | 1536 | 1.00 | 3.72 | 0.04 | 2.40 | 0.64 | 87.37 | 0 | 0 | 4 |
| 188 | DENSE | 6144 | 1536 | 4.00 | 3.78 | 0.02 | 6.61 | 1.75 | 87.57 | 0 | 0 | 0 |
| 190 | DENSE | 6144 | 1536 | 4.00 | 4.43 | 0.04 | 5.30 | 1.20 | 89.74 | 0 | 0 | 0 |
| 194 | DENSE | 4608 | 1536 | 3.00 | 3.58 | 0.07 | 4.34 | 1.21 | 88.14 | 0 | 1 | 0 |
| 195 | DENSE | 1536 | 1536 | 1.00 | 4.18 | 0.09 | 2.36 | 0.56 | 89.23 | 0 | 1 | 3 |
| 199 | DENSE | 6144 | 1536 | 4.00 | 3.87 | 0.02 | 6.87 | 1.78 | 87.67 | 0 | 0 | 0 |
| 201 | DENSE | 6144 | 1536 | 4.00 | 4.69 | 0.03 | 6.06 | 1.29 | 89.80 | 0 | 0 | 0 |
| 205 | DENSE | 4608 | 1536 | 3.00 | 4.35 | 0.06 | 5.08 | 1.17 | 88.78 | 0 | 0 | 0 |
| 206 | DENSE | 1536 | 1536 | 1.00 | 8.54 | 0.04 | 4.52 | 0.53 | 93.21 | 0 | 0 | 4 |
| 210 | DENSE | 6144 | 1536 | 4.00 | 3.93 | 0.01 | 7.08 | 1.80 | 87.50 | 0 | 0 | 0 |
| 212 | DENSE | 6144 | 1536 | 4.00 | 5.33 | 0.03 | 7.11 | 1.33 | 91.03 | 0 | 0 | 0 |
| 216 | DENSE | 4608 | 1536 | 3.00 | 4.25 | 0.07 | 5.44 | 1.28 | 90.37 | 0 | 1 | 0 |
| 217 | DENSE | 1536 | 1536 | 1.00 | 6.19 | 0.06 | 5.94 | 0.96 | 92.81 | 0 | 0 | 2 |
| 221 | DENSE | 6144 | 1536 | 4.00 | 3.73 | 0.01 | 6.90 | 1.85 | 86.29 | 0 | 0 | 0 |
| 223 | DENSE | 6144 | 1536 | 4.00 | 4.87 | 0.04 | 6.21 | 1.27 | 92.22 | 0 | 0 | 0 |
| 227 | DENSE | 4608 | 1536 | 3.00 | 4.03 | 0.05 | 5.23 | 1.30 | 89.89 | 0 | 0 | 0 |
| 228 | DENSE | 1536 | 1536 | 1.00 | 4.71 | 0.07 | 4.44 | 0.94 | 91.02 | 0 | 0 | 2 |
| 232 | DENSE | 6144 | 1536 | 4.00 | 3.31 | 0.01 | 6.71 | 2.03 | 82.57 | 1 | 0 | 0 |
| 234 | DENSE | 6144 | 1536 | 4.00 | 4.99 | 0.02 | 6.44 | 1.29 | 93.01 | 1 | 0 | 0 |
| 238 | DENSE | 4608 | 1536 | 3.00 | 3.64 | 0.03 | 5.10 | 1.40 | 88.47 | 0 | 0 | 0 |
| 239 | DENSE | 1536 | 1536 | 1.00 | 2.70 | 0.09 | 4.75 | 1.76 | 77.16 | 18 | 0 | 3 |
| 243 | DENSE | 6144 | 1536 | 4.00 | 3.28 | 0.02 | 6.40 | 1.95 | 83.15 | 1 | 0 | 0 |
| 245 | DENSE | 6144 | 1536 | 4.00 | 4.08 | 0.03 | 7.65 | 1.87 | 90.48 | 8 | 0 | 0 |
| 249 | DENSE | 4608 | 1536 | 3.00 | 3.39 | 0.02 | 4.94 | 1.46 | 87.90 | 0 | 0 | 0 |
| 250 | DENSE | 1536 | 1536 | 1.00 | 2.69 | 0.08 | 5.32 | 1.98 | 70.46 | 25 | 0 | 3 |
| 254 | DENSE | 6144 | 1536 | 4.00 | 3.07 | 0.01 | 6.95 | 2.26 | 78.99 | 3 | 0 | 0 |
| 256 | DENSE | 6144 | 1536 | 4.00 | 4.69 | 0.03 | 8.36 | 1.78 | 91.46 | 4 | 0 | 0 |
| 260 | DENSE | 4608 | 1536 | 3.00 | 3.41 | 0.01 | 5.06 | 1.48 | 87.16 | 0 | 0 | 0 |
| 261 | DENSE | 1536 | 1536 | 1.00 | 2.42 | 0.02 | 4.44 | 1.84 | 73.47 | 6 | 0 | 3 |
| 265 | DENSE | 6144 | 1536 | 4.00 | 3.30 | 0.01 | 6.63 | 2.01 | 82.90 | 3 | 0 | 0 |
| 267 | DENSE | 6144 | 1536 | 4.00 | 4.72 | 0.04 | 8.24 | 1.75 | 90.96 | 5 | 0 | 0 |
bigscience-bloom-1b1 Layer Plots
Layer 7
Layer=7 | N=4608 | M=1536 | Q=3.00 | alpha=3.55 | D_ks=0.02 | alpha-hat=5.09 | num traps=0
Layer 8
Layer=8 | N=1536 | M=1536 | Q=1.00 | alpha=3.84 | D_ks=0.06 | alpha-hat=4.42 | num traps=1
Layer 12
Layer=12 | N=6144 | M=1536 | Q=4.00 | alpha=4.45 | D_ks=0.05 | alpha-hat=8.28 | num traps=1
Layer 14
Layer=14 | N=6144 | M=1536 | Q=4.00 | alpha=3.72 | D_ks=0.02 | alpha-hat=5.79 | num traps=4
Layer 18
Layer=18 | N=4608 | M=1536 | Q=3.00 | alpha=4.67 | D_ks=0.02 | alpha-hat=5.98 | num traps=0
Layer 19
Layer=19 | N=1536 | M=1536 | Q=1.00 | alpha=4.11 | D_ks=0.02 | alpha-hat=4.23 | num traps=2
Layer 23
Layer=23 | N=6144 | M=1536 | Q=4.00 | alpha=3.28 | D_ks=0.05 | alpha-hat=6.41 | num traps=1
Layer 25
Layer=25 | N=6144 | M=1536 | Q=4.00 | alpha=4.56 | D_ks=0.02 | alpha-hat=6.96 | num traps=0
Layer 29
Layer=29 | N=4608 | M=1536 | Q=3.00 | alpha=4.78 | D_ks=0.03 | alpha-hat=6.05 | num traps=0
Layer 30
Layer=30 | N=1536 | M=1536 | Q=1.00 | alpha=3.46 | D_ks=0.04 | alpha-hat=3.27 | num traps=1
Layer 34
Layer=34 | N=6144 | M=1536 | Q=4.00 | alpha=3.17 | D_ks=0.04 | alpha-hat=5.98 | num traps=1
Layer 36
Layer=36 | N=6144 | M=1536 | Q=4.00 | alpha=4.16 | D_ks=0.05 | alpha-hat=5.62 | num traps=0
Layer 40
Layer=40 | N=4608 | M=1536 | Q=3.00 | alpha=4.66 | D_ks=0.03 | alpha-hat=5.89 | num traps=0
Layer 41
Layer=41 | N=1536 | M=1536 | Q=1.00 | alpha=4.33 | D_ks=0.06 | alpha-hat=4.63 | num traps=1
Layer 45
Layer=45 | N=6144 | M=1536 | Q=4.00 | alpha=3.80 | D_ks=0.01 | alpha-hat=6.79 | num traps=1
Layer 47
Layer=47 | N=6144 | M=1536 | Q=4.00 | alpha=3.26 | D_ks=0.09 | alpha-hat=4.51 | num traps=1
Layer 51
Layer=51 | N=4608 | M=1536 | Q=3.00 | alpha=4.28 | D_ks=0.03 | alpha-hat=5.54 | num traps=0
Layer 52
Layer=52 | N=1536 | M=1536 | Q=1.00 | alpha=4.11 | D_ks=0.04 | alpha-hat=4.54 | num traps=2
Layer 56
Layer=56 | N=6144 | M=1536 | Q=4.00 | alpha=3.64 | D_ks=0.01 | alpha-hat=5.73 | num traps=1
Layer 58
Layer=58 | N=6144 | M=1536 | Q=4.00 | alpha=4.22 | D_ks=0.03 | alpha-hat=5.83 | num traps=7
Layer 62
Layer=62 | N=4608 | M=1536 | Q=3.00 | alpha=4.02 | D_ks=0.03 | alpha-hat=5.55 | num traps=0
Layer 63
Layer=63 | N=1536 | M=1536 | Q=1.00 | alpha=4.44 | D_ks=0.04 | alpha-hat=4.08 | num traps=0
Layer 67
Layer=67 | N=6144 | M=1536 | Q=4.00 | alpha=3.33 | D_ks=0.01 | alpha-hat=6.46 | num traps=0
Layer 69
Layer=69 | N=6144 | M=1536 | Q=4.00 | alpha=3.67 | D_ks=0.04 | alpha-hat=6.42 | num traps=7
Layer 73
Layer=73 | N=4608 | M=1536 | Q=3.00 | alpha=3.49 | D_ks=0.05 | alpha-hat=4.54 | num traps=0
Layer 74
Layer=74 | N=1536 | M=1536 | Q=1.00 | alpha=4.24 | D_ks=0.08 | alpha-hat=2.79 | num traps=0
Layer 78
Layer=78 | N=6144 | M=1536 | Q=4.00 | alpha=3.42 | D_ks=0.02 | alpha-hat=6.70 | num traps=0
Layer 80
Layer=80 | N=6144 | M=1536 | Q=4.00 | alpha=3.68 | D_ks=0.03 | alpha-hat=5.93 | num traps=5
Layer 84
Layer=84 | N=4608 | M=1536 | Q=3.00 | alpha=2.48 | D_ks=0.08 | alpha-hat=3.29 | num traps=0
Layer 85
Layer=85 | N=1536 | M=1536 | Q=1.00 | alpha=3.81 | D_ks=0.09 | alpha-hat=1.75 | num traps=0
Layer 89
Layer=89 | N=6144 | M=1536 | Q=4.00 | alpha=3.66 | D_ks=0.01 | alpha-hat=6.57 | num traps=2
Layer 91
Layer=91 | N=6144 | M=1536 | Q=4.00 | alpha=4.03 | D_ks=0.02 | alpha-hat=5.84 | num traps=2
Layer 95
Layer=95 | N=4608 | M=1536 | Q=3.00 | alpha=2.31 | D_ks=0.08 | alpha-hat=2.99 | num traps=0
Layer 96
Layer=96 | N=1536 | M=1536 | Q=1.00 | alpha=3.64 | D_ks=0.05 | alpha-hat=1.25 | num traps=0
Layer 100
Layer=100 | N=6144 | M=1536 | Q=4.00 | alpha=3.70 | D_ks=0.02 | alpha-hat=5.31 | num traps=0
Layer 102
Layer=102 | N=6144 | M=1536 | Q=4.00 | alpha=3.63 | D_ks=0.04 | alpha-hat=3.69 | num traps=0
Layer 106
Layer=106 | N=4608 | M=1536 | Q=3.00 | alpha=3.25 | D_ks=0.09 | alpha-hat=4.23 | num traps=0
Layer 107
Layer=107 | N=1536 | M=1536 | Q=1.00 | alpha=3.93 | D_ks=0.08 | alpha-hat=1.86 | num traps=0
Layer 111
Layer=111 | N=6144 | M=1536 | Q=4.00 | alpha=3.40 | D_ks=0.03 | alpha-hat=5.10 | num traps=0
Layer 113
Layer=113 | N=6144 | M=1536 | Q=4.00 | alpha=3.27 | D_ks=0.05 | alpha-hat=3.34 | num traps=0
Layer 117
Layer=117 | N=4608 | M=1536 | Q=3.00 | alpha=3.97 | D_ks=0.06 | alpha-hat=4.82 | num traps=0
Layer 118
Layer=118 | N=1536 | M=1536 | Q=1.00 | alpha=6.91 | D_ks=0.04 | alpha-hat=3.65 | num traps=0
Layer 122
Layer=122 | N=6144 | M=1536 | Q=4.00 | alpha=3.15 | D_ks=0.06 | alpha-hat=4.78 | num traps=0
Layer 124
Layer=124 | N=6144 | M=1536 | Q=4.00 | alpha=3.97 | D_ks=0.04 | alpha-hat=3.71 | num traps=0
Layer 128
Layer=128 | N=4608 | M=1536 | Q=3.00 | alpha=2.73 | D_ks=0.07 | alpha-hat=3.54 | num traps=0
Layer 129
Layer=129 | N=1536 | M=1536 | Q=1.00 | alpha=3.26 | D_ks=0.10 | alpha-hat=1.03 | num traps=0
Layer 133
Layer=133 | N=6144 | M=1536 | Q=4.00 | alpha=3.82 | D_ks=0.03 | alpha-hat=6.57 | num traps=0
Layer 135
Layer=135 | N=6144 | M=1536 | Q=4.00 | alpha=5.02 | D_ks=0.05 | alpha-hat=4.69 | num traps=0
Layer 139
Layer=139 | N=4608 | M=1536 | Q=3.00 | alpha=3.51 | D_ks=0.05 | alpha-hat=4.55 | num traps=0
Layer 140
Layer=140 | N=1536 | M=1536 | Q=1.00 | alpha=3.85 | D_ks=0.09 | alpha-hat=1.54 | num traps=0
Layer 144
Layer=144 | N=6144 | M=1536 | Q=4.00 | alpha=3.87 | D_ks=0.03 | alpha-hat=6.72 | num traps=0
Layer 146
Layer=146 | N=6144 | M=1536 | Q=4.00 | alpha=4.56 | D_ks=0.05 | alpha-hat=4.58 | num traps=0
Layer 150
Layer=150 | N=4608 | M=1536 | Q=3.00 | alpha=3.64 | D_ks=0.05 | alpha-hat=4.46 | num traps=0
Layer 151
Layer=151 | N=1536 | M=1536 | Q=1.00 | alpha=3.14 | D_ks=0.08 | alpha-hat=1.41 | num traps=0
Layer 155
Layer=155 | N=6144 | M=1536 | Q=4.00 | alpha=3.60 | D_ks=0.03 | alpha-hat=6.28 | num traps=0
Layer 157
Layer=157 | N=6144 | M=1536 | Q=4.00 | alpha=4.47 | D_ks=0.05 | alpha-hat=4.44 | num traps=0
Layer 161
Layer=161 | N=4608 | M=1536 | Q=3.00 | alpha=3.81 | D_ks=0.06 | alpha-hat=4.62 | num traps=0
Layer 162
Layer=162 | N=1536 | M=1536 | Q=1.00 | alpha=5.04 | D_ks=0.12 | alpha-hat=3.54 | num traps=0
Layer 166
Layer=166 | N=6144 | M=1536 | Q=4.00 | alpha=3.86 | D_ks=0.04 | alpha-hat=6.69 | num traps=0
Layer 168
Layer=168 | N=6144 | M=1536 | Q=4.00 | alpha=4.12 | D_ks=0.04 | alpha-hat=4.38 | num traps=0
Layer 172
Layer=172 | N=4608 | M=1536 | Q=3.00 | alpha=3.52 | D_ks=0.06 | alpha-hat=4.64 | num traps=0
Layer 173
Layer=173 | N=1536 | M=1536 | Q=1.00 | alpha=5.79 | D_ks=0.08 | alpha-hat=2.19 | num traps=0
Layer 177
Layer=177 | N=6144 | M=1536 | Q=4.00 | alpha=3.82 | D_ks=0.03 | alpha-hat=6.60 | num traps=0
Layer 179
Layer=179 | N=6144 | M=1536 | Q=4.00 | alpha=4.29 | D_ks=0.04 | alpha-hat=4.85 | num traps=0
Layer 183
Layer=183 | N=4608 | M=1536 | Q=3.00 | alpha=3.65 | D_ks=0.07 | alpha-hat=4.53 | num traps=0
Layer 184
Layer=184 | N=1536 | M=1536 | Q=1.00 | alpha=3.72 | D_ks=0.04 | alpha-hat=2.40 | num traps=0
Layer 188
Layer=188 | N=6144 | M=1536 | Q=4.00 | alpha=3.78 | D_ks=0.02 | alpha-hat=6.61 | num traps=0
Layer 190
Layer=190 | N=6144 | M=1536 | Q=4.00 | alpha=4.43 | D_ks=0.04 | alpha-hat=5.30 | num traps=0
Layer 194
Layer=194 | N=4608 | M=1536 | Q=3.00 | alpha=3.58 | D_ks=0.07 | alpha-hat=4.34 | num traps=0
Layer 195
Layer=195 | N=1536 | M=1536 | Q=1.00 | alpha=4.18 | D_ks=0.09 | alpha-hat=2.36 | num traps=0
Layer 199
Layer=199 | N=6144 | M=1536 | Q=4.00 | alpha=3.87 | D_ks=0.02 | alpha-hat=6.87 | num traps=0
Layer 201
Layer=201 | N=6144 | M=1536 | Q=4.00 | alpha=4.69 | D_ks=0.03 | alpha-hat=6.06 | num traps=0
Layer 205
Layer=205 | N=4608 | M=1536 | Q=3.00 | alpha=4.35 | D_ks=0.06 | alpha-hat=5.08 | num traps=0
Layer 206
Layer=206 | N=1536 | M=1536 | Q=1.00 | alpha=8.54 | D_ks=0.04 | alpha-hat=4.52 | num traps=0
Layer 210
Layer=210 | N=6144 | M=1536 | Q=4.00 | alpha=3.93 | D_ks=0.01 | alpha-hat=7.08 | num traps=0
Layer 212
Layer=212 | N=6144 | M=1536 | Q=4.00 | alpha=5.33 | D_ks=0.03 | alpha-hat=7.11 | num traps=0
Layer 216
Layer=216 | N=4608 | M=1536 | Q=3.00 | alpha=4.25 | D_ks=0.07 | alpha-hat=5.44 | num traps=0
Layer 217
Layer=217 | N=1536 | M=1536 | Q=1.00 | alpha=6.19 | D_ks=0.06 | alpha-hat=5.94 | num traps=0
Layer 221
Layer=221 | N=6144 | M=1536 | Q=4.00 | alpha=3.73 | D_ks=0.01 | alpha-hat=6.90 | num traps=0
Layer 223
Layer=223 | N=6144 | M=1536 | Q=4.00 | alpha=4.87 | D_ks=0.04 | alpha-hat=6.21 | num traps=0
Layer 227
Layer=227 | N=4608 | M=1536 | Q=3.00 | alpha=4.03 | D_ks=0.05 | alpha-hat=5.23 | num traps=0
Layer 228
Layer=228 | N=1536 | M=1536 | Q=1.00 | alpha=4.71 | D_ks=0.07 | alpha-hat=4.44 | num traps=0
Layer 232
Layer=232 | N=6144 | M=1536 | Q=4.00 | alpha=3.31 | D_ks=0.01 | alpha-hat=6.71 | num traps=1
Layer 234
Layer=234 | N=6144 | M=1536 | Q=4.00 | alpha=4.99 | D_ks=0.02 | alpha-hat=6.44 | num traps=1
Layer 238
Layer=238 | N=4608 | M=1536 | Q=3.00 | alpha=3.64 | D_ks=0.03 | alpha-hat=5.10 | num traps=0
Layer 239
Layer=239 | N=1536 | M=1536 | Q=1.00 | alpha=2.70 | D_ks=0.09 | alpha-hat=4.75 | num traps=18
Layer 243
Layer=243 | N=6144 | M=1536 | Q=4.00 | alpha=3.28 | D_ks=0.02 | alpha-hat=6.40 | num traps=1
Layer 245
Layer=245 | N=6144 | M=1536 | Q=4.00 | alpha=4.08 | D_ks=0.03 | alpha-hat=7.65 | num traps=8
Layer 249
Layer=249 | N=4608 | M=1536 | Q=3.00 | alpha=3.39 | D_ks=0.02 | alpha-hat=4.94 | num traps=0
Layer 250
Layer=250 | N=1536 | M=1536 | Q=1.00 | alpha=2.69 | D_ks=0.08 | alpha-hat=5.32 | num traps=25
Layer 254
Layer=254 | N=6144 | M=1536 | Q=4.00 | alpha=3.07 | D_ks=0.01 | alpha-hat=6.95 | num traps=3
Layer 256
Layer=256 | N=6144 | M=1536 | Q=4.00 | alpha=4.69 | D_ks=0.03 | alpha-hat=8.36 | num traps=4
Layer 260
Layer=260 | N=4608 | M=1536 | Q=3.00 | alpha=3.41 | D_ks=0.01 | alpha-hat=5.06 | num traps=0
Layer 261
Layer=261 | N=1536 | M=1536 | Q=1.00 | alpha=2.42 | D_ks=0.02 | alpha-hat=4.44 | num traps=6
Layer 265
Layer=265 | N=6144 | M=1536 | Q=4.00 | alpha=3.30 | D_ks=0.01 | alpha-hat=6.63 | num traps=3
Layer 267
Layer=267 | N=6144 | M=1536 | Q=4.00 | alpha=4.72 | D_ks=0.04 | alpha-hat=8.24 | num traps=5