bigscience-bloom-560m
Find this model in the BLOOM model summary
bigscience-bloom-560m Model Summary Plots
bigscience-bloom-560m 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
3072
1024
3.00
4.04
0.03
4.93
1.22
85.49
0
0
0
8
DENSE
1024
1024
1.00
3.71
0.07
3.63
0.98
83.14
1
0
3
12
DENSE
4096
1024
4.00
4.41
0.06
7.42
1.68
89.63
1
0
0
14
DENSE
4096
1024
4.00
3.46
0.02
4.47
1.29
86.12
2
0
0
18
DENSE
3072
1024
3.00
4.47
0.03
5.35
1.20
87.61
0
0
0
19
DENSE
1024
1024
1.00
3.94
0.06
2.70
0.68
84.03
1
0
3
23
DENSE
4096
1024
4.00
3.36
0.04
5.76
1.71
87.90
1
0
0
25
DENSE
4096
1024
4.00
4.10
0.02
4.72
1.15
90.08
1
0
0
29
DENSE
3072
1024
3.00
4.79
0.04
5.25
1.10
88.28
0
0
0
30
DENSE
1024
1024
1.00
4.12
0.04
2.01
0.49
87.72
0
0
3
34
DENSE
4096
1024
4.00
3.05
0.04
4.98
1.63
85.50
1
0
0
36
DENSE
4096
1024
4.00
3.88
0.04
4.10
1.06
88.95
0
0
0
40
DENSE
3072
1024
3.00
4.73
0.03
5.01
1.06
89.43
0
0
0
41
DENSE
1024
1024
1.00
4.75
0.05
2.75
0.58
88.12
0
0
3
45
DENSE
4096
1024
4.00
3.53
0.02
5.51
1.56
88.06
1
0
0
47
DENSE
4096
1024
4.00
3.32
0.08
3.41
1.03
87.96
0
1
0
51
DENSE
3072
1024
3.00
4.25
0.04
4.67
1.10
87.99
0
0
0
52
DENSE
1024
1024
1.00
4.70
0.10
2.99
0.64
89.81
0
1
3
56
DENSE
4096
1024
4.00
3.63
0.02
6.87
1.89
84.49
0
0
0
58
DENSE
4096
1024
4.00
4.29
0.05
5.87
1.37
89.25
8
0
0
62
DENSE
3072
1024
3.00
3.97
0.05
4.16
1.05
87.96
0
0
0
63
DENSE
1024
1024
1.00
3.34
0.08
1.42
0.43
88.51
0
1
3
67
DENSE
4096
1024
4.00
3.66
0.02
6.17
1.69
84.86
0
0
0
69
DENSE
4096
1024
4.00
4.05
0.03
5.00
1.23
89.15
4
0
0
73
DENSE
3072
1024
3.00
2.38
0.05
2.93
1.23
81.06
0
0
0
74
DENSE
1024
1024
1.00
4.65
0.06
1.53
0.33
91.37
0
0
4
78
DENSE
4096
1024
4.00
3.72
0.02
5.97
1.61
85.64
2
0
0
80
DENSE
4096
1024
4.00
4.06
0.03
5.40
1.33
87.02
1
0
0
84
DENSE
3072
1024
3.00
2.18
0.10
2.47
1.13
79.28
0
4
0
85
DENSE
1024
1024
1.00
3.95
0.06
1.45
0.37
85.45
0
0
3
89
DENSE
4096
1024
4.00
3.54
0.03
4.66
1.31
82.51
0
0
0
91
DENSE
4096
1024
4.00
4.16
0.04
3.80
0.91
83.54
1
0
0
95
DENSE
3072
1024
3.00
4.27
0.08
4.79
1.12
79.83
0
0
0
96
DENSE
1024
1024
1.00
2.88
0.10
0.49
0.17
85.71
0
0
2
100
DENSE
4096
1024
4.00
3.62
0.03
4.21
1.16
77.96
0
0
0
102
DENSE
4096
1024
4.00
3.12
0.06
2.52
0.81
80.30
1
0
0
106
DENSE
3072
1024
3.00
5.55
0.04
6.23
1.12
83.47
0
0
0
107
DENSE
1024
1024
1.00
5.68
0.04
2.17
0.38
90.31
0
0
3
111
DENSE
4096
1024
4.00
3.28
0.05
3.60
1.10
74.52
0
0
0
113
DENSE
4096
1024
4.00
3.78
0.04
3.06
0.81
77.04
0
0
0
117
DENSE
3072
1024
3.00
2.62
0.07
5.42
2.07
74.39
0
1
0
118
DENSE
1024
1024
1.00
4.75
0.07
0.80
0.17
87.22
0
0
3
122
DENSE
4096
1024
4.00
3.51
0.04
5.05
1.44
82.94
0
0
0
124
DENSE
4096
1024
4.00
4.06
0.05
3.83
0.94
87.55
1
0
0
128
DENSE
3072
1024
3.00
3.36
0.08
3.70
1.10
84.81
0
1
0
129
DENSE
1024
1024
1.00
5.27
0.04
1.71
0.33
93.56
0
0
2
133
DENSE
4096
1024
4.00
3.75
0.03
5.27
1.41
85.53
0
0
0
135
DENSE
4096
1024
4.00
4.83
0.03
4.06
0.84
90.64
1
0
0
139
DENSE
3072
1024
3.00
3.32
0.07
5.29
1.59
81.38
0
1
0
140
DENSE
1024
1024
1.00
4.99
0.09
1.31
0.26
88.84
0
0
3
144
DENSE
4096
1024
4.00
4.52
0.04
6.64
1.47
86.14
0
0
0
146
DENSE
4096
1024
4.00
4.65
0.06
4.05
0.87
92.36
0
0
0
150
DENSE
3072
1024
3.00
3.67
0.06
4.17
1.14
85.68
0
0
0
151
DENSE
1024
1024
1.00
3.30
0.08
0.99
0.30
89.52
0
0
1
155
DENSE
4096
1024
4.00
3.89
0.05
5.62
1.44
86.30
0
0
0
157
DENSE
4096
1024
4.00
4.39
0.07
3.74
0.85
91.12
0
1
0
161
DENSE
3072
1024
3.00
4.46
0.04
5.39
1.21
85.81
0
0
0
162
DENSE
1024
1024
1.00
2.62
0.13
0.93
0.35
88.49
0
2
2
166
DENSE
4096
1024
4.00
4.48
0.04
6.52
1.45
86.69
0
0
0
168
DENSE
4096
1024
4.00
3.86
0.07
3.47
0.90
89.74
0
2
0
172
DENSE
3072
1024
3.00
3.43
0.07
3.75
1.09
86.85
0
0
0
173
DENSE
1024
1024
1.00
5.14
0.10
1.73
0.34
89.15
0
1
3
177
DENSE
4096
1024
4.00
4.48
0.04
6.55
1.46
87.14
0
0
0
179
DENSE
4096
1024
4.00
4.36
0.05
4.00
0.92
88.87
0
0
0
183
DENSE
3072
1024
3.00
3.42
0.05
3.83
1.12
87.94
0
0
0
184
DENSE
1024
1024
1.00
2.84
0.08
0.81
0.28
88.88
0
0
2
188
DENSE
4096
1024
4.00
4.35
0.04
6.29
1.45
87.73
0
0
0
190
DENSE
4096
1024
4.00
3.93
0.04
4.07
1.04
88.65
0
0
0
194
DENSE
3072
1024
3.00
5.00
0.05
6.34
1.27
87.45
0
0
0
195
DENSE
1024
1024
1.00
3.17
0.09
1.18
0.37
89.43
0
1
2
199
DENSE
4096
1024
4.00
4.13
0.03
6.09
1.47
88.27
1
0
0
201
DENSE
4096
1024
4.00
4.34
0.03
4.91
1.13
88.72
0
0
0
205
DENSE
3072
1024
3.00
2.92
0.08
5.89
2.02
82.26
0
1
0
206
DENSE
1024
1024
1.00
5.11
0.05
3.32
0.65
89.48
0
0
3
210
DENSE
4096
1024
4.00
4.15
0.02
6.23
1.50
88.17
1
0
0
212
DENSE
4096
1024
4.00
3.96
0.03
4.55
1.15
89.14
0
0
0
216
DENSE
3072
1024
3.00
3.20
0.08
4.13
1.29
87.95
0
3
0
217
DENSE
1024
1024
1.00
4.22
0.04
2.42
0.57
92.69
0
0
1
221
DENSE
4096
1024
4.00
4.12
0.02
6.33
1.54
87.80
1
0
0
223
DENSE
4096
1024
4.00
3.97
0.03
4.92
1.24
89.62
0
0
0
227
DENSE
3072
1024
3.00
2.93
0.08
3.20
1.09
87.55
0
1
0
228
DENSE
1024
1024
1.00
2.74
0.09
3.12
1.14
83.60
1
0
1
232
DENSE
4096
1024
4.00
3.65
0.02
5.79
1.59
86.18
0
0
0
234
DENSE
4096
1024
4.00
3.31
0.04
4.94
1.49
86.57
0
0
0
238
DENSE
3072
1024
3.00
3.40
0.03
5.70
1.68
85.42
0
0
0
239
DENSE
1024
1024
1.00
2.24
0.10
3.57
1.59
65.64
16
0
2
243
DENSE
4096
1024
4.00
3.41
0.02
5.67
1.66
84.15
0
0
0
245
DENSE
4096
1024
4.00
2.73
0.08
5.34
1.95
78.71
13
0
0
249
DENSE
3072
1024
3.00
2.83
0.01
7.66
2.71
69.06
12
0
0
250
DENSE
1024
1024
1.00
2.50
0.07
5.46
2.18
53.11
26
0
2
254
DENSE
4096
1024
4.00
3.07
0.02
5.84
1.91
80.73
1
0
0
256
DENSE
4096
1024
4.00
3.81
0.06
7.11
1.87
81.14
16
0
0
260
DENSE
3072
1024
3.00
2.84
0.01
4.96
1.74
79.27
0
0
0
261
DENSE
1024
1024
1.00
2.22
0.07
3.21
1.45
63.55
16
0
2
265
DENSE
4096
1024
4.00
3.29
0.02
5.89
1.79
83.00
0
0
0
267
DENSE
4096
1024
4.00
3.36
0.03
5.50
1.64
85.56
6
0
0
bigscience-bloom-560m Layer Plots
Layer 7
Layer=7 | N=3072 | M=1024 | Q=3.00 | alpha=4.04 | D_ks=0.03 | alpha-hat=4.93 | num traps=0
Layer 8
Layer=8 | N=1024 | M=1024 | Q=1.00 | alpha=3.71 | D_ks=0.07 | alpha-hat=3.63 | num traps=1
Layer 12
Layer=12 | N=4096 | M=1024 | Q=4.00 | alpha=4.41 | D_ks=0.06 | alpha-hat=7.42 | num traps=1
Layer 14
Layer=14 | N=4096 | M=1024 | Q=4.00 | alpha=3.46 | D_ks=0.02 | alpha-hat=4.47 | num traps=2
Layer 18
Layer=18 | N=3072 | M=1024 | Q=3.00 | alpha=4.47 | D_ks=0.03 | alpha-hat=5.35 | num traps=0
Layer 19
Layer=19 | N=1024 | M=1024 | Q=1.00 | alpha=3.94 | D_ks=0.06 | alpha-hat=2.70 | num traps=1
Layer 23
Layer=23 | N=4096 | M=1024 | Q=4.00 | alpha=3.36 | D_ks=0.04 | alpha-hat=5.76 | num traps=1
Layer 25
Layer=25 | N=4096 | M=1024 | Q=4.00 | alpha=4.10 | D_ks=0.02 | alpha-hat=4.72 | num traps=1
Layer 29
Layer=29 | N=3072 | M=1024 | Q=3.00 | alpha=4.79 | D_ks=0.04 | alpha-hat=5.25 | num traps=0
Layer 30
Layer=30 | N=1024 | M=1024 | Q=1.00 | alpha=4.12 | D_ks=0.04 | alpha-hat=2.01 | num traps=0
Layer 34
Layer=34 | N=4096 | M=1024 | Q=4.00 | alpha=3.05 | D_ks=0.04 | alpha-hat=4.98 | num traps=1
Layer 36
Layer=36 | N=4096 | M=1024 | Q=4.00 | alpha=3.88 | D_ks=0.04 | alpha-hat=4.10 | num traps=0
Layer 40
Layer=40 | N=3072 | M=1024 | Q=3.00 | alpha=4.73 | D_ks=0.03 | alpha-hat=5.01 | num traps=0
Layer 41
Layer=41 | N=1024 | M=1024 | Q=1.00 | alpha=4.75 | D_ks=0.05 | alpha-hat=2.75 | num traps=0
Layer 45
Layer=45 | N=4096 | M=1024 | Q=4.00 | alpha=3.53 | D_ks=0.02 | alpha-hat=5.51 | num traps=1
Layer 47
Layer=47 | N=4096 | M=1024 | Q=4.00 | alpha=3.32 | D_ks=0.08 | alpha-hat=3.41 | num traps=0
Layer 51
Layer=51 | N=3072 | M=1024 | Q=3.00 | alpha=4.25 | D_ks=0.04 | alpha-hat=4.67 | num traps=0
Layer 52
Layer=52 | N=1024 | M=1024 | Q=1.00 | alpha=4.70 | D_ks=0.10 | alpha-hat=2.99 | num traps=0
Layer 56
Layer=56 | N=4096 | M=1024 | Q=4.00 | alpha=3.63 | D_ks=0.02 | alpha-hat=6.87 | num traps=0
Layer 58
Layer=58 | N=4096 | M=1024 | Q=4.00 | alpha=4.29 | D_ks=0.05 | alpha-hat=5.87 | num traps=8
Layer 62
Layer=62 | N=3072 | M=1024 | Q=3.00 | alpha=3.97 | D_ks=0.05 | alpha-hat=4.16 | num traps=0
Layer 63
Layer=63 | N=1024 | M=1024 | Q=1.00 | alpha=3.34 | D_ks=0.08 | alpha-hat=1.42 | num traps=0
Layer 67
Layer=67 | N=4096 | M=1024 | Q=4.00 | alpha=3.66 | D_ks=0.02 | alpha-hat=6.17 | num traps=0
Layer 69
Layer=69 | N=4096 | M=1024 | Q=4.00 | alpha=4.05 | D_ks=0.03 | alpha-hat=5.00 | num traps=4
Layer 73
Layer=73 | N=3072 | M=1024 | Q=3.00 | alpha=2.38 | D_ks=0.05 | alpha-hat=2.93 | num traps=0
Layer 74
Layer=74 | N=1024 | M=1024 | Q=1.00 | alpha=4.65 | D_ks=0.06 | alpha-hat=1.53 | num traps=0
Layer 78
Layer=78 | N=4096 | M=1024 | Q=4.00 | alpha=3.72 | D_ks=0.02 | alpha-hat=5.97 | num traps=2
Layer 80
Layer=80 | N=4096 | M=1024 | Q=4.00 | alpha=4.06 | D_ks=0.03 | alpha-hat=5.40 | num traps=1
Layer 84
Layer=84 | N=3072 | M=1024 | Q=3.00 | alpha=2.18 | D_ks=0.10 | alpha-hat=2.47 | num traps=0
Layer 85
Layer=85 | N=1024 | M=1024 | Q=1.00 | alpha=3.95 | D_ks=0.06 | alpha-hat=1.45 | num traps=0
Layer 89
Layer=89 | N=4096 | M=1024 | Q=4.00 | alpha=3.54 | D_ks=0.03 | alpha-hat=4.66 | num traps=0
Layer 91
Layer=91 | N=4096 | M=1024 | Q=4.00 | alpha=4.16 | D_ks=0.04 | alpha-hat=3.80 | num traps=1
Layer 95
Layer=95 | N=3072 | M=1024 | Q=3.00 | alpha=4.27 | D_ks=0.08 | alpha-hat=4.79 | num traps=0
Layer 96
Layer=96 | N=1024 | M=1024 | Q=1.00 | alpha=2.88 | D_ks=0.10 | alpha-hat=0.49 | num traps=0
Layer 100
Layer=100 | N=4096 | M=1024 | Q=4.00 | alpha=3.62 | D_ks=0.03 | alpha-hat=4.21 | num traps=0
Layer 102
Layer=102 | N=4096 | M=1024 | Q=4.00 | alpha=3.12 | D_ks=0.06 | alpha-hat=2.52 | num traps=1
Layer 106
Layer=106 | N=3072 | M=1024 | Q=3.00 | alpha=5.55 | D_ks=0.04 | alpha-hat=6.23 | num traps=0
Layer 107
Layer=107 | N=1024 | M=1024 | Q=1.00 | alpha=5.68 | D_ks=0.04 | alpha-hat=2.17 | num traps=0
Layer 111
Layer=111 | N=4096 | M=1024 | Q=4.00 | alpha=3.28 | D_ks=0.05 | alpha-hat=3.60 | num traps=0
Layer 113
Layer=113 | N=4096 | M=1024 | Q=4.00 | alpha=3.78 | D_ks=0.04 | alpha-hat=3.06 | num traps=0
Layer 117
Layer=117 | N=3072 | M=1024 | Q=3.00 | alpha=2.62 | D_ks=0.07 | alpha-hat=5.42 | num traps=0
Layer 118
Layer=118 | N=1024 | M=1024 | Q=1.00 | alpha=4.75 | D_ks=0.07 | alpha-hat=0.80 | num traps=0
Layer 122
Layer=122 | N=4096 | M=1024 | Q=4.00 | alpha=3.51 | D_ks=0.04 | alpha-hat=5.05 | num traps=0
Layer 124
Layer=124 | N=4096 | M=1024 | Q=4.00 | alpha=4.06 | D_ks=0.05 | alpha-hat=3.83 | num traps=1
Layer 128
Layer=128 | N=3072 | M=1024 | Q=3.00 | alpha=3.36 | D_ks=0.08 | alpha-hat=3.70 | num traps=0
Layer 129
Layer=129 | N=1024 | M=1024 | Q=1.00 | alpha=5.27 | D_ks=0.04 | alpha-hat=1.71 | num traps=0
Layer 133
Layer=133 | N=4096 | M=1024 | Q=4.00 | alpha=3.75 | D_ks=0.03 | alpha-hat=5.27 | num traps=0
Layer 135
Layer=135 | N=4096 | M=1024 | Q=4.00 | alpha=4.83 | D_ks=0.03 | alpha-hat=4.06 | num traps=1
Layer 139
Layer=139 | N=3072 | M=1024 | Q=3.00 | alpha=3.32 | D_ks=0.07 | alpha-hat=5.29 | num traps=0
Layer 140
Layer=140 | N=1024 | M=1024 | Q=1.00 | alpha=4.99 | D_ks=0.09 | alpha-hat=1.31 | num traps=0
Layer 144
Layer=144 | N=4096 | M=1024 | Q=4.00 | alpha=4.52 | D_ks=0.04 | alpha-hat=6.64 | num traps=0
Layer 146
Layer=146 | N=4096 | M=1024 | Q=4.00 | alpha=4.65 | D_ks=0.06 | alpha-hat=4.05 | num traps=0
Layer 150
Layer=150 | N=3072 | M=1024 | Q=3.00 | alpha=3.67 | D_ks=0.06 | alpha-hat=4.17 | num traps=0
Layer 151
Layer=151 | N=1024 | M=1024 | Q=1.00 | alpha=3.30 | D_ks=0.08 | alpha-hat=0.99 | num traps=0
Layer 155
Layer=155 | N=4096 | M=1024 | Q=4.00 | alpha=3.89 | D_ks=0.05 | alpha-hat=5.62 | num traps=0
Layer 157
Layer=157 | N=4096 | M=1024 | Q=4.00 | alpha=4.39 | D_ks=0.07 | alpha-hat=3.74 | num traps=0
Layer 161
Layer=161 | N=3072 | M=1024 | Q=3.00 | alpha=4.46 | D_ks=0.04 | alpha-hat=5.39 | num traps=0
Layer 162
Layer=162 | N=1024 | M=1024 | Q=1.00 | alpha=2.62 | D_ks=0.13 | alpha-hat=0.93 | num traps=0
Layer 166
Layer=166 | N=4096 | M=1024 | Q=4.00 | alpha=4.48 | D_ks=0.04 | alpha-hat=6.52 | num traps=0
Layer 168
Layer=168 | N=4096 | M=1024 | Q=4.00 | alpha=3.86 | D_ks=0.07 | alpha-hat=3.47 | num traps=0
Layer 172
Layer=172 | N=3072 | M=1024 | Q=3.00 | alpha=3.43 | D_ks=0.07 | alpha-hat=3.75 | num traps=0
Layer 173
Layer=173 | N=1024 | M=1024 | Q=1.00 | alpha=5.14 | D_ks=0.10 | alpha-hat=1.73 | num traps=0
Layer 177
Layer=177 | N=4096 | M=1024 | Q=4.00 | alpha=4.48 | D_ks=0.04 | alpha-hat=6.55 | num traps=0
Layer 179
Layer=179 | N=4096 | M=1024 | Q=4.00 | alpha=4.36 | D_ks=0.05 | alpha-hat=4.00 | num traps=0
Layer 183
Layer=183 | N=3072 | M=1024 | Q=3.00 | alpha=3.42 | D_ks=0.05 | alpha-hat=3.83 | num traps=0
Layer 184
Layer=184 | N=1024 | M=1024 | Q=1.00 | alpha=2.84 | D_ks=0.08 | alpha-hat=0.81 | num traps=0
Layer 188
Layer=188 | N=4096 | M=1024 | Q=4.00 | alpha=4.35 | D_ks=0.04 | alpha-hat=6.29 | num traps=0
Layer 190
Layer=190 | N=4096 | M=1024 | Q=4.00 | alpha=3.93 | D_ks=0.04 | alpha-hat=4.07 | num traps=0
Layer 194
Layer=194 | N=3072 | M=1024 | Q=3.00 | alpha=5.00 | D_ks=0.05 | alpha-hat=6.34 | num traps=0
Layer 195
Layer=195 | N=1024 | M=1024 | Q=1.00 | alpha=3.17 | D_ks=0.09 | alpha-hat=1.18 | num traps=0
Layer 199
Layer=199 | N=4096 | M=1024 | Q=4.00 | alpha=4.13 | D_ks=0.03 | alpha-hat=6.09 | num traps=1
Layer 201
Layer=201 | N=4096 | M=1024 | Q=4.00 | alpha=4.34 | D_ks=0.03 | alpha-hat=4.91 | num traps=0
Layer 205
Layer=205 | N=3072 | M=1024 | Q=3.00 | alpha=2.92 | D_ks=0.08 | alpha-hat=5.89 | num traps=0
Layer 206
Layer=206 | N=1024 | M=1024 | Q=1.00 | alpha=5.11 | D_ks=0.05 | alpha-hat=3.32 | num traps=0
Layer 210
Layer=210 | N=4096 | M=1024 | Q=4.00 | alpha=4.15 | D_ks=0.02 | alpha-hat=6.23 | num traps=1
Layer 212
Layer=212 | N=4096 | M=1024 | Q=4.00 | alpha=3.96 | D_ks=0.03 | alpha-hat=4.55 | num traps=0
Layer 216
Layer=216 | N=3072 | M=1024 | Q=3.00 | alpha=3.20 | D_ks=0.08 | alpha-hat=4.13 | num traps=0
Layer 217
Layer=217 | N=1024 | M=1024 | Q=1.00 | alpha=4.22 | D_ks=0.04 | alpha-hat=2.42 | num traps=0
Layer 221
Layer=221 | N=4096 | M=1024 | Q=4.00 | alpha=4.12 | D_ks=0.02 | alpha-hat=6.33 | num traps=1
Layer 223
Layer=223 | N=4096 | M=1024 | Q=4.00 | alpha=3.97 | D_ks=0.03 | alpha-hat=4.92 | num traps=0
Layer 227
Layer=227 | N=3072 | M=1024 | Q=3.00 | alpha=2.93 | D_ks=0.08 | alpha-hat=3.20 | num traps=0
Layer 228
Layer=228 | N=1024 | M=1024 | Q=1.00 | alpha=2.74 | D_ks=0.09 | alpha-hat=3.12 | num traps=1
Layer 232
Layer=232 | N=4096 | M=1024 | Q=4.00 | alpha=3.65 | D_ks=0.02 | alpha-hat=5.79 | num traps=0
Layer 234
Layer=234 | N=4096 | M=1024 | Q=4.00 | alpha=3.31 | D_ks=0.04 | alpha-hat=4.94 | num traps=0
Layer 238
Layer=238 | N=3072 | M=1024 | Q=3.00 | alpha=3.40 | D_ks=0.03 | alpha-hat=5.70 | num traps=0
Layer 239
Layer=239 | N=1024 | M=1024 | Q=1.00 | alpha=2.24 | D_ks=0.10 | alpha-hat=3.57 | num traps=16
Layer 243
Layer=243 | N=4096 | M=1024 | Q=4.00 | alpha=3.41 | D_ks=0.02 | alpha-hat=5.67 | num traps=0
Layer 245
Layer=245 | N=4096 | M=1024 | Q=4.00 | alpha=2.73 | D_ks=0.08 | alpha-hat=5.34 | num traps=13
Layer 249
Layer=249 | N=3072 | M=1024 | Q=3.00 | alpha=2.83 | D_ks=0.01 | alpha-hat=7.66 | num traps=12
Layer 250
Layer=250 | N=1024 | M=1024 | Q=1.00 | alpha=2.50 | D_ks=0.07 | alpha-hat=5.46 | num traps=26
Layer 254
Layer=254 | N=4096 | M=1024 | Q=4.00 | alpha=3.07 | D_ks=0.02 | alpha-hat=5.84 | num traps=1
Layer 256
Layer=256 | N=4096 | M=1024 | Q=4.00 | alpha=3.81 | D_ks=0.06 | alpha-hat=7.11 | num traps=16
Layer 260
Layer=260 | N=3072 | M=1024 | Q=3.00 | alpha=2.84 | D_ks=0.01 | alpha-hat=4.96 | num traps=0
Layer 261
Layer=261 | N=1024 | M=1024 | Q=1.00 | alpha=2.22 | D_ks=0.07 | alpha-hat=3.21 | num traps=16
Layer 265
Layer=265 | N=4096 | M=1024 | Q=4.00 | alpha=3.29 | D_ks=0.02 | alpha-hat=5.89 | num traps=0
Layer 267
Layer=267 | N=4096 | M=1024 | Q=4.00 | alpha=3.36 | D_ks=0.03 | alpha-hat=5.50 | num traps=6
bigscience-bloom-560m Model Summary Plots
bigscience-bloom-560m 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 | 3072 | 1024 | 3.00 | 4.04 | 0.03 | 4.93 | 1.22 | 85.49 | 0 | 0 | 0 |
| 8 | DENSE | 1024 | 1024 | 1.00 | 3.71 | 0.07 | 3.63 | 0.98 | 83.14 | 1 | 0 | 3 |
| 12 | DENSE | 4096 | 1024 | 4.00 | 4.41 | 0.06 | 7.42 | 1.68 | 89.63 | 1 | 0 | 0 |
| 14 | DENSE | 4096 | 1024 | 4.00 | 3.46 | 0.02 | 4.47 | 1.29 | 86.12 | 2 | 0 | 0 |
| 18 | DENSE | 3072 | 1024 | 3.00 | 4.47 | 0.03 | 5.35 | 1.20 | 87.61 | 0 | 0 | 0 |
| 19 | DENSE | 1024 | 1024 | 1.00 | 3.94 | 0.06 | 2.70 | 0.68 | 84.03 | 1 | 0 | 3 |
| 23 | DENSE | 4096 | 1024 | 4.00 | 3.36 | 0.04 | 5.76 | 1.71 | 87.90 | 1 | 0 | 0 |
| 25 | DENSE | 4096 | 1024 | 4.00 | 4.10 | 0.02 | 4.72 | 1.15 | 90.08 | 1 | 0 | 0 |
| 29 | DENSE | 3072 | 1024 | 3.00 | 4.79 | 0.04 | 5.25 | 1.10 | 88.28 | 0 | 0 | 0 |
| 30 | DENSE | 1024 | 1024 | 1.00 | 4.12 | 0.04 | 2.01 | 0.49 | 87.72 | 0 | 0 | 3 |
| 34 | DENSE | 4096 | 1024 | 4.00 | 3.05 | 0.04 | 4.98 | 1.63 | 85.50 | 1 | 0 | 0 |
| 36 | DENSE | 4096 | 1024 | 4.00 | 3.88 | 0.04 | 4.10 | 1.06 | 88.95 | 0 | 0 | 0 |
| 40 | DENSE | 3072 | 1024 | 3.00 | 4.73 | 0.03 | 5.01 | 1.06 | 89.43 | 0 | 0 | 0 |
| 41 | DENSE | 1024 | 1024 | 1.00 | 4.75 | 0.05 | 2.75 | 0.58 | 88.12 | 0 | 0 | 3 |
| 45 | DENSE | 4096 | 1024 | 4.00 | 3.53 | 0.02 | 5.51 | 1.56 | 88.06 | 1 | 0 | 0 |
| 47 | DENSE | 4096 | 1024 | 4.00 | 3.32 | 0.08 | 3.41 | 1.03 | 87.96 | 0 | 1 | 0 |
| 51 | DENSE | 3072 | 1024 | 3.00 | 4.25 | 0.04 | 4.67 | 1.10 | 87.99 | 0 | 0 | 0 |
| 52 | DENSE | 1024 | 1024 | 1.00 | 4.70 | 0.10 | 2.99 | 0.64 | 89.81 | 0 | 1 | 3 |
| 56 | DENSE | 4096 | 1024 | 4.00 | 3.63 | 0.02 | 6.87 | 1.89 | 84.49 | 0 | 0 | 0 |
| 58 | DENSE | 4096 | 1024 | 4.00 | 4.29 | 0.05 | 5.87 | 1.37 | 89.25 | 8 | 0 | 0 |
| 62 | DENSE | 3072 | 1024 | 3.00 | 3.97 | 0.05 | 4.16 | 1.05 | 87.96 | 0 | 0 | 0 |
| 63 | DENSE | 1024 | 1024 | 1.00 | 3.34 | 0.08 | 1.42 | 0.43 | 88.51 | 0 | 1 | 3 |
| 67 | DENSE | 4096 | 1024 | 4.00 | 3.66 | 0.02 | 6.17 | 1.69 | 84.86 | 0 | 0 | 0 |
| 69 | DENSE | 4096 | 1024 | 4.00 | 4.05 | 0.03 | 5.00 | 1.23 | 89.15 | 4 | 0 | 0 |
| 73 | DENSE | 3072 | 1024 | 3.00 | 2.38 | 0.05 | 2.93 | 1.23 | 81.06 | 0 | 0 | 0 |
| 74 | DENSE | 1024 | 1024 | 1.00 | 4.65 | 0.06 | 1.53 | 0.33 | 91.37 | 0 | 0 | 4 |
| 78 | DENSE | 4096 | 1024 | 4.00 | 3.72 | 0.02 | 5.97 | 1.61 | 85.64 | 2 | 0 | 0 |
| 80 | DENSE | 4096 | 1024 | 4.00 | 4.06 | 0.03 | 5.40 | 1.33 | 87.02 | 1 | 0 | 0 |
| 84 | DENSE | 3072 | 1024 | 3.00 | 2.18 | 0.10 | 2.47 | 1.13 | 79.28 | 0 | 4 | 0 |
| 85 | DENSE | 1024 | 1024 | 1.00 | 3.95 | 0.06 | 1.45 | 0.37 | 85.45 | 0 | 0 | 3 |
| 89 | DENSE | 4096 | 1024 | 4.00 | 3.54 | 0.03 | 4.66 | 1.31 | 82.51 | 0 | 0 | 0 |
| 91 | DENSE | 4096 | 1024 | 4.00 | 4.16 | 0.04 | 3.80 | 0.91 | 83.54 | 1 | 0 | 0 |
| 95 | DENSE | 3072 | 1024 | 3.00 | 4.27 | 0.08 | 4.79 | 1.12 | 79.83 | 0 | 0 | 0 |
| 96 | DENSE | 1024 | 1024 | 1.00 | 2.88 | 0.10 | 0.49 | 0.17 | 85.71 | 0 | 0 | 2 |
| 100 | DENSE | 4096 | 1024 | 4.00 | 3.62 | 0.03 | 4.21 | 1.16 | 77.96 | 0 | 0 | 0 |
| 102 | DENSE | 4096 | 1024 | 4.00 | 3.12 | 0.06 | 2.52 | 0.81 | 80.30 | 1 | 0 | 0 |
| 106 | DENSE | 3072 | 1024 | 3.00 | 5.55 | 0.04 | 6.23 | 1.12 | 83.47 | 0 | 0 | 0 |
| 107 | DENSE | 1024 | 1024 | 1.00 | 5.68 | 0.04 | 2.17 | 0.38 | 90.31 | 0 | 0 | 3 |
| 111 | DENSE | 4096 | 1024 | 4.00 | 3.28 | 0.05 | 3.60 | 1.10 | 74.52 | 0 | 0 | 0 |
| 113 | DENSE | 4096 | 1024 | 4.00 | 3.78 | 0.04 | 3.06 | 0.81 | 77.04 | 0 | 0 | 0 |
| 117 | DENSE | 3072 | 1024 | 3.00 | 2.62 | 0.07 | 5.42 | 2.07 | 74.39 | 0 | 1 | 0 |
| 118 | DENSE | 1024 | 1024 | 1.00 | 4.75 | 0.07 | 0.80 | 0.17 | 87.22 | 0 | 0 | 3 |
| 122 | DENSE | 4096 | 1024 | 4.00 | 3.51 | 0.04 | 5.05 | 1.44 | 82.94 | 0 | 0 | 0 |
| 124 | DENSE | 4096 | 1024 | 4.00 | 4.06 | 0.05 | 3.83 | 0.94 | 87.55 | 1 | 0 | 0 |
| 128 | DENSE | 3072 | 1024 | 3.00 | 3.36 | 0.08 | 3.70 | 1.10 | 84.81 | 0 | 1 | 0 |
| 129 | DENSE | 1024 | 1024 | 1.00 | 5.27 | 0.04 | 1.71 | 0.33 | 93.56 | 0 | 0 | 2 |
| 133 | DENSE | 4096 | 1024 | 4.00 | 3.75 | 0.03 | 5.27 | 1.41 | 85.53 | 0 | 0 | 0 |
| 135 | DENSE | 4096 | 1024 | 4.00 | 4.83 | 0.03 | 4.06 | 0.84 | 90.64 | 1 | 0 | 0 |
| 139 | DENSE | 3072 | 1024 | 3.00 | 3.32 | 0.07 | 5.29 | 1.59 | 81.38 | 0 | 1 | 0 |
| 140 | DENSE | 1024 | 1024 | 1.00 | 4.99 | 0.09 | 1.31 | 0.26 | 88.84 | 0 | 0 | 3 |
| 144 | DENSE | 4096 | 1024 | 4.00 | 4.52 | 0.04 | 6.64 | 1.47 | 86.14 | 0 | 0 | 0 |
| 146 | DENSE | 4096 | 1024 | 4.00 | 4.65 | 0.06 | 4.05 | 0.87 | 92.36 | 0 | 0 | 0 |
| 150 | DENSE | 3072 | 1024 | 3.00 | 3.67 | 0.06 | 4.17 | 1.14 | 85.68 | 0 | 0 | 0 |
| 151 | DENSE | 1024 | 1024 | 1.00 | 3.30 | 0.08 | 0.99 | 0.30 | 89.52 | 0 | 0 | 1 |
| 155 | DENSE | 4096 | 1024 | 4.00 | 3.89 | 0.05 | 5.62 | 1.44 | 86.30 | 0 | 0 | 0 |
| 157 | DENSE | 4096 | 1024 | 4.00 | 4.39 | 0.07 | 3.74 | 0.85 | 91.12 | 0 | 1 | 0 |
| 161 | DENSE | 3072 | 1024 | 3.00 | 4.46 | 0.04 | 5.39 | 1.21 | 85.81 | 0 | 0 | 0 |
| 162 | DENSE | 1024 | 1024 | 1.00 | 2.62 | 0.13 | 0.93 | 0.35 | 88.49 | 0 | 2 | 2 |
| 166 | DENSE | 4096 | 1024 | 4.00 | 4.48 | 0.04 | 6.52 | 1.45 | 86.69 | 0 | 0 | 0 |
| 168 | DENSE | 4096 | 1024 | 4.00 | 3.86 | 0.07 | 3.47 | 0.90 | 89.74 | 0 | 2 | 0 |
| 172 | DENSE | 3072 | 1024 | 3.00 | 3.43 | 0.07 | 3.75 | 1.09 | 86.85 | 0 | 0 | 0 |
| 173 | DENSE | 1024 | 1024 | 1.00 | 5.14 | 0.10 | 1.73 | 0.34 | 89.15 | 0 | 1 | 3 |
| 177 | DENSE | 4096 | 1024 | 4.00 | 4.48 | 0.04 | 6.55 | 1.46 | 87.14 | 0 | 0 | 0 |
| 179 | DENSE | 4096 | 1024 | 4.00 | 4.36 | 0.05 | 4.00 | 0.92 | 88.87 | 0 | 0 | 0 |
| 183 | DENSE | 3072 | 1024 | 3.00 | 3.42 | 0.05 | 3.83 | 1.12 | 87.94 | 0 | 0 | 0 |
| 184 | DENSE | 1024 | 1024 | 1.00 | 2.84 | 0.08 | 0.81 | 0.28 | 88.88 | 0 | 0 | 2 |
| 188 | DENSE | 4096 | 1024 | 4.00 | 4.35 | 0.04 | 6.29 | 1.45 | 87.73 | 0 | 0 | 0 |
| 190 | DENSE | 4096 | 1024 | 4.00 | 3.93 | 0.04 | 4.07 | 1.04 | 88.65 | 0 | 0 | 0 |
| 194 | DENSE | 3072 | 1024 | 3.00 | 5.00 | 0.05 | 6.34 | 1.27 | 87.45 | 0 | 0 | 0 |
| 195 | DENSE | 1024 | 1024 | 1.00 | 3.17 | 0.09 | 1.18 | 0.37 | 89.43 | 0 | 1 | 2 |
| 199 | DENSE | 4096 | 1024 | 4.00 | 4.13 | 0.03 | 6.09 | 1.47 | 88.27 | 1 | 0 | 0 |
| 201 | DENSE | 4096 | 1024 | 4.00 | 4.34 | 0.03 | 4.91 | 1.13 | 88.72 | 0 | 0 | 0 |
| 205 | DENSE | 3072 | 1024 | 3.00 | 2.92 | 0.08 | 5.89 | 2.02 | 82.26 | 0 | 1 | 0 |
| 206 | DENSE | 1024 | 1024 | 1.00 | 5.11 | 0.05 | 3.32 | 0.65 | 89.48 | 0 | 0 | 3 |
| 210 | DENSE | 4096 | 1024 | 4.00 | 4.15 | 0.02 | 6.23 | 1.50 | 88.17 | 1 | 0 | 0 |
| 212 | DENSE | 4096 | 1024 | 4.00 | 3.96 | 0.03 | 4.55 | 1.15 | 89.14 | 0 | 0 | 0 |
| 216 | DENSE | 3072 | 1024 | 3.00 | 3.20 | 0.08 | 4.13 | 1.29 | 87.95 | 0 | 3 | 0 |
| 217 | DENSE | 1024 | 1024 | 1.00 | 4.22 | 0.04 | 2.42 | 0.57 | 92.69 | 0 | 0 | 1 |
| 221 | DENSE | 4096 | 1024 | 4.00 | 4.12 | 0.02 | 6.33 | 1.54 | 87.80 | 1 | 0 | 0 |
| 223 | DENSE | 4096 | 1024 | 4.00 | 3.97 | 0.03 | 4.92 | 1.24 | 89.62 | 0 | 0 | 0 |
| 227 | DENSE | 3072 | 1024 | 3.00 | 2.93 | 0.08 | 3.20 | 1.09 | 87.55 | 0 | 1 | 0 |
| 228 | DENSE | 1024 | 1024 | 1.00 | 2.74 | 0.09 | 3.12 | 1.14 | 83.60 | 1 | 0 | 1 |
| 232 | DENSE | 4096 | 1024 | 4.00 | 3.65 | 0.02 | 5.79 | 1.59 | 86.18 | 0 | 0 | 0 |
| 234 | DENSE | 4096 | 1024 | 4.00 | 3.31 | 0.04 | 4.94 | 1.49 | 86.57 | 0 | 0 | 0 |
| 238 | DENSE | 3072 | 1024 | 3.00 | 3.40 | 0.03 | 5.70 | 1.68 | 85.42 | 0 | 0 | 0 |
| 239 | DENSE | 1024 | 1024 | 1.00 | 2.24 | 0.10 | 3.57 | 1.59 | 65.64 | 16 | 0 | 2 |
| 243 | DENSE | 4096 | 1024 | 4.00 | 3.41 | 0.02 | 5.67 | 1.66 | 84.15 | 0 | 0 | 0 |
| 245 | DENSE | 4096 | 1024 | 4.00 | 2.73 | 0.08 | 5.34 | 1.95 | 78.71 | 13 | 0 | 0 |
| 249 | DENSE | 3072 | 1024 | 3.00 | 2.83 | 0.01 | 7.66 | 2.71 | 69.06 | 12 | 0 | 0 |
| 250 | DENSE | 1024 | 1024 | 1.00 | 2.50 | 0.07 | 5.46 | 2.18 | 53.11 | 26 | 0 | 2 |
| 254 | DENSE | 4096 | 1024 | 4.00 | 3.07 | 0.02 | 5.84 | 1.91 | 80.73 | 1 | 0 | 0 |
| 256 | DENSE | 4096 | 1024 | 4.00 | 3.81 | 0.06 | 7.11 | 1.87 | 81.14 | 16 | 0 | 0 |
| 260 | DENSE | 3072 | 1024 | 3.00 | 2.84 | 0.01 | 4.96 | 1.74 | 79.27 | 0 | 0 | 0 |
| 261 | DENSE | 1024 | 1024 | 1.00 | 2.22 | 0.07 | 3.21 | 1.45 | 63.55 | 16 | 0 | 2 |
| 265 | DENSE | 4096 | 1024 | 4.00 | 3.29 | 0.02 | 5.89 | 1.79 | 83.00 | 0 | 0 | 0 |
| 267 | DENSE | 4096 | 1024 | 4.00 | 3.36 | 0.03 | 5.50 | 1.64 | 85.56 | 6 | 0 | 0 |
bigscience-bloom-560m Layer Plots
Layer 7
Layer=7 | N=3072 | M=1024 | Q=3.00 | alpha=4.04 | D_ks=0.03 | alpha-hat=4.93 | num traps=0
Layer 8
Layer=8 | N=1024 | M=1024 | Q=1.00 | alpha=3.71 | D_ks=0.07 | alpha-hat=3.63 | num traps=1
Layer 12
Layer=12 | N=4096 | M=1024 | Q=4.00 | alpha=4.41 | D_ks=0.06 | alpha-hat=7.42 | num traps=1
Layer 14
Layer=14 | N=4096 | M=1024 | Q=4.00 | alpha=3.46 | D_ks=0.02 | alpha-hat=4.47 | num traps=2
Layer 18
Layer=18 | N=3072 | M=1024 | Q=3.00 | alpha=4.47 | D_ks=0.03 | alpha-hat=5.35 | num traps=0
Layer 19
Layer=19 | N=1024 | M=1024 | Q=1.00 | alpha=3.94 | D_ks=0.06 | alpha-hat=2.70 | num traps=1
Layer 23
Layer=23 | N=4096 | M=1024 | Q=4.00 | alpha=3.36 | D_ks=0.04 | alpha-hat=5.76 | num traps=1
Layer 25
Layer=25 | N=4096 | M=1024 | Q=4.00 | alpha=4.10 | D_ks=0.02 | alpha-hat=4.72 | num traps=1
Layer 29
Layer=29 | N=3072 | M=1024 | Q=3.00 | alpha=4.79 | D_ks=0.04 | alpha-hat=5.25 | num traps=0
Layer 30
Layer=30 | N=1024 | M=1024 | Q=1.00 | alpha=4.12 | D_ks=0.04 | alpha-hat=2.01 | num traps=0
Layer 34
Layer=34 | N=4096 | M=1024 | Q=4.00 | alpha=3.05 | D_ks=0.04 | alpha-hat=4.98 | num traps=1
Layer 36
Layer=36 | N=4096 | M=1024 | Q=4.00 | alpha=3.88 | D_ks=0.04 | alpha-hat=4.10 | num traps=0
Layer 40
Layer=40 | N=3072 | M=1024 | Q=3.00 | alpha=4.73 | D_ks=0.03 | alpha-hat=5.01 | num traps=0
Layer 41
Layer=41 | N=1024 | M=1024 | Q=1.00 | alpha=4.75 | D_ks=0.05 | alpha-hat=2.75 | num traps=0
Layer 45
Layer=45 | N=4096 | M=1024 | Q=4.00 | alpha=3.53 | D_ks=0.02 | alpha-hat=5.51 | num traps=1
Layer 47
Layer=47 | N=4096 | M=1024 | Q=4.00 | alpha=3.32 | D_ks=0.08 | alpha-hat=3.41 | num traps=0
Layer 51
Layer=51 | N=3072 | M=1024 | Q=3.00 | alpha=4.25 | D_ks=0.04 | alpha-hat=4.67 | num traps=0
Layer 52
Layer=52 | N=1024 | M=1024 | Q=1.00 | alpha=4.70 | D_ks=0.10 | alpha-hat=2.99 | num traps=0
Layer 56
Layer=56 | N=4096 | M=1024 | Q=4.00 | alpha=3.63 | D_ks=0.02 | alpha-hat=6.87 | num traps=0
Layer 58
Layer=58 | N=4096 | M=1024 | Q=4.00 | alpha=4.29 | D_ks=0.05 | alpha-hat=5.87 | num traps=8
Layer 62
Layer=62 | N=3072 | M=1024 | Q=3.00 | alpha=3.97 | D_ks=0.05 | alpha-hat=4.16 | num traps=0
Layer 63
Layer=63 | N=1024 | M=1024 | Q=1.00 | alpha=3.34 | D_ks=0.08 | alpha-hat=1.42 | num traps=0
Layer 67
Layer=67 | N=4096 | M=1024 | Q=4.00 | alpha=3.66 | D_ks=0.02 | alpha-hat=6.17 | num traps=0
Layer 69
Layer=69 | N=4096 | M=1024 | Q=4.00 | alpha=4.05 | D_ks=0.03 | alpha-hat=5.00 | num traps=4
Layer 73
Layer=73 | N=3072 | M=1024 | Q=3.00 | alpha=2.38 | D_ks=0.05 | alpha-hat=2.93 | num traps=0
Layer 74
Layer=74 | N=1024 | M=1024 | Q=1.00 | alpha=4.65 | D_ks=0.06 | alpha-hat=1.53 | num traps=0
Layer 78
Layer=78 | N=4096 | M=1024 | Q=4.00 | alpha=3.72 | D_ks=0.02 | alpha-hat=5.97 | num traps=2
Layer 80
Layer=80 | N=4096 | M=1024 | Q=4.00 | alpha=4.06 | D_ks=0.03 | alpha-hat=5.40 | num traps=1
Layer 84
Layer=84 | N=3072 | M=1024 | Q=3.00 | alpha=2.18 | D_ks=0.10 | alpha-hat=2.47 | num traps=0
Layer 85
Layer=85 | N=1024 | M=1024 | Q=1.00 | alpha=3.95 | D_ks=0.06 | alpha-hat=1.45 | num traps=0
Layer 89
Layer=89 | N=4096 | M=1024 | Q=4.00 | alpha=3.54 | D_ks=0.03 | alpha-hat=4.66 | num traps=0
Layer 91
Layer=91 | N=4096 | M=1024 | Q=4.00 | alpha=4.16 | D_ks=0.04 | alpha-hat=3.80 | num traps=1
Layer 95
Layer=95 | N=3072 | M=1024 | Q=3.00 | alpha=4.27 | D_ks=0.08 | alpha-hat=4.79 | num traps=0
Layer 96
Layer=96 | N=1024 | M=1024 | Q=1.00 | alpha=2.88 | D_ks=0.10 | alpha-hat=0.49 | num traps=0
Layer 100
Layer=100 | N=4096 | M=1024 | Q=4.00 | alpha=3.62 | D_ks=0.03 | alpha-hat=4.21 | num traps=0
Layer 102
Layer=102 | N=4096 | M=1024 | Q=4.00 | alpha=3.12 | D_ks=0.06 | alpha-hat=2.52 | num traps=1
Layer 106
Layer=106 | N=3072 | M=1024 | Q=3.00 | alpha=5.55 | D_ks=0.04 | alpha-hat=6.23 | num traps=0
Layer 107
Layer=107 | N=1024 | M=1024 | Q=1.00 | alpha=5.68 | D_ks=0.04 | alpha-hat=2.17 | num traps=0
Layer 111
Layer=111 | N=4096 | M=1024 | Q=4.00 | alpha=3.28 | D_ks=0.05 | alpha-hat=3.60 | num traps=0
Layer 113
Layer=113 | N=4096 | M=1024 | Q=4.00 | alpha=3.78 | D_ks=0.04 | alpha-hat=3.06 | num traps=0
Layer 117
Layer=117 | N=3072 | M=1024 | Q=3.00 | alpha=2.62 | D_ks=0.07 | alpha-hat=5.42 | num traps=0
Layer 118
Layer=118 | N=1024 | M=1024 | Q=1.00 | alpha=4.75 | D_ks=0.07 | alpha-hat=0.80 | num traps=0
Layer 122
Layer=122 | N=4096 | M=1024 | Q=4.00 | alpha=3.51 | D_ks=0.04 | alpha-hat=5.05 | num traps=0
Layer 124
Layer=124 | N=4096 | M=1024 | Q=4.00 | alpha=4.06 | D_ks=0.05 | alpha-hat=3.83 | num traps=1
Layer 128
Layer=128 | N=3072 | M=1024 | Q=3.00 | alpha=3.36 | D_ks=0.08 | alpha-hat=3.70 | num traps=0
Layer 129
Layer=129 | N=1024 | M=1024 | Q=1.00 | alpha=5.27 | D_ks=0.04 | alpha-hat=1.71 | num traps=0
Layer 133
Layer=133 | N=4096 | M=1024 | Q=4.00 | alpha=3.75 | D_ks=0.03 | alpha-hat=5.27 | num traps=0
Layer 135
Layer=135 | N=4096 | M=1024 | Q=4.00 | alpha=4.83 | D_ks=0.03 | alpha-hat=4.06 | num traps=1
Layer 139
Layer=139 | N=3072 | M=1024 | Q=3.00 | alpha=3.32 | D_ks=0.07 | alpha-hat=5.29 | num traps=0
Layer 140
Layer=140 | N=1024 | M=1024 | Q=1.00 | alpha=4.99 | D_ks=0.09 | alpha-hat=1.31 | num traps=0
Layer 144
Layer=144 | N=4096 | M=1024 | Q=4.00 | alpha=4.52 | D_ks=0.04 | alpha-hat=6.64 | num traps=0
Layer 146
Layer=146 | N=4096 | M=1024 | Q=4.00 | alpha=4.65 | D_ks=0.06 | alpha-hat=4.05 | num traps=0
Layer 150
Layer=150 | N=3072 | M=1024 | Q=3.00 | alpha=3.67 | D_ks=0.06 | alpha-hat=4.17 | num traps=0
Layer 151
Layer=151 | N=1024 | M=1024 | Q=1.00 | alpha=3.30 | D_ks=0.08 | alpha-hat=0.99 | num traps=0
Layer 155
Layer=155 | N=4096 | M=1024 | Q=4.00 | alpha=3.89 | D_ks=0.05 | alpha-hat=5.62 | num traps=0
Layer 157
Layer=157 | N=4096 | M=1024 | Q=4.00 | alpha=4.39 | D_ks=0.07 | alpha-hat=3.74 | num traps=0
Layer 161
Layer=161 | N=3072 | M=1024 | Q=3.00 | alpha=4.46 | D_ks=0.04 | alpha-hat=5.39 | num traps=0
Layer 162
Layer=162 | N=1024 | M=1024 | Q=1.00 | alpha=2.62 | D_ks=0.13 | alpha-hat=0.93 | num traps=0
Layer 166
Layer=166 | N=4096 | M=1024 | Q=4.00 | alpha=4.48 | D_ks=0.04 | alpha-hat=6.52 | num traps=0
Layer 168
Layer=168 | N=4096 | M=1024 | Q=4.00 | alpha=3.86 | D_ks=0.07 | alpha-hat=3.47 | num traps=0
Layer 172
Layer=172 | N=3072 | M=1024 | Q=3.00 | alpha=3.43 | D_ks=0.07 | alpha-hat=3.75 | num traps=0
Layer 173
Layer=173 | N=1024 | M=1024 | Q=1.00 | alpha=5.14 | D_ks=0.10 | alpha-hat=1.73 | num traps=0
Layer 177
Layer=177 | N=4096 | M=1024 | Q=4.00 | alpha=4.48 | D_ks=0.04 | alpha-hat=6.55 | num traps=0
Layer 179
Layer=179 | N=4096 | M=1024 | Q=4.00 | alpha=4.36 | D_ks=0.05 | alpha-hat=4.00 | num traps=0
Layer 183
Layer=183 | N=3072 | M=1024 | Q=3.00 | alpha=3.42 | D_ks=0.05 | alpha-hat=3.83 | num traps=0
Layer 184
Layer=184 | N=1024 | M=1024 | Q=1.00 | alpha=2.84 | D_ks=0.08 | alpha-hat=0.81 | num traps=0
Layer 188
Layer=188 | N=4096 | M=1024 | Q=4.00 | alpha=4.35 | D_ks=0.04 | alpha-hat=6.29 | num traps=0
Layer 190
Layer=190 | N=4096 | M=1024 | Q=4.00 | alpha=3.93 | D_ks=0.04 | alpha-hat=4.07 | num traps=0
Layer 194
Layer=194 | N=3072 | M=1024 | Q=3.00 | alpha=5.00 | D_ks=0.05 | alpha-hat=6.34 | num traps=0
Layer 195
Layer=195 | N=1024 | M=1024 | Q=1.00 | alpha=3.17 | D_ks=0.09 | alpha-hat=1.18 | num traps=0
Layer 199
Layer=199 | N=4096 | M=1024 | Q=4.00 | alpha=4.13 | D_ks=0.03 | alpha-hat=6.09 | num traps=1
Layer 201
Layer=201 | N=4096 | M=1024 | Q=4.00 | alpha=4.34 | D_ks=0.03 | alpha-hat=4.91 | num traps=0
Layer 205
Layer=205 | N=3072 | M=1024 | Q=3.00 | alpha=2.92 | D_ks=0.08 | alpha-hat=5.89 | num traps=0
Layer 206
Layer=206 | N=1024 | M=1024 | Q=1.00 | alpha=5.11 | D_ks=0.05 | alpha-hat=3.32 | num traps=0
Layer 210
Layer=210 | N=4096 | M=1024 | Q=4.00 | alpha=4.15 | D_ks=0.02 | alpha-hat=6.23 | num traps=1
Layer 212
Layer=212 | N=4096 | M=1024 | Q=4.00 | alpha=3.96 | D_ks=0.03 | alpha-hat=4.55 | num traps=0
Layer 216
Layer=216 | N=3072 | M=1024 | Q=3.00 | alpha=3.20 | D_ks=0.08 | alpha-hat=4.13 | num traps=0
Layer 217
Layer=217 | N=1024 | M=1024 | Q=1.00 | alpha=4.22 | D_ks=0.04 | alpha-hat=2.42 | num traps=0
Layer 221
Layer=221 | N=4096 | M=1024 | Q=4.00 | alpha=4.12 | D_ks=0.02 | alpha-hat=6.33 | num traps=1
Layer 223
Layer=223 | N=4096 | M=1024 | Q=4.00 | alpha=3.97 | D_ks=0.03 | alpha-hat=4.92 | num traps=0
Layer 227
Layer=227 | N=3072 | M=1024 | Q=3.00 | alpha=2.93 | D_ks=0.08 | alpha-hat=3.20 | num traps=0
Layer 228
Layer=228 | N=1024 | M=1024 | Q=1.00 | alpha=2.74 | D_ks=0.09 | alpha-hat=3.12 | num traps=1
Layer 232
Layer=232 | N=4096 | M=1024 | Q=4.00 | alpha=3.65 | D_ks=0.02 | alpha-hat=5.79 | num traps=0
Layer 234
Layer=234 | N=4096 | M=1024 | Q=4.00 | alpha=3.31 | D_ks=0.04 | alpha-hat=4.94 | num traps=0
Layer 238
Layer=238 | N=3072 | M=1024 | Q=3.00 | alpha=3.40 | D_ks=0.03 | alpha-hat=5.70 | num traps=0
Layer 239
Layer=239 | N=1024 | M=1024 | Q=1.00 | alpha=2.24 | D_ks=0.10 | alpha-hat=3.57 | num traps=16
Layer 243
Layer=243 | N=4096 | M=1024 | Q=4.00 | alpha=3.41 | D_ks=0.02 | alpha-hat=5.67 | num traps=0
Layer 245
Layer=245 | N=4096 | M=1024 | Q=4.00 | alpha=2.73 | D_ks=0.08 | alpha-hat=5.34 | num traps=13
Layer 249
Layer=249 | N=3072 | M=1024 | Q=3.00 | alpha=2.83 | D_ks=0.01 | alpha-hat=7.66 | num traps=12
Layer 250
Layer=250 | N=1024 | M=1024 | Q=1.00 | alpha=2.50 | D_ks=0.07 | alpha-hat=5.46 | num traps=26
Layer 254
Layer=254 | N=4096 | M=1024 | Q=4.00 | alpha=3.07 | D_ks=0.02 | alpha-hat=5.84 | num traps=1
Layer 256
Layer=256 | N=4096 | M=1024 | Q=4.00 | alpha=3.81 | D_ks=0.06 | alpha-hat=7.11 | num traps=16
Layer 260
Layer=260 | N=3072 | M=1024 | Q=3.00 | alpha=2.84 | D_ks=0.01 | alpha-hat=4.96 | num traps=0
Layer 261
Layer=261 | N=1024 | M=1024 | Q=1.00 | alpha=2.22 | D_ks=0.07 | alpha-hat=3.21 | num traps=16
Layer 265
Layer=265 | N=4096 | M=1024 | Q=4.00 | alpha=3.29 | D_ks=0.02 | alpha-hat=5.89 | num traps=0
Layer 267
Layer=267 | N=4096 | M=1024 | Q=4.00 | alpha=3.36 | D_ks=0.03 | alpha-hat=5.50 | num traps=6