google-flan-t5-base
Find this model in the FlanT5 model summary
google-flan-t5-base Model Summary Plots
google-flan-t5-base Model Selected Details
layer_type
N
M
Q
alpha
D
alpha-hat
log_SN
% Rand
num_traps
num_fingers
rank_loss
layer_id
1
EMBEDDING
32128
768
41.83
3.39
0.02
27.60
8.15
76.46
0
0
0
8
DENSE
768
768
1.00
4.10
0.12
5.71
1.39
91.61
0
3
0
9
DENSE
768
768
1.00
3.26
0.12
10.29
3.16
92.16
0
3
0
10
DENSE
768
768
1.00
6.58
0.14
16.57
2.52
91.87
0
7
1
11
DENSE
768
768
1.00
3.06
0.03
10.61
3.47
81.25
0
0
0
12
EMBEDDING
32
12
2.67
1.72
0.20
7.05
4.11
58.01
0
0
0
17
DENSE
2048
768
2.67
3.03
0.04
10.89
3.60
87.27
0
0
0
18
DENSE
2048
768
2.67
3.47
0.07
11.10
3.20
91.20
0
0
0
19
DENSE
2048
768
2.67
3.44
0.02
11.84
3.45
86.50
0
0
0
28
DENSE
768
768
1.00
4.67
0.04
6.93
1.48
89.92
0
0
1
29
DENSE
768
768
1.00
4.37
0.03
14.34
3.28
90.88
0
0
0
30
DENSE
768
768
1.00
3.40
0.06
8.91
2.62
89.63
0
0
1
31
DENSE
768
768
1.00
2.66
0.02
10.05
3.77
76.00
0
0
0
36
DENSE
2048
768
2.67
3.39
0.02
12.69
3.75
87.82
0
0
0
37
DENSE
2048
768
2.67
4.52
0.05
15.81
3.50
92.61
0
0
0
38
DENSE
2048
768
2.67
3.11
0.02
11.56
3.72
83.38
0
0
0
47
DENSE
768
768
1.00
3.96
0.03
6.17
1.56
90.38
0
0
1
48
DENSE
768
768
1.00
3.92
0.03
13.34
3.40
89.22
0
0
0
49
DENSE
768
768
1.00
2.94
0.09
8.42
2.86
89.80
0
0
0
50
DENSE
768
768
1.00
3.04
0.03
10.85
3.57
82.63
0
0
1
55
DENSE
2048
768
2.67
3.52
0.02
12.54
3.56
88.94
0
0
0
56
DENSE
2048
768
2.67
4.47
0.03
19.96
4.47
92.69
3
0
0
57
DENSE
2048
768
2.67
3.29
0.02
12.16
3.70
85.60
0
0
0
66
DENSE
768
768
1.00
3.86
0.05
5.28
1.37
88.74
0
0
1
67
DENSE
768
768
1.00
4.32
0.04
13.55
3.13
90.53
0
0
1
68
DENSE
768
768
1.00
3.63
0.09
10.93
3.01
90.63
0
1
0
69
DENSE
768
768
1.00
3.09
0.02
11.33
3.67
81.94
0
0
0
74
DENSE
2048
768
2.67
3.53
0.02
12.38
3.51
88.64
0
0
0
75
DENSE
2048
768
2.67
5.35
0.04
18.36
3.43
94.32
0
0
0
76
DENSE
2048
768
2.67
3.48
0.02
12.70
3.65
86.48
0
0
0
85
DENSE
768
768
1.00
3.79
0.04
5.17
1.36
88.25
0
0
1
86
DENSE
768
768
1.00
3.56
0.03
11.41
3.21
88.15
0
0
0
87
DENSE
768
768
1.00
2.73
0.10
8.43
3.09
88.51
0
0
0
88
DENSE
768
768
1.00
3.75
0.04
14.17
3.78
84.51
0
0
0
93
DENSE
2048
768
2.67
3.52
0.02
12.42
3.53
88.30
0
0
0
94
DENSE
2048
768
2.67
5.14
0.05
18.28
3.56
93.86
0
0
0
95
DENSE
2048
768
2.67
3.77
0.02
14.10
3.74
87.40
0
0
0
104
DENSE
768
768
1.00
3.65
0.04
4.66
1.28
88.28
0
0
0
105
DENSE
768
768
1.00
3.92
0.04
12.21
3.11
89.76
0
0
0
106
DENSE
768
768
1.00
2.63
0.10
8.51
3.23
88.87
0
1
0
107
DENSE
768
768
1.00
3.43
0.03
12.79
3.73
85.70
0
0
0
112
DENSE
2048
768
2.67
3.55
0.02
12.66
3.57
87.00
0
0
0
113
DENSE
2048
768
2.67
5.92
0.04
21.78
3.68
93.33
0
0
0
114
DENSE
2048
768
2.67
3.80
0.03
14.53
3.83
87.30
0
0
0
123
DENSE
768
768
1.00
4.09
0.05
4.79
1.17
88.76
0
0
1
124
DENSE
768
768
1.00
3.98
0.06
11.61
2.92
90.18
0
0
1
125
DENSE
768
768
1.00
3.99
0.07
13.27
3.32
87.53
0
0
1
126
DENSE
768
768
1.00
3.29
0.05
12.11
3.68
86.83
0
0
1
131
DENSE
2048
768
2.67
3.43
0.02
12.22
3.56
86.26
0
0
0
132
DENSE
2048
768
2.67
5.35
0.04
20.05
3.75
92.89
0
0
0
133
DENSE
2048
768
2.67
4.02
0.03
14.89
3.70
88.18
0
0
0
142
DENSE
768
768
1.00
3.20
0.06
3.51
1.10
85.39
0
0
1
143
DENSE
768
768
1.00
3.12
0.06
9.26
2.96
85.44
0
0
0
144
DENSE
768
768
1.00
2.29
0.10
7.75
3.38
85.95
0
0
0
145
DENSE
768
768
1.00
4.02
0.04
15.27
3.80
86.68
0
0
0
150
DENSE
2048
768
2.67
3.48
0.03
12.24
3.52
85.84
0
0
0
151
DENSE
2048
768
2.67
5.09
0.04
19.24
3.78
92.43
0
0
0
152
DENSE
2048
768
2.67
4.16
0.04
15.26
3.67
88.27
0
0
0
161
DENSE
768
768
1.00
3.72
0.05
4.08
1.10
84.84
0
0
1
162
DENSE
768
768
1.00
3.62
0.04
10.42
2.88
84.67
0
0
0
163
DENSE
768
768
1.00
5.54
0.09
19.05
3.44
87.95
0
0
0
164
DENSE
768
768
1.00
4.72
0.03
18.59
3.94
86.17
0
0
0
169
DENSE
2048
768
2.67
3.65
0.03
12.74
3.49
86.19
0
0
0
170
DENSE
2048
768
2.67
4.52
0.03
19.28
4.27
92.71
3
0
0
171
DENSE
2048
768
2.67
4.36
0.03
16.56
3.80
88.32
0
0
0
180
DENSE
768
768
1.00
3.90
0.04
3.75
0.96
86.59
0
0
1
181
DENSE
768
768
1.00
4.19
0.05
11.35
2.71
89.29
0
0
0
182
DENSE
768
768
1.00
4.88
0.08
16.55
3.39
91.45
0
0
0
183
DENSE
768
768
1.00
3.86
0.07
14.97
3.88
85.91
0
0
0
188
DENSE
2048
768
2.67
3.76
0.04
12.44
3.30
87.56
0
0
0
189
DENSE
2048
768
2.67
5.53
0.05
21.53
3.90
92.24
0
0
0
190
DENSE
2048
768
2.67
4.54
0.03
16.67
3.67
88.86
0
0
0
199
DENSE
768
768
1.00
3.33
0.04
3.18
0.95
85.40
0
0
1
200
DENSE
768
768
1.00
3.52
0.04
9.73
2.76
86.93
0
0
1
201
DENSE
768
768
1.00
2.57
0.11
9.25
3.60
86.49
0
5
0
202
DENSE
768
768
1.00
2.57
0.10
9.87
3.84
84.90
0
4
0
207
DENSE
2048
768
2.67
3.89
0.03
12.51
3.21
88.38
0
0
0
208
DENSE
2048
768
2.67
4.72
0.04
18.40
3.90
92.44
1
0
0
209
DENSE
2048
768
2.67
4.17
0.04
15.00
3.60
89.77
0
0
0
218
DENSE
768
768
1.00
3.38
0.04
3.35
0.99
81.74
0
0
2
219
DENSE
768
768
1.00
3.59
0.04
9.55
2.66
84.41
0
0
1
220
DENSE
768
768
1.00
2.73
0.07
9.91
3.63
88.47
0
0
0
221
DENSE
768
768
1.00
3.33
0.05
12.77
3.83
83.31
0
0
0
226
DENSE
2048
768
2.67
3.96
0.04
12.81
3.23
88.44
0
0
0
227
DENSE
2048
768
2.67
4.37
0.03
17.96
4.11
91.33
2
0
0
228
DENSE
2048
768
2.67
3.68
0.03
14.19
3.86
86.94
0
0
0
241
DENSE
768
768
1.00
3.18
0.05
3.96
1.25
80.36
0
0
2
242
DENSE
768
768
1.00
3.22
0.09
10.37
3.22
82.92
5
0
0
243
DENSE
768
768
1.00
3.82
0.06
9.70
2.54
86.31
1
0
0
244
DENSE
768
768
1.00
2.84
0.05
9.83
3.46
70.54
0
0
0
245
EMBEDDING
32
12
2.67
1.19
0.17
3.76
3.16
66.97
11
0
0
250
DENSE
768
768
1.00
3.23
0.07
4.31
1.33
85.57
0
0
1
251
DENSE
768
768
1.00
2.53
0.07
7.71
3.05
82.02
0
0
0
252
DENSE
768
768
1.00
4.83
0.04
13.02
2.69
91.28
0
0
1
253
DENSE
768
768
1.00
3.20
0.03
11.70
3.65
78.06
0
0
0
258
DENSE
2048
768
2.67
3.15
0.04
11.97
3.80
85.68
0
0
0
259
DENSE
2048
768
2.67
4.82
0.03
14.61
3.03
94.16
0
0
0
260
DENSE
2048
768
2.67
3.54
0.03
13.30
3.75
82.21
0
0
0
269
DENSE
768
768
1.00
3.48
0.03
2.68
0.77
81.86
0
0
3
270
DENSE
768
768
1.00
3.37
0.04
9.47
2.81
81.46
0
0
0
271
DENSE
768
768
1.00
4.80
0.09
11.31
2.35
85.38
0
0
0
272
DENSE
768
768
1.00
2.56
0.02
9.23
3.61
68.56
0
0
1
277
DENSE
768
768
1.00
3.24
0.04
3.31
1.02
84.56
0
0
1
278
DENSE
768
768
1.00
2.77
0.05
8.66
3.13
78.42
0
0
1
279
DENSE
768
768
1.00
6.59
0.04
18.65
2.83
88.25
0
0
0
280
DENSE
768
768
1.00
2.89
0.03
10.42
3.61
74.29
0
0
0
285
DENSE
2048
768
2.67
3.67
0.02
13.20
3.60
87.53
0
0
0
286
DENSE
2048
768
2.67
5.01
0.02
17.28
3.45
92.51
0
0
0
287
DENSE
2048
768
2.67
4.16
0.03
16.63
3.99
84.62
0
0
0
296
DENSE
768
768
1.00
2.68
0.04
3.02
1.13
77.51
0
0
1
297
DENSE
768
768
1.00
3.31
0.03
8.42
2.55
81.57
0
0
0
298
DENSE
768
768
1.00
3.89
0.11
9.62
2.47
85.94
0
4
0
299
DENSE
768
768
1.00
2.43
0.03
10.16
4.17
64.06
0
0
0
304
DENSE
768
768
1.00
3.43
0.06
3.51
1.02
87.20
0
0
2
305
DENSE
768
768
1.00
3.16
0.04
9.10
2.88
85.42
0
0
0
306
DENSE
768
768
1.00
5.88
0.05
14.91
2.54
94.48
0
0
0
307
DENSE
768
768
1.00
3.35
0.04
13.31
3.98
72.28
1
0
0
312
DENSE
2048
768
2.67
2.78
0.06
10.35
3.72
85.29
0
1
0
313
DENSE
2048
768
2.67
3.08
0.09
11.51
3.73
90.13
0
4
0
314
DENSE
2048
768
2.67
4.20
0.06
19.50
4.64
77.77
1
0
0
323
DENSE
768
768
1.00
3.39
0.06
3.06
0.90
87.76
0
0
2
324
DENSE
768
768
1.00
4.25
0.05
11.06
2.60
89.10
0
0
0
325
DENSE
768
768
1.00
4.20
0.05
11.81
2.81
89.29
0
0
0
326
DENSE
768
768
1.00
2.77
0.04
11.91
4.30
69.77
1
0
0
331
DENSE
768
768
1.00
3.25
0.05
3.98
1.23
86.62
0
0
1
332
DENSE
768
768
1.00
3.22
0.03
9.86
3.06
86.76
0
0
1
333
DENSE
768
768
1.00
4.40
0.13
12.08
2.75
94.49
0
5
0
334
DENSE
768
768
1.00
3.47
0.05
14.99
4.33
70.51
1
0
0
339
DENSE
2048
768
2.67
3.00
0.05
11.49
3.83
85.51
0
0
0
340
DENSE
2048
768
2.67
3.98
0.08
15.79
3.96
90.81
0
1
0
341
DENSE
2048
768
2.67
4.02
0.06
19.84
4.93
74.77
2
0
0
350
DENSE
768
768
1.00
3.85
0.06
4.42
1.15
88.89
0
0
1
351
DENSE
768
768
1.00
4.23
0.04
12.41
2.93
90.44
0
0
0
352
DENSE
768
768
1.00
3.79
0.10
11.98
3.17
90.37
0
1
0
353
DENSE
768
768
1.00
3.33
0.05
14.34
4.30
74.17
0
0
0
358
DENSE
768
768
1.00
2.61
0.04
4.00
1.53
79.10
0
0
1
359
DENSE
768
768
1.00
2.74
0.03
9.10
3.33
79.09
0
0
0
360
DENSE
768
768
1.00
5.71
0.06
16.18
2.83
93.34
0
0
0
361
DENSE
768
768
1.00
3.56
0.05
15.03
4.22
71.33
0
0
0
366
DENSE
2048
768
2.67
3.84
0.03
14.39
3.75
87.14
0
0
0
367
DENSE
2048
768
2.67
4.94
0.04
19.49
3.95
92.05
0
0
0
368
DENSE
2048
768
2.67
3.84
0.06
18.49
4.82
76.72
0
0
0
377
DENSE
768
768
1.00
2.96
0.04
4.08
1.38
84.70
0
0
1
378
DENSE
768
768
1.00
3.69
0.04
11.49
3.11
88.45
0
0
0
379
DENSE
768
768
1.00
4.94
0.12
15.46
3.13
92.93
0
1
0
380
DENSE
768
768
1.00
3.68
0.08
16.94
4.61
73.97
1
0
0
385
DENSE
768
768
1.00
3.10
0.04
4.25
1.37
82.76
0
0
1
386
DENSE
768
768
1.00
2.98
0.03
9.74
3.27
82.02
0
0
0
387
DENSE
768
768
1.00
4.44
0.08
13.69
3.08
89.17
0
0
0
388
DENSE
768
768
1.00
3.53
0.05
15.17
4.29
72.63
0
0
0
393
DENSE
2048
768
2.67
3.21
0.03
11.84
3.69
86.06
0
0
0
394
DENSE
2048
768
2.67
4.34
0.04
17.31
3.99
91.00
0
0
0
395
DENSE
2048
768
2.67
3.95
0.04
18.57
4.70
77.70
0
0
0
404
DENSE
768
768
1.00
3.66
0.06
4.72
1.29
87.26
0
0
1
405
DENSE
768
768
1.00
4.10
0.05
12.40
3.02
90.07
0
0
0
406
DENSE
768
768
1.00
3.23
0.12
10.41
3.23
93.53
0
5
0
407
DENSE
768
768
1.00
3.70
0.08
17.66
4.78
74.01
0
0
0
412
DENSE
768
768
1.00
3.33
0.06
4.85
1.46
84.98
0
0
1
413
DENSE
768
768
1.00
3.22
0.05
10.60
3.29
84.12
0
0
0
414
DENSE
768
768
1.00
4.93
0.12
14.79
3.00
91.89
0
5
0
415
DENSE
768
768
1.00
3.58
0.06
15.90
4.44
74.03
0
0
0
420
DENSE
2048
768
2.67
3.68
0.03
13.31
3.62
86.81
0
0
0
421
DENSE
2048
768
2.67
4.48
0.02
18.71
4.17
91.26
0
0
0
422
DENSE
2048
768
2.67
3.75
0.03
17.37
4.63
80.11
0
0
0
431
DENSE
768
768
1.00
3.60
0.04
4.34
1.21
88.68
0
0
1
432
DENSE
768
768
1.00
4.63
0.05
13.51
2.92
91.56
0
0
0
433
DENSE
768
768
1.00
5.20
0.14
16.90
3.25
94.55
0
7
0
434
DENSE
768
768
1.00
2.80
0.13
13.06
4.67
77.82
0
4
0
439
DENSE
768
768
1.00
3.31
0.08
5.04
1.52
84.91
0
1
1
440
DENSE
768
768
1.00
2.99
0.05
9.86
3.30
84.50
0
0
0
441
DENSE
768
768
1.00
4.26
0.10
13.35
3.13
92.80
0
0
0
442
DENSE
768
768
1.00
3.75
0.06
16.90
4.51
76.85
0
0
0
447
DENSE
2048
768
2.67
3.73
0.02
13.09
3.51
87.44
0
0
0
448
DENSE
2048
768
2.67
4.73
0.02
20.02
4.23
91.68
0
0
0
449
DENSE
2048
768
2.67
3.91
0.04
17.75
4.54
82.30
0
0
0
458
DENSE
768
768
1.00
3.63
0.06
4.03
1.11
88.12
0
0
1
459
DENSE
768
768
1.00
3.22
0.11
9.27
2.88
89.56
0
6
0
460
DENSE
768
768
1.00
4.09
0.09
13.39
3.27
94.57
0
0
0
461
DENSE
768
768
1.00
1.86
0.10
9.51
5.10
74.78
0
3
0
466
DENSE
768
768
1.00
3.22
0.06
4.76
1.48
84.89
0
0
1
467
DENSE
768
768
1.00
2.91
0.05
9.61
3.30
84.06
0
0
0
468
DENSE
768
768
1.00
8.33
0.13
27.49
3.30
93.08
0
1
1
469
DENSE
768
768
1.00
3.82
0.07
17.96
4.71
76.92
0
0
0
474
DENSE
2048
768
2.67
3.89
0.03
13.08
3.37
88.66
0
0
0
475
DENSE
2048
768
2.67
4.80
0.03
20.30
4.23
91.94
0
0
0
476
DENSE
2048
768
2.67
4.12
0.02
18.41
4.47
85.50
0
0
0
485
DENSE
768
768
1.00
3.30
0.03
4.35
1.32
88.26
0
0
0
486
DENSE
768
768
1.00
5.17
0.06
14.51
2.81
93.54
0
0
0
487
DENSE
768
768
1.00
6.21
0.12
20.82
3.35
95.16
0
1
0
488
DENSE
768
768
1.00
2.37
0.10
11.43
4.83
76.11
0
0
0
493
DENSE
768
768
1.00
2.07
0.10
2.88
1.39
80.19
0
1
1
494
DENSE
768
768
1.00
1.93
0.11
6.13
3.17
81.19
0
5
0
495
DENSE
768
768
1.00
2.85
0.13
9.70
3.40
89.21
0
0
0
496
DENSE
768
768
1.00
3.98
0.08
18.55
4.65
79.64
0
0
0
501
DENSE
2048
768
2.67
4.00
0.02
13.14
3.28
88.35
0
0
0
502
DENSE
2048
768
2.67
4.95
0.03
21.44
4.33
91.63
0
0
0
503
DENSE
2048
768
2.67
4.44
0.03
19.55
4.40
86.73
0
0
0
512
DENSE
768
768
1.00
3.89
0.03
4.31
1.11
91.95
0
0
1
513
DENSE
768
768
1.00
5.42
0.03
15.81
2.92
94.14
0
0
1
514
DENSE
768
768
1.00
3.45
0.12
12.01
3.49
93.27
0
1
0
515
DENSE
768
768
1.00
2.16
0.08
10.37
4.80
77.83
0
0
0
520
DENSE
768
768
1.00
2.43
0.06
3.89
1.60
80.04
0
0
1
521
DENSE
768
768
1.00
2.54
0.07
8.50
3.35
81.90
0
1
0
522
DENSE
768
768
1.00
9.23
0.14
33.08
3.59
86.88
0
1
0
523
DENSE
768
768
1.00
3.96
0.09
19.22
4.85
76.96
0
0
0
528
DENSE
2048
768
2.67
3.74
0.03
12.24
3.27
88.43
0
0
0
529
DENSE
2048
768
2.67
4.21
0.03
19.37
4.60
89.73
0
0
0
530
DENSE
2048
768
2.67
4.68
0.05
20.15
4.31
88.71
0
0
0
539
DENSE
768
768
1.00
4.37
0.02
6.11
1.40
91.69
0
0
1
540
DENSE
768
768
1.00
3.48
0.12
10.36
2.97
93.73
0
7
0
541
DENSE
768
768
1.00
6.91
0.14
23.37
3.38
94.00
0
1
0
542
DENSE
768
768
1.00
4.08
0.09
18.41
4.51
82.31
0
0
0
547
DENSE
768
768
1.00
2.08
0.05
3.17
1.52
72.28
0
0
1
548
DENSE
768
768
1.00
2.06
0.06
6.92
3.37
74.49
0
0
0
549
DENSE
768
768
1.00
2.00
0.14
7.77
3.89
81.42
0
7
0
550
DENSE
768
768
1.00
3.84
0.07
17.69
4.61
84.72
0
0
0
555
DENSE
2048
768
2.67
3.34
0.02
12.61
3.77
84.30
0
0
0
556
DENSE
2048
768
2.67
3.64
0.03
19.39
5.33
84.84
1
0
0
557
DENSE
2048
768
2.67
3.94
0.07
18.38
4.66
83.59
1
0
0
google-flan-t5-base Layer Plots
Layer 1
Layer=1 | N=32128 | M=768 | Q=41.83 | alpha=3.39 | D_ks=0.02 | alpha-hat=27.60 | num traps=0
Layer 8
Layer=8 | N=768 | M=768 | Q=1.00 | alpha=4.10 | D_ks=0.12 | alpha-hat=5.71 | num traps=0
Layer 9
Layer=9 | N=768 | M=768 | Q=1.00 | alpha=3.26 | D_ks=0.12 | alpha-hat=10.29 | num traps=0
Layer 10
Layer=10 | N=768 | M=768 | Q=1.00 | alpha=6.58 | D_ks=0.14 | alpha-hat=16.57 | num traps=0
Layer 11
Layer=11 | N=768 | M=768 | Q=1.00 | alpha=3.06 | D_ks=0.03 | alpha-hat=10.61 | num traps=0
Layer 12
Layer=12 | N=32 | M=12 | Q=2.67 | alpha=1.72 | D_ks=0.20 | alpha-hat=7.05 | num traps=0
Layer 17
Layer=17 | N=2048 | M=768 | Q=2.67 | alpha=3.03 | D_ks=0.04 | alpha-hat=10.89 | num traps=0
Layer 18
Layer=18 | N=2048 | M=768 | Q=2.67 | alpha=3.47 | D_ks=0.07 | alpha-hat=11.10 | num traps=0
Layer 19
Layer=19 | N=2048 | M=768 | Q=2.67 | alpha=3.44 | D_ks=0.02 | alpha-hat=11.84 | num traps=0
Layer 28
Layer=28 | N=768 | M=768 | Q=1.00 | alpha=4.67 | D_ks=0.04 | alpha-hat=6.93 | num traps=0
Layer 29
Layer=29 | N=768 | M=768 | Q=1.00 | alpha=4.37 | D_ks=0.03 | alpha-hat=14.34 | num traps=0
Layer 30
Layer=30 | N=768 | M=768 | Q=1.00 | alpha=3.40 | D_ks=0.06 | alpha-hat=8.91 | num traps=0
Layer 31
Layer=31 | N=768 | M=768 | Q=1.00 | alpha=2.66 | D_ks=0.02 | alpha-hat=10.05 | num traps=0
Layer 36
Layer=36 | N=2048 | M=768 | Q=2.67 | alpha=3.39 | D_ks=0.02 | alpha-hat=12.69 | num traps=0
Layer 37
Layer=37 | N=2048 | M=768 | Q=2.67 | alpha=4.52 | D_ks=0.05 | alpha-hat=15.81 | num traps=0
Layer 38
Layer=38 | N=2048 | M=768 | Q=2.67 | alpha=3.11 | D_ks=0.02 | alpha-hat=11.56 | num traps=0
Layer 47
Layer=47 | N=768 | M=768 | Q=1.00 | alpha=3.96 | D_ks=0.03 | alpha-hat=6.17 | num traps=0
Layer 48
Layer=48 | N=768 | M=768 | Q=1.00 | alpha=3.92 | D_ks=0.03 | alpha-hat=13.34 | num traps=0
Layer 49
Layer=49 | N=768 | M=768 | Q=1.00 | alpha=2.94 | D_ks=0.09 | alpha-hat=8.42 | num traps=0
Layer 50
Layer=50 | N=768 | M=768 | Q=1.00 | alpha=3.04 | D_ks=0.03 | alpha-hat=10.85 | num traps=0
Layer 55
Layer=55 | N=2048 | M=768 | Q=2.67 | alpha=3.52 | D_ks=0.02 | alpha-hat=12.54 | num traps=0
Layer 56
Layer=56 | N=2048 | M=768 | Q=2.67 | alpha=4.47 | D_ks=0.03 | alpha-hat=19.96 | num traps=3
Layer 57
Layer=57 | N=2048 | M=768 | Q=2.67 | alpha=3.29 | D_ks=0.02 | alpha-hat=12.16 | num traps=0
Layer 66
Layer=66 | N=768 | M=768 | Q=1.00 | alpha=3.86 | D_ks=0.05 | alpha-hat=5.28 | num traps=0
Layer 67
Layer=67 | N=768 | M=768 | Q=1.00 | alpha=4.32 | D_ks=0.04 | alpha-hat=13.55 | num traps=0
Layer 68
Layer=68 | N=768 | M=768 | Q=1.00 | alpha=3.63 | D_ks=0.09 | alpha-hat=10.93 | num traps=0
Layer 69
Layer=69 | N=768 | M=768 | Q=1.00 | alpha=3.09 | D_ks=0.02 | alpha-hat=11.33 | num traps=0
Layer 74
Layer=74 | N=2048 | M=768 | Q=2.67 | alpha=3.53 | D_ks=0.02 | alpha-hat=12.38 | num traps=0
Layer 75
Layer=75 | N=2048 | M=768 | Q=2.67 | alpha=5.35 | D_ks=0.04 | alpha-hat=18.36 | num traps=0
Layer 76
Layer=76 | N=2048 | M=768 | Q=2.67 | alpha=3.48 | D_ks=0.02 | alpha-hat=12.70 | num traps=0
Layer 85
Layer=85 | N=768 | M=768 | Q=1.00 | alpha=3.79 | D_ks=0.04 | alpha-hat=5.17 | num traps=0
Layer 86
Layer=86 | N=768 | M=768 | Q=1.00 | alpha=3.56 | D_ks=0.03 | alpha-hat=11.41 | num traps=0
Layer 87
Layer=87 | N=768 | M=768 | Q=1.00 | alpha=2.73 | D_ks=0.10 | alpha-hat=8.43 | num traps=0
Layer 88
Layer=88 | N=768 | M=768 | Q=1.00 | alpha=3.75 | D_ks=0.04 | alpha-hat=14.17 | num traps=0
Layer 93
Layer=93 | N=2048 | M=768 | Q=2.67 | alpha=3.52 | D_ks=0.02 | alpha-hat=12.42 | num traps=0
Layer 94
Layer=94 | N=2048 | M=768 | Q=2.67 | alpha=5.14 | D_ks=0.05 | alpha-hat=18.28 | num traps=0
Layer 95
Layer=95 | N=2048 | M=768 | Q=2.67 | alpha=3.77 | D_ks=0.02 | alpha-hat=14.10 | num traps=0
Layer 104
Layer=104 | N=768 | M=768 | Q=1.00 | alpha=3.65 | D_ks=0.04 | alpha-hat=4.66 | num traps=0
Layer 105
Layer=105 | N=768 | M=768 | Q=1.00 | alpha=3.92 | D_ks=0.04 | alpha-hat=12.21 | num traps=0
Layer 106
Layer=106 | N=768 | M=768 | Q=1.00 | alpha=2.63 | D_ks=0.10 | alpha-hat=8.51 | num traps=0
Layer 107
Layer=107 | N=768 | M=768 | Q=1.00 | alpha=3.43 | D_ks=0.03 | alpha-hat=12.79 | num traps=0
Layer 112
Layer=112 | N=2048 | M=768 | Q=2.67 | alpha=3.55 | D_ks=0.02 | alpha-hat=12.66 | num traps=0
Layer 113
Layer=113 | N=2048 | M=768 | Q=2.67 | alpha=5.92 | D_ks=0.04 | alpha-hat=21.78 | num traps=0
Layer 114
Layer=114 | N=2048 | M=768 | Q=2.67 | alpha=3.80 | D_ks=0.03 | alpha-hat=14.53 | num traps=0
Layer 123
Layer=123 | N=768 | M=768 | Q=1.00 | alpha=4.09 | D_ks=0.05 | alpha-hat=4.79 | num traps=0
Layer 124
Layer=124 | N=768 | M=768 | Q=1.00 | alpha=3.98 | D_ks=0.06 | alpha-hat=11.61 | num traps=0
Layer 125
Layer=125 | N=768 | M=768 | Q=1.00 | alpha=3.99 | D_ks=0.07 | alpha-hat=13.27 | num traps=0
Layer 126
Layer=126 | N=768 | M=768 | Q=1.00 | alpha=3.29 | D_ks=0.05 | alpha-hat=12.11 | num traps=0
Layer 131
Layer=131 | N=2048 | M=768 | Q=2.67 | alpha=3.43 | D_ks=0.02 | alpha-hat=12.22 | num traps=0
Layer 132
Layer=132 | N=2048 | M=768 | Q=2.67 | alpha=5.35 | D_ks=0.04 | alpha-hat=20.05 | num traps=0
Layer 133
Layer=133 | N=2048 | M=768 | Q=2.67 | alpha=4.02 | D_ks=0.03 | alpha-hat=14.89 | num traps=0
Layer 142
Layer=142 | N=768 | M=768 | Q=1.00 | alpha=3.20 | D_ks=0.06 | alpha-hat=3.51 | num traps=0
Layer 143
Layer=143 | N=768 | M=768 | Q=1.00 | alpha=3.12 | D_ks=0.06 | alpha-hat=9.26 | num traps=0
Layer 144
Layer=144 | N=768 | M=768 | Q=1.00 | alpha=2.29 | D_ks=0.10 | alpha-hat=7.75 | num traps=0
Layer 145
Layer=145 | N=768 | M=768 | Q=1.00 | alpha=4.02 | D_ks=0.04 | alpha-hat=15.27 | num traps=0
Layer 150
Layer=150 | N=2048 | M=768 | Q=2.67 | alpha=3.48 | D_ks=0.03 | alpha-hat=12.24 | num traps=0
Layer 151
Layer=151 | N=2048 | M=768 | Q=2.67 | alpha=5.09 | D_ks=0.04 | alpha-hat=19.24 | num traps=0
Layer 152
Layer=152 | N=2048 | M=768 | Q=2.67 | alpha=4.16 | D_ks=0.04 | alpha-hat=15.26 | num traps=0
Layer 161
Layer=161 | N=768 | M=768 | Q=1.00 | alpha=3.72 | D_ks=0.05 | alpha-hat=4.08 | num traps=0
Layer 162
Layer=162 | N=768 | M=768 | Q=1.00 | alpha=3.62 | D_ks=0.04 | alpha-hat=10.42 | num traps=0
Layer 163
Layer=163 | N=768 | M=768 | Q=1.00 | alpha=5.54 | D_ks=0.09 | alpha-hat=19.05 | num traps=0
Layer 164
Layer=164 | N=768 | M=768 | Q=1.00 | alpha=4.72 | D_ks=0.03 | alpha-hat=18.59 | num traps=0
Layer 169
Layer=169 | N=2048 | M=768 | Q=2.67 | alpha=3.65 | D_ks=0.03 | alpha-hat=12.74 | num traps=0
Layer 170
Layer=170 | N=2048 | M=768 | Q=2.67 | alpha=4.52 | D_ks=0.03 | alpha-hat=19.28 | num traps=3
Layer 171
Layer=171 | N=2048 | M=768 | Q=2.67 | alpha=4.36 | D_ks=0.03 | alpha-hat=16.56 | num traps=0
Layer 180
Layer=180 | N=768 | M=768 | Q=1.00 | alpha=3.90 | D_ks=0.04 | alpha-hat=3.75 | num traps=0
Layer 181
Layer=181 | N=768 | M=768 | Q=1.00 | alpha=4.19 | D_ks=0.05 | alpha-hat=11.35 | num traps=0
Layer 182
Layer=182 | N=768 | M=768 | Q=1.00 | alpha=4.88 | D_ks=0.08 | alpha-hat=16.55 | num traps=0
Layer 183
Layer=183 | N=768 | M=768 | Q=1.00 | alpha=3.86 | D_ks=0.07 | alpha-hat=14.97 | num traps=0
Layer 188
Layer=188 | N=2048 | M=768 | Q=2.67 | alpha=3.76 | D_ks=0.04 | alpha-hat=12.44 | num traps=0
Layer 189
Layer=189 | N=2048 | M=768 | Q=2.67 | alpha=5.53 | D_ks=0.05 | alpha-hat=21.53 | num traps=0
Layer 190
Layer=190 | N=2048 | M=768 | Q=2.67 | alpha=4.54 | D_ks=0.03 | alpha-hat=16.67 | num traps=0
Layer 199
Layer=199 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.04 | alpha-hat=3.18 | num traps=0
Layer 200
Layer=200 | N=768 | M=768 | Q=1.00 | alpha=3.52 | D_ks=0.04 | alpha-hat=9.73 | num traps=0
Layer 201
Layer=201 | N=768 | M=768 | Q=1.00 | alpha=2.57 | D_ks=0.11 | alpha-hat=9.25 | num traps=0
Layer 202
Layer=202 | N=768 | M=768 | Q=1.00 | alpha=2.57 | D_ks=0.10 | alpha-hat=9.87 | num traps=0
Layer 207
Layer=207 | N=2048 | M=768 | Q=2.67 | alpha=3.89 | D_ks=0.03 | alpha-hat=12.51 | num traps=0
Layer 208
Layer=208 | N=2048 | M=768 | Q=2.67 | alpha=4.72 | D_ks=0.04 | alpha-hat=18.40 | num traps=1
Layer 209
Layer=209 | N=2048 | M=768 | Q=2.67 | alpha=4.17 | D_ks=0.04 | alpha-hat=15.00 | num traps=0
Layer 218
Layer=218 | N=768 | M=768 | Q=1.00 | alpha=3.38 | D_ks=0.04 | alpha-hat=3.35 | num traps=0
Layer 219
Layer=219 | N=768 | M=768 | Q=1.00 | alpha=3.59 | D_ks=0.04 | alpha-hat=9.55 | num traps=0
Layer 220
Layer=220 | N=768 | M=768 | Q=1.00 | alpha=2.73 | D_ks=0.07 | alpha-hat=9.91 | num traps=0
Layer 221
Layer=221 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.05 | alpha-hat=12.77 | num traps=0
Layer 226
Layer=226 | N=2048 | M=768 | Q=2.67 | alpha=3.96 | D_ks=0.04 | alpha-hat=12.81 | num traps=0
Layer 227
Layer=227 | N=2048 | M=768 | Q=2.67 | alpha=4.37 | D_ks=0.03 | alpha-hat=17.96 | num traps=2
Layer 228
Layer=228 | N=2048 | M=768 | Q=2.67 | alpha=3.68 | D_ks=0.03 | alpha-hat=14.19 | num traps=0
Layer 241
Layer=241 | N=768 | M=768 | Q=1.00 | alpha=3.18 | D_ks=0.05 | alpha-hat=3.96 | num traps=0
Layer 242
Layer=242 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.09 | alpha-hat=10.37 | num traps=5
Layer 243
Layer=243 | N=768 | M=768 | Q=1.00 | alpha=3.82 | D_ks=0.06 | alpha-hat=9.70 | num traps=1
Layer 244
Layer=244 | N=768 | M=768 | Q=1.00 | alpha=2.84 | D_ks=0.05 | alpha-hat=9.83 | num traps=0
Layer 245
Layer=245 | N=32 | M=12 | Q=2.67 | alpha=1.19 | D_ks=0.17 | alpha-hat=3.76 | num traps=11
Layer 250
Layer=250 | N=768 | M=768 | Q=1.00 | alpha=3.23 | D_ks=0.07 | alpha-hat=4.31 | num traps=0
Layer 251
Layer=251 | N=768 | M=768 | Q=1.00 | alpha=2.53 | D_ks=0.07 | alpha-hat=7.71 | num traps=0
Layer 252
Layer=252 | N=768 | M=768 | Q=1.00 | alpha=4.83 | D_ks=0.04 | alpha-hat=13.02 | num traps=0
Layer 253
Layer=253 | N=768 | M=768 | Q=1.00 | alpha=3.20 | D_ks=0.03 | alpha-hat=11.70 | num traps=0
Layer 258
Layer=258 | N=2048 | M=768 | Q=2.67 | alpha=3.15 | D_ks=0.04 | alpha-hat=11.97 | num traps=0
Layer 259
Layer=259 | N=2048 | M=768 | Q=2.67 | alpha=4.82 | D_ks=0.03 | alpha-hat=14.61 | num traps=0
Layer 260
Layer=260 | N=2048 | M=768 | Q=2.67 | alpha=3.54 | D_ks=0.03 | alpha-hat=13.30 | num traps=0
Layer 269
Layer=269 | N=768 | M=768 | Q=1.00 | alpha=3.48 | D_ks=0.03 | alpha-hat=2.68 | num traps=0
Layer 270
Layer=270 | N=768 | M=768 | Q=1.00 | alpha=3.37 | D_ks=0.04 | alpha-hat=9.47 | num traps=0
Layer 271
Layer=271 | N=768 | M=768 | Q=1.00 | alpha=4.80 | D_ks=0.09 | alpha-hat=11.31 | num traps=0
Layer 272
Layer=272 | N=768 | M=768 | Q=1.00 | alpha=2.56 | D_ks=0.02 | alpha-hat=9.23 | num traps=0
Layer 277
Layer=277 | N=768 | M=768 | Q=1.00 | alpha=3.24 | D_ks=0.04 | alpha-hat=3.31 | num traps=0
Layer 278
Layer=278 | N=768 | M=768 | Q=1.00 | alpha=2.77 | D_ks=0.05 | alpha-hat=8.66 | num traps=0
Layer 279
Layer=279 | N=768 | M=768 | Q=1.00 | alpha=6.59 | D_ks=0.04 | alpha-hat=18.65 | num traps=0
Layer 280
Layer=280 | N=768 | M=768 | Q=1.00 | alpha=2.89 | D_ks=0.03 | alpha-hat=10.42 | num traps=0
Layer 285
Layer=285 | N=2048 | M=768 | Q=2.67 | alpha=3.67 | D_ks=0.02 | alpha-hat=13.20 | num traps=0
Layer 286
Layer=286 | N=2048 | M=768 | Q=2.67 | alpha=5.01 | D_ks=0.02 | alpha-hat=17.28 | num traps=0
Layer 287
Layer=287 | N=2048 | M=768 | Q=2.67 | alpha=4.16 | D_ks=0.03 | alpha-hat=16.63 | num traps=0
Layer 296
Layer=296 | N=768 | M=768 | Q=1.00 | alpha=2.68 | D_ks=0.04 | alpha-hat=3.02 | num traps=0
Layer 297
Layer=297 | N=768 | M=768 | Q=1.00 | alpha=3.31 | D_ks=0.03 | alpha-hat=8.42 | num traps=0
Layer 298
Layer=298 | N=768 | M=768 | Q=1.00 | alpha=3.89 | D_ks=0.11 | alpha-hat=9.62 | num traps=0
Layer 299
Layer=299 | N=768 | M=768 | Q=1.00 | alpha=2.43 | D_ks=0.03 | alpha-hat=10.16 | num traps=0
Layer 304
Layer=304 | N=768 | M=768 | Q=1.00 | alpha=3.43 | D_ks=0.06 | alpha-hat=3.51 | num traps=0
Layer 305
Layer=305 | N=768 | M=768 | Q=1.00 | alpha=3.16 | D_ks=0.04 | alpha-hat=9.10 | num traps=0
Layer 306
Layer=306 | N=768 | M=768 | Q=1.00 | alpha=5.88 | D_ks=0.05 | alpha-hat=14.91 | num traps=0
Layer 307
Layer=307 | N=768 | M=768 | Q=1.00 | alpha=3.35 | D_ks=0.04 | alpha-hat=13.31 | num traps=1
Layer 312
Layer=312 | N=2048 | M=768 | Q=2.67 | alpha=2.78 | D_ks=0.06 | alpha-hat=10.35 | num traps=0
Layer 313
Layer=313 | N=2048 | M=768 | Q=2.67 | alpha=3.08 | D_ks=0.09 | alpha-hat=11.51 | num traps=0
Layer 314
Layer=314 | N=2048 | M=768 | Q=2.67 | alpha=4.20 | D_ks=0.06 | alpha-hat=19.50 | num traps=1
Layer 323
Layer=323 | N=768 | M=768 | Q=1.00 | alpha=3.39 | D_ks=0.06 | alpha-hat=3.06 | num traps=0
Layer 324
Layer=324 | N=768 | M=768 | Q=1.00 | alpha=4.25 | D_ks=0.05 | alpha-hat=11.06 | num traps=0
Layer 325
Layer=325 | N=768 | M=768 | Q=1.00 | alpha=4.20 | D_ks=0.05 | alpha-hat=11.81 | num traps=0
Layer 326
Layer=326 | N=768 | M=768 | Q=1.00 | alpha=2.77 | D_ks=0.04 | alpha-hat=11.91 | num traps=1
Layer 331
Layer=331 | N=768 | M=768 | Q=1.00 | alpha=3.25 | D_ks=0.05 | alpha-hat=3.98 | num traps=0
Layer 332
Layer=332 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.03 | alpha-hat=9.86 | num traps=0
Layer 333
Layer=333 | N=768 | M=768 | Q=1.00 | alpha=4.40 | D_ks=0.13 | alpha-hat=12.08 | num traps=0
Layer 334
Layer=334 | N=768 | M=768 | Q=1.00 | alpha=3.47 | D_ks=0.05 | alpha-hat=14.99 | num traps=1
Layer 339
Layer=339 | N=2048 | M=768 | Q=2.67 | alpha=3.00 | D_ks=0.05 | alpha-hat=11.49 | num traps=0
Layer 340
Layer=340 | N=2048 | M=768 | Q=2.67 | alpha=3.98 | D_ks=0.08 | alpha-hat=15.79 | num traps=0
Layer 341
Layer=341 | N=2048 | M=768 | Q=2.67 | alpha=4.02 | D_ks=0.06 | alpha-hat=19.84 | num traps=2
Layer 350
Layer=350 | N=768 | M=768 | Q=1.00 | alpha=3.85 | D_ks=0.06 | alpha-hat=4.42 | num traps=0
Layer 351
Layer=351 | N=768 | M=768 | Q=1.00 | alpha=4.23 | D_ks=0.04 | alpha-hat=12.41 | num traps=0
Layer 352
Layer=352 | N=768 | M=768 | Q=1.00 | alpha=3.79 | D_ks=0.10 | alpha-hat=11.98 | num traps=0
Layer 353
Layer=353 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.05 | alpha-hat=14.34 | num traps=0
Layer 358
Layer=358 | N=768 | M=768 | Q=1.00 | alpha=2.61 | D_ks=0.04 | alpha-hat=4.00 | num traps=0
Layer 359
Layer=359 | N=768 | M=768 | Q=1.00 | alpha=2.74 | D_ks=0.03 | alpha-hat=9.10 | num traps=0
Layer 360
Layer=360 | N=768 | M=768 | Q=1.00 | alpha=5.71 | D_ks=0.06 | alpha-hat=16.18 | num traps=0
Layer 361
Layer=361 | N=768 | M=768 | Q=1.00 | alpha=3.56 | D_ks=0.05 | alpha-hat=15.03 | num traps=0
Layer 366
Layer=366 | N=2048 | M=768 | Q=2.67 | alpha=3.84 | D_ks=0.03 | alpha-hat=14.39 | num traps=0
Layer 367
Layer=367 | N=2048 | M=768 | Q=2.67 | alpha=4.94 | D_ks=0.04 | alpha-hat=19.49 | num traps=0
Layer 368
Layer=368 | N=2048 | M=768 | Q=2.67 | alpha=3.84 | D_ks=0.06 | alpha-hat=18.49 | num traps=0
Layer 377
Layer=377 | N=768 | M=768 | Q=1.00 | alpha=2.96 | D_ks=0.04 | alpha-hat=4.08 | num traps=0
Layer 378
Layer=378 | N=768 | M=768 | Q=1.00 | alpha=3.69 | D_ks=0.04 | alpha-hat=11.49 | num traps=0
Layer 379
Layer=379 | N=768 | M=768 | Q=1.00 | alpha=4.94 | D_ks=0.12 | alpha-hat=15.46 | num traps=0
Layer 380
Layer=380 | N=768 | M=768 | Q=1.00 | alpha=3.68 | D_ks=0.08 | alpha-hat=16.94 | num traps=1
Layer 385
Layer=385 | N=768 | M=768 | Q=1.00 | alpha=3.10 | D_ks=0.04 | alpha-hat=4.25 | num traps=0
Layer 386
Layer=386 | N=768 | M=768 | Q=1.00 | alpha=2.98 | D_ks=0.03 | alpha-hat=9.74 | num traps=0
Layer 387
Layer=387 | N=768 | M=768 | Q=1.00 | alpha=4.44 | D_ks=0.08 | alpha-hat=13.69 | num traps=0
Layer 388
Layer=388 | N=768 | M=768 | Q=1.00 | alpha=3.53 | D_ks=0.05 | alpha-hat=15.17 | num traps=0
Layer 393
Layer=393 | N=2048 | M=768 | Q=2.67 | alpha=3.21 | D_ks=0.03 | alpha-hat=11.84 | num traps=0
Layer 394
Layer=394 | N=2048 | M=768 | Q=2.67 | alpha=4.34 | D_ks=0.04 | alpha-hat=17.31 | num traps=0
Layer 395
Layer=395 | N=2048 | M=768 | Q=2.67 | alpha=3.95 | D_ks=0.04 | alpha-hat=18.57 | num traps=0
Layer 404
Layer=404 | N=768 | M=768 | Q=1.00 | alpha=3.66 | D_ks=0.06 | alpha-hat=4.72 | num traps=0
Layer 405
Layer=405 | N=768 | M=768 | Q=1.00 | alpha=4.10 | D_ks=0.05 | alpha-hat=12.40 | num traps=0
Layer 406
Layer=406 | N=768 | M=768 | Q=1.00 | alpha=3.23 | D_ks=0.12 | alpha-hat=10.41 | num traps=0
Layer 407
Layer=407 | N=768 | M=768 | Q=1.00 | alpha=3.70 | D_ks=0.08 | alpha-hat=17.66 | num traps=0
Layer 412
Layer=412 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.06 | alpha-hat=4.85 | num traps=0
Layer 413
Layer=413 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.05 | alpha-hat=10.60 | num traps=0
Layer 414
Layer=414 | N=768 | M=768 | Q=1.00 | alpha=4.93 | D_ks=0.12 | alpha-hat=14.79 | num traps=0
Layer 415
Layer=415 | N=768 | M=768 | Q=1.00 | alpha=3.58 | D_ks=0.06 | alpha-hat=15.90 | num traps=0
Layer 420
Layer=420 | N=2048 | M=768 | Q=2.67 | alpha=3.68 | D_ks=0.03 | alpha-hat=13.31 | num traps=0
Layer 421
Layer=421 | N=2048 | M=768 | Q=2.67 | alpha=4.48 | D_ks=0.02 | alpha-hat=18.71 | num traps=0
Layer 422
Layer=422 | N=2048 | M=768 | Q=2.67 | alpha=3.75 | D_ks=0.03 | alpha-hat=17.37 | num traps=0
Layer 431
Layer=431 | N=768 | M=768 | Q=1.00 | alpha=3.60 | D_ks=0.04 | alpha-hat=4.34 | num traps=0
Layer 432
Layer=432 | N=768 | M=768 | Q=1.00 | alpha=4.63 | D_ks=0.05 | alpha-hat=13.51 | num traps=0
Layer 433
Layer=433 | N=768 | M=768 | Q=1.00 | alpha=5.20 | D_ks=0.14 | alpha-hat=16.90 | num traps=0
Layer 434
Layer=434 | N=768 | M=768 | Q=1.00 | alpha=2.80 | D_ks=0.13 | alpha-hat=13.06 | num traps=0
Layer 439
Layer=439 | N=768 | M=768 | Q=1.00 | alpha=3.31 | D_ks=0.08 | alpha-hat=5.04 | num traps=0
Layer 440
Layer=440 | N=768 | M=768 | Q=1.00 | alpha=2.99 | D_ks=0.05 | alpha-hat=9.86 | num traps=0
Layer 441
Layer=441 | N=768 | M=768 | Q=1.00 | alpha=4.26 | D_ks=0.10 | alpha-hat=13.35 | num traps=0
Layer 442
Layer=442 | N=768 | M=768 | Q=1.00 | alpha=3.75 | D_ks=0.06 | alpha-hat=16.90 | num traps=0
Layer 447
Layer=447 | N=2048 | M=768 | Q=2.67 | alpha=3.73 | D_ks=0.02 | alpha-hat=13.09 | num traps=0
Layer 448
Layer=448 | N=2048 | M=768 | Q=2.67 | alpha=4.73 | D_ks=0.02 | alpha-hat=20.02 | num traps=0
Layer 449
Layer=449 | N=2048 | M=768 | Q=2.67 | alpha=3.91 | D_ks=0.04 | alpha-hat=17.75 | num traps=0
Layer 458
Layer=458 | N=768 | M=768 | Q=1.00 | alpha=3.63 | D_ks=0.06 | alpha-hat=4.03 | num traps=0
Layer 459
Layer=459 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.11 | alpha-hat=9.27 | num traps=0
Layer 460
Layer=460 | N=768 | M=768 | Q=1.00 | alpha=4.09 | D_ks=0.09 | alpha-hat=13.39 | num traps=0
Layer 461
Layer=461 | N=768 | M=768 | Q=1.00 | alpha=1.86 | D_ks=0.10 | alpha-hat=9.51 | num traps=0
Layer 466
Layer=466 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.06 | alpha-hat=4.76 | num traps=0
Layer 467
Layer=467 | N=768 | M=768 | Q=1.00 | alpha=2.91 | D_ks=0.05 | alpha-hat=9.61 | num traps=0
Layer 468
Layer=468 | N=768 | M=768 | Q=1.00 | alpha=8.33 | D_ks=0.13 | alpha-hat=27.49 | num traps=0
Layer 469
Layer=469 | N=768 | M=768 | Q=1.00 | alpha=3.82 | D_ks=0.07 | alpha-hat=17.96 | num traps=0
Layer 474
Layer=474 | N=2048 | M=768 | Q=2.67 | alpha=3.89 | D_ks=0.03 | alpha-hat=13.08 | num traps=0
Layer 475
Layer=475 | N=2048 | M=768 | Q=2.67 | alpha=4.80 | D_ks=0.03 | alpha-hat=20.30 | num traps=0
Layer 476
Layer=476 | N=2048 | M=768 | Q=2.67 | alpha=4.12 | D_ks=0.02 | alpha-hat=18.41 | num traps=0
Layer 485
Layer=485 | N=768 | M=768 | Q=1.00 | alpha=3.30 | D_ks=0.03 | alpha-hat=4.35 | num traps=0
Layer 486
Layer=486 | N=768 | M=768 | Q=1.00 | alpha=5.17 | D_ks=0.06 | alpha-hat=14.51 | num traps=0
Layer 487
Layer=487 | N=768 | M=768 | Q=1.00 | alpha=6.21 | D_ks=0.12 | alpha-hat=20.82 | num traps=0
Layer 488
Layer=488 | N=768 | M=768 | Q=1.00 | alpha=2.37 | D_ks=0.10 | alpha-hat=11.43 | num traps=0
Layer 493
Layer=493 | N=768 | M=768 | Q=1.00 | alpha=2.07 | D_ks=0.10 | alpha-hat=2.88 | num traps=0
Layer 494
Layer=494 | N=768 | M=768 | Q=1.00 | alpha=1.93 | D_ks=0.11 | alpha-hat=6.13 | num traps=0
Layer 495
Layer=495 | N=768 | M=768 | Q=1.00 | alpha=2.85 | D_ks=0.13 | alpha-hat=9.70 | num traps=0
Layer 496
Layer=496 | N=768 | M=768 | Q=1.00 | alpha=3.98 | D_ks=0.08 | alpha-hat=18.55 | num traps=0
Layer 501
Layer=501 | N=2048 | M=768 | Q=2.67 | alpha=4.00 | D_ks=0.02 | alpha-hat=13.14 | num traps=0
Layer 502
Layer=502 | N=2048 | M=768 | Q=2.67 | alpha=4.95 | D_ks=0.03 | alpha-hat=21.44 | num traps=0
Layer 503
Layer=503 | N=2048 | M=768 | Q=2.67 | alpha=4.44 | D_ks=0.03 | alpha-hat=19.55 | num traps=0
Layer 512
Layer=512 | N=768 | M=768 | Q=1.00 | alpha=3.89 | D_ks=0.03 | alpha-hat=4.31 | num traps=0
Layer 513
Layer=513 | N=768 | M=768 | Q=1.00 | alpha=5.42 | D_ks=0.03 | alpha-hat=15.81 | num traps=0
Layer 514
Layer=514 | N=768 | M=768 | Q=1.00 | alpha=3.45 | D_ks=0.12 | alpha-hat=12.01 | num traps=0
Layer 515
Layer=515 | N=768 | M=768 | Q=1.00 | alpha=2.16 | D_ks=0.08 | alpha-hat=10.37 | num traps=0
Layer 520
Layer=520 | N=768 | M=768 | Q=1.00 | alpha=2.43 | D_ks=0.06 | alpha-hat=3.89 | num traps=0
Layer 521
Layer=521 | N=768 | M=768 | Q=1.00 | alpha=2.54 | D_ks=0.07 | alpha-hat=8.50 | num traps=0
Layer 522
Layer=522 | N=768 | M=768 | Q=1.00 | alpha=9.23 | D_ks=0.14 | alpha-hat=33.08 | num traps=0
Layer 523
Layer=523 | N=768 | M=768 | Q=1.00 | alpha=3.96 | D_ks=0.09 | alpha-hat=19.22 | num traps=0
Layer 528
Layer=528 | N=2048 | M=768 | Q=2.67 | alpha=3.74 | D_ks=0.03 | alpha-hat=12.24 | num traps=0
Layer 529
Layer=529 | N=2048 | M=768 | Q=2.67 | alpha=4.21 | D_ks=0.03 | alpha-hat=19.37 | num traps=0
Layer 530
Layer=530 | N=2048 | M=768 | Q=2.67 | alpha=4.68 | D_ks=0.05 | alpha-hat=20.15 | num traps=0
Layer 539
Layer=539 | N=768 | M=768 | Q=1.00 | alpha=4.37 | D_ks=0.02 | alpha-hat=6.11 | num traps=0
Layer 540
Layer=540 | N=768 | M=768 | Q=1.00 | alpha=3.48 | D_ks=0.12 | alpha-hat=10.36 | num traps=0
Layer 541
Layer=541 | N=768 | M=768 | Q=1.00 | alpha=6.91 | D_ks=0.14 | alpha-hat=23.37 | num traps=0
Layer 542
Layer=542 | N=768 | M=768 | Q=1.00 | alpha=4.08 | D_ks=0.09 | alpha-hat=18.41 | num traps=0
Layer 547
Layer=547 | N=768 | M=768 | Q=1.00 | alpha=2.08 | D_ks=0.05 | alpha-hat=3.17 | num traps=0
Layer 548
Layer=548 | N=768 | M=768 | Q=1.00 | alpha=2.06 | D_ks=0.06 | alpha-hat=6.92 | num traps=0
Layer 549
Layer=549 | N=768 | M=768 | Q=1.00 | alpha=2.00 | D_ks=0.14 | alpha-hat=7.77 | num traps=0
Layer 550
Layer=550 | N=768 | M=768 | Q=1.00 | alpha=3.84 | D_ks=0.07 | alpha-hat=17.69 | num traps=0
Layer 555
Layer=555 | N=2048 | M=768 | Q=2.67 | alpha=3.34 | D_ks=0.02 | alpha-hat=12.61 | num traps=0
Layer 556
Layer=556 | N=2048 | M=768 | Q=2.67 | alpha=3.64 | D_ks=0.03 | alpha-hat=19.39 | num traps=1
Layer 557
Layer=557 | N=2048 | M=768 | Q=2.67 | alpha=3.94 | D_ks=0.07 | alpha-hat=18.38 | num traps=1
google-flan-t5-base Model Summary Plots
google-flan-t5-base Model Selected Details
| layer_type | N | M | Q | alpha | D | alpha-hat | log_SN | % Rand | num_traps | num_fingers | rank_loss | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| layer_id | ||||||||||||
| 1 | EMBEDDING | 32128 | 768 | 41.83 | 3.39 | 0.02 | 27.60 | 8.15 | 76.46 | 0 | 0 | 0 |
| 8 | DENSE | 768 | 768 | 1.00 | 4.10 | 0.12 | 5.71 | 1.39 | 91.61 | 0 | 3 | 0 |
| 9 | DENSE | 768 | 768 | 1.00 | 3.26 | 0.12 | 10.29 | 3.16 | 92.16 | 0 | 3 | 0 |
| 10 | DENSE | 768 | 768 | 1.00 | 6.58 | 0.14 | 16.57 | 2.52 | 91.87 | 0 | 7 | 1 |
| 11 | DENSE | 768 | 768 | 1.00 | 3.06 | 0.03 | 10.61 | 3.47 | 81.25 | 0 | 0 | 0 |
| 12 | EMBEDDING | 32 | 12 | 2.67 | 1.72 | 0.20 | 7.05 | 4.11 | 58.01 | 0 | 0 | 0 |
| 17 | DENSE | 2048 | 768 | 2.67 | 3.03 | 0.04 | 10.89 | 3.60 | 87.27 | 0 | 0 | 0 |
| 18 | DENSE | 2048 | 768 | 2.67 | 3.47 | 0.07 | 11.10 | 3.20 | 91.20 | 0 | 0 | 0 |
| 19 | DENSE | 2048 | 768 | 2.67 | 3.44 | 0.02 | 11.84 | 3.45 | 86.50 | 0 | 0 | 0 |
| 28 | DENSE | 768 | 768 | 1.00 | 4.67 | 0.04 | 6.93 | 1.48 | 89.92 | 0 | 0 | 1 |
| 29 | DENSE | 768 | 768 | 1.00 | 4.37 | 0.03 | 14.34 | 3.28 | 90.88 | 0 | 0 | 0 |
| 30 | DENSE | 768 | 768 | 1.00 | 3.40 | 0.06 | 8.91 | 2.62 | 89.63 | 0 | 0 | 1 |
| 31 | DENSE | 768 | 768 | 1.00 | 2.66 | 0.02 | 10.05 | 3.77 | 76.00 | 0 | 0 | 0 |
| 36 | DENSE | 2048 | 768 | 2.67 | 3.39 | 0.02 | 12.69 | 3.75 | 87.82 | 0 | 0 | 0 |
| 37 | DENSE | 2048 | 768 | 2.67 | 4.52 | 0.05 | 15.81 | 3.50 | 92.61 | 0 | 0 | 0 |
| 38 | DENSE | 2048 | 768 | 2.67 | 3.11 | 0.02 | 11.56 | 3.72 | 83.38 | 0 | 0 | 0 |
| 47 | DENSE | 768 | 768 | 1.00 | 3.96 | 0.03 | 6.17 | 1.56 | 90.38 | 0 | 0 | 1 |
| 48 | DENSE | 768 | 768 | 1.00 | 3.92 | 0.03 | 13.34 | 3.40 | 89.22 | 0 | 0 | 0 |
| 49 | DENSE | 768 | 768 | 1.00 | 2.94 | 0.09 | 8.42 | 2.86 | 89.80 | 0 | 0 | 0 |
| 50 | DENSE | 768 | 768 | 1.00 | 3.04 | 0.03 | 10.85 | 3.57 | 82.63 | 0 | 0 | 1 |
| 55 | DENSE | 2048 | 768 | 2.67 | 3.52 | 0.02 | 12.54 | 3.56 | 88.94 | 0 | 0 | 0 |
| 56 | DENSE | 2048 | 768 | 2.67 | 4.47 | 0.03 | 19.96 | 4.47 | 92.69 | 3 | 0 | 0 |
| 57 | DENSE | 2048 | 768 | 2.67 | 3.29 | 0.02 | 12.16 | 3.70 | 85.60 | 0 | 0 | 0 |
| 66 | DENSE | 768 | 768 | 1.00 | 3.86 | 0.05 | 5.28 | 1.37 | 88.74 | 0 | 0 | 1 |
| 67 | DENSE | 768 | 768 | 1.00 | 4.32 | 0.04 | 13.55 | 3.13 | 90.53 | 0 | 0 | 1 |
| 68 | DENSE | 768 | 768 | 1.00 | 3.63 | 0.09 | 10.93 | 3.01 | 90.63 | 0 | 1 | 0 |
| 69 | DENSE | 768 | 768 | 1.00 | 3.09 | 0.02 | 11.33 | 3.67 | 81.94 | 0 | 0 | 0 |
| 74 | DENSE | 2048 | 768 | 2.67 | 3.53 | 0.02 | 12.38 | 3.51 | 88.64 | 0 | 0 | 0 |
| 75 | DENSE | 2048 | 768 | 2.67 | 5.35 | 0.04 | 18.36 | 3.43 | 94.32 | 0 | 0 | 0 |
| 76 | DENSE | 2048 | 768 | 2.67 | 3.48 | 0.02 | 12.70 | 3.65 | 86.48 | 0 | 0 | 0 |
| 85 | DENSE | 768 | 768 | 1.00 | 3.79 | 0.04 | 5.17 | 1.36 | 88.25 | 0 | 0 | 1 |
| 86 | DENSE | 768 | 768 | 1.00 | 3.56 | 0.03 | 11.41 | 3.21 | 88.15 | 0 | 0 | 0 |
| 87 | DENSE | 768 | 768 | 1.00 | 2.73 | 0.10 | 8.43 | 3.09 | 88.51 | 0 | 0 | 0 |
| 88 | DENSE | 768 | 768 | 1.00 | 3.75 | 0.04 | 14.17 | 3.78 | 84.51 | 0 | 0 | 0 |
| 93 | DENSE | 2048 | 768 | 2.67 | 3.52 | 0.02 | 12.42 | 3.53 | 88.30 | 0 | 0 | 0 |
| 94 | DENSE | 2048 | 768 | 2.67 | 5.14 | 0.05 | 18.28 | 3.56 | 93.86 | 0 | 0 | 0 |
| 95 | DENSE | 2048 | 768 | 2.67 | 3.77 | 0.02 | 14.10 | 3.74 | 87.40 | 0 | 0 | 0 |
| 104 | DENSE | 768 | 768 | 1.00 | 3.65 | 0.04 | 4.66 | 1.28 | 88.28 | 0 | 0 | 0 |
| 105 | DENSE | 768 | 768 | 1.00 | 3.92 | 0.04 | 12.21 | 3.11 | 89.76 | 0 | 0 | 0 |
| 106 | DENSE | 768 | 768 | 1.00 | 2.63 | 0.10 | 8.51 | 3.23 | 88.87 | 0 | 1 | 0 |
| 107 | DENSE | 768 | 768 | 1.00 | 3.43 | 0.03 | 12.79 | 3.73 | 85.70 | 0 | 0 | 0 |
| 112 | DENSE | 2048 | 768 | 2.67 | 3.55 | 0.02 | 12.66 | 3.57 | 87.00 | 0 | 0 | 0 |
| 113 | DENSE | 2048 | 768 | 2.67 | 5.92 | 0.04 | 21.78 | 3.68 | 93.33 | 0 | 0 | 0 |
| 114 | DENSE | 2048 | 768 | 2.67 | 3.80 | 0.03 | 14.53 | 3.83 | 87.30 | 0 | 0 | 0 |
| 123 | DENSE | 768 | 768 | 1.00 | 4.09 | 0.05 | 4.79 | 1.17 | 88.76 | 0 | 0 | 1 |
| 124 | DENSE | 768 | 768 | 1.00 | 3.98 | 0.06 | 11.61 | 2.92 | 90.18 | 0 | 0 | 1 |
| 125 | DENSE | 768 | 768 | 1.00 | 3.99 | 0.07 | 13.27 | 3.32 | 87.53 | 0 | 0 | 1 |
| 126 | DENSE | 768 | 768 | 1.00 | 3.29 | 0.05 | 12.11 | 3.68 | 86.83 | 0 | 0 | 1 |
| 131 | DENSE | 2048 | 768 | 2.67 | 3.43 | 0.02 | 12.22 | 3.56 | 86.26 | 0 | 0 | 0 |
| 132 | DENSE | 2048 | 768 | 2.67 | 5.35 | 0.04 | 20.05 | 3.75 | 92.89 | 0 | 0 | 0 |
| 133 | DENSE | 2048 | 768 | 2.67 | 4.02 | 0.03 | 14.89 | 3.70 | 88.18 | 0 | 0 | 0 |
| 142 | DENSE | 768 | 768 | 1.00 | 3.20 | 0.06 | 3.51 | 1.10 | 85.39 | 0 | 0 | 1 |
| 143 | DENSE | 768 | 768 | 1.00 | 3.12 | 0.06 | 9.26 | 2.96 | 85.44 | 0 | 0 | 0 |
| 144 | DENSE | 768 | 768 | 1.00 | 2.29 | 0.10 | 7.75 | 3.38 | 85.95 | 0 | 0 | 0 |
| 145 | DENSE | 768 | 768 | 1.00 | 4.02 | 0.04 | 15.27 | 3.80 | 86.68 | 0 | 0 | 0 |
| 150 | DENSE | 2048 | 768 | 2.67 | 3.48 | 0.03 | 12.24 | 3.52 | 85.84 | 0 | 0 | 0 |
| 151 | DENSE | 2048 | 768 | 2.67 | 5.09 | 0.04 | 19.24 | 3.78 | 92.43 | 0 | 0 | 0 |
| 152 | DENSE | 2048 | 768 | 2.67 | 4.16 | 0.04 | 15.26 | 3.67 | 88.27 | 0 | 0 | 0 |
| 161 | DENSE | 768 | 768 | 1.00 | 3.72 | 0.05 | 4.08 | 1.10 | 84.84 | 0 | 0 | 1 |
| 162 | DENSE | 768 | 768 | 1.00 | 3.62 | 0.04 | 10.42 | 2.88 | 84.67 | 0 | 0 | 0 |
| 163 | DENSE | 768 | 768 | 1.00 | 5.54 | 0.09 | 19.05 | 3.44 | 87.95 | 0 | 0 | 0 |
| 164 | DENSE | 768 | 768 | 1.00 | 4.72 | 0.03 | 18.59 | 3.94 | 86.17 | 0 | 0 | 0 |
| 169 | DENSE | 2048 | 768 | 2.67 | 3.65 | 0.03 | 12.74 | 3.49 | 86.19 | 0 | 0 | 0 |
| 170 | DENSE | 2048 | 768 | 2.67 | 4.52 | 0.03 | 19.28 | 4.27 | 92.71 | 3 | 0 | 0 |
| 171 | DENSE | 2048 | 768 | 2.67 | 4.36 | 0.03 | 16.56 | 3.80 | 88.32 | 0 | 0 | 0 |
| 180 | DENSE | 768 | 768 | 1.00 | 3.90 | 0.04 | 3.75 | 0.96 | 86.59 | 0 | 0 | 1 |
| 181 | DENSE | 768 | 768 | 1.00 | 4.19 | 0.05 | 11.35 | 2.71 | 89.29 | 0 | 0 | 0 |
| 182 | DENSE | 768 | 768 | 1.00 | 4.88 | 0.08 | 16.55 | 3.39 | 91.45 | 0 | 0 | 0 |
| 183 | DENSE | 768 | 768 | 1.00 | 3.86 | 0.07 | 14.97 | 3.88 | 85.91 | 0 | 0 | 0 |
| 188 | DENSE | 2048 | 768 | 2.67 | 3.76 | 0.04 | 12.44 | 3.30 | 87.56 | 0 | 0 | 0 |
| 189 | DENSE | 2048 | 768 | 2.67 | 5.53 | 0.05 | 21.53 | 3.90 | 92.24 | 0 | 0 | 0 |
| 190 | DENSE | 2048 | 768 | 2.67 | 4.54 | 0.03 | 16.67 | 3.67 | 88.86 | 0 | 0 | 0 |
| 199 | DENSE | 768 | 768 | 1.00 | 3.33 | 0.04 | 3.18 | 0.95 | 85.40 | 0 | 0 | 1 |
| 200 | DENSE | 768 | 768 | 1.00 | 3.52 | 0.04 | 9.73 | 2.76 | 86.93 | 0 | 0 | 1 |
| 201 | DENSE | 768 | 768 | 1.00 | 2.57 | 0.11 | 9.25 | 3.60 | 86.49 | 0 | 5 | 0 |
| 202 | DENSE | 768 | 768 | 1.00 | 2.57 | 0.10 | 9.87 | 3.84 | 84.90 | 0 | 4 | 0 |
| 207 | DENSE | 2048 | 768 | 2.67 | 3.89 | 0.03 | 12.51 | 3.21 | 88.38 | 0 | 0 | 0 |
| 208 | DENSE | 2048 | 768 | 2.67 | 4.72 | 0.04 | 18.40 | 3.90 | 92.44 | 1 | 0 | 0 |
| 209 | DENSE | 2048 | 768 | 2.67 | 4.17 | 0.04 | 15.00 | 3.60 | 89.77 | 0 | 0 | 0 |
| 218 | DENSE | 768 | 768 | 1.00 | 3.38 | 0.04 | 3.35 | 0.99 | 81.74 | 0 | 0 | 2 |
| 219 | DENSE | 768 | 768 | 1.00 | 3.59 | 0.04 | 9.55 | 2.66 | 84.41 | 0 | 0 | 1 |
| 220 | DENSE | 768 | 768 | 1.00 | 2.73 | 0.07 | 9.91 | 3.63 | 88.47 | 0 | 0 | 0 |
| 221 | DENSE | 768 | 768 | 1.00 | 3.33 | 0.05 | 12.77 | 3.83 | 83.31 | 0 | 0 | 0 |
| 226 | DENSE | 2048 | 768 | 2.67 | 3.96 | 0.04 | 12.81 | 3.23 | 88.44 | 0 | 0 | 0 |
| 227 | DENSE | 2048 | 768 | 2.67 | 4.37 | 0.03 | 17.96 | 4.11 | 91.33 | 2 | 0 | 0 |
| 228 | DENSE | 2048 | 768 | 2.67 | 3.68 | 0.03 | 14.19 | 3.86 | 86.94 | 0 | 0 | 0 |
| 241 | DENSE | 768 | 768 | 1.00 | 3.18 | 0.05 | 3.96 | 1.25 | 80.36 | 0 | 0 | 2 |
| 242 | DENSE | 768 | 768 | 1.00 | 3.22 | 0.09 | 10.37 | 3.22 | 82.92 | 5 | 0 | 0 |
| 243 | DENSE | 768 | 768 | 1.00 | 3.82 | 0.06 | 9.70 | 2.54 | 86.31 | 1 | 0 | 0 |
| 244 | DENSE | 768 | 768 | 1.00 | 2.84 | 0.05 | 9.83 | 3.46 | 70.54 | 0 | 0 | 0 |
| 245 | EMBEDDING | 32 | 12 | 2.67 | 1.19 | 0.17 | 3.76 | 3.16 | 66.97 | 11 | 0 | 0 |
| 250 | DENSE | 768 | 768 | 1.00 | 3.23 | 0.07 | 4.31 | 1.33 | 85.57 | 0 | 0 | 1 |
| 251 | DENSE | 768 | 768 | 1.00 | 2.53 | 0.07 | 7.71 | 3.05 | 82.02 | 0 | 0 | 0 |
| 252 | DENSE | 768 | 768 | 1.00 | 4.83 | 0.04 | 13.02 | 2.69 | 91.28 | 0 | 0 | 1 |
| 253 | DENSE | 768 | 768 | 1.00 | 3.20 | 0.03 | 11.70 | 3.65 | 78.06 | 0 | 0 | 0 |
| 258 | DENSE | 2048 | 768 | 2.67 | 3.15 | 0.04 | 11.97 | 3.80 | 85.68 | 0 | 0 | 0 |
| 259 | DENSE | 2048 | 768 | 2.67 | 4.82 | 0.03 | 14.61 | 3.03 | 94.16 | 0 | 0 | 0 |
| 260 | DENSE | 2048 | 768 | 2.67 | 3.54 | 0.03 | 13.30 | 3.75 | 82.21 | 0 | 0 | 0 |
| 269 | DENSE | 768 | 768 | 1.00 | 3.48 | 0.03 | 2.68 | 0.77 | 81.86 | 0 | 0 | 3 |
| 270 | DENSE | 768 | 768 | 1.00 | 3.37 | 0.04 | 9.47 | 2.81 | 81.46 | 0 | 0 | 0 |
| 271 | DENSE | 768 | 768 | 1.00 | 4.80 | 0.09 | 11.31 | 2.35 | 85.38 | 0 | 0 | 0 |
| 272 | DENSE | 768 | 768 | 1.00 | 2.56 | 0.02 | 9.23 | 3.61 | 68.56 | 0 | 0 | 1 |
| 277 | DENSE | 768 | 768 | 1.00 | 3.24 | 0.04 | 3.31 | 1.02 | 84.56 | 0 | 0 | 1 |
| 278 | DENSE | 768 | 768 | 1.00 | 2.77 | 0.05 | 8.66 | 3.13 | 78.42 | 0 | 0 | 1 |
| 279 | DENSE | 768 | 768 | 1.00 | 6.59 | 0.04 | 18.65 | 2.83 | 88.25 | 0 | 0 | 0 |
| 280 | DENSE | 768 | 768 | 1.00 | 2.89 | 0.03 | 10.42 | 3.61 | 74.29 | 0 | 0 | 0 |
| 285 | DENSE | 2048 | 768 | 2.67 | 3.67 | 0.02 | 13.20 | 3.60 | 87.53 | 0 | 0 | 0 |
| 286 | DENSE | 2048 | 768 | 2.67 | 5.01 | 0.02 | 17.28 | 3.45 | 92.51 | 0 | 0 | 0 |
| 287 | DENSE | 2048 | 768 | 2.67 | 4.16 | 0.03 | 16.63 | 3.99 | 84.62 | 0 | 0 | 0 |
| 296 | DENSE | 768 | 768 | 1.00 | 2.68 | 0.04 | 3.02 | 1.13 | 77.51 | 0 | 0 | 1 |
| 297 | DENSE | 768 | 768 | 1.00 | 3.31 | 0.03 | 8.42 | 2.55 | 81.57 | 0 | 0 | 0 |
| 298 | DENSE | 768 | 768 | 1.00 | 3.89 | 0.11 | 9.62 | 2.47 | 85.94 | 0 | 4 | 0 |
| 299 | DENSE | 768 | 768 | 1.00 | 2.43 | 0.03 | 10.16 | 4.17 | 64.06 | 0 | 0 | 0 |
| 304 | DENSE | 768 | 768 | 1.00 | 3.43 | 0.06 | 3.51 | 1.02 | 87.20 | 0 | 0 | 2 |
| 305 | DENSE | 768 | 768 | 1.00 | 3.16 | 0.04 | 9.10 | 2.88 | 85.42 | 0 | 0 | 0 |
| 306 | DENSE | 768 | 768 | 1.00 | 5.88 | 0.05 | 14.91 | 2.54 | 94.48 | 0 | 0 | 0 |
| 307 | DENSE | 768 | 768 | 1.00 | 3.35 | 0.04 | 13.31 | 3.98 | 72.28 | 1 | 0 | 0 |
| 312 | DENSE | 2048 | 768 | 2.67 | 2.78 | 0.06 | 10.35 | 3.72 | 85.29 | 0 | 1 | 0 |
| 313 | DENSE | 2048 | 768 | 2.67 | 3.08 | 0.09 | 11.51 | 3.73 | 90.13 | 0 | 4 | 0 |
| 314 | DENSE | 2048 | 768 | 2.67 | 4.20 | 0.06 | 19.50 | 4.64 | 77.77 | 1 | 0 | 0 |
| 323 | DENSE | 768 | 768 | 1.00 | 3.39 | 0.06 | 3.06 | 0.90 | 87.76 | 0 | 0 | 2 |
| 324 | DENSE | 768 | 768 | 1.00 | 4.25 | 0.05 | 11.06 | 2.60 | 89.10 | 0 | 0 | 0 |
| 325 | DENSE | 768 | 768 | 1.00 | 4.20 | 0.05 | 11.81 | 2.81 | 89.29 | 0 | 0 | 0 |
| 326 | DENSE | 768 | 768 | 1.00 | 2.77 | 0.04 | 11.91 | 4.30 | 69.77 | 1 | 0 | 0 |
| 331 | DENSE | 768 | 768 | 1.00 | 3.25 | 0.05 | 3.98 | 1.23 | 86.62 | 0 | 0 | 1 |
| 332 | DENSE | 768 | 768 | 1.00 | 3.22 | 0.03 | 9.86 | 3.06 | 86.76 | 0 | 0 | 1 |
| 333 | DENSE | 768 | 768 | 1.00 | 4.40 | 0.13 | 12.08 | 2.75 | 94.49 | 0 | 5 | 0 |
| 334 | DENSE | 768 | 768 | 1.00 | 3.47 | 0.05 | 14.99 | 4.33 | 70.51 | 1 | 0 | 0 |
| 339 | DENSE | 2048 | 768 | 2.67 | 3.00 | 0.05 | 11.49 | 3.83 | 85.51 | 0 | 0 | 0 |
| 340 | DENSE | 2048 | 768 | 2.67 | 3.98 | 0.08 | 15.79 | 3.96 | 90.81 | 0 | 1 | 0 |
| 341 | DENSE | 2048 | 768 | 2.67 | 4.02 | 0.06 | 19.84 | 4.93 | 74.77 | 2 | 0 | 0 |
| 350 | DENSE | 768 | 768 | 1.00 | 3.85 | 0.06 | 4.42 | 1.15 | 88.89 | 0 | 0 | 1 |
| 351 | DENSE | 768 | 768 | 1.00 | 4.23 | 0.04 | 12.41 | 2.93 | 90.44 | 0 | 0 | 0 |
| 352 | DENSE | 768 | 768 | 1.00 | 3.79 | 0.10 | 11.98 | 3.17 | 90.37 | 0 | 1 | 0 |
| 353 | DENSE | 768 | 768 | 1.00 | 3.33 | 0.05 | 14.34 | 4.30 | 74.17 | 0 | 0 | 0 |
| 358 | DENSE | 768 | 768 | 1.00 | 2.61 | 0.04 | 4.00 | 1.53 | 79.10 | 0 | 0 | 1 |
| 359 | DENSE | 768 | 768 | 1.00 | 2.74 | 0.03 | 9.10 | 3.33 | 79.09 | 0 | 0 | 0 |
| 360 | DENSE | 768 | 768 | 1.00 | 5.71 | 0.06 | 16.18 | 2.83 | 93.34 | 0 | 0 | 0 |
| 361 | DENSE | 768 | 768 | 1.00 | 3.56 | 0.05 | 15.03 | 4.22 | 71.33 | 0 | 0 | 0 |
| 366 | DENSE | 2048 | 768 | 2.67 | 3.84 | 0.03 | 14.39 | 3.75 | 87.14 | 0 | 0 | 0 |
| 367 | DENSE | 2048 | 768 | 2.67 | 4.94 | 0.04 | 19.49 | 3.95 | 92.05 | 0 | 0 | 0 |
| 368 | DENSE | 2048 | 768 | 2.67 | 3.84 | 0.06 | 18.49 | 4.82 | 76.72 | 0 | 0 | 0 |
| 377 | DENSE | 768 | 768 | 1.00 | 2.96 | 0.04 | 4.08 | 1.38 | 84.70 | 0 | 0 | 1 |
| 378 | DENSE | 768 | 768 | 1.00 | 3.69 | 0.04 | 11.49 | 3.11 | 88.45 | 0 | 0 | 0 |
| 379 | DENSE | 768 | 768 | 1.00 | 4.94 | 0.12 | 15.46 | 3.13 | 92.93 | 0 | 1 | 0 |
| 380 | DENSE | 768 | 768 | 1.00 | 3.68 | 0.08 | 16.94 | 4.61 | 73.97 | 1 | 0 | 0 |
| 385 | DENSE | 768 | 768 | 1.00 | 3.10 | 0.04 | 4.25 | 1.37 | 82.76 | 0 | 0 | 1 |
| 386 | DENSE | 768 | 768 | 1.00 | 2.98 | 0.03 | 9.74 | 3.27 | 82.02 | 0 | 0 | 0 |
| 387 | DENSE | 768 | 768 | 1.00 | 4.44 | 0.08 | 13.69 | 3.08 | 89.17 | 0 | 0 | 0 |
| 388 | DENSE | 768 | 768 | 1.00 | 3.53 | 0.05 | 15.17 | 4.29 | 72.63 | 0 | 0 | 0 |
| 393 | DENSE | 2048 | 768 | 2.67 | 3.21 | 0.03 | 11.84 | 3.69 | 86.06 | 0 | 0 | 0 |
| 394 | DENSE | 2048 | 768 | 2.67 | 4.34 | 0.04 | 17.31 | 3.99 | 91.00 | 0 | 0 | 0 |
| 395 | DENSE | 2048 | 768 | 2.67 | 3.95 | 0.04 | 18.57 | 4.70 | 77.70 | 0 | 0 | 0 |
| 404 | DENSE | 768 | 768 | 1.00 | 3.66 | 0.06 | 4.72 | 1.29 | 87.26 | 0 | 0 | 1 |
| 405 | DENSE | 768 | 768 | 1.00 | 4.10 | 0.05 | 12.40 | 3.02 | 90.07 | 0 | 0 | 0 |
| 406 | DENSE | 768 | 768 | 1.00 | 3.23 | 0.12 | 10.41 | 3.23 | 93.53 | 0 | 5 | 0 |
| 407 | DENSE | 768 | 768 | 1.00 | 3.70 | 0.08 | 17.66 | 4.78 | 74.01 | 0 | 0 | 0 |
| 412 | DENSE | 768 | 768 | 1.00 | 3.33 | 0.06 | 4.85 | 1.46 | 84.98 | 0 | 0 | 1 |
| 413 | DENSE | 768 | 768 | 1.00 | 3.22 | 0.05 | 10.60 | 3.29 | 84.12 | 0 | 0 | 0 |
| 414 | DENSE | 768 | 768 | 1.00 | 4.93 | 0.12 | 14.79 | 3.00 | 91.89 | 0 | 5 | 0 |
| 415 | DENSE | 768 | 768 | 1.00 | 3.58 | 0.06 | 15.90 | 4.44 | 74.03 | 0 | 0 | 0 |
| 420 | DENSE | 2048 | 768 | 2.67 | 3.68 | 0.03 | 13.31 | 3.62 | 86.81 | 0 | 0 | 0 |
| 421 | DENSE | 2048 | 768 | 2.67 | 4.48 | 0.02 | 18.71 | 4.17 | 91.26 | 0 | 0 | 0 |
| 422 | DENSE | 2048 | 768 | 2.67 | 3.75 | 0.03 | 17.37 | 4.63 | 80.11 | 0 | 0 | 0 |
| 431 | DENSE | 768 | 768 | 1.00 | 3.60 | 0.04 | 4.34 | 1.21 | 88.68 | 0 | 0 | 1 |
| 432 | DENSE | 768 | 768 | 1.00 | 4.63 | 0.05 | 13.51 | 2.92 | 91.56 | 0 | 0 | 0 |
| 433 | DENSE | 768 | 768 | 1.00 | 5.20 | 0.14 | 16.90 | 3.25 | 94.55 | 0 | 7 | 0 |
| 434 | DENSE | 768 | 768 | 1.00 | 2.80 | 0.13 | 13.06 | 4.67 | 77.82 | 0 | 4 | 0 |
| 439 | DENSE | 768 | 768 | 1.00 | 3.31 | 0.08 | 5.04 | 1.52 | 84.91 | 0 | 1 | 1 |
| 440 | DENSE | 768 | 768 | 1.00 | 2.99 | 0.05 | 9.86 | 3.30 | 84.50 | 0 | 0 | 0 |
| 441 | DENSE | 768 | 768 | 1.00 | 4.26 | 0.10 | 13.35 | 3.13 | 92.80 | 0 | 0 | 0 |
| 442 | DENSE | 768 | 768 | 1.00 | 3.75 | 0.06 | 16.90 | 4.51 | 76.85 | 0 | 0 | 0 |
| 447 | DENSE | 2048 | 768 | 2.67 | 3.73 | 0.02 | 13.09 | 3.51 | 87.44 | 0 | 0 | 0 |
| 448 | DENSE | 2048 | 768 | 2.67 | 4.73 | 0.02 | 20.02 | 4.23 | 91.68 | 0 | 0 | 0 |
| 449 | DENSE | 2048 | 768 | 2.67 | 3.91 | 0.04 | 17.75 | 4.54 | 82.30 | 0 | 0 | 0 |
| 458 | DENSE | 768 | 768 | 1.00 | 3.63 | 0.06 | 4.03 | 1.11 | 88.12 | 0 | 0 | 1 |
| 459 | DENSE | 768 | 768 | 1.00 | 3.22 | 0.11 | 9.27 | 2.88 | 89.56 | 0 | 6 | 0 |
| 460 | DENSE | 768 | 768 | 1.00 | 4.09 | 0.09 | 13.39 | 3.27 | 94.57 | 0 | 0 | 0 |
| 461 | DENSE | 768 | 768 | 1.00 | 1.86 | 0.10 | 9.51 | 5.10 | 74.78 | 0 | 3 | 0 |
| 466 | DENSE | 768 | 768 | 1.00 | 3.22 | 0.06 | 4.76 | 1.48 | 84.89 | 0 | 0 | 1 |
| 467 | DENSE | 768 | 768 | 1.00 | 2.91 | 0.05 | 9.61 | 3.30 | 84.06 | 0 | 0 | 0 |
| 468 | DENSE | 768 | 768 | 1.00 | 8.33 | 0.13 | 27.49 | 3.30 | 93.08 | 0 | 1 | 1 |
| 469 | DENSE | 768 | 768 | 1.00 | 3.82 | 0.07 | 17.96 | 4.71 | 76.92 | 0 | 0 | 0 |
| 474 | DENSE | 2048 | 768 | 2.67 | 3.89 | 0.03 | 13.08 | 3.37 | 88.66 | 0 | 0 | 0 |
| 475 | DENSE | 2048 | 768 | 2.67 | 4.80 | 0.03 | 20.30 | 4.23 | 91.94 | 0 | 0 | 0 |
| 476 | DENSE | 2048 | 768 | 2.67 | 4.12 | 0.02 | 18.41 | 4.47 | 85.50 | 0 | 0 | 0 |
| 485 | DENSE | 768 | 768 | 1.00 | 3.30 | 0.03 | 4.35 | 1.32 | 88.26 | 0 | 0 | 0 |
| 486 | DENSE | 768 | 768 | 1.00 | 5.17 | 0.06 | 14.51 | 2.81 | 93.54 | 0 | 0 | 0 |
| 487 | DENSE | 768 | 768 | 1.00 | 6.21 | 0.12 | 20.82 | 3.35 | 95.16 | 0 | 1 | 0 |
| 488 | DENSE | 768 | 768 | 1.00 | 2.37 | 0.10 | 11.43 | 4.83 | 76.11 | 0 | 0 | 0 |
| 493 | DENSE | 768 | 768 | 1.00 | 2.07 | 0.10 | 2.88 | 1.39 | 80.19 | 0 | 1 | 1 |
| 494 | DENSE | 768 | 768 | 1.00 | 1.93 | 0.11 | 6.13 | 3.17 | 81.19 | 0 | 5 | 0 |
| 495 | DENSE | 768 | 768 | 1.00 | 2.85 | 0.13 | 9.70 | 3.40 | 89.21 | 0 | 0 | 0 |
| 496 | DENSE | 768 | 768 | 1.00 | 3.98 | 0.08 | 18.55 | 4.65 | 79.64 | 0 | 0 | 0 |
| 501 | DENSE | 2048 | 768 | 2.67 | 4.00 | 0.02 | 13.14 | 3.28 | 88.35 | 0 | 0 | 0 |
| 502 | DENSE | 2048 | 768 | 2.67 | 4.95 | 0.03 | 21.44 | 4.33 | 91.63 | 0 | 0 | 0 |
| 503 | DENSE | 2048 | 768 | 2.67 | 4.44 | 0.03 | 19.55 | 4.40 | 86.73 | 0 | 0 | 0 |
| 512 | DENSE | 768 | 768 | 1.00 | 3.89 | 0.03 | 4.31 | 1.11 | 91.95 | 0 | 0 | 1 |
| 513 | DENSE | 768 | 768 | 1.00 | 5.42 | 0.03 | 15.81 | 2.92 | 94.14 | 0 | 0 | 1 |
| 514 | DENSE | 768 | 768 | 1.00 | 3.45 | 0.12 | 12.01 | 3.49 | 93.27 | 0 | 1 | 0 |
| 515 | DENSE | 768 | 768 | 1.00 | 2.16 | 0.08 | 10.37 | 4.80 | 77.83 | 0 | 0 | 0 |
| 520 | DENSE | 768 | 768 | 1.00 | 2.43 | 0.06 | 3.89 | 1.60 | 80.04 | 0 | 0 | 1 |
| 521 | DENSE | 768 | 768 | 1.00 | 2.54 | 0.07 | 8.50 | 3.35 | 81.90 | 0 | 1 | 0 |
| 522 | DENSE | 768 | 768 | 1.00 | 9.23 | 0.14 | 33.08 | 3.59 | 86.88 | 0 | 1 | 0 |
| 523 | DENSE | 768 | 768 | 1.00 | 3.96 | 0.09 | 19.22 | 4.85 | 76.96 | 0 | 0 | 0 |
| 528 | DENSE | 2048 | 768 | 2.67 | 3.74 | 0.03 | 12.24 | 3.27 | 88.43 | 0 | 0 | 0 |
| 529 | DENSE | 2048 | 768 | 2.67 | 4.21 | 0.03 | 19.37 | 4.60 | 89.73 | 0 | 0 | 0 |
| 530 | DENSE | 2048 | 768 | 2.67 | 4.68 | 0.05 | 20.15 | 4.31 | 88.71 | 0 | 0 | 0 |
| 539 | DENSE | 768 | 768 | 1.00 | 4.37 | 0.02 | 6.11 | 1.40 | 91.69 | 0 | 0 | 1 |
| 540 | DENSE | 768 | 768 | 1.00 | 3.48 | 0.12 | 10.36 | 2.97 | 93.73 | 0 | 7 | 0 |
| 541 | DENSE | 768 | 768 | 1.00 | 6.91 | 0.14 | 23.37 | 3.38 | 94.00 | 0 | 1 | 0 |
| 542 | DENSE | 768 | 768 | 1.00 | 4.08 | 0.09 | 18.41 | 4.51 | 82.31 | 0 | 0 | 0 |
| 547 | DENSE | 768 | 768 | 1.00 | 2.08 | 0.05 | 3.17 | 1.52 | 72.28 | 0 | 0 | 1 |
| 548 | DENSE | 768 | 768 | 1.00 | 2.06 | 0.06 | 6.92 | 3.37 | 74.49 | 0 | 0 | 0 |
| 549 | DENSE | 768 | 768 | 1.00 | 2.00 | 0.14 | 7.77 | 3.89 | 81.42 | 0 | 7 | 0 |
| 550 | DENSE | 768 | 768 | 1.00 | 3.84 | 0.07 | 17.69 | 4.61 | 84.72 | 0 | 0 | 0 |
| 555 | DENSE | 2048 | 768 | 2.67 | 3.34 | 0.02 | 12.61 | 3.77 | 84.30 | 0 | 0 | 0 |
| 556 | DENSE | 2048 | 768 | 2.67 | 3.64 | 0.03 | 19.39 | 5.33 | 84.84 | 1 | 0 | 0 |
| 557 | DENSE | 2048 | 768 | 2.67 | 3.94 | 0.07 | 18.38 | 4.66 | 83.59 | 1 | 0 | 0 |
google-flan-t5-base Layer Plots
Layer 1
Layer=1 | N=32128 | M=768 | Q=41.83 | alpha=3.39 | D_ks=0.02 | alpha-hat=27.60 | num traps=0
Layer 8
Layer=8 | N=768 | M=768 | Q=1.00 | alpha=4.10 | D_ks=0.12 | alpha-hat=5.71 | num traps=0
Layer 9
Layer=9 | N=768 | M=768 | Q=1.00 | alpha=3.26 | D_ks=0.12 | alpha-hat=10.29 | num traps=0
Layer 10
Layer=10 | N=768 | M=768 | Q=1.00 | alpha=6.58 | D_ks=0.14 | alpha-hat=16.57 | num traps=0
Layer 11
Layer=11 | N=768 | M=768 | Q=1.00 | alpha=3.06 | D_ks=0.03 | alpha-hat=10.61 | num traps=0
Layer 12
Layer=12 | N=32 | M=12 | Q=2.67 | alpha=1.72 | D_ks=0.20 | alpha-hat=7.05 | num traps=0
Layer 17
Layer=17 | N=2048 | M=768 | Q=2.67 | alpha=3.03 | D_ks=0.04 | alpha-hat=10.89 | num traps=0
Layer 18
Layer=18 | N=2048 | M=768 | Q=2.67 | alpha=3.47 | D_ks=0.07 | alpha-hat=11.10 | num traps=0
Layer 19
Layer=19 | N=2048 | M=768 | Q=2.67 | alpha=3.44 | D_ks=0.02 | alpha-hat=11.84 | num traps=0
Layer 28
Layer=28 | N=768 | M=768 | Q=1.00 | alpha=4.67 | D_ks=0.04 | alpha-hat=6.93 | num traps=0
Layer 29
Layer=29 | N=768 | M=768 | Q=1.00 | alpha=4.37 | D_ks=0.03 | alpha-hat=14.34 | num traps=0
Layer 30
Layer=30 | N=768 | M=768 | Q=1.00 | alpha=3.40 | D_ks=0.06 | alpha-hat=8.91 | num traps=0
Layer 31
Layer=31 | N=768 | M=768 | Q=1.00 | alpha=2.66 | D_ks=0.02 | alpha-hat=10.05 | num traps=0
Layer 36
Layer=36 | N=2048 | M=768 | Q=2.67 | alpha=3.39 | D_ks=0.02 | alpha-hat=12.69 | num traps=0
Layer 37
Layer=37 | N=2048 | M=768 | Q=2.67 | alpha=4.52 | D_ks=0.05 | alpha-hat=15.81 | num traps=0
Layer 38
Layer=38 | N=2048 | M=768 | Q=2.67 | alpha=3.11 | D_ks=0.02 | alpha-hat=11.56 | num traps=0
Layer 47
Layer=47 | N=768 | M=768 | Q=1.00 | alpha=3.96 | D_ks=0.03 | alpha-hat=6.17 | num traps=0
Layer 48
Layer=48 | N=768 | M=768 | Q=1.00 | alpha=3.92 | D_ks=0.03 | alpha-hat=13.34 | num traps=0
Layer 49
Layer=49 | N=768 | M=768 | Q=1.00 | alpha=2.94 | D_ks=0.09 | alpha-hat=8.42 | num traps=0
Layer 50
Layer=50 | N=768 | M=768 | Q=1.00 | alpha=3.04 | D_ks=0.03 | alpha-hat=10.85 | num traps=0
Layer 55
Layer=55 | N=2048 | M=768 | Q=2.67 | alpha=3.52 | D_ks=0.02 | alpha-hat=12.54 | num traps=0
Layer 56
Layer=56 | N=2048 | M=768 | Q=2.67 | alpha=4.47 | D_ks=0.03 | alpha-hat=19.96 | num traps=3
Layer 57
Layer=57 | N=2048 | M=768 | Q=2.67 | alpha=3.29 | D_ks=0.02 | alpha-hat=12.16 | num traps=0
Layer 66
Layer=66 | N=768 | M=768 | Q=1.00 | alpha=3.86 | D_ks=0.05 | alpha-hat=5.28 | num traps=0
Layer 67
Layer=67 | N=768 | M=768 | Q=1.00 | alpha=4.32 | D_ks=0.04 | alpha-hat=13.55 | num traps=0
Layer 68
Layer=68 | N=768 | M=768 | Q=1.00 | alpha=3.63 | D_ks=0.09 | alpha-hat=10.93 | num traps=0
Layer 69
Layer=69 | N=768 | M=768 | Q=1.00 | alpha=3.09 | D_ks=0.02 | alpha-hat=11.33 | num traps=0
Layer 74
Layer=74 | N=2048 | M=768 | Q=2.67 | alpha=3.53 | D_ks=0.02 | alpha-hat=12.38 | num traps=0
Layer 75
Layer=75 | N=2048 | M=768 | Q=2.67 | alpha=5.35 | D_ks=0.04 | alpha-hat=18.36 | num traps=0
Layer 76
Layer=76 | N=2048 | M=768 | Q=2.67 | alpha=3.48 | D_ks=0.02 | alpha-hat=12.70 | num traps=0
Layer 85
Layer=85 | N=768 | M=768 | Q=1.00 | alpha=3.79 | D_ks=0.04 | alpha-hat=5.17 | num traps=0
Layer 86
Layer=86 | N=768 | M=768 | Q=1.00 | alpha=3.56 | D_ks=0.03 | alpha-hat=11.41 | num traps=0
Layer 87
Layer=87 | N=768 | M=768 | Q=1.00 | alpha=2.73 | D_ks=0.10 | alpha-hat=8.43 | num traps=0
Layer 88
Layer=88 | N=768 | M=768 | Q=1.00 | alpha=3.75 | D_ks=0.04 | alpha-hat=14.17 | num traps=0
Layer 93
Layer=93 | N=2048 | M=768 | Q=2.67 | alpha=3.52 | D_ks=0.02 | alpha-hat=12.42 | num traps=0
Layer 94
Layer=94 | N=2048 | M=768 | Q=2.67 | alpha=5.14 | D_ks=0.05 | alpha-hat=18.28 | num traps=0
Layer 95
Layer=95 | N=2048 | M=768 | Q=2.67 | alpha=3.77 | D_ks=0.02 | alpha-hat=14.10 | num traps=0
Layer 104
Layer=104 | N=768 | M=768 | Q=1.00 | alpha=3.65 | D_ks=0.04 | alpha-hat=4.66 | num traps=0
Layer 105
Layer=105 | N=768 | M=768 | Q=1.00 | alpha=3.92 | D_ks=0.04 | alpha-hat=12.21 | num traps=0
Layer 106
Layer=106 | N=768 | M=768 | Q=1.00 | alpha=2.63 | D_ks=0.10 | alpha-hat=8.51 | num traps=0
Layer 107
Layer=107 | N=768 | M=768 | Q=1.00 | alpha=3.43 | D_ks=0.03 | alpha-hat=12.79 | num traps=0
Layer 112
Layer=112 | N=2048 | M=768 | Q=2.67 | alpha=3.55 | D_ks=0.02 | alpha-hat=12.66 | num traps=0
Layer 113
Layer=113 | N=2048 | M=768 | Q=2.67 | alpha=5.92 | D_ks=0.04 | alpha-hat=21.78 | num traps=0
Layer 114
Layer=114 | N=2048 | M=768 | Q=2.67 | alpha=3.80 | D_ks=0.03 | alpha-hat=14.53 | num traps=0
Layer 123
Layer=123 | N=768 | M=768 | Q=1.00 | alpha=4.09 | D_ks=0.05 | alpha-hat=4.79 | num traps=0
Layer 124
Layer=124 | N=768 | M=768 | Q=1.00 | alpha=3.98 | D_ks=0.06 | alpha-hat=11.61 | num traps=0
Layer 125
Layer=125 | N=768 | M=768 | Q=1.00 | alpha=3.99 | D_ks=0.07 | alpha-hat=13.27 | num traps=0
Layer 126
Layer=126 | N=768 | M=768 | Q=1.00 | alpha=3.29 | D_ks=0.05 | alpha-hat=12.11 | num traps=0
Layer 131
Layer=131 | N=2048 | M=768 | Q=2.67 | alpha=3.43 | D_ks=0.02 | alpha-hat=12.22 | num traps=0
Layer 132
Layer=132 | N=2048 | M=768 | Q=2.67 | alpha=5.35 | D_ks=0.04 | alpha-hat=20.05 | num traps=0
Layer 133
Layer=133 | N=2048 | M=768 | Q=2.67 | alpha=4.02 | D_ks=0.03 | alpha-hat=14.89 | num traps=0
Layer 142
Layer=142 | N=768 | M=768 | Q=1.00 | alpha=3.20 | D_ks=0.06 | alpha-hat=3.51 | num traps=0
Layer 143
Layer=143 | N=768 | M=768 | Q=1.00 | alpha=3.12 | D_ks=0.06 | alpha-hat=9.26 | num traps=0
Layer 144
Layer=144 | N=768 | M=768 | Q=1.00 | alpha=2.29 | D_ks=0.10 | alpha-hat=7.75 | num traps=0
Layer 145
Layer=145 | N=768 | M=768 | Q=1.00 | alpha=4.02 | D_ks=0.04 | alpha-hat=15.27 | num traps=0
Layer 150
Layer=150 | N=2048 | M=768 | Q=2.67 | alpha=3.48 | D_ks=0.03 | alpha-hat=12.24 | num traps=0
Layer 151
Layer=151 | N=2048 | M=768 | Q=2.67 | alpha=5.09 | D_ks=0.04 | alpha-hat=19.24 | num traps=0
Layer 152
Layer=152 | N=2048 | M=768 | Q=2.67 | alpha=4.16 | D_ks=0.04 | alpha-hat=15.26 | num traps=0
Layer 161
Layer=161 | N=768 | M=768 | Q=1.00 | alpha=3.72 | D_ks=0.05 | alpha-hat=4.08 | num traps=0
Layer 162
Layer=162 | N=768 | M=768 | Q=1.00 | alpha=3.62 | D_ks=0.04 | alpha-hat=10.42 | num traps=0
Layer 163
Layer=163 | N=768 | M=768 | Q=1.00 | alpha=5.54 | D_ks=0.09 | alpha-hat=19.05 | num traps=0
Layer 164
Layer=164 | N=768 | M=768 | Q=1.00 | alpha=4.72 | D_ks=0.03 | alpha-hat=18.59 | num traps=0
Layer 169
Layer=169 | N=2048 | M=768 | Q=2.67 | alpha=3.65 | D_ks=0.03 | alpha-hat=12.74 | num traps=0
Layer 170
Layer=170 | N=2048 | M=768 | Q=2.67 | alpha=4.52 | D_ks=0.03 | alpha-hat=19.28 | num traps=3
Layer 171
Layer=171 | N=2048 | M=768 | Q=2.67 | alpha=4.36 | D_ks=0.03 | alpha-hat=16.56 | num traps=0
Layer 180
Layer=180 | N=768 | M=768 | Q=1.00 | alpha=3.90 | D_ks=0.04 | alpha-hat=3.75 | num traps=0
Layer 181
Layer=181 | N=768 | M=768 | Q=1.00 | alpha=4.19 | D_ks=0.05 | alpha-hat=11.35 | num traps=0
Layer 182
Layer=182 | N=768 | M=768 | Q=1.00 | alpha=4.88 | D_ks=0.08 | alpha-hat=16.55 | num traps=0
Layer 183
Layer=183 | N=768 | M=768 | Q=1.00 | alpha=3.86 | D_ks=0.07 | alpha-hat=14.97 | num traps=0
Layer 188
Layer=188 | N=2048 | M=768 | Q=2.67 | alpha=3.76 | D_ks=0.04 | alpha-hat=12.44 | num traps=0
Layer 189
Layer=189 | N=2048 | M=768 | Q=2.67 | alpha=5.53 | D_ks=0.05 | alpha-hat=21.53 | num traps=0
Layer 190
Layer=190 | N=2048 | M=768 | Q=2.67 | alpha=4.54 | D_ks=0.03 | alpha-hat=16.67 | num traps=0
Layer 199
Layer=199 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.04 | alpha-hat=3.18 | num traps=0
Layer 200
Layer=200 | N=768 | M=768 | Q=1.00 | alpha=3.52 | D_ks=0.04 | alpha-hat=9.73 | num traps=0
Layer 201
Layer=201 | N=768 | M=768 | Q=1.00 | alpha=2.57 | D_ks=0.11 | alpha-hat=9.25 | num traps=0
Layer 202
Layer=202 | N=768 | M=768 | Q=1.00 | alpha=2.57 | D_ks=0.10 | alpha-hat=9.87 | num traps=0
Layer 207
Layer=207 | N=2048 | M=768 | Q=2.67 | alpha=3.89 | D_ks=0.03 | alpha-hat=12.51 | num traps=0
Layer 208
Layer=208 | N=2048 | M=768 | Q=2.67 | alpha=4.72 | D_ks=0.04 | alpha-hat=18.40 | num traps=1
Layer 209
Layer=209 | N=2048 | M=768 | Q=2.67 | alpha=4.17 | D_ks=0.04 | alpha-hat=15.00 | num traps=0
Layer 218
Layer=218 | N=768 | M=768 | Q=1.00 | alpha=3.38 | D_ks=0.04 | alpha-hat=3.35 | num traps=0
Layer 219
Layer=219 | N=768 | M=768 | Q=1.00 | alpha=3.59 | D_ks=0.04 | alpha-hat=9.55 | num traps=0
Layer 220
Layer=220 | N=768 | M=768 | Q=1.00 | alpha=2.73 | D_ks=0.07 | alpha-hat=9.91 | num traps=0
Layer 221
Layer=221 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.05 | alpha-hat=12.77 | num traps=0
Layer 226
Layer=226 | N=2048 | M=768 | Q=2.67 | alpha=3.96 | D_ks=0.04 | alpha-hat=12.81 | num traps=0
Layer 227
Layer=227 | N=2048 | M=768 | Q=2.67 | alpha=4.37 | D_ks=0.03 | alpha-hat=17.96 | num traps=2
Layer 228
Layer=228 | N=2048 | M=768 | Q=2.67 | alpha=3.68 | D_ks=0.03 | alpha-hat=14.19 | num traps=0
Layer 241
Layer=241 | N=768 | M=768 | Q=1.00 | alpha=3.18 | D_ks=0.05 | alpha-hat=3.96 | num traps=0
Layer 242
Layer=242 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.09 | alpha-hat=10.37 | num traps=5
Layer 243
Layer=243 | N=768 | M=768 | Q=1.00 | alpha=3.82 | D_ks=0.06 | alpha-hat=9.70 | num traps=1
Layer 244
Layer=244 | N=768 | M=768 | Q=1.00 | alpha=2.84 | D_ks=0.05 | alpha-hat=9.83 | num traps=0
Layer 245
Layer=245 | N=32 | M=12 | Q=2.67 | alpha=1.19 | D_ks=0.17 | alpha-hat=3.76 | num traps=11
Layer 250
Layer=250 | N=768 | M=768 | Q=1.00 | alpha=3.23 | D_ks=0.07 | alpha-hat=4.31 | num traps=0
Layer 251
Layer=251 | N=768 | M=768 | Q=1.00 | alpha=2.53 | D_ks=0.07 | alpha-hat=7.71 | num traps=0
Layer 252
Layer=252 | N=768 | M=768 | Q=1.00 | alpha=4.83 | D_ks=0.04 | alpha-hat=13.02 | num traps=0
Layer 253
Layer=253 | N=768 | M=768 | Q=1.00 | alpha=3.20 | D_ks=0.03 | alpha-hat=11.70 | num traps=0
Layer 258
Layer=258 | N=2048 | M=768 | Q=2.67 | alpha=3.15 | D_ks=0.04 | alpha-hat=11.97 | num traps=0
Layer 259
Layer=259 | N=2048 | M=768 | Q=2.67 | alpha=4.82 | D_ks=0.03 | alpha-hat=14.61 | num traps=0
Layer 260
Layer=260 | N=2048 | M=768 | Q=2.67 | alpha=3.54 | D_ks=0.03 | alpha-hat=13.30 | num traps=0
Layer 269
Layer=269 | N=768 | M=768 | Q=1.00 | alpha=3.48 | D_ks=0.03 | alpha-hat=2.68 | num traps=0
Layer 270
Layer=270 | N=768 | M=768 | Q=1.00 | alpha=3.37 | D_ks=0.04 | alpha-hat=9.47 | num traps=0
Layer 271
Layer=271 | N=768 | M=768 | Q=1.00 | alpha=4.80 | D_ks=0.09 | alpha-hat=11.31 | num traps=0
Layer 272
Layer=272 | N=768 | M=768 | Q=1.00 | alpha=2.56 | D_ks=0.02 | alpha-hat=9.23 | num traps=0
Layer 277
Layer=277 | N=768 | M=768 | Q=1.00 | alpha=3.24 | D_ks=0.04 | alpha-hat=3.31 | num traps=0
Layer 278
Layer=278 | N=768 | M=768 | Q=1.00 | alpha=2.77 | D_ks=0.05 | alpha-hat=8.66 | num traps=0
Layer 279
Layer=279 | N=768 | M=768 | Q=1.00 | alpha=6.59 | D_ks=0.04 | alpha-hat=18.65 | num traps=0
Layer 280
Layer=280 | N=768 | M=768 | Q=1.00 | alpha=2.89 | D_ks=0.03 | alpha-hat=10.42 | num traps=0
Layer 285
Layer=285 | N=2048 | M=768 | Q=2.67 | alpha=3.67 | D_ks=0.02 | alpha-hat=13.20 | num traps=0
Layer 286
Layer=286 | N=2048 | M=768 | Q=2.67 | alpha=5.01 | D_ks=0.02 | alpha-hat=17.28 | num traps=0
Layer 287
Layer=287 | N=2048 | M=768 | Q=2.67 | alpha=4.16 | D_ks=0.03 | alpha-hat=16.63 | num traps=0
Layer 296
Layer=296 | N=768 | M=768 | Q=1.00 | alpha=2.68 | D_ks=0.04 | alpha-hat=3.02 | num traps=0
Layer 297
Layer=297 | N=768 | M=768 | Q=1.00 | alpha=3.31 | D_ks=0.03 | alpha-hat=8.42 | num traps=0
Layer 298
Layer=298 | N=768 | M=768 | Q=1.00 | alpha=3.89 | D_ks=0.11 | alpha-hat=9.62 | num traps=0
Layer 299
Layer=299 | N=768 | M=768 | Q=1.00 | alpha=2.43 | D_ks=0.03 | alpha-hat=10.16 | num traps=0
Layer 304
Layer=304 | N=768 | M=768 | Q=1.00 | alpha=3.43 | D_ks=0.06 | alpha-hat=3.51 | num traps=0
Layer 305
Layer=305 | N=768 | M=768 | Q=1.00 | alpha=3.16 | D_ks=0.04 | alpha-hat=9.10 | num traps=0
Layer 306
Layer=306 | N=768 | M=768 | Q=1.00 | alpha=5.88 | D_ks=0.05 | alpha-hat=14.91 | num traps=0
Layer 307
Layer=307 | N=768 | M=768 | Q=1.00 | alpha=3.35 | D_ks=0.04 | alpha-hat=13.31 | num traps=1
Layer 312
Layer=312 | N=2048 | M=768 | Q=2.67 | alpha=2.78 | D_ks=0.06 | alpha-hat=10.35 | num traps=0
Layer 313
Layer=313 | N=2048 | M=768 | Q=2.67 | alpha=3.08 | D_ks=0.09 | alpha-hat=11.51 | num traps=0
Layer 314
Layer=314 | N=2048 | M=768 | Q=2.67 | alpha=4.20 | D_ks=0.06 | alpha-hat=19.50 | num traps=1
Layer 323
Layer=323 | N=768 | M=768 | Q=1.00 | alpha=3.39 | D_ks=0.06 | alpha-hat=3.06 | num traps=0
Layer 324
Layer=324 | N=768 | M=768 | Q=1.00 | alpha=4.25 | D_ks=0.05 | alpha-hat=11.06 | num traps=0
Layer 325
Layer=325 | N=768 | M=768 | Q=1.00 | alpha=4.20 | D_ks=0.05 | alpha-hat=11.81 | num traps=0
Layer 326
Layer=326 | N=768 | M=768 | Q=1.00 | alpha=2.77 | D_ks=0.04 | alpha-hat=11.91 | num traps=1
Layer 331
Layer=331 | N=768 | M=768 | Q=1.00 | alpha=3.25 | D_ks=0.05 | alpha-hat=3.98 | num traps=0
Layer 332
Layer=332 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.03 | alpha-hat=9.86 | num traps=0
Layer 333
Layer=333 | N=768 | M=768 | Q=1.00 | alpha=4.40 | D_ks=0.13 | alpha-hat=12.08 | num traps=0
Layer 334
Layer=334 | N=768 | M=768 | Q=1.00 | alpha=3.47 | D_ks=0.05 | alpha-hat=14.99 | num traps=1
Layer 339
Layer=339 | N=2048 | M=768 | Q=2.67 | alpha=3.00 | D_ks=0.05 | alpha-hat=11.49 | num traps=0
Layer 340
Layer=340 | N=2048 | M=768 | Q=2.67 | alpha=3.98 | D_ks=0.08 | alpha-hat=15.79 | num traps=0
Layer 341
Layer=341 | N=2048 | M=768 | Q=2.67 | alpha=4.02 | D_ks=0.06 | alpha-hat=19.84 | num traps=2
Layer 350
Layer=350 | N=768 | M=768 | Q=1.00 | alpha=3.85 | D_ks=0.06 | alpha-hat=4.42 | num traps=0
Layer 351
Layer=351 | N=768 | M=768 | Q=1.00 | alpha=4.23 | D_ks=0.04 | alpha-hat=12.41 | num traps=0
Layer 352
Layer=352 | N=768 | M=768 | Q=1.00 | alpha=3.79 | D_ks=0.10 | alpha-hat=11.98 | num traps=0
Layer 353
Layer=353 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.05 | alpha-hat=14.34 | num traps=0
Layer 358
Layer=358 | N=768 | M=768 | Q=1.00 | alpha=2.61 | D_ks=0.04 | alpha-hat=4.00 | num traps=0
Layer 359
Layer=359 | N=768 | M=768 | Q=1.00 | alpha=2.74 | D_ks=0.03 | alpha-hat=9.10 | num traps=0
Layer 360
Layer=360 | N=768 | M=768 | Q=1.00 | alpha=5.71 | D_ks=0.06 | alpha-hat=16.18 | num traps=0
Layer 361
Layer=361 | N=768 | M=768 | Q=1.00 | alpha=3.56 | D_ks=0.05 | alpha-hat=15.03 | num traps=0
Layer 366
Layer=366 | N=2048 | M=768 | Q=2.67 | alpha=3.84 | D_ks=0.03 | alpha-hat=14.39 | num traps=0
Layer 367
Layer=367 | N=2048 | M=768 | Q=2.67 | alpha=4.94 | D_ks=0.04 | alpha-hat=19.49 | num traps=0
Layer 368
Layer=368 | N=2048 | M=768 | Q=2.67 | alpha=3.84 | D_ks=0.06 | alpha-hat=18.49 | num traps=0
Layer 377
Layer=377 | N=768 | M=768 | Q=1.00 | alpha=2.96 | D_ks=0.04 | alpha-hat=4.08 | num traps=0
Layer 378
Layer=378 | N=768 | M=768 | Q=1.00 | alpha=3.69 | D_ks=0.04 | alpha-hat=11.49 | num traps=0
Layer 379
Layer=379 | N=768 | M=768 | Q=1.00 | alpha=4.94 | D_ks=0.12 | alpha-hat=15.46 | num traps=0
Layer 380
Layer=380 | N=768 | M=768 | Q=1.00 | alpha=3.68 | D_ks=0.08 | alpha-hat=16.94 | num traps=1
Layer 385
Layer=385 | N=768 | M=768 | Q=1.00 | alpha=3.10 | D_ks=0.04 | alpha-hat=4.25 | num traps=0
Layer 386
Layer=386 | N=768 | M=768 | Q=1.00 | alpha=2.98 | D_ks=0.03 | alpha-hat=9.74 | num traps=0
Layer 387
Layer=387 | N=768 | M=768 | Q=1.00 | alpha=4.44 | D_ks=0.08 | alpha-hat=13.69 | num traps=0
Layer 388
Layer=388 | N=768 | M=768 | Q=1.00 | alpha=3.53 | D_ks=0.05 | alpha-hat=15.17 | num traps=0
Layer 393
Layer=393 | N=2048 | M=768 | Q=2.67 | alpha=3.21 | D_ks=0.03 | alpha-hat=11.84 | num traps=0
Layer 394
Layer=394 | N=2048 | M=768 | Q=2.67 | alpha=4.34 | D_ks=0.04 | alpha-hat=17.31 | num traps=0
Layer 395
Layer=395 | N=2048 | M=768 | Q=2.67 | alpha=3.95 | D_ks=0.04 | alpha-hat=18.57 | num traps=0
Layer 404
Layer=404 | N=768 | M=768 | Q=1.00 | alpha=3.66 | D_ks=0.06 | alpha-hat=4.72 | num traps=0
Layer 405
Layer=405 | N=768 | M=768 | Q=1.00 | alpha=4.10 | D_ks=0.05 | alpha-hat=12.40 | num traps=0
Layer 406
Layer=406 | N=768 | M=768 | Q=1.00 | alpha=3.23 | D_ks=0.12 | alpha-hat=10.41 | num traps=0
Layer 407
Layer=407 | N=768 | M=768 | Q=1.00 | alpha=3.70 | D_ks=0.08 | alpha-hat=17.66 | num traps=0
Layer 412
Layer=412 | N=768 | M=768 | Q=1.00 | alpha=3.33 | D_ks=0.06 | alpha-hat=4.85 | num traps=0
Layer 413
Layer=413 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.05 | alpha-hat=10.60 | num traps=0
Layer 414
Layer=414 | N=768 | M=768 | Q=1.00 | alpha=4.93 | D_ks=0.12 | alpha-hat=14.79 | num traps=0
Layer 415
Layer=415 | N=768 | M=768 | Q=1.00 | alpha=3.58 | D_ks=0.06 | alpha-hat=15.90 | num traps=0
Layer 420
Layer=420 | N=2048 | M=768 | Q=2.67 | alpha=3.68 | D_ks=0.03 | alpha-hat=13.31 | num traps=0
Layer 421
Layer=421 | N=2048 | M=768 | Q=2.67 | alpha=4.48 | D_ks=0.02 | alpha-hat=18.71 | num traps=0
Layer 422
Layer=422 | N=2048 | M=768 | Q=2.67 | alpha=3.75 | D_ks=0.03 | alpha-hat=17.37 | num traps=0
Layer 431
Layer=431 | N=768 | M=768 | Q=1.00 | alpha=3.60 | D_ks=0.04 | alpha-hat=4.34 | num traps=0
Layer 432
Layer=432 | N=768 | M=768 | Q=1.00 | alpha=4.63 | D_ks=0.05 | alpha-hat=13.51 | num traps=0
Layer 433
Layer=433 | N=768 | M=768 | Q=1.00 | alpha=5.20 | D_ks=0.14 | alpha-hat=16.90 | num traps=0
Layer 434
Layer=434 | N=768 | M=768 | Q=1.00 | alpha=2.80 | D_ks=0.13 | alpha-hat=13.06 | num traps=0
Layer 439
Layer=439 | N=768 | M=768 | Q=1.00 | alpha=3.31 | D_ks=0.08 | alpha-hat=5.04 | num traps=0
Layer 440
Layer=440 | N=768 | M=768 | Q=1.00 | alpha=2.99 | D_ks=0.05 | alpha-hat=9.86 | num traps=0
Layer 441
Layer=441 | N=768 | M=768 | Q=1.00 | alpha=4.26 | D_ks=0.10 | alpha-hat=13.35 | num traps=0
Layer 442
Layer=442 | N=768 | M=768 | Q=1.00 | alpha=3.75 | D_ks=0.06 | alpha-hat=16.90 | num traps=0
Layer 447
Layer=447 | N=2048 | M=768 | Q=2.67 | alpha=3.73 | D_ks=0.02 | alpha-hat=13.09 | num traps=0
Layer 448
Layer=448 | N=2048 | M=768 | Q=2.67 | alpha=4.73 | D_ks=0.02 | alpha-hat=20.02 | num traps=0
Layer 449
Layer=449 | N=2048 | M=768 | Q=2.67 | alpha=3.91 | D_ks=0.04 | alpha-hat=17.75 | num traps=0
Layer 458
Layer=458 | N=768 | M=768 | Q=1.00 | alpha=3.63 | D_ks=0.06 | alpha-hat=4.03 | num traps=0
Layer 459
Layer=459 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.11 | alpha-hat=9.27 | num traps=0
Layer 460
Layer=460 | N=768 | M=768 | Q=1.00 | alpha=4.09 | D_ks=0.09 | alpha-hat=13.39 | num traps=0
Layer 461
Layer=461 | N=768 | M=768 | Q=1.00 | alpha=1.86 | D_ks=0.10 | alpha-hat=9.51 | num traps=0
Layer 466
Layer=466 | N=768 | M=768 | Q=1.00 | alpha=3.22 | D_ks=0.06 | alpha-hat=4.76 | num traps=0
Layer 467
Layer=467 | N=768 | M=768 | Q=1.00 | alpha=2.91 | D_ks=0.05 | alpha-hat=9.61 | num traps=0
Layer 468
Layer=468 | N=768 | M=768 | Q=1.00 | alpha=8.33 | D_ks=0.13 | alpha-hat=27.49 | num traps=0
Layer 469
Layer=469 | N=768 | M=768 | Q=1.00 | alpha=3.82 | D_ks=0.07 | alpha-hat=17.96 | num traps=0
Layer 474
Layer=474 | N=2048 | M=768 | Q=2.67 | alpha=3.89 | D_ks=0.03 | alpha-hat=13.08 | num traps=0
Layer 475
Layer=475 | N=2048 | M=768 | Q=2.67 | alpha=4.80 | D_ks=0.03 | alpha-hat=20.30 | num traps=0
Layer 476
Layer=476 | N=2048 | M=768 | Q=2.67 | alpha=4.12 | D_ks=0.02 | alpha-hat=18.41 | num traps=0
Layer 485
Layer=485 | N=768 | M=768 | Q=1.00 | alpha=3.30 | D_ks=0.03 | alpha-hat=4.35 | num traps=0
Layer 486
Layer=486 | N=768 | M=768 | Q=1.00 | alpha=5.17 | D_ks=0.06 | alpha-hat=14.51 | num traps=0
Layer 487
Layer=487 | N=768 | M=768 | Q=1.00 | alpha=6.21 | D_ks=0.12 | alpha-hat=20.82 | num traps=0
Layer 488
Layer=488 | N=768 | M=768 | Q=1.00 | alpha=2.37 | D_ks=0.10 | alpha-hat=11.43 | num traps=0
Layer 493
Layer=493 | N=768 | M=768 | Q=1.00 | alpha=2.07 | D_ks=0.10 | alpha-hat=2.88 | num traps=0
Layer 494
Layer=494 | N=768 | M=768 | Q=1.00 | alpha=1.93 | D_ks=0.11 | alpha-hat=6.13 | num traps=0
Layer 495
Layer=495 | N=768 | M=768 | Q=1.00 | alpha=2.85 | D_ks=0.13 | alpha-hat=9.70 | num traps=0
Layer 496
Layer=496 | N=768 | M=768 | Q=1.00 | alpha=3.98 | D_ks=0.08 | alpha-hat=18.55 | num traps=0
Layer 501
Layer=501 | N=2048 | M=768 | Q=2.67 | alpha=4.00 | D_ks=0.02 | alpha-hat=13.14 | num traps=0
Layer 502
Layer=502 | N=2048 | M=768 | Q=2.67 | alpha=4.95 | D_ks=0.03 | alpha-hat=21.44 | num traps=0
Layer 503
Layer=503 | N=2048 | M=768 | Q=2.67 | alpha=4.44 | D_ks=0.03 | alpha-hat=19.55 | num traps=0
Layer 512
Layer=512 | N=768 | M=768 | Q=1.00 | alpha=3.89 | D_ks=0.03 | alpha-hat=4.31 | num traps=0
Layer 513
Layer=513 | N=768 | M=768 | Q=1.00 | alpha=5.42 | D_ks=0.03 | alpha-hat=15.81 | num traps=0
Layer 514
Layer=514 | N=768 | M=768 | Q=1.00 | alpha=3.45 | D_ks=0.12 | alpha-hat=12.01 | num traps=0
Layer 515
Layer=515 | N=768 | M=768 | Q=1.00 | alpha=2.16 | D_ks=0.08 | alpha-hat=10.37 | num traps=0
Layer 520
Layer=520 | N=768 | M=768 | Q=1.00 | alpha=2.43 | D_ks=0.06 | alpha-hat=3.89 | num traps=0
Layer 521
Layer=521 | N=768 | M=768 | Q=1.00 | alpha=2.54 | D_ks=0.07 | alpha-hat=8.50 | num traps=0
Layer 522
Layer=522 | N=768 | M=768 | Q=1.00 | alpha=9.23 | D_ks=0.14 | alpha-hat=33.08 | num traps=0
Layer 523
Layer=523 | N=768 | M=768 | Q=1.00 | alpha=3.96 | D_ks=0.09 | alpha-hat=19.22 | num traps=0
Layer 528
Layer=528 | N=2048 | M=768 | Q=2.67 | alpha=3.74 | D_ks=0.03 | alpha-hat=12.24 | num traps=0
Layer 529
Layer=529 | N=2048 | M=768 | Q=2.67 | alpha=4.21 | D_ks=0.03 | alpha-hat=19.37 | num traps=0
Layer 530
Layer=530 | N=2048 | M=768 | Q=2.67 | alpha=4.68 | D_ks=0.05 | alpha-hat=20.15 | num traps=0
Layer 539
Layer=539 | N=768 | M=768 | Q=1.00 | alpha=4.37 | D_ks=0.02 | alpha-hat=6.11 | num traps=0
Layer 540
Layer=540 | N=768 | M=768 | Q=1.00 | alpha=3.48 | D_ks=0.12 | alpha-hat=10.36 | num traps=0
Layer 541
Layer=541 | N=768 | M=768 | Q=1.00 | alpha=6.91 | D_ks=0.14 | alpha-hat=23.37 | num traps=0
Layer 542
Layer=542 | N=768 | M=768 | Q=1.00 | alpha=4.08 | D_ks=0.09 | alpha-hat=18.41 | num traps=0
Layer 547
Layer=547 | N=768 | M=768 | Q=1.00 | alpha=2.08 | D_ks=0.05 | alpha-hat=3.17 | num traps=0
Layer 548
Layer=548 | N=768 | M=768 | Q=1.00 | alpha=2.06 | D_ks=0.06 | alpha-hat=6.92 | num traps=0
Layer 549
Layer=549 | N=768 | M=768 | Q=1.00 | alpha=2.00 | D_ks=0.14 | alpha-hat=7.77 | num traps=0
Layer 550
Layer=550 | N=768 | M=768 | Q=1.00 | alpha=3.84 | D_ks=0.07 | alpha-hat=17.69 | num traps=0
Layer 555
Layer=555 | N=2048 | M=768 | Q=2.67 | alpha=3.34 | D_ks=0.02 | alpha-hat=12.61 | num traps=0
Layer 556
Layer=556 | N=2048 | M=768 | Q=2.67 | alpha=3.64 | D_ks=0.03 | alpha-hat=19.39 | num traps=1
Layer 557
Layer=557 | N=2048 | M=768 | Q=2.67 | alpha=3.94 | D_ks=0.07 | alpha-hat=18.38 | num traps=1