Bielik-11B-v2.3-Instruct


Find this model in the Bielik model summary

Bielik-11B-v2.3-Instruct Model Set Plots

Bielik Compared to Base Model Plots

Bielik-11B-v2.3-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 32128 4096 7.84375 5.360415 0.059230 14.205348 896
2 dense 32128 4096 7.84375 3.606819 0.011537 -3.093647 206
3 dense 14336 4096 3.50000 4.556274 0.033108 -5.770667 206
4 dense 14336 4096 3.50000 3.828472 0.035861 -2.133421 94
5 dense 14336 4096 3.50000 3.854428 0.027360 -2.257598 117
6 dense 4096 1024 4.00000 1.504161 0.022643 -1.296400 181 over-trained
7 dense 4096 4096 1.00000 2.314871 0.012773 -1.026890 216
8 dense 4096 4096 1.00000 1.586735 0.030433 -0.418891 360 over-trained
9 dense 4096 1024 4.00000 2.573120 0.016575 -4.157377 107
10 dense 4096 1024 4.00000 3.563344 0.021296 -7.763320 88
11 dense 4096 4096 1.00000 1.912091 0.030764 -0.884136 227 over-trained
12 dense 4096 4096 1.00000 3.247596 0.019047 -4.264480 165
13 dense 14336 4096 3.50000 2.712196 0.068150 -2.842085 808
14 dense 14336 4096 3.50000 2.751127 0.064238 -2.771070 736
15 dense 14336 4096 3.50000 5.061656 0.021791 -6.371158 259
16 dense 4096 1024 4.00000 1.882073 0.043702 -1.983643 102 over-trained
17 dense 4096 1024 4.00000 8.851173 0.088639 -5.807069 53 under-trained
18 dense 14336 4096 3.50000 9.264889 0.021382 2.508274 90 under-trained
19 dense 4096 1024 4.00000 4.505520 0.111158 2.121604 151
20 dense 4096 4096 1.00000 4.779142 0.026530 1.926942 38
21 dense 4096 4096 1.00000 4.021927 0.027834 3.520589 83
22 dense 14336 4096 3.50000 4.215880 0.029407 4.036139 475
23 dense 14336 4096 3.50000 4.541304 0.012849 2.899900 396
24 dense 14336 4096 3.50000 5.622157 0.055891 2.444189 236
25 dense 14336 4096 3.50000 3.654723 0.016119 3.457657 692
26 dense 14336 4096 3.50000 8.753764 0.019168 2.494599 100 under-trained
27 dense 4096 1024 4.00000 4.139236 0.057222 2.631093 47
28 dense 4096 4096 1.00000 4.505311 0.033257 1.540191 203
29 dense 4096 4096 1.00000 3.067739 0.034998 3.199207 138
30 dense 4096 1024 4.00000 8.000452 0.068750 -4.292801 67 under-trained
31 dense 14336 4096 3.50000 7.504554 0.019233 2.301347 205 under-trained
32 dense 14336 4096 3.50000 6.568278 0.019443 3.158475 120 under-trained
33 dense 14336 4096 3.50000 3.503441 0.025039 3.706691 875
34 dense 4096 1024 4.00000 5.151992 0.053616 1.916877 41
35 dense 4096 4096 1.00000 4.648129 0.033762 1.332087 61
36 dense 4096 4096 1.00000 3.123066 0.049398 2.667617 190
37 dense 4096 1024 4.00000 5.092159 0.096557 -2.784028 166
38 dense 4096 4096 1.00000 5.050408 0.037160 0.465901 158
39 dense 4096 1024 4.00000 5.253313 0.092718 1.862279 69
40 dense 14336 4096 3.50000 8.083453 0.022292 2.765342 132 under-trained
41 dense 14336 4096 3.50000 4.983989 0.036128 2.071491 376
42 dense 4096 1024 4.00000 9.140790 0.032370 -5.554855 58 under-trained
43 dense 14336 4096 3.50000 3.329117 0.013343 3.818584 788
44 dense 4096 4096 1.00000 3.173345 0.062658 2.601476 312
45 dense 4096 4096 1.00000 3.983085 0.024261 3.477898 110
46 dense 14336 4096 3.50000 3.813723 0.010022 4.124516 513
47 dense 14336 4096 3.50000 7.551595 0.020872 2.724602 138 under-trained
48 dense 4096 1024 4.00000 5.872065 0.029246 2.774857 42
49 dense 4096 4096 1.00000 4.269302 0.034492 0.254037 204
50 dense 4096 1024 4.00000 5.846818 0.045348 -3.112336 96
51 dense 14336 4096 3.50000 4.978806 0.016899 2.499385 141
52 dense 4096 1024 4.00000 6.040684 0.079054 -3.333262 142 under-trained
53 dense 4096 4096 1.00000 3.057353 0.055240 2.527671 224
54 dense 4096 1024 4.00000 2.770213 0.090434 1.133328 202
55 dense 4096 4096 1.00000 4.011867 0.044987 0.138340 224
56 dense 14336 4096 3.50000 3.421081 0.017010 3.825695 754
57 dense 14336 4096 3.50000 5.860599 0.019450 2.940202 90
58 dense 14336 4096 3.50000 7.544151 0.061404 2.741188 162 under-trained
59 dense 4096 1024 4.00000 3.933351 0.078434 -2.078005 250
60 dense 4096 4096 1.00000 3.719860 0.044124 3.072858 110
61 dense 14336 4096 3.50000 4.448964 0.062027 2.013019 440
62 dense 14336 4096 3.50000 3.826416 0.017361 4.139980 387
63 dense 14336 4096 3.50000 6.665994 0.035454 2.508398 182 under-trained
64 dense 4096 1024 4.00000 3.917465 0.113067 1.689234 127
65 dense 4096 4096 1.00000 5.351081 0.045215 0.040347 79
66 dense 4096 4096 1.00000 3.567646 0.055592 2.569911 186
67 dense 14336 4096 3.50000 3.687882 0.056616 1.748525 670
68 dense 14336 4096 3.50000 3.655850 0.024466 3.951510 514
69 dense 14336 4096 3.50000 5.653643 0.043819 2.014660 196
70 dense 4096 1024 4.00000 4.677888 0.095549 1.389054 118
71 dense 4096 4096 1.00000 3.583636 0.052950 0.044799 238
72 dense 4096 1024 4.00000 5.788212 0.057503 -3.037489 83
73 dense 4096 1024 4.00000 5.562361 0.029600 -12.720827 59
74 dense 14336 4096 3.50000 4.295498 0.042399 2.240636 360
75 dense 14336 4096 3.50000 3.672585 0.016291 -4.056394 115
76 dense 14336 4096 3.50000 3.853801 0.013388 -4.597975 156
77 dense 4096 4096 1.00000 2.917576 0.035035 -4.009797 178
78 dense 4096 4096 1.00000 5.081910 0.025361 -8.971352 61
79 dense 4096 1024 4.00000 2.775193 0.022201 -5.377686 150
80 dense 4096 4096 1.00000 2.876578 0.064842 1.911393 346
81 dense 4096 1024 4.00000 7.871678 0.109162 -3.671296 69 under-trained
82 dense 14336 4096 3.50000 5.139446 0.045099 1.755727 247
83 dense 14336 4096 3.50000 3.800443 0.029713 4.041881 400
84 dense 14336 4096 3.50000 4.794735 0.036477 2.400004 167
85 dense 4096 4096 1.00000 4.303307 0.031243 0.229506 131
86 dense 4096 1024 4.00000 1.923044 0.110340 0.575916 536 over-trained
87 dense 4096 4096 1.00000 2.347914 0.075797 1.630825 722
88 dense 14336 4096 3.50000 4.648485 0.035656 2.523190 216
89 dense 14336 4096 3.50000 3.778649 0.028868 4.152450 463
90 dense 14336 4096 3.50000 5.823562 0.041436 1.847456 145
91 dense 4096 1024 4.00000 2.316272 0.118551 0.689792 370
92 dense 4096 4096 1.00000 3.257465 0.061568 -0.039269 387
93 dense 4096 1024 4.00000 6.739849 0.087735 -3.756394 83 under-trained
94 dense 4096 4096 1.00000 2.960051 0.052231 2.298368 297
95 dense 14336 4096 3.50000 4.625642 0.026630 4.979659 107
96 dense 4096 1024 4.00000 4.225970 0.086680 -2.050973 178
97 dense 4096 1024 4.00000 3.242900 0.103611 1.302068 155
98 dense 4096 4096 1.00000 3.498573 0.041642 0.029869 311
99 dense 14336 4096 3.50000 5.747580 0.043857 1.836144 184
100 dense 14336 4096 3.50000 3.612054 0.035496 2.115322 663
101 dense 4096 4096 1.00000 3.117874 0.079339 0.085427 449
102 dense 4096 4096 1.00000 2.373775 0.068540 1.549893 698
103 dense 4096 1024 4.00000 2.088523 0.108146 0.574364 459
104 dense 14336 4096 3.50000 4.987190 0.037430 1.621905 343
105 dense 14336 4096 3.50000 3.842049 0.020200 4.412908 481
106 dense 14336 4096 3.50000 4.865287 0.013977 2.695955 264
107 dense 4096 1024 4.00000 3.779340 0.079149 -1.615301 283
108 dense 4096 4096 1.00000 2.990138 0.048154 1.911715 268
109 dense 4096 1024 4.00000 5.396460 0.107977 -3.222268 237
110 dense 4096 4096 1.00000 4.490376 0.028095 0.255309 215
111 dense 14336 4096 3.50000 4.118411 0.028179 4.925165 352
112 dense 4096 1024 4.00000 3.013367 0.086694 0.889081 194
113 dense 14336 4096 3.50000 5.163112 0.010758 2.258199 287
114 dense 14336 4096 3.50000 6.339995 0.060554 2.218016 191 under-trained
115 dense 4096 4096 1.00000 3.778015 0.032172 0.524959 158
116 dense 4096 1024 4.00000 2.372236 0.093028 0.807903 322
117 dense 14336 4096 3.50000 6.107819 0.063378 2.147441 334 under-trained
118 dense 14336 4096 3.50000 4.730794 0.023299 5.864367 202
119 dense 14336 4096 3.50000 5.026949 0.012124 2.201051 391
120 dense 4096 1024 4.00000 12.509198 0.122980 -8.298528 75 under-trained
121 dense 4096 4096 1.00000 2.789646 0.058212 2.020877 321
122 dense 4096 4096 1.00000 2.728380 0.066352 2.353738 534
123 dense 4096 4096 1.00000 4.043009 0.034858 1.153403 170
124 dense 4096 1024 4.00000 6.927236 0.076192 2.701919 33 under-trained
125 dense 14336 4096 3.50000 7.165964 0.019332 2.802962 141 under-trained
126 dense 14336 4096 3.50000 5.137755 0.018788 6.478530 171
127 dense 14336 4096 3.50000 5.099418 0.009477 2.280070 384
128 dense 4096 1024 4.00000 9.546071 0.103592 -4.366424 87 under-trained
129 dense 14336 4096 3.50000 6.854804 0.026129 -11.419198 150 under-trained
130 dense 14336 4096 3.50000 3.802014 0.011947 -4.158633 256
131 dense 14336 4096 3.50000 4.242456 0.014286 -5.455752 232
132 dense 4096 1024 4.00000 3.232470 0.026362 -6.534842 115
133 dense 4096 4096 1.00000 6.424385 0.062582 -13.433379 71 under-trained
134 dense 4096 4096 1.00000 3.046847 0.036025 -4.477626 181
135 dense 4096 1024 4.00000 5.937397 0.047055 -14.384766 55
136 dense 4096 4096 1.00000 6.524849 0.035249 -13.442750 42 under-trained
137 dense 4096 1024 4.00000 6.131526 0.050605 -14.216442 30 under-trained
138 dense 4096 4096 1.00000 2.874562 0.027282 -4.207329 231
139 dense 4096 1024 4.00000 3.065285 0.027870 -5.884567 120
140 dense 14336 4096 3.50000 3.824507 0.008835 -4.289578 270
141 dense 14336 4096 3.50000 7.750778 0.021458 -13.384559 127 under-trained
142 dense 14336 4096 3.50000 4.326345 0.015276 -5.851579 236
143 dense 4096 1024 4.00000 5.320029 0.049653 -12.695237 61
144 dense 4096 4096 1.00000 2.756640 0.023311 -3.814540 258
145 dense 4096 4096 1.00000 6.516253 0.041685 -13.455371 60 under-trained
146 dense 4096 1024 4.00000 2.865403 0.022049 -5.340609 138
147 dense 14336 4096 3.50000 8.260609 0.026430 -14.693100 110 under-trained
148 dense 14336 4096 3.50000 3.851233 0.010972 -4.318585 339
149 dense 14336 4096 3.50000 4.406960 0.018170 -6.010049 293
150 dense 4096 4096 1.00000 2.520512 0.025622 -3.118840 393
151 dense 4096 1024 4.00000 5.154252 0.025386 -11.965636 72
152 dense 4096 4096 1.00000 4.494447 0.030337 -7.013171 127
153 dense 4096 1024 4.00000 2.566578 0.019766 -4.493509 176
154 dense 14336 4096 3.50000 3.804351 0.014979 -4.315532 399
155 dense 14336 4096 3.50000 8.448808 0.026499 -14.636251 102 under-trained
156 dense 14336 4096 3.50000 4.409711 0.021069 -6.051615 320
157 dense 4096 4096 1.00000 4.112264 0.017990 -6.297585 106
158 dense 4096 1024 4.00000 2.504433 0.016672 -4.174921 175
159 dense 4096 4096 1.00000 2.457357 0.025227 -2.917944 396
160 dense 14336 4096 3.50000 10.010087 0.027221 3.219654 108 under-trained
161 dense 4096 1024 4.00000 4.054218 0.039244 -9.409293 113
162 dense 14336 4096 3.50000 7.751903 0.030390 2.240002 292 under-trained
163 dense 14336 4096 3.50000 5.955768 0.026264 7.643885 273
164 dense 14336 4096 3.50000 7.837772 0.018616 1.991954 214 under-trained
165 dense 4096 1024 4.00000 10.786011 0.102615 -4.092220 67 under-trained
166 dense 4096 4096 1.00000 4.427295 0.037830 3.660073 251
167 dense 4096 1024 4.00000 4.223172 0.071707 1.502978 121
168 dense 14336 4096 3.50000 11.166956 0.020578 2.995277 87 under-trained
169 dense 14336 4096 3.50000 6.401491 0.026872 7.978624 246 under-trained
170 dense 4096 4096 1.00000 3.907219 0.020754 3.036078 122
171 dense 4096 4096 1.00000 4.521099 0.015795 3.469847 98
172 dense 4096 4096 1.00000 5.353560 0.028511 0.208028 248
173 dense 4096 1024 4.00000 5.391084 0.029901 1.606353 51
174 dense 14336 4096 3.50000 11.520040 0.028930 3.466662 106 under-trained
175 dense 14336 4096 3.50000 6.695221 0.031398 8.337930 273 under-trained
176 dense 14336 4096 3.50000 5.646842 0.024038 6.420911 408
177 dense 4096 1024 4.00000 10.303440 0.048436 -4.048413 39 under-trained
178 dense 14336 4096 3.50000 4.094736 0.031416 5.776353 406
179 dense 14336 4096 3.50000 5.352500 0.020928 3.282138 319
180 dense 14336 4096 3.50000 8.103799 0.020205 4.521816 130 under-trained
181 dense 4096 1024 4.00000 2.759343 0.091064 1.886759 206
182 dense 4096 4096 1.00000 4.334783 0.025718 3.805210 230
183 dense 4096 4096 1.00000 3.552081 0.031389 3.809861 82
184 dense 4096 1024 4.00000 8.763309 0.030989 -3.884172 46 under-trained
185 dense 4096 4096 1.00000 3.809548 0.020933 3.788601 85
186 dense 4096 4096 1.00000 5.091949 0.046653 0.108309 134
187 dense 4096 1024 4.00000 5.857066 0.042089 3.470462 34
188 dense 4096 1024 4.00000 8.549455 0.043643 -4.171599 48 under-trained
189 dense 14336 4096 3.50000 4.274248 0.018668 5.523298 301
190 dense 14336 4096 3.50000 4.887628 0.035324 3.199994 292
191 dense 14336 4096 3.50000 7.357753 0.015755 3.643744 65 under-trained
192 dense 14336 4096 3.50000 4.960438 0.040586 2.846849 155
193 dense 14336 4096 3.50000 4.021605 0.022978 4.977192 390
194 dense 14336 4096 3.50000 5.488187 0.030818 2.659116 249
195 dense 4096 1024 4.00000 5.413974 0.109334 2.261950 86
196 dense 4096 4096 1.00000 3.871186 0.030670 0.341444 149
197 dense 4096 1024 4.00000 5.659127 0.101777 -2.753175 142
198 dense 4096 4096 1.00000 4.731522 0.042108 3.984250 31
199 dense 14336 4096 3.50000 4.190808 0.036396 2.541918 446
200 dense 14336 4096 3.50000 3.696913 0.016714 -4.030486 200
201 dense 14336 4096 3.50000 3.970045 0.014156 -4.672758 160
202 dense 4096 1024 4.00000 3.054710 0.029718 -6.065976 113
203 dense 4096 4096 1.00000 5.186524 0.025290 -9.818756 80
204 dense 4096 4096 1.00000 2.938072 0.052959 -4.204107 291
205 dense 4096 1024 4.00000 6.494001 0.042210 -15.747359 42 under-trained
206 dense 14336 4096 3.50000 5.812362 0.022039 -9.417266 93
207 dense 14336 4096 3.50000 3.707992 0.016403 -4.091951 135
208 dense 14336 4096 3.50000 3.838929 0.013758 -4.454688 161
209 dense 4096 1024 4.00000 2.956600 0.022618 -4.992849 132
210 dense 4096 4096 1.00000 5.665998 0.024555 -10.604418 48
211 dense 4096 4096 1.00000 2.886083 0.030560 -3.597128 192
212 dense 4096 1024 4.00000 5.871041 0.082685 -14.316405 88
213 dense 4096 1024 4.00000 4.618031 0.107854 -11.336351 189
214 dense 14336 4096 3.50000 5.465514 0.026634 -8.729905 134
215 dense 14336 4096 3.50000 3.783776 0.017879 -4.273743 97
216 dense 14336 4096 3.50000 3.926953 0.012208 -4.703458 129
217 dense 4096 1024 4.00000 3.459169 0.030417 -6.929627 90
218 dense 4096 4096 1.00000 6.153008 0.047625 -12.182116 59 under-trained
219 dense 4096 4096 1.00000 3.022591 0.055428 -4.421406 281
220 dense 14336 4096 3.50000 3.744995 0.015961 -4.182391 117
221 dense 14336 4096 3.50000 5.114740 0.022018 -7.726253 133
222 dense 14336 4096 3.50000 3.895761 0.013613 -4.575889 137
223 dense 4096 1024 4.00000 3.395387 0.028965 -6.817932 82
224 dense 4096 4096 1.00000 3.401504 0.094582 -6.969273 376
225 dense 4096 4096 1.00000 2.930707 0.055525 -4.133375 316
226 dense 4096 1024 4.00000 6.565065 0.100767 -16.436791 94 under-trained
227 dense 4096 4096 1.00000 2.884676 0.043964 -4.123923 284
228 dense 4096 1024 4.00000 7.854019 0.047952 -19.159339 20 under-trained
229 dense 4096 4096 1.00000 5.370024 0.028646 -10.535220 61
230 dense 4096 1024 4.00000 3.380141 0.029461 -6.788033 89
231 dense 14336 4096 3.50000 3.877971 0.012636 -4.336641 179
232 dense 14336 4096 3.50000 3.721811 0.015392 -3.896835 123
233 dense 14336 4096 3.50000 5.315478 0.018889 -7.922807 77
234 dense 14336 4096 3.50000 4.941040 0.010191 2.229353 369
235 dense 14336 4096 3.50000 3.865946 0.019098 -4.105862 106
236 dense 14336 4096 3.50000 6.069857 0.029420 2.798387 180 under-trained
237 dense 4096 1024 4.00000 3.811466 0.028833 -7.962829 76
238 dense 4096 4096 1.00000 7.200078 0.037283 -15.081398 54 under-trained
239 dense 4096 4096 1.00000 3.079403 0.053732 -4.602914 271
240 dense 4096 1024 4.00000 7.993334 0.099953 -20.520076 69 under-trained
241 dense 4096 4096 1.00000 2.464545 0.064363 1.987666 592
242 dense 4096 4096 1.00000 3.729397 0.032336 0.788961 183
243 dense 4096 1024 4.00000 2.553457 0.094629 1.010065 256
244 dense 14336 4096 3.50000 7.050767 0.022853 3.375228 109 under-trained
245 dense 14336 4096 3.50000 4.948573 0.008581 6.077627 221
246 dense 14336 4096 3.50000 4.952539 0.014300 2.273840 443
247 dense 4096 1024 4.00000 8.983318 0.118376 -5.186881 111 under-trained
248 dense 4096 1024 4.00000 11.870754 0.050335 -4.871986 26 under-trained
249 dense 14336 4096 3.50000 5.185948 0.018796 6.360169 269
250 dense 14336 4096 3.50000 6.628221 0.009310 3.179174 204 under-trained
251 dense 4096 1024 4.00000 4.236272 0.103360 1.855845 130
252 dense 4096 4096 1.00000 3.557017 0.055269 1.023927 365
253 dense 4096 4096 1.00000 3.034367 0.073988 2.728100 395
254 dense 14336 4096 3.50000 5.391084 0.011564 2.226450 350
255 dense 14336 4096 3.50000 6.277817 0.025879 2.544409 360 under-trained
256 dense 14336 4096 3.50000 4.995217 0.021391 6.328518 318
257 dense 4096 4096 1.00000 2.547255 0.069116 1.933881 553
258 dense 4096 1024 4.00000 4.934244 0.116560 1.475388 93
259 dense 14336 4096 3.50000 6.275057 0.015679 3.121539 75 under-trained
260 dense 4096 4096 1.00000 5.009590 0.042893 1.146824 152
261 dense 4096 1024 4.00000 5.805909 0.111346 -1.493125 216
262 dense 14336 4096 3.50000 7.369787 0.038428 3.125704 353 under-trained
263 dense 14336 4096 3.50000 5.164507 0.019981 6.611344 316
264 dense 14336 4096 3.50000 6.933179 0.020466 3.470784 261 under-trained
265 dense 4096 1024 4.00000 3.358276 0.070102 1.108141 150
266 dense 4096 4096 1.00000 3.762597 0.028935 1.409348 426
267 dense 4096 4096 1.00000 3.006844 0.043795 2.344255 335
268 dense 4096 1024 4.00000 5.879009 0.046771 -2.453121 138
269 dense 14336 4096 3.50000 3.683124 0.015339 -2.407766 303
270 dense 14336 4096 3.50000 9.713124 0.048233 3.324889 245 under-trained
271 dense 14336 4096 3.50000 5.010854 0.019175 6.598992 383
272 dense 4096 1024 4.00000 3.705837 0.033568 -7.905736 94
273 dense 4096 4096 1.00000 7.524693 0.030471 -14.828930 42 under-trained
274 dense 4096 4096 1.00000 3.277583 0.053074 -4.915811 224
275 dense 4096 1024 4.00000 6.064218 0.091184 -14.600508 98 under-trained
276 dense 14336 4096 3.50000 5.854959 0.021701 -7.811250 203
277 dense 14336 4096 3.50000 3.452315 0.013520 -1.439462 420
278 dense 14336 4096 3.50000 3.699519 0.016870 -2.352888 352
279 dense 4096 1024 4.00000 3.734459 0.029441 -7.694899 93
280 dense 4096 4096 1.00000 6.172193 0.033636 -11.519567 73 under-trained
281 dense 4096 4096 1.00000 3.344698 0.035678 -4.717486 170
282 dense 4096 1024 4.00000 5.762506 0.081909 -13.645637 94
283 dense 14336 4096 3.50000 3.421802 0.014616 -1.421937 470
284 dense 4096 1024 4.00000 3.538103 0.026025 -7.079318 109
285 dense 4096 4096 1.00000 4.369308 0.019343 -7.123037 136
286 dense 14336 4096 3.50000 3.600234 0.016040 -2.053038 401
287 dense 14336 4096 3.50000 5.712990 0.017216 -7.339787 191
288 dense 4096 1024 4.00000 5.548669 0.030927 -12.421969 53
289 dense 4096 4096 1.00000 3.127520 0.031534 -4.314085 178
290 dense 14336 4096 3.50000 5.401940 0.014136 -6.645041 225
291 dense 4096 1024 4.00000 3.515227 0.030914 -7.135493 101
292 dense 4096 4096 1.00000 3.867499 0.021147 -5.882308 128
293 dense 4096 4096 1.00000 3.082640 0.033982 -4.175452 186
294 dense 4096 1024 4.00000 4.637563 0.037506 -10.002406 58
295 dense 14336 4096 3.50000 3.330371 0.016258 -0.915986 546
296 dense 14336 4096 3.50000 3.481687 0.018466 -1.514847 485
297 dense 4096 4096 1.00000 4.424057 0.022769 -7.878081 108
298 dense 14336 4096 3.50000 5.094477 0.019860 -5.957227 233
299 dense 14336 4096 3.50000 3.304440 0.013431 -0.584011 532
300 dense 14336 4096 3.50000 3.416814 0.016050 -1.280664 484
301 dense 4096 1024 4.00000 3.246848 0.027290 -6.298124 139
302 dense 4096 4096 1.00000 2.992065 0.029193 -3.908607 240
303 dense 4096 1024 4.00000 4.722056 0.027883 -10.178978 53
304 dense 4096 1024 4.00000 4.299136 0.032718 -9.175487 89
305 dense 14336 4096 3.50000 3.231560 0.013151 -0.239581 577
306 dense 14336 4096 3.50000 3.362525 0.016254 -1.028973 483
307 dense 4096 1024 4.00000 3.162407 0.019304 -6.047197 149
308 dense 4096 4096 1.00000 3.846481 0.020583 -5.847773 105
309 dense 4096 4096 1.00000 2.824943 0.026835 -3.690060 266
310 dense 14336 4096 3.50000 4.734551 0.012002 -5.545261 213
311 dense 14336 4096 3.50000 3.200586 0.014063 -0.076178 613
312 dense 14336 4096 3.50000 4.297953 0.015325 1.680437 545
313 dense 4096 1024 4.00000 3.165980 0.020577 -6.024405 134
314 dense 4096 4096 1.00000 4.074433 0.022451 -6.564292 88
315 dense 4096 4096 1.00000 2.874394 0.023210 -3.442501 239
316 dense 4096 1024 4.00000 4.314810 0.017079 -8.805674 81
317 dense 14336 4096 3.50000 3.225771 0.014337 -0.748065 577
318 dense 14336 4096 3.50000 3.960371 0.023053 1.769601 737
319 dense 14336 4096 3.50000 5.470898 0.029985 7.613063 454
320 dense 14336 4096 3.50000 7.232160 0.049649 5.162035 373 under-trained
321 dense 4096 1024 4.00000 5.689554 0.032368 1.659938 82
322 dense 4096 4096 1.00000 4.520165 0.014658 2.207075 183
323 dense 4096 4096 1.00000 4.468413 0.020720 3.739645 76
324 dense 4096 1024 4.00000 8.189422 0.026166 -1.696174 62 under-trained
325 dense 14336 4096 3.50000 6.370339 0.034257 5.488562 372 under-trained
326 dense 4096 4096 1.00000 3.378089 0.038212 2.843444 300
327 dense 4096 4096 1.00000 6.156325 0.019687 2.302173 106 under-trained
328 dense 4096 1024 4.00000 4.584634 0.051734 1.288601 79
329 dense 4096 1024 4.00000 4.100992 0.077694 0.439421 249
330 dense 14336 4096 3.50000 3.577324 0.028100 4.867710 75
331 dense 14336 4096 3.50000 4.579583 0.019637 1.694171 465
332 dense 4096 1024 4.00000 8.603131 0.100874 -1.698972 112 under-trained
333 dense 4096 4096 1.00000 4.097144 0.031081 3.574877 59
334 dense 4096 4096 1.00000 5.868596 0.049009 2.360159 211
335 dense 4096 1024 4.00000 4.185419 0.031994 1.055153 69
336 dense 14336 4096 3.50000 3.570066 0.037122 4.587022 128
337 dense 14336 4096 3.50000 6.439840 0.065782 2.661332 328 under-trained
338 dense 14336 4096 3.50000 5.393056 0.025584 4.980423 455
339 dense 14336 4096 3.50000 6.178895 0.059596 3.657829 279 under-trained
340 dense 14336 4096 3.50000 3.628760 0.023562 4.758327 129
341 dense 14336 4096 3.50000 4.863204 0.033921 5.823983 604
342 dense 4096 1024 4.00000 3.595528 0.092102 1.039402 156
343 dense 4096 4096 1.00000 4.240186 0.025040 2.912434 280
344 dense 4096 4096 1.00000 3.056688 0.047862 2.686364 366
345 dense 4096 1024 4.00000 3.957759 0.072005 1.029508 230
346 dense 14336 4096 3.50000 2.429112 0.015258 -0.882350 767
347 dense 14336 4096 3.50000 2.620805 0.010481 1.160461 659
348 dense 14336 4096 3.50000 2.533819 0.005492 0.298346 695
349 dense 4096 1024 4.00000 2.910946 0.023073 -4.950271 149
350 dense 4096 4096 1.00000 2.572073 0.016893 -2.189152 268
351 dense 4096 1024 4.00000 2.806859 0.016638 -4.259662 179
352 dense 4096 4096 1.00000 2.788949 0.020893 -2.249351 153