Bielik-11B-v2.2-Instruct


Find this model in the Bielik model summary

Bielik-11B-v2.2-Instruct Model Set Plots

Bielik Compared to Base Model Plots

Bielik-11B-v2.2-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 32128 4096 7.84375 3.639308 0.011883 -2.976996 198
2 dense 14336 4096 3.50000 4.657258 0.032216 -5.806488 202
3 dense 14336 4096 3.50000 3.822606 0.031922 -2.069395 105
4 dense 14336 4096 3.50000 3.882376 0.030479 -2.210073 121
5 dense 4096 1024 4.00000 1.507830 0.021841 -1.300178 176 over-trained
6 dense 4096 4096 1.00000 2.312484 0.014940 -0.952580 215
7 dense 4096 4096 1.00000 1.589283 0.031167 -0.415466 364 over-trained
8 dense 4096 1024 4.00000 2.557476 0.017131 -3.762577 106
9 dense 4096 1024 4.00000 3.634953 0.021761 -7.932963 82
10 dense 4096 4096 1.00000 1.925296 0.031839 -0.886611 229 over-trained
11 dense 4096 4096 1.00000 3.280646 0.019239 -4.255865 166
12 dense 14336 4096 3.50000 2.741783 0.067775 -2.838929 773
13 dense 14336 4096 3.50000 2.764255 0.064821 -2.751755 728
14 dense 14336 4096 3.50000 5.169183 0.022999 -6.455797 245
15 dense 4096 1024 4.00000 1.836143 0.043192 -1.924678 150 over-trained
16 dense 14336 4096 3.50000 4.016250 0.020226 -4.265362 348
17 dense 4096 1024 4.00000 4.787115 0.028088 -10.327288 66
18 dense 4096 4096 1.00000 2.625952 0.019897 -2.748542 310
19 dense 4096 4096 1.00000 3.903748 0.018892 -5.143547 138
20 dense 4096 1024 4.00000 2.656690 0.025767 -4.173292 196
21 dense 14336 4096 3.50000 4.004503 0.019196 -4.285068 351
22 dense 14336 4096 3.50000 5.527630 0.012750 -8.784517 157
23 dense 4096 1024 4.00000 2.454011 0.026236 -3.496656 123
24 dense 14336 4096 3.50000 5.864762 0.018955 -9.846915 125
25 dense 14336 4096 3.50000 4.303808 0.017450 -5.361985 219
26 dense 14336 4096 3.50000 4.439746 0.021134 -5.660917 170
27 dense 4096 1024 4.00000 4.456062 0.100137 -10.155507 181
28 dense 4096 4096 1.00000 4.732747 0.018912 -8.584614 79
29 dense 4096 4096 1.00000 2.378406 0.023104 -2.224569 327
30 dense 4096 4096 1.00000 4.642188 0.032961 -8.463333 72
31 dense 4096 1024 4.00000 2.598296 0.029267 -4.626537 130
32 dense 14336 4096 3.50000 4.201777 0.009698 -5.367067 273
33 dense 14336 4096 3.50000 4.024664 0.009806 -4.898983 336
34 dense 14336 4096 3.50000 6.117135 0.017037 -9.911293 125 under-trained
35 dense 4096 1024 4.00000 5.120087 0.028620 -11.266652 46
36 dense 4096 4096 1.00000 2.534110 0.024911 -3.425322 303
37 dense 4096 1024 4.00000 6.449196 0.076449 -15.901676 79 under-trained
38 dense 4096 4096 1.00000 2.801734 0.027235 -4.524848 292
39 dense 4096 4096 1.00000 7.275695 0.037856 -14.738748 37 under-trained
40 dense 4096 1024 4.00000 2.910043 0.024399 -5.418074 140
41 dense 14336 4096 3.50000 4.273518 0.010966 -5.319143 184
42 dense 14336 4096 3.50000 6.293695 0.018057 -10.389261 117 under-trained
43 dense 14336 4096 3.50000 4.512657 0.010929 -5.917251 169
44 dense 4096 1024 4.00000 2.653455 0.024181 -4.397412 157
45 dense 4096 1024 4.00000 5.117607 0.034493 -11.520366 61
46 dense 14336 4096 3.50000 6.030936 0.016481 -9.455950 152 under-trained
47 dense 14336 4096 3.50000 4.046782 0.012009 -4.932561 259
48 dense 14336 4096 3.50000 4.279409 0.010344 -5.516961 194
49 dense 4096 4096 1.00000 2.643099 0.023978 -3.727411 291
50 dense 4096 4096 1.00000 4.528884 0.019341 -7.865206 87
51 dense 4096 4096 1.00000 5.225024 0.026624 -10.099432 62
52 dense 4096 1024 4.00000 2.649286 0.028539 -4.913120 169
53 dense 14336 4096 3.50000 4.349909 0.012745 -5.702724 168
54 dense 14336 4096 3.50000 6.059784 0.019829 -10.106449 127 under-trained
55 dense 14336 4096 3.50000 4.126347 0.011763 -5.130065 179
56 dense 4096 4096 1.00000 2.776004 0.028472 -4.295888 237
57 dense 4096 1024 4.00000 6.506787 0.048873 -15.550567 48 under-trained
58 dense 14336 4096 3.50000 4.008927 0.012407 -4.906579 157
59 dense 4096 1024 4.00000 2.760663 0.026400 -4.918177 130
60 dense 14336 4096 3.50000 5.905015 0.019247 -9.588773 131
61 dense 4096 4096 1.00000 5.544708 0.045102 -11.039543 56
62 dense 4096 4096 1.00000 2.783102 0.031639 -3.595174 209
63 dense 4096 1024 4.00000 6.288959 0.035476 -14.730124 40 under-trained
64 dense 14336 4096 3.50000 4.267756 0.010845 -5.457134 171
65 dense 4096 1024 4.00000 2.906645 0.018427 -5.417493 133
66 dense 14336 4096 3.50000 4.258030 0.017986 -5.358032 105
67 dense 4096 4096 1.00000 5.762208 0.027217 -11.188126 55
68 dense 4096 4096 1.00000 2.912098 0.030393 -4.411589 222
69 dense 4096 1024 4.00000 6.772854 0.046003 -16.439074 32 under-trained
70 dense 14336 4096 3.50000 5.390673 0.022242 -8.306149 166
71 dense 14336 4096 3.50000 3.979428 0.014429 -4.796564 121
72 dense 14336 4096 3.50000 5.795345 0.030165 -9.297377 74
73 dense 4096 4096 1.00000 2.806757 0.039561 -3.818715 284
74 dense 14336 4096 3.50000 3.724538 0.014956 -4.071104 131
75 dense 14336 4096 3.50000 3.924616 0.013068 -4.642841 152
76 dense 4096 1024 4.00000 2.808799 0.022604 -5.382396 154
77 dense 4096 4096 1.00000 5.188681 0.030264 -9.084068 59
78 dense 4096 1024 4.00000 5.668839 0.029346 -12.791525 58
79 dense 14336 4096 3.50000 5.846625 0.022334 -9.146604 103
80 dense 14336 4096 3.50000 3.685477 0.015169 -4.233602 144
81 dense 14336 4096 3.50000 3.814831 0.015927 -4.556118 185
82 dense 4096 1024 4.00000 2.724479 0.026713 -4.633188 140
83 dense 4096 4096 1.00000 4.965900 0.020701 -8.295610 65
84 dense 4096 4096 1.00000 2.718482 0.023330 -3.206017 233
85 dense 4096 1024 4.00000 5.164482 0.089770 -12.332193 120
86 dense 4096 4096 1.00000 2.996874 0.043179 -4.373650 232
87 dense 4096 1024 4.00000 4.995312 0.100498 -11.962145 146
88 dense 4096 4096 1.00000 5.765014 0.032884 -11.353189 67
89 dense 14336 4096 3.50000 3.722618 0.016427 -4.327458 158
90 dense 14336 4096 3.50000 3.980792 0.016710 -4.928264 96
91 dense 14336 4096 3.50000 6.395036 0.033993 -10.682825 66 under-trained
92 dense 4096 1024 4.00000 3.137732 0.038538 -6.437307 139
93 dense 14336 4096 3.50000 5.691454 0.021056 -9.079779 100
94 dense 14336 4096 3.50000 3.739905 0.016894 -4.317076 183
95 dense 14336 4096 3.50000 3.959820 0.013522 -4.814919 145
96 dense 4096 1024 4.00000 3.299748 0.045404 -6.559475 91
97 dense 4096 4096 1.00000 4.469126 0.086531 -8.694805 172
98 dense 4096 4096 1.00000 2.985998 0.038244 -4.297666 221
99 dense 4096 1024 4.00000 6.495672 0.056330 -15.650984 57 under-trained
100 dense 14336 4096 3.50000 5.819074 0.024510 -9.155404 82
101 dense 14336 4096 3.50000 3.836394 0.014925 -4.326192 129
102 dense 14336 4096 3.50000 4.051316 0.010795 -4.888326 172
103 dense 4096 1024 4.00000 3.179366 0.030475 -5.760176 87
104 dense 4096 4096 1.00000 3.356808 0.093992 -6.410579 417
105 dense 4096 4096 1.00000 2.944939 0.033213 -4.318686 215
106 dense 4096 1024 4.00000 5.555231 0.033664 -13.155703 66
107 dense 4096 1024 4.00000 4.548276 0.100099 -11.480659 190
108 dense 4096 4096 1.00000 3.137079 0.058394 -4.449816 244
109 dense 4096 4096 1.00000 6.431304 0.030826 -12.165461 60 under-trained
110 dense 4096 1024 4.00000 3.547759 0.033219 -7.356226 90
111 dense 14336 4096 3.50000 4.232365 0.017321 -5.307518 114
112 dense 14336 4096 3.50000 4.018637 0.019011 -4.615621 84
113 dense 14336 4096 3.50000 6.431309 0.026910 -10.625760 114 under-trained
114 dense 4096 4096 1.00000 3.153397 0.052125 -4.470119 246
115 dense 4096 4096 1.00000 4.605631 0.106874 -9.765190 259
116 dense 4096 1024 4.00000 3.262450 0.040035 -6.665565 147
117 dense 4096 1024 4.00000 5.756039 0.097095 -14.468338 114
118 dense 14336 4096 3.50000 3.957127 0.015126 -4.458297 132
119 dense 14336 4096 3.50000 6.818453 0.018119 -11.078004 96 under-trained
120 dense 14336 4096 3.50000 4.239682 0.015157 -5.210865 129
121 dense 14336 4096 3.50000 6.407324 0.019007 -9.786191 150 under-trained
122 dense 14336 4096 3.50000 3.930476 0.012251 -4.564570 170
123 dense 14336 4096 3.50000 4.287314 0.010262 -5.496900 184
124 dense 4096 1024 4.00000 3.173510 0.024770 -5.664124 124
125 dense 4096 4096 1.00000 6.935082 0.031825 -14.042950 54 under-trained
126 dense 4096 4096 1.00000 3.139653 0.032877 -4.075502 153
127 dense 4096 1024 4.00000 4.075619 0.110070 -9.876062 240
128 dense 4096 1024 4.00000 6.081028 0.040750 -14.576583 55 under-trained
129 dense 4096 4096 1.00000 3.112663 0.037222 -4.545719 164
130 dense 4096 4096 1.00000 5.575091 0.076904 -11.288135 138
131 dense 4096 1024 4.00000 3.271126 0.028964 -6.562496 115
132 dense 14336 4096 3.50000 3.864993 0.010575 -4.182418 259
133 dense 14336 4096 3.50000 4.305771 0.016899 -5.487845 239
134 dense 14336 4096 3.50000 7.052298 0.023091 -11.505408 145 under-trained
135 dense 4096 1024 4.00000 6.007802 0.032854 -13.802210 33 under-trained
136 dense 14336 4096 3.50000 7.892376 0.021210 -13.315839 135 under-trained
137 dense 14336 4096 3.50000 3.876339 0.008620 -4.294465 259
138 dense 14336 4096 3.50000 4.391642 0.016212 -5.872455 234
139 dense 4096 1024 4.00000 3.134700 0.029346 -5.950244 110
140 dense 4096 4096 1.00000 6.583172 0.031489 -13.280782 44 under-trained
141 dense 4096 4096 1.00000 2.927454 0.027721 -4.255111 224
142 dense 4096 1024 4.00000 5.513362 0.051563 -13.027039 58
143 dense 4096 4096 1.00000 2.790839 0.024379 -3.834511 253
144 dense 4096 4096 1.00000 6.366140 0.048752 -13.004450 65 under-trained
145 dense 14336 4096 3.50000 8.390486 0.026945 -14.662612 112 under-trained
146 dense 14336 4096 3.50000 4.488813 0.017560 -6.046167 269
147 dense 14336 4096 3.50000 3.891106 0.012537 -4.301354 333
148 dense 4096 1024 4.00000 2.904526 0.023047 -5.358177 124
149 dense 4096 4096 1.00000 4.652637 0.029664 -7.239348 118
150 dense 4096 4096 1.00000 2.546930 0.025238 -3.149425 380
151 dense 4096 1024 4.00000 5.284789 0.040215 -12.200113 71
152 dense 4096 1024 4.00000 2.590020 0.019031 -4.492469 175
153 dense 14336 4096 3.50000 3.858489 0.015976 -4.318582 379
154 dense 14336 4096 3.50000 8.556283 0.025445 -14.601230 119 under-trained
155 dense 14336 4096 3.50000 4.481399 0.021026 -6.052773 306
156 dense 14336 4096 3.50000 3.863415 0.015483 -4.519762 368
157 dense 14336 4096 3.50000 7.943415 0.021933 -13.227920 114 under-trained
158 dense 4096 1024 4.00000 4.059592 0.041141 -9.229500 111
159 dense 14336 4096 3.50000 4.337038 0.019601 -5.761398 321
160 dense 4096 4096 1.00000 4.163371 0.017206 -6.370736 104
161 dense 4096 1024 4.00000 2.521243 0.016690 -4.145340 169
162 dense 4096 4096 1.00000 2.480002 0.024491 -2.940462 375
163 dense 14336 4096 3.50000 7.211115 0.017049 -10.920443 133 under-trained
164 dense 14336 4096 3.50000 3.769099 0.015565 -4.231233 388
165 dense 14336 4096 3.50000 4.211706 0.020541 -5.500738 353
166 dense 4096 1024 4.00000 2.440386 0.027611 -4.031525 143
167 dense 4096 4096 1.00000 3.297821 0.020156 -5.351436 190
168 dense 4096 4096 1.00000 2.386621 0.023424 -2.963573 376
169 dense 4096 1024 4.00000 3.922681 0.041712 -8.523317 79
170 dense 4096 4096 1.00000 3.762907 0.014791 -4.791748 158
171 dense 4096 4096 1.00000 2.407240 0.024308 -2.866261 372
172 dense 4096 1024 4.00000 2.424429 0.025346 -3.914757 124
173 dense 4096 1024 4.00000 3.595705 0.032032 -7.298106 128
174 dense 14336 4096 3.50000 3.752932 0.015596 -4.213173 391
175 dense 14336 4096 3.50000 6.662011 0.021600 -9.108973 147 under-trained
176 dense 14336 4096 3.50000 4.239174 0.022139 -5.517934 330
177 dense 4096 4096 1.00000 2.838041 0.029550 -3.814386 209
178 dense 4096 4096 1.00000 5.090131 0.029572 -8.179467 111
179 dense 4096 1024 4.00000 2.513474 0.026756 -4.341539 193
180 dense 4096 1024 4.00000 6.106091 0.031724 -14.250516 44 under-trained
181 dense 14336 4096 3.50000 4.109257 0.010328 -4.817289 207
182 dense 14336 4096 3.50000 7.373846 0.024050 -12.072226 138 under-trained
183 dense 14336 4096 3.50000 4.685237 0.015298 -6.393760 188
184 dense 14336 4096 3.50000 6.934648 0.021445 -11.352143 96 under-trained
185 dense 14336 4096 3.50000 4.130187 0.012505 -5.019707 158
186 dense 14336 4096 3.50000 4.562855 0.012578 -6.112940 144
187 dense 4096 1024 4.00000 2.775664 0.019559 -4.893001 136
188 dense 4096 4096 1.00000 5.332584 0.096811 -10.758876 174
189 dense 4096 4096 1.00000 2.923673 0.027343 -3.512343 199
190 dense 4096 1024 4.00000 5.620675 0.093746 -13.762207 116
191 dense 4096 4096 1.00000 3.206399 0.038607 -4.869725 168
192 dense 4096 1024 4.00000 6.227051 0.091764 -15.301916 91 under-trained
193 dense 4096 4096 1.00000 5.980688 0.100838 -11.944956 132
194 dense 4096 1024 4.00000 3.026804 0.024697 -5.899724 148
195 dense 14336 4096 3.50000 4.546533 0.018960 -6.006832 102
196 dense 14336 4096 3.50000 4.384275 0.023596 -5.369825 52
197 dense 14336 4096 3.50000 6.724026 0.018296 -10.897857 87 under-trained
198 dense 4096 4096 1.00000 3.065789 0.049675 -4.382054 221
199 dense 4096 4096 1.00000 5.260725 0.025356 -9.907463 83
200 dense 4096 1024 4.00000 3.118082 0.032274 -6.180640 108
201 dense 4096 1024 4.00000 6.623866 0.030517 -15.851189 43 under-trained
202 dense 14336 4096 3.50000 3.729945 0.019503 -4.014573 204
203 dense 14336 4096 3.50000 6.030605 0.022147 -9.691582 87 under-trained
204 dense 14336 4096 3.50000 4.004491 0.018129 -4.654986 159
205 dense 14336 4096 3.50000 5.927095 0.023659 -9.420144 87
206 dense 14336 4096 3.50000 3.667870 0.020506 -4.015753 204
207 dense 14336 4096 3.50000 3.913065 0.013479 -4.518508 139
208 dense 4096 1024 4.00000 3.023803 0.022206 -5.120385 126
209 dense 4096 4096 1.00000 5.643213 0.022960 -10.502482 51
210 dense 4096 4096 1.00000 3.554215 0.031060 -4.440093 45
211 dense 4096 1024 4.00000 5.785875 0.088025 -14.027124 94
212 dense 4096 4096 1.00000 6.406946 0.045238 -12.521294 56 under-trained
213 dense 4096 4096 1.00000 2.980395 0.056756 -4.357962 322
214 dense 4096 1024 4.00000 3.575163 0.036210 -7.108245 79
215 dense 4096 1024 4.00000 7.564055 0.042169 -18.401316 38 under-trained
216 dense 14336 4096 3.50000 3.884604 0.019808 -4.361977 87
217 dense 14336 4096 3.50000 5.781060 0.026832 -9.087055 91
218 dense 14336 4096 3.50000 3.993752 0.013412 -4.756663 134
219 dense 4096 4096 1.00000 3.016996 0.057946 -4.269012 293
220 dense 4096 4096 1.00000 3.718685 0.093735 -7.535425 310
221 dense 4096 1024 4.00000 3.450875 0.036130 -6.964849 90
222 dense 4096 1024 4.00000 6.706865 0.109230 -16.632229 102 under-trained
223 dense 14336 4096 3.50000 3.863647 0.020114 -4.287063 92
224 dense 14336 4096 3.50000 5.192874 0.022287 -7.692694 134
225 dense 14336 4096 3.50000 3.958409 0.015015 -4.623898 130
226 dense 14336 4096 3.50000 5.389031 0.017297 -7.891231 81
227 dense 14336 4096 3.50000 3.776502 0.014710 -3.937820 143
228 dense 14336 4096 3.50000 3.957319 0.012720 -4.410209 161
229 dense 4096 1024 4.00000 3.511966 0.030901 -7.031911 87
230 dense 4096 4096 1.00000 5.428614 0.028413 -10.503138 62
231 dense 4096 4096 1.00000 2.929112 0.048756 -4.173196 281
232 dense 4096 1024 4.00000 7.123984 0.087465 -17.286638 61 under-trained
233 dense 4096 1024 4.00000 9.128052 0.106874 -22.991485 59 under-trained
234 dense 14336 4096 3.50000 5.958766 0.018564 -8.909175 91
235 dense 4096 4096 1.00000 3.246007 0.059671 -4.830613 237
236 dense 14336 4096 3.50000 4.073313 0.016208 -4.631485 141
237 dense 4096 1024 4.00000 3.965116 0.032113 -8.224132 64
238 dense 14336 4096 3.50000 3.989022 0.020274 -4.220906 93
239 dense 4096 4096 1.00000 6.315342 0.102947 -13.108568 141 under-trained
240 dense 14336 4096 3.50000 5.681953 0.029084 -7.896472 135
241 dense 14336 4096 3.50000 3.963970 0.021914 -3.824175 104
242 dense 14336 4096 3.50000 4.086942 0.019169 -4.292234 144
243 dense 4096 1024 4.00000 3.966476 0.035914 -8.328762 71
244 dense 4096 4096 1.00000 6.087920 0.106096 -12.502084 145 under-trained
245 dense 4096 4096 1.00000 3.669766 0.068442 -5.434651 175
246 dense 4096 1024 4.00000 7.701982 0.097533 -19.539925 67 under-trained
247 dense 4096 1024 4.00000 6.359839 0.099910 -15.654723 99 under-trained
248 dense 4096 4096 1.00000 4.472778 0.035217 -6.075226 28
249 dense 4096 4096 1.00000 4.726607 0.102218 -9.132495 219
250 dense 4096 1024 4.00000 3.730345 0.035629 -7.170794 69
251 dense 14336 4096 3.50000 3.869739 0.016933 -3.388656 114
252 dense 14336 4096 3.50000 5.478817 0.025400 -7.469606 120
253 dense 14336 4096 3.50000 4.005456 0.016071 -3.844259 165
254 dense 14336 4096 3.50000 5.650702 0.020400 -7.642661 131
255 dense 14336 4096 3.50000 3.753289 0.016266 -2.627941 176
256 dense 14336 4096 3.50000 3.872312 0.017747 -3.012384 236
257 dense 4096 1024 4.00000 3.740395 0.040079 -7.731396 94
258 dense 4096 4096 1.00000 6.062673 0.036339 -11.314372 65 under-trained
259 dense 4096 4096 1.00000 3.795809 0.050062 -5.623091 95
260 dense 4096 1024 4.00000 5.575242 0.108705 -13.591371 127
261 dense 4096 1024 4.00000 4.704370 0.101665 -11.000664 167
262 dense 4096 4096 1.00000 3.630670 0.054543 -5.362259 136
263 dense 4096 4096 1.00000 6.266737 0.028590 -11.766302 61 under-trained
264 dense 14336 4096 3.50000 3.578865 0.014218 -2.077331 248
265 dense 14336 4096 3.50000 3.779829 0.014360 -2.618795 285
266 dense 14336 4096 3.50000 5.743167 0.021523 -7.736300 170
267 dense 4096 1024 4.00000 3.765263 0.030584 -7.717156 105
268 dense 4096 4096 1.00000 3.502689 0.054521 -5.224780 178
269 dense 4096 4096 1.00000 5.609841 0.100855 -10.959921 166
270 dense 4096 1024 4.00000 3.829736 0.036271 -8.110585 89
271 dense 4096 1024 4.00000 5.865220 0.083817 -14.030286 99
272 dense 14336 4096 3.50000 3.531095 0.014757 -1.759909 324
273 dense 14336 4096 3.50000 5.951049 0.020616 -7.981345 177
274 dense 14336 4096 3.50000 3.754789 0.015604 -2.463235 305
275 dense 14336 4096 3.50000 6.082287 0.019756 -8.029299 179 under-trained
276 dense 14336 4096 3.50000 3.520554 0.014763 -1.435212 383
277 dense 14336 4096 3.50000 3.773576 0.017208 -2.406479 351
278 dense 4096 1024 4.00000 3.850866 0.029768 -7.897956 81
279 dense 4096 4096 1.00000 6.741886 0.031706 -12.525413 55 under-trained
280 dense 4096 4096 1.00000 3.294830 0.041002 -4.618862 216
281 dense 4096 1024 4.00000 6.726252 0.054579 -15.818209 46 under-trained
282 dense 4096 4096 1.00000 3.157665 0.032321 -4.312847 196
283 dense 4096 1024 4.00000 5.827112 0.031684 -12.955119 40
284 dense 4096 4096 1.00000 4.461746 0.019199 -7.145551 129
285 dense 4096 1024 4.00000 3.688803 0.030280 -7.322023 85
286 dense 14336 4096 3.50000 3.662887 0.018012 -2.092978 400
287 dense 14336 4096 3.50000 3.495275 0.015602 -1.416907 423
288 dense 14336 4096 3.50000 5.806778 0.019970 -7.360878 198
289 dense 4096 4096 1.00000 3.118900 0.035807 -4.182782 203
290 dense 4096 4096 1.00000 3.879176 0.017268 -5.827731 133
291 dense 4096 1024 4.00000 3.629468 0.030916 -7.300963 97
292 dense 4096 1024 4.00000 4.646296 0.043209 -9.959816 68
293 dense 14336 4096 3.50000 3.392412 0.016680 -0.887772 506
294 dense 14336 4096 3.50000 5.540914 0.015096 -6.683984 196
295 dense 14336 4096 3.50000 3.565017 0.018948 -1.553794 440
296 dense 14336 4096 3.50000 5.184146 0.020909 -5.946772 235
297 dense 14336 4096 3.50000 3.350239 0.013930 -0.538482 514
298 dense 14336 4096 3.50000 3.479114 0.016203 -1.306331 475
299 dense 4096 1024 4.00000 3.308910 0.024489 -6.394096 137
300 dense 4096 4096 1.00000 4.515263 0.022862 -7.929126 108
301 dense 4096 4096 1.00000 3.043139 0.030961 -3.935812 236
302 dense 4096 1024 4.00000 4.787326 0.034048 -10.273535 55
303 dense 4096 4096 1.00000 3.934856 0.018302 -5.969934 112
304 dense 4096 1024 4.00000 4.612362 0.034053 -9.733086 52
305 dense 4096 1024 4.00000 3.257146 0.025266 -6.154859 113
306 dense 4096 4096 1.00000 2.857760 0.027804 -3.670387 268
307 dense 14336 4096 3.50000 3.284624 0.014010 -0.187955 541
308 dense 14336 4096 3.50000 4.827208 0.012755 -5.572984 188
309 dense 14336 4096 3.50000 3.396087 0.017115 -1.041546 515
310 dense 4096 1024 4.00000 4.369157 0.022944 -8.886575 85
311 dense 4096 4096 1.00000 2.937503 0.025144 -3.464945 222
312 dense 4096 4096 1.00000 4.117652 0.025954 -6.518490 85
313 dense 14336 4096 3.50000 4.477901 0.022050 -4.806520 170
314 dense 14336 4096 3.50000 3.283948 0.015543 -0.760550 558
315 dense 14336 4096 3.50000 3.239966 0.014390 -0.019900 600
316 dense 32128 4096 7.84375 2.719413 0.039952 5.135713 108
317 dense 4096 1024 4.00000 3.254055 0.025362 -6.129001 112
318 dense 14336 4096 3.50000 4.039529 0.017829 -3.741277 181
319 dense 14336 4096 3.50000 3.184332 0.016998 0.075838 605
320 dense 14336 4096 3.50000 3.180094 0.015353 -0.444986 585
321 dense 4096 1024 4.00000 3.160602 0.032634 -5.702796 90
322 dense 4096 4096 1.00000 3.419961 0.014726 -4.249620 144
323 dense 4096 4096 1.00000 2.774287 0.024482 -3.196195 287
324 dense 4096 1024 4.00000 4.025277 0.025795 -7.178817 74
325 dense 4096 4096 1.00000 3.530005 0.020622 -4.279914 121
326 dense 4096 1024 4.00000 3.965337 0.021442 -7.078203 62
327 dense 4096 1024 4.00000 3.195471 0.027780 -6.104476 119
328 dense 4096 4096 1.00000 2.919205 0.023675 -3.010581 228
329 dense 14336 4096 3.50000 3.109253 0.017693 -0.084971 586
330 dense 14336 4096 3.50000 3.485107 0.011539 -2.545155 352
331 dense 14336 4096 3.50000 3.020668 0.014097 -0.126912 554
332 dense 14336 4096 3.50000 3.152992 0.011225 -1.827331 451
333 dense 14336 4096 3.50000 3.025272 0.017125 -0.309579 544
334 dense 14336 4096 3.50000 2.913403 0.012130 0.244527 579
335 dense 4096 1024 4.00000 3.151016 0.022301 -5.608934 119
336 dense 4096 4096 1.00000 3.186514 0.021315 -3.071034 226
337 dense 4096 4096 1.00000 2.855083 0.025200 -2.685476 225
338 dense 4096 1024 4.00000 3.623625 0.012989 -5.810733 107
339 dense 4096 1024 4.00000 3.277754 0.012641 -5.117870 142
340 dense 4096 4096 1.00000 2.796542 0.020808 -2.591589 246
341 dense 4096 4096 1.00000 2.909569 0.016695 -2.510440 232
342 dense 14336 4096 3.50000 2.865051 0.016197 0.139212 629
343 dense 14336 4096 3.50000 2.788799 0.011098 0.523970 590
344 dense 14336 4096 3.50000 2.798553 0.015324 -1.269431 630
345 dense 4096 1024 4.00000 3.209937 0.030102 -5.860203 115
346 dense 4096 4096 1.00000 2.838387 0.021339 -2.268364 122
347 dense 14336 4096 3.50000 2.432256 0.015677 -0.877410 752
348 dense 14336 4096 3.50000 2.641068 0.010460 1.174840 626
349 dense 14336 4096 3.50000 2.543169 0.006051 0.301627 647
350 dense 4096 1024 4.00000 2.957809 0.024055 -4.986397 150
351 dense 4096 4096 1.00000 2.585504 0.018292 -2.143651 254
352 dense 4096 1024 4.00000 2.840373 0.016191 -4.305920 175