Qwen2-72B-Instruct


Find this model in the Qwen2.0 model summary

Qwen2-72B-Instruct Model Set Plots

Qwen2.0 Compared to Base Model Plots

Qwen2-72B-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 29568 8192 3.609375 2.674178 0.017063 -0.323278 229
2 dense 29568 8192 3.609375 2.656680 0.016242 -0.314494 245
3 dense 8192 1024 8.000000 1.684680 0.029190 -1.471343 820 over-trained
4 dense 8192 8192 1.000000 2.569245 0.021023 -1.088434 226
5 dense 8192 8192 1.000000 2.023011 0.032603 -0.776065 66
6 dense 8192 1024 8.000000 2.751561 0.044612 -3.241472 128
7 dense 29568 8192 3.609375 2.936315 0.011211 -0.180138 421
8 dense 29568 8192 3.609375 3.549250 0.017907 -0.677620 415
9 dense 29568 8192 3.609375 2.940821 0.012966 0.284061 277
10 dense 29568 8192 3.609375 2.935970 0.013830 0.288458 295
11 dense 8192 1024 8.000000 1.593138 0.020523 -2.868279 284 over-trained
12 dense 8192 8192 1.000000 1.556159 0.055799 -0.436480 2911 over-trained
13 dense 8192 8192 1.000000 2.072609 0.045396 -2.273621 39
14 dense 8192 1024 8.000000 2.807028 0.036808 -3.332852 62
15 dense 29568 8192 3.609375 3.856968 0.014295 -0.865417 256
16 dense 29568 8192 3.609375 2.976182 0.028210 -0.428572 342
17 dense 8192 1024 8.000000 3.271178 0.080913 -5.298234 138
18 dense 8192 8192 1.000000 3.575198 0.034356 -2.619743 161
19 dense 8192 1024 8.000000 2.261417 0.024572 -2.743644 136
20 dense 8192 8192 1.000000 2.028141 0.048421 -2.122625 283
21 dense 29568 8192 3.609375 2.999624 0.029843 -0.361710 336
22 dense 29568 8192 3.609375 4.064989 0.016400 -1.175995 338
23 dense 29568 8192 3.609375 2.461471 0.060154 -0.448431 1049
24 dense 29568 8192 3.609375 2.558532 0.060446 -0.454063 899
25 dense 8192 1024 8.000000 1.571483 0.021742 -1.412736 797 over-trained
26 dense 8192 8192 1.000000 4.589934 0.035542 -4.095326 73
27 dense 8192 8192 1.000000 1.519191 0.025110 -1.240696 2877 over-trained
28 dense 8192 1024 8.000000 3.402231 0.085169 -5.453727 167
29 dense 8192 1024 8.000000 2.408627 0.045520 -2.607732 74
30 dense 29568 8192 3.609375 2.750762 0.063152 -0.648406 1042
31 dense 29568 8192 3.609375 2.845566 0.061633 -0.669681 886
32 dense 29568 8192 3.609375 4.160116 0.017179 -1.448080 494
33 dense 8192 1024 8.000000 4.395557 0.068996 -6.784494 62
34 dense 8192 8192 1.000000 4.399649 0.029836 -4.000452 69
35 dense 8192 8192 1.000000 2.132078 0.044544 -1.787966 273
36 dense 8192 8192 1.000000 4.052456 0.035211 -3.422887 78
37 dense 8192 1024 8.000000 2.500355 0.046603 -2.819762 71
38 dense 8192 8192 1.000000 2.092692 0.048068 -1.818738 393
39 dense 8192 1024 8.000000 3.486141 0.090868 -5.692729 157
40 dense 29568 8192 3.609375 4.211850 0.010054 -1.797264 430
41 dense 29568 8192 3.609375 4.165652 0.015982 -1.213489 200
42 dense 29568 8192 3.609375 4.129336 0.017333 -1.186378 224
43 dense 29568 8192 3.609375 3.901117 0.011153 -1.297041 278
44 dense 8192 1024 8.000000 2.145424 0.056104 -2.075223 154
45 dense 29568 8192 3.609375 4.195998 0.011261 -1.977266 477
46 dense 29568 8192 3.609375 3.918242 0.011710 -1.287055 221
47 dense 8192 8192 1.000000 3.304282 0.069453 -3.188717 458
48 dense 8192 8192 1.000000 2.152444 0.034671 -1.909462 335
49 dense 8192 1024 8.000000 3.932818 0.085866 -6.111025 126
50 dense 29568 8192 3.609375 3.750612 0.014774 -1.217471 177
51 dense 8192 1024 8.000000 2.422632 0.044371 -2.540634 97
52 dense 8192 8192 1.000000 4.236952 0.036511 -3.699986 106
53 dense 8192 8192 1.000000 2.270628 0.031875 -1.821877 399
54 dense 8192 1024 8.000000 3.773852 0.082727 -5.791272 142
55 dense 29568 8192 3.609375 4.172760 0.013429 -1.983264 514
56 dense 29568 8192 3.609375 3.684904 0.016914 -1.249801 349
57 dense 29568 8192 3.609375 3.606899 0.021885 -1.348252 382
58 dense 29568 8192 3.609375 4.131034 0.010517 -1.983029 467
59 dense 29568 8192 3.609375 3.727400 0.019954 -1.401825 309
60 dense 8192 1024 8.000000 2.541505 0.056106 -2.694113 82
61 dense 8192 1024 8.000000 4.312871 0.068069 -6.830026 112
62 dense 8192 8192 1.000000 2.154880 0.040213 -1.771251 338
63 dense 8192 8192 1.000000 4.269011 0.025241 -4.195058 139
64 dense 29568 8192 3.609375 4.175681 0.007319 -2.004009 396
65 dense 29568 8192 3.609375 3.851109 0.021356 -1.563649 260
66 dense 29568 8192 3.609375 4.042393 0.018646 -1.615513 154
67 dense 8192 1024 8.000000 2.907164 0.038158 -2.938742 113
68 dense 8192 8192 1.000000 3.483980 0.051475 -3.247942 353
69 dense 8192 1024 8.000000 4.556334 0.069449 -7.560434 101
70 dense 8192 8192 1.000000 2.575569 0.028823 -2.369393 362
71 dense 29568 8192 3.609375 4.182014 0.027886 -1.862507 122
72 dense 8192 8192 1.000000 2.430633 0.029478 -1.957839 414
73 dense 8192 1024 8.000000 3.837346 0.070280 -5.501371 185
74 dense 8192 1024 8.000000 2.272129 0.045271 -2.354945 219
75 dense 8192 8192 1.000000 4.016518 0.042362 -3.508261 195
76 dense 29568 8192 3.609375 4.279289 0.007643 -2.049447 360
77 dense 29568 8192 3.609375 4.378691 0.024965 -1.941135 80
78 dense 29568 8192 3.609375 4.281133 0.007793 -1.937531 244
79 dense 29568 8192 3.609375 4.451180 0.022214 -2.140017 100
80 dense 8192 1024 8.000000 5.121817 0.080039 -8.302133 87
81 dense 8192 1024 8.000000 2.644835 0.035333 -2.816089 167
82 dense 8192 8192 1.000000 4.038529 0.039451 -3.584364 154
83 dense 8192 8192 1.000000 2.626474 0.030335 -2.322300 402
84 dense 29568 8192 3.609375 4.541146 0.024502 -2.258898 99
85 dense 29568 8192 3.609375 4.458797 0.029177 -2.209165 103
86 dense 29568 8192 3.609375 4.481491 0.025620 -2.200332 90
87 dense 29568 8192 3.609375 4.206659 0.010825 -1.892494 272
88 dense 8192 1024 8.000000 2.904905 0.034293 -2.958125 111
89 dense 8192 8192 1.000000 4.605971 0.063265 -4.275585 199
90 dense 8192 8192 1.000000 2.688672 0.032812 -2.507961 446
91 dense 8192 1024 8.000000 5.127453 0.051579 -7.248724 63
92 dense 29568 8192 3.609375 4.266330 0.012925 -1.887029 251
93 dense 29568 8192 3.609375 4.356840 0.037082 -2.116342 144
94 dense 29568 8192 3.609375 4.451617 0.034382 -2.245233 125
95 dense 8192 1024 8.000000 2.722098 0.039732 -2.952414 128
96 dense 8192 8192 1.000000 4.088298 0.059751 -3.626895 242
97 dense 8192 8192 1.000000 2.646088 0.031393 -2.267348 438
98 dense 8192 1024 8.000000 3.850562 0.078221 -5.959000 188
99 dense 8192 1024 8.000000 2.614107 0.041516 -2.683295 133
100 dense 8192 8192 1.000000 3.531498 0.064230 -3.292572 387
101 dense 8192 8192 1.000000 2.638145 0.030959 -2.081233 378
102 dense 8192 1024 8.000000 5.673568 0.085561 -8.197260 65
103 dense 29568 8192 3.609375 4.390131 0.010208 -2.026913 213
104 dense 29568 8192 3.609375 4.008733 0.049331 -2.146306 262
105 dense 29568 8192 3.609375 4.036866 0.049930 -2.236845 247
106 dense 29568 8192 3.609375 4.308999 0.010906 -1.869250 208
107 dense 29568 8192 3.609375 3.537760 0.056564 -1.725644 665
108 dense 29568 8192 3.609375 3.650567 0.055965 -1.845366 564
109 dense 8192 1024 8.000000 2.980906 0.033878 -3.359544 101
110 dense 8192 8192 1.000000 3.513273 0.066494 -3.026914 408
111 dense 8192 8192 1.000000 2.843540 0.031915 -2.611808 365
112 dense 8192 1024 8.000000 4.711826 0.072674 -7.082132 83
113 dense 29568 8192 3.609375 4.531025 0.042400 -2.320066 164
114 dense 8192 1024 8.000000 2.890382 0.032735 -3.059353 103
115 dense 8192 8192 1.000000 4.576550 0.050704 -4.248015 130
116 dense 8192 8192 1.000000 2.799445 0.031498 -2.627529 392
117 dense 8192 1024 8.000000 4.937658 0.078843 -7.999279 89
118 dense 29568 8192 3.609375 4.218117 0.014037 -1.768299 192
119 dense 29568 8192 3.609375 3.468384 0.061119 -1.828175 782
120 dense 29568 8192 3.609375 4.041673 0.014314 -1.588183 180
121 dense 29568 8192 3.609375 3.880299 0.047628 -1.966486 313
122 dense 29568 8192 3.609375 3.952182 0.044622 -2.057320 283
123 dense 8192 1024 8.000000 2.709714 0.030915 -2.536173 106
124 dense 8192 8192 1.000000 3.592578 0.061656 -2.822831 319
125 dense 8192 8192 1.000000 2.575541 0.027792 -1.555554 393
126 dense 8192 1024 8.000000 3.379685 0.082616 -5.182263 211
127 dense 29568 8192 3.609375 3.467617 0.058739 -1.686562 774
128 dense 29568 8192 3.609375 3.411211 0.058473 -1.688020 791
129 dense 8192 1024 8.000000 3.441927 0.084742 -5.211779 203
130 dense 8192 8192 1.000000 2.836925 0.025484 -2.369694 330
131 dense 8192 8192 1.000000 3.702761 0.046673 -2.874510 160
132 dense 29568 8192 3.609375 4.014950 0.011423 -1.581267 181
133 dense 8192 1024 8.000000 3.007015 0.025960 -3.462328 132
134 dense 29568 8192 3.609375 4.169513 0.036144 -1.989665 206
135 dense 29568 8192 3.609375 3.732841 0.013886 -1.449119 449
136 dense 29568 8192 3.609375 4.433396 0.032178 -2.030031 134
137 dense 8192 1024 8.000000 3.850746 0.082030 -5.984407 156
138 dense 8192 8192 1.000000 2.893683 0.027269 -2.517950 324
139 dense 8192 8192 1.000000 3.169093 0.062759 -2.664108 543
140 dense 8192 1024 8.000000 3.015360 0.020144 -3.459416 165
141 dense 8192 1024 8.000000 2.923578 0.055011 -2.695372 50
142 dense 29568 8192 3.609375 4.228966 0.033906 -2.079385 222
143 dense 29568 8192 3.609375 4.533335 0.033913 -2.156726 146
144 dense 29568 8192 3.609375 3.906767 0.012543 -1.643430 211
145 dense 8192 8192 1.000000 2.553867 0.034813 -1.678415 385
146 dense 8192 1024 8.000000 3.347870 0.078676 -4.894935 190
147 dense 8192 8192 1.000000 4.094112 0.031922 -3.073158 55
148 dense 8192 8192 1.000000 3.181993 0.028970 -2.033030 231
149 dense 29568 8192 3.609375 3.706222 0.013778 -1.293700 181
150 dense 8192 1024 8.000000 2.525053 0.034308 -1.922820 73
151 dense 29568 8192 3.609375 3.346322 0.046799 -1.484685 609
152 dense 29568 8192 3.609375 3.322790 0.045457 -1.464858 668
153 dense 8192 1024 8.000000 3.345996 0.051446 -3.807912 112
154 dense 8192 8192 1.000000 2.423675 0.030604 -1.329676 356
155 dense 8192 8192 1.000000 2.819695 0.037881 -2.066612 370
156 dense 8192 8192 1.000000 3.576287 0.032936 -2.547880 146
157 dense 29568 8192 3.609375 3.712738 0.056919 -1.658616 610
158 dense 29568 8192 3.609375 3.980700 0.008108 -1.605717 444
159 dense 8192 1024 8.000000 3.148512 0.022034 -3.736435 130
160 dense 29568 8192 3.609375 4.678050 0.018543 -2.028231 92
161 dense 8192 1024 8.000000 2.731864 0.069687 -3.414159 369
162 dense 29568 8192 3.609375 4.897681 0.021955 -2.314971 124
163 dense 29568 8192 3.609375 4.427831 0.009671 -2.382058 648
164 dense 29568 8192 3.609375 3.826957 0.063432 -1.890364 652
165 dense 8192 8192 1.000000 2.800763 0.029565 -1.726259 398
166 dense 8192 8192 1.000000 3.900639 0.018563 -2.917027 102
167 dense 8192 1024 8.000000 2.990716 0.026109 -2.894992 103
168 dense 8192 1024 8.000000 4.301865 0.031825 -5.738064 43
169 dense 8192 1024 8.000000 2.810868 0.030474 -3.044880 133
170 dense 8192 1024 8.000000 3.300501 0.055749 -5.214044 255
171 dense 8192 8192 1.000000 2.676193 0.029195 -1.731353 409
172 dense 8192 8192 1.000000 3.629212 0.030520 -3.028590 164
173 dense 29568 8192 3.609375 4.815405 0.048146 -2.726130 198
174 dense 29568 8192 3.609375 4.728270 0.042369 -2.489534 211
175 dense 29568 8192 3.609375 5.034958 0.024371 -3.211161 784
176 dense 29568 8192 3.609375 5.684032 0.035944 -3.351785 117
177 dense 8192 1024 8.000000 3.515504 0.061398 -4.964656 228
178 dense 8192 8192 1.000000 2.984731 0.032723 -2.061204 379
179 dense 29568 8192 3.609375 4.722166 0.032749 -2.606913 38
180 dense 29568 8192 3.609375 5.241636 0.027583 -3.320670 840
181 dense 8192 8192 1.000000 3.802979 0.030724 -3.339823 219
182 dense 8192 1024 8.000000 3.231489 0.024845 -3.814695 121
183 dense 29568 8192 3.609375 5.929625 0.029712 -3.554745 140
184 dense 29568 8192 3.609375 5.662985 0.027475 -3.883497 733
185 dense 8192 8192 1.000000 2.925989 0.029588 -2.140520 459
186 dense 8192 8192 1.000000 4.023504 0.020905 -3.769797 291
187 dense 8192 1024 8.000000 3.264032 0.029828 -3.503289 77
188 dense 8192 1024 8.000000 3.690787 0.020830 -5.471347 217
189 dense 29568 8192 3.609375 5.405370 0.031491 -3.365298 222
190 dense 8192 1024 8.000000 3.163835 0.047060 -3.767443 99
191 dense 29568 8192 3.609375 5.899161 0.026361 -3.552761 180
192 dense 29568 8192 3.609375 5.460477 0.024874 -3.445323 250
193 dense 29568 8192 3.609375 5.613656 0.025524 -3.825685 760
194 dense 8192 1024 8.000000 4.261817 0.038498 -6.626498 127
195 dense 8192 8192 1.000000 2.910114 0.029611 -2.207270 423
196 dense 8192 8192 1.000000 4.258007 0.022009 -4.004892 180
197 dense 8192 1024 8.000000 3.001499 0.025177 -3.224427 109
198 dense 29568 8192 3.609375 5.728819 0.028035 -4.115219 775
199 dense 29568 8192 3.609375 5.533282 0.021632 -3.570532 225
200 dense 29568 8192 3.609375 6.025001 0.024246 -3.777515 159 under-trained
201 dense 8192 8192 1.000000 2.863272 0.030219 -2.084958 380
202 dense 8192 8192 1.000000 4.038220 0.016115 -3.456855 159
203 dense 8192 1024 8.000000 3.973907 0.032216 -5.803849 112
204 dense 8192 8192 1.000000 4.265401 0.013096 -3.913777 172
205 dense 29568 8192 3.609375 6.020698 0.030025 -4.561487 735 under-trained
206 dense 8192 1024 8.000000 3.133322 0.033874 -3.455852 117
207 dense 8192 8192 1.000000 3.004861 0.030249 -2.141427 417
208 dense 8192 1024 8.000000 3.680810 0.030035 -5.648988 203
209 dense 29568 8192 3.609375 5.962175 0.021789 -3.633818 182
210 dense 29568 8192 3.609375 5.587436 0.021926 -3.555328 245
211 dense 8192 8192 1.000000 3.068440 0.031283 -2.257210 380
212 dense 8192 1024 8.000000 4.640203 0.049508 -7.795924 142
213 dense 8192 8192 1.000000 4.809979 0.020418 -5.074538 133
214 dense 29568 8192 3.609375 6.359579 0.034685 -4.866034 726 under-trained
215 dense 29568 8192 3.609375 5.606547 0.014857 -3.442342 267
216 dense 29568 8192 3.609375 5.958918 0.018005 -3.521398 202
217 dense 8192 1024 8.000000 3.405367 0.029366 -4.054867 85
218 dense 8192 8192 1.000000 5.084304 0.027834 -4.941816 182
219 dense 29568 8192 3.609375 5.793462 0.017885 -3.489381 280
220 dense 8192 1024 8.000000 3.458614 0.027714 -3.998341 94
221 dense 8192 8192 1.000000 3.284339 0.030366 -2.932656 355
222 dense 8192 1024 8.000000 5.971571 0.037500 -9.936261 74
223 dense 29568 8192 3.609375 6.614101 0.037581 -5.129158 711 under-trained
224 dense 29568 8192 3.609375 6.003142 0.018726 -3.423807 257 under-trained
225 dense 29568 8192 3.609375 6.165956 0.021741 -3.328430 267 under-trained
226 dense 8192 1024 8.000000 4.342006 0.017182 -6.673474 140
227 dense 8192 8192 1.000000 4.516134 0.023373 -4.281800 178
228 dense 8192 1024 8.000000 3.377677 0.023559 -4.033008 123
229 dense 29568 8192 3.609375 5.844669 0.021000 -3.323622 333
230 dense 29568 8192 3.609375 4.835171 0.032722 -3.883440 57
231 dense 8192 8192 1.000000 3.318263 0.030467 -2.998415 374
232 dense 8192 8192 1.000000 6.855633 0.021811 -8.010845 117 under-trained
233 dense 8192 1024 8.000000 8.806989 0.029469 -16.196474 45 under-trained
234 dense 29568 8192 3.609375 4.960306 0.037291 -4.044690 53
235 dense 29568 8192 3.609375 5.987852 0.017892 -3.497888 314
236 dense 29568 8192 3.609375 6.247478 0.021097 -3.440525 252 under-trained
237 dense 8192 1024 8.000000 3.706849 0.038750 -4.994055 71
238 dense 8192 8192 1.000000 3.356367 0.032761 -3.504270 421
239 dense 29568 8192 3.609375 7.369249 0.046042 -6.207442 672 under-trained
240 dense 8192 8192 1.000000 6.362737 0.019539 -7.409461 197 under-trained
241 dense 8192 8192 1.000000 3.182913 0.029647 -3.210478 565
242 dense 29568 8192 3.609375 6.151834 0.020223 -3.556126 332 under-trained
243 dense 29568 8192 3.609375 6.411627 0.021115 -3.407685 264 under-trained
244 dense 8192 1024 8.000000 3.433342 0.034614 -4.379721 95
245 dense 8192 1024 8.000000 7.316155 0.030072 -12.328625 61 under-trained
246 dense 8192 1024 8.000000 7.336053 0.026958 -12.825407 79 under-trained
247 dense 8192 8192 1.000000 6.684094 0.018974 -8.683690 141 under-trained
248 dense 29568 8192 3.609375 6.207242 0.022459 -3.756718 355 under-trained
249 dense 8192 8192 1.000000 3.405724 0.032076 -3.655428 502
250 dense 8192 1024 8.000000 3.637269 0.022154 -5.021715 107
251 dense 29568 8192 3.609375 5.318140 0.043366 -4.496562 51
252 dense 29568 8192 3.609375 6.449903 0.022747 -3.647018 289 under-trained
253 dense 8192 1024 8.000000 3.779149 0.029950 -5.379318 90
254 dense 29568 8192 3.609375 6.321151 0.023338 -3.865335 354 under-trained
255 dense 29568 8192 3.609375 6.598842 0.018714 -3.784489 276 under-trained
256 dense 29568 8192 3.609375 7.758475 0.040064 -6.663900 568 under-trained
257 dense 8192 8192 1.000000 8.594081 0.022811 -11.398703 83 under-trained
258 dense 8192 8192 1.000000 3.455079 0.032008 -3.829317 543
259 dense 8192 1024 8.000000 9.486324 0.106792 -17.708741 109 under-trained
260 dense 8192 8192 1.000000 3.356535 0.027720 -3.275654 449
261 dense 29568 8192 3.609375 6.391044 0.015999 -3.660449 301 under-trained
262 dense 29568 8192 3.609375 6.160122 0.021043 -3.710287 368 under-trained
263 dense 29568 8192 3.609375 5.430728 0.039280 -4.632980 49
264 dense 8192 1024 8.000000 3.519996 0.024348 -4.763039 143
265 dense 8192 8192 1.000000 6.552956 0.030018 -7.824750 110 under-trained
266 dense 8192 1024 8.000000 5.643362 0.043042 -9.667298 110
267 dense 8192 8192 1.000000 3.334572 0.032246 -3.282944 434
268 dense 29568 8192 3.609375 6.416197 0.014029 -3.777592 294 under-trained
269 dense 8192 8192 1.000000 6.328543 0.020994 -6.902082 115 under-trained
270 dense 8192 1024 8.000000 3.647925 0.032872 -4.718942 70
271 dense 8192 1024 8.000000 6.788996 0.040792 -12.058251 68 under-trained
272 dense 29568 8192 3.609375 7.829997 0.036291 -6.598440 541 under-trained
273 dense 29568 8192 3.609375 6.232005 0.015583 -3.807614 332 under-trained
274 dense 8192 8192 1.000000 7.776684 0.026709 -9.981578 79 under-trained
275 dense 29568 8192 3.609375 6.338627 0.010603 -3.904101 289 under-trained
276 dense 8192 1024 8.000000 3.431832 0.027471 -4.764604 127
277 dense 8192 1024 8.000000 7.256743 0.026815 -12.897006 66 under-trained
278 dense 8192 8192 1.000000 3.341492 0.031185 -3.736895 500
279 dense 29568 8192 3.609375 7.896898 0.031279 -6.609502 477 under-trained
280 dense 29568 8192 3.609375 6.442359 0.009772 -3.807812 259 under-trained
281 dense 8192 8192 1.000000 3.388238 0.026974 -3.353123 413
282 dense 8192 1024 8.000000 3.365818 0.041257 -4.488879 160
283 dense 29568 8192 3.609375 6.349881 0.013469 -3.997873 288 under-trained
284 dense 29568 8192 3.609375 7.862056 0.029542 -6.658272 469 under-trained
285 dense 8192 1024 8.000000 6.439098 0.018806 -10.368387 66 under-trained
286 dense 8192 8192 1.000000 6.139377 0.014851 -6.483910 97 under-trained
287 dense 29568 8192 3.609375 6.282549 0.009790 -4.091410 287 under-trained
288 dense 29568 8192 3.609375 8.372946 0.026331 -7.755527 374 under-trained
289 dense 29568 8192 3.609375 6.384340 0.011222 -4.233334 285 under-trained
290 dense 8192 1024 8.000000 3.045451 0.025266 -3.003281 149
291 dense 8192 8192 1.000000 3.110862 0.026877 -2.815633 503
292 dense 8192 8192 1.000000 5.814824 0.017826 -6.184275 143
293 dense 8192 1024 8.000000 5.543496 0.030056 -7.752589 110
294 dense 29568 8192 3.609375 6.566561 0.015747 -4.105220 184 under-trained
295 dense 8192 8192 1.000000 3.535227 0.027099 -3.619771 397
296 dense 29568 8192 3.609375 6.483499 0.009997 -4.401659 264 under-trained
297 dense 8192 1024 8.000000 3.470302 0.030444 -4.670660 189
298 dense 8192 1024 8.000000 7.373337 0.023184 -11.931973 67 under-trained
299 dense 29568 8192 3.609375 6.506892 0.008052 -4.186118 243 under-trained
300 dense 8192 8192 1.000000 7.075387 0.065029 -8.645099 178 under-trained
301 dense 29568 8192 3.609375 8.497237 0.021449 -7.901259 323 under-trained
302 dense 29568 8192 3.609375 6.491361 0.012651 -4.468970 257 under-trained
303 dense 8192 1024 8.000000 5.193879 0.029985 -7.349781 103
304 dense 8192 1024 8.000000 3.450263 0.024153 -4.333659 116
305 dense 29568 8192 3.609375 8.555081 0.011448 -8.028564 244 under-trained
306 dense 29568 8192 3.609375 6.434474 0.011591 -4.201717 284 under-trained
307 dense 8192 8192 1.000000 3.458837 0.025248 -2.953818 360
308 dense 8192 8192 1.000000 6.304297 0.027503 -6.035972 63 under-trained
309 dense 8192 1024 8.000000 3.402314 0.021381 -4.069497 152
310 dense 8192 8192 1.000000 5.934539 0.082993 -7.240266 246
311 dense 8192 8192 1.000000 3.436337 0.024619 -2.999166 422
312 dense 8192 1024 8.000000 5.237280 0.093740 -8.596369 221
313 dense 29568 8192 3.609375 6.266243 0.015714 -4.452266 322 under-trained
314 dense 29568 8192 3.609375 6.261051 0.012892 -4.172172 309 under-trained
315 dense 29568 8192 3.609375 8.689896 0.011341 -8.200303 166 under-trained
316 dense 29568 8192 3.609375 6.207742 0.014993 -4.020835 310 under-trained
317 dense 29568 8192 3.609375 6.327477 0.015561 -4.400488 291 under-trained
318 dense 8192 8192 1.000000 5.214470 0.054840 -6.446204 183
319 dense 8192 1024 8.000000 3.736087 0.025625 -5.301325 143
320 dense 8192 8192 1.000000 3.635038 0.030867 -3.138408 360
321 dense 8192 1024 8.000000 4.901360 0.082442 -8.957121 206
322 dense 29568 8192 3.609375 8.835440 0.014629 -8.449683 139 under-trained
323 dense 8192 8192 1.000000 6.198886 0.047734 -8.031464 140 under-trained
324 dense 8192 1024 8.000000 6.253787 0.078374 -11.796581 134 under-trained
325 dense 29568 8192 3.609375 9.185117 0.020804 -9.000313 85 under-trained
326 dense 8192 1024 8.000000 3.931832 0.029091 -5.836972 117
327 dense 8192 8192 1.000000 3.937831 0.031420 -3.862353 296
328 dense 29568 8192 3.609375 6.295550 0.017149 -4.416553 291 under-trained
329 dense 29568 8192 3.609375 6.339527 0.015784 -4.124822 226 under-trained
330 dense 29568 8192 3.609375 6.571300 0.022078 -4.591425 160 under-trained
331 dense 8192 1024 8.000000 4.135060 0.033232 -6.193311 100
332 dense 8192 8192 1.000000 6.146015 0.055461 -8.009201 120 under-trained
333 dense 29568 8192 3.609375 6.073459 0.021426 -3.927359 323 under-trained
334 dense 29568 8192 3.609375 8.847529 0.024954 -8.941760 161 under-trained
335 dense 8192 1024 8.000000 7.486082 0.090711 -14.401556 112 under-trained
336 dense 8192 8192 1.000000 4.124527 0.030431 -4.308462 288
337 dense 29568 8192 3.609375 9.097609 0.027453 -9.252797 140 under-trained
338 dense 29568 8192 3.609375 6.459072 0.022298 -4.159428 152 under-trained
339 dense 8192 1024 8.000000 3.965335 0.033920 -5.983892 164
340 dense 8192 8192 1.000000 4.149065 0.027762 -4.397002 270
341 dense 29568 8192 3.609375 6.810123 0.023105 -4.851352 111 under-trained
342 dense 8192 1024 8.000000 8.251783 0.092240 -15.662978 82 under-trained
343 dense 8192 8192 1.000000 6.870127 0.059939 -9.021263 146 under-trained
344 dense 29568 8192 3.609375 6.268571 0.015122 -3.875520 219 under-trained
345 dense 8192 8192 1.000000 6.271461 0.043511 -7.858445 89 under-trained
346 dense 8192 1024 8.000000 5.579423 0.078940 -10.165322 152
347 dense 29568 8192 3.609375 9.026809 0.025942 -9.141238 78 under-trained
348 dense 29568 8192 3.609375 6.152906 0.015293 -3.519422 228 under-trained
349 dense 8192 1024 8.000000 4.159090 0.025601 -6.200448 130
350 dense 8192 8192 1.000000 4.376336 0.034441 -4.853776 249
351 dense 29568 8192 3.609375 6.147518 0.022803 -3.438106 179 under-trained
352 dense 8192 8192 1.000000 4.257433 0.029606 -4.497694 260
353 dense 8192 8192 1.000000 6.811972 0.051715 -8.888111 98 under-trained
354 dense 8192 1024 8.000000 4.255541 0.025836 -6.584137 130
355 dense 29568 8192 3.609375 7.649576 0.040791 -7.867407 337 under-trained
356 dense 8192 1024 8.000000 5.226700 0.081403 -9.770444 179
357 dense 29568 8192 3.609375 6.524624 0.021471 -4.027873 114 under-trained
358 dense 8192 8192 1.000000 4.397067 0.029827 -4.782036 247
359 dense 8192 1024 8.000000 4.224897 0.035425 -6.596792 126
360 dense 29568 8192 3.609375 6.207143 0.021127 -3.741319 137 under-trained
361 dense 29568 8192 3.609375 6.324661 0.020634 -3.464732 114 under-trained
362 dense 29568 8192 3.609375 8.764725 0.020619 -8.924231 88 under-trained
363 dense 8192 8192 1.000000 5.213777 0.044254 -6.628735 171
364 dense 8192 1024 8.000000 6.599951 0.082156 -12.608893 107 under-trained
365 dense 8192 1024 8.000000 5.776206 0.103114 -10.993048 188
366 dense 29568 8192 3.609375 6.451387 0.012456 -4.091272 148 under-trained
367 dense 29568 8192 3.609375 7.869406 0.050800 -8.025314 367 under-trained
368 dense 8192 8192 1.000000 5.081655 0.062318 -6.552625 216
369 dense 8192 1024 8.000000 4.145362 0.043797 -6.528168 149
370 dense 8192 8192 1.000000 4.422475 0.038565 -4.446300 210
371 dense 29568 8192 3.609375 6.323951 0.020907 -3.602019 161 under-trained
372 dense 29568 8192 3.609375 6.262200 0.015790 -3.535286 185 under-trained
373 dense 8192 1024 8.000000 5.909569 0.088822 -11.429842 169
374 dense 29568 8192 3.609375 6.512134 0.012374 -4.135196 162 under-trained
375 dense 29568 8192 3.609375 8.503960 0.021820 -8.764474 138 under-trained
376 dense 8192 1024 8.000000 4.297030 0.031070 -6.802854 123
377 dense 8192 8192 1.000000 6.593909 0.041880 -8.524363 111 under-trained
378 dense 8192 8192 1.000000 4.239720 0.030315 -4.309731 277
379 dense 29568 8192 3.609375 6.269062 0.016575 -3.850890 207 under-trained
380 dense 8192 8192 1.000000 6.121357 0.031937 -7.837636 88 under-trained
381 dense 29568 8192 3.609375 8.274679 0.018145 -8.197714 117 under-trained
382 dense 8192 1024 8.000000 5.866981 0.078059 -11.416922 145
383 dense 29568 8192 3.609375 6.138289 0.016305 -3.402550 200 under-trained
384 dense 8192 1024 8.000000 4.928856 0.041437 -7.769524 52
385 dense 8192 8192 1.000000 4.301168 0.028615 -4.292393 261
386 dense 8192 8192 1.000000 7.186210 0.027899 -9.195140 59 under-trained
387 dense 29568 8192 3.609375 6.078402 0.016501 -3.372117 293 under-trained
388 dense 29568 8192 3.609375 7.910821 0.026954 -8.096294 157 under-trained
389 dense 29568 8192 3.609375 5.953085 0.012256 -2.873588 302
390 dense 8192 1024 8.000000 4.852518 0.029442 -7.657391 94
391 dense 8192 1024 8.000000 9.451109 0.086106 -18.131283 63 under-trained
392 dense 8192 8192 1.000000 4.472440 0.028894 -4.361953 249
393 dense 29568 8192 3.609375 5.970070 0.014243 -2.869762 333
394 dense 8192 8192 1.000000 4.505076 0.043017 -4.131448 307
395 dense 8192 1024 8.000000 5.292736 0.040299 -8.572054 74
396 dense 29568 8192 3.609375 7.735951 0.014611 -7.476239 239 under-trained
397 dense 29568 8192 3.609375 6.194276 0.014660 -3.482655 294 under-trained
398 dense 8192 8192 1.000000 5.963168 0.073092 -8.077420 185
399 dense 8192 1024 8.000000 8.516750 0.097904 -16.531268 101 under-trained
400 dense 29568 8192 3.609375 6.326094 0.016069 -3.690974 242 under-trained
401 dense 29568 8192 3.609375 6.130815 0.012556 -3.065065 272 under-trained
402 dense 8192 8192 1.000000 7.583212 0.027834 -9.834444 82 under-trained
403 dense 8192 1024 8.000000 4.907151 0.040269 -7.779466 55
404 dense 8192 1024 8.000000 7.791261 0.039316 -14.599289 53 under-trained
405 dense 8192 8192 1.000000 4.332929 0.034116 -4.193597 277
406 dense 29568 8192 3.609375 7.580893 0.019646 -7.703499 200 under-trained
407 dense 29568 8192 3.609375 6.159410 0.014420 -3.635983 237 under-trained
408 dense 29568 8192 3.609375 5.958324 0.014402 -3.077434 247
409 dense 8192 8192 1.000000 7.172762 0.042273 -9.888947 102 under-trained
410 dense 29568 8192 3.609375 7.877203 0.035925 -8.039241 293 under-trained
411 dense 8192 8192 1.000000 4.517845 0.036274 -4.242671 254
412 dense 8192 1024 8.000000 9.964095 0.072305 -19.140527 60 under-trained
413 dense 8192 1024 8.000000 4.792765 0.033375 -7.878812 109
414 dense 29568 8192 3.609375 6.532119 0.021896 -3.942458 135 under-trained
415 dense 29568 8192 3.609375 6.167874 0.020594 -3.179877 154 under-trained
416 dense 8192 8192 1.000000 6.574073 0.035969 -8.540991 109 under-trained
417 dense 8192 1024 8.000000 4.825393 0.024760 -7.655121 99
418 dense 8192 8192 1.000000 4.308071 0.033655 -4.197828 283
419 dense 8192 1024 8.000000 5.660782 0.078673 -11.147478 172
420 dense 29568 8192 3.609375 8.134923 0.047972 -7.990710 370 under-trained
421 dense 8192 8192 1.000000 6.098046 0.078647 -7.614308 215 under-trained
422 dense 8192 1024 8.000000 9.384174 0.084469 -18.134456 57 under-trained
423 dense 8192 8192 1.000000 4.744460 0.045953 -4.710358 265
424 dense 8192 1024 8.000000 4.819694 0.039600 -7.933818 140
425 dense 29568 8192 3.609375 6.722427 0.019560 -4.396103 174 under-trained
426 dense 29568 8192 3.609375 6.552483 0.017404 -3.688134 141 under-trained
427 dense 29568 8192 3.609375 9.783432 0.021369 -10.158258 93 under-trained
428 dense 8192 1024 8.000000 5.065414 0.029839 -8.137517 107
429 dense 8192 8192 1.000000 4.539517 0.036784 -4.687067 278
430 dense 8192 8192 1.000000 7.747065 0.024640 -9.594410 58 under-trained
431 dense 29568 8192 3.609375 6.593409 0.019277 -3.946841 178 under-trained
432 dense 29568 8192 3.609375 9.409483 0.017659 -9.586875 115 under-trained
433 dense 29568 8192 3.609375 6.963631 0.019184 -4.784658 153 under-trained
434 dense 8192 1024 8.000000 6.979867 0.101803 -13.397227 162 under-trained
435 dense 29568 8192 3.609375 6.401783 0.059364 -4.740833 486 under-trained
436 dense 8192 8192 1.000000 7.556702 0.024544 -9.496577 81 under-trained
437 dense 8192 1024 8.000000 7.121244 0.032736 -12.998710 65 under-trained
438 dense 29568 8192 3.609375 10.004478 0.018601 -10.464015 82 under-trained
439 dense 8192 1024 8.000000 4.792482 0.028530 -7.764198 115
440 dense 8192 8192 1.000000 4.590976 0.032011 -4.909231 264
441 dense 29568 8192 3.609375 7.158272 0.022300 -4.606661 138 under-trained
442 dense 29568 8192 3.609375 6.479223 0.054987 -4.975246 444 under-trained
443 dense 8192 8192 1.000000 8.139581 0.023651 -10.547770 68 under-trained
444 dense 8192 1024 8.000000 9.933803 0.051378 -18.749312 32 under-trained
445 dense 8192 8192 1.000000 4.434887 0.028076 -4.797507 314
446 dense 29568 8192 3.609375 8.945162 0.059006 -9.285994 303 under-trained
447 dense 29568 8192 3.609375 6.637111 0.041791 -4.550740 316 under-trained
448 dense 8192 1024 8.000000 4.793173 0.032272 -7.547350 113
449 dense 8192 8192 1.000000 7.580769 0.026087 -9.941647 83 under-trained
450 dense 29568 8192 3.609375 6.293310 0.032253 -4.894224 297 under-trained
451 dense 29568 8192 3.609375 8.160011 0.058215 -8.424337 405 under-trained
452 dense 8192 1024 8.000000 8.672425 0.048758 -16.502799 49 under-trained
453 dense 8192 8192 1.000000 4.559423 0.036503 -4.935243 279
454 dense 8192 1024 8.000000 4.845047 0.030005 -7.544970 105
455 dense 29568 8192 3.609375 5.992395 0.038288 -4.111480 391
456 dense 8192 8192 1.000000 4.140803 0.033620 -4.477547 368
457 dense 8192 1024 8.000000 9.535028 0.031556 -17.994623 56 under-trained
458 dense 29568 8192 3.609375 10.281775 0.019315 -10.684031 89 under-trained
459 dense 29568 8192 3.609375 6.247113 0.039674 -4.612771 385 under-trained
460 dense 8192 1024 8.000000 4.352673 0.022717 -6.622894 140
461 dense 8192 8192 1.000000 7.845351 0.029905 -9.948616 106 under-trained
462 dense 29568 8192 3.609375 5.911228 0.039823 -3.813357 435
463 dense 8192 1024 8.000000 8.113017 0.039293 -15.399575 70 under-trained
464 dense 8192 1024 8.000000 4.414944 0.023621 -6.885193 122
465 dense 8192 8192 1.000000 6.965365 0.032027 -8.496839 151 under-trained
466 dense 29568 8192 3.609375 6.451581 0.040438 -4.992940 367 under-trained
467 dense 8192 8192 1.000000 4.256690 0.029468 -4.383601 313
468 dense 29568 8192 3.609375 9.881136 0.016301 -10.157487 129 under-trained
469 dense 29568 8192 3.609375 6.035042 0.037724 -4.158274 438 under-trained
470 dense 8192 8192 1.000000 6.817606 0.037804 -7.840817 149 under-trained
471 dense 8192 1024 8.000000 4.659215 0.020387 -7.216354 140
472 dense 29568 8192 3.609375 7.320828 0.025826 -5.558162 108 under-trained
473 dense 29568 8192 3.609375 7.047629 0.026483 -4.751219 97 under-trained
474 dense 29568 8192 3.609375 8.404614 0.050036 -8.733327 299 under-trained
475 dense 8192 1024 8.000000 8.125075 0.087250 -14.690855 113 under-trained
476 dense 8192 8192 1.000000 4.129245 0.032073 -4.035853 376
477 dense 29568 8192 3.609375 6.794911 0.020933 -4.628513 154 under-trained
478 dense 29568 8192 3.609375 7.631837 0.046919 -7.751569 396 under-trained
479 dense 29568 8192 3.609375 7.113843 0.020231 -5.430574 159 under-trained
480 dense 8192 8192 1.000000 6.363198 0.029290 -5.722847 144 under-trained
481 dense 8192 8192 1.000000 4.295773 0.030028 -4.409640 311
482 dense 8192 1024 8.000000 4.493293 0.019588 -6.837529 149
483 dense 8192 1024 8.000000 7.089033 0.046951 -13.255598 93 under-trained
484 dense 8192 8192 1.000000 4.214357 0.031345 -4.282118 375
485 dense 29568 8192 3.609375 6.922151 0.019667 -5.288918 267 under-trained
486 dense 8192 1024 8.000000 7.573211 0.092436 -14.245291 119 under-trained
487 dense 29568 8192 3.609375 6.768347 0.016440 -4.553643 176 under-trained
488 dense 8192 8192 1.000000 9.737928 0.036363 -12.796346 48 under-trained
489 dense 8192 1024 8.000000 4.436036 0.035412 -6.848373 177
490 dense 29568 8192 3.609375 7.303503 0.043577 -7.435038 436 under-trained
491 dense 8192 8192 1.000000 10.867241 0.053396 -15.495260 79 under-trained
492 dense 8192 1024 8.000000 9.882081 0.085510 -18.719636 83 under-trained
493 dense 29568 8192 3.609375 7.074380 0.041472 -7.060099 449 under-trained
494 dense 29568 8192 3.609375 6.683572 0.014582 -4.147095 281 under-trained
495 dense 8192 8192 1.000000 4.403462 0.028148 -4.434370 351
496 dense 29568 8192 3.609375 6.951548 0.017402 -4.858113 304 under-trained
497 dense 8192 1024 8.000000 4.778734 0.022852 -7.533029 120
498 dense 29568 8192 3.609375 6.721008 0.013545 -4.061336 295 under-trained
499 dense 8192 1024 8.000000 4.508154 0.024606 -7.115140 127
500 dense 8192 8192 1.000000 4.015106 0.031072 -3.743385 414
501 dense 8192 8192 1.000000 7.519570 0.030160 -9.658975 110 under-trained
502 dense 8192 1024 8.000000 8.745096 0.030069 -16.127931 49 under-trained
503 dense 29568 8192 3.609375 6.812746 0.038802 -6.486949 430 under-trained
504 dense 29568 8192 3.609375 6.992632 0.016238 -4.553283 317 under-trained
505 dense 8192 8192 1.000000 7.817057 0.029991 -9.187040 95 under-trained
506 dense 8192 1024 8.000000 7.520175 0.028901 -13.301737 63 under-trained
507 dense 29568 8192 3.609375 6.635845 0.029940 -6.269880 405 under-trained
508 dense 29568 8192 3.609375 6.904780 0.015944 -4.489028 339 under-trained
509 dense 8192 1024 8.000000 4.364705 0.020491 -6.423519 157
510 dense 29568 8192 3.609375 6.694287 0.013063 -3.946849 310 under-trained
511 dense 8192 8192 1.000000 4.060723 0.029987 -3.805757 377
512 dense 8192 8192 1.000000 7.871563 0.032790 -10.225024 80 under-trained
513 dense 29568 8192 3.609375 6.796566 0.012841 -4.070822 339 under-trained
514 dense 29568 8192 3.609375 6.322607 0.021787 -6.079901 369 under-trained
515 dense 8192 1024 8.000000 4.171881 0.020211 -6.092150 183
516 dense 29568 8192 3.609375 7.115805 0.016958 -4.686602 317 under-trained
517 dense 8192 8192 1.000000 4.027275 0.029322 -3.797077 400
518 dense 8192 1024 8.000000 7.069161 0.027687 -12.710573 74 under-trained
519 dense 8192 1024 8.000000 4.392581 0.028656 -6.800634 119
520 dense 29568 8192 3.609375 6.875196 0.017176 -4.429164 418 under-trained
521 dense 8192 8192 1.000000 6.153852 0.025638 -6.926468 132 under-trained
522 dense 29568 8192 3.609375 6.238656 0.018600 -5.940056 335 under-trained
523 dense 8192 8192 1.000000 4.182547 0.030093 -3.826416 330
524 dense 29568 8192 3.609375 6.546927 0.017626 -3.879652 454 under-trained
525 dense 8192 1024 8.000000 8.237570 0.038813 -14.795999 40 under-trained
526 dense 29568 8192 3.609375 6.260725 0.020527 -3.735457 540 under-trained
527 dense 29568 8192 3.609375 6.635875 0.021969 -4.410154 492 under-trained
528 dense 29568 8192 3.609375 5.708011 0.017289 -4.893795 445
529 dense 8192 8192 1.000000 4.105511 0.026819 -3.701795 323
530 dense 8192 8192 1.000000 5.774664 0.031080 -6.797688 176
531 dense 8192 1024 8.000000 4.514576 0.022340 -7.037182 130
532 dense 8192 1024 8.000000 5.405372 0.024424 -9.066992 132
533 dense 8192 8192 1.000000 4.023195 0.030664 -3.911074 375
534 dense 8192 1024 8.000000 5.687624 0.016919 -9.683705 114
535 dense 29568 8192 3.609375 5.660349 0.016157 -4.755144 425
536 dense 8192 8192 1.000000 5.576613 0.024592 -5.727579 142
537 dense 8192 1024 8.000000 4.563764 0.029688 -6.971115 131
538 dense 29568 8192 3.609375 6.223441 0.022269 -3.559677 536 under-trained
539 dense 29568 8192 3.609375 6.670758 0.026594 -4.402301 489 under-trained
540 dense 29568 8192 3.609375 5.314770 0.012406 -3.931729 475
541 dense 8192 1024 8.000000 4.245318 0.036261 -7.224032 144
542 dense 29568 8192 3.609375 5.977360 0.022687 -3.122151 601
543 dense 8192 1024 8.000000 4.416177 0.026915 -6.977972 144
544 dense 29568 8192 3.609375 6.385383 0.026656 -3.866470 570 under-trained
545 dense 8192 8192 1.000000 4.052779 0.029361 -3.717902 294
546 dense 8192 8192 1.000000 4.272697 0.017725 -3.405854 187
547 dense 29568 8192 3.609375 5.966415 0.028270 -3.281130 625
548 dense 8192 1024 8.000000 4.352510 0.019439 -7.055823 110
549 dense 8192 8192 1.000000 4.312826 0.019532 -4.359200 129
550 dense 29568 8192 3.609375 5.681086 0.020156 -2.587402 601
551 dense 29568 8192 3.609375 4.701023 0.012735 -2.803528 454
552 dense 8192 1024 8.000000 4.522851 0.042054 -6.916173 90
553 dense 8192 8192 1.000000 4.008090 0.041888 -3.223902 360
554 dense 8192 1024 8.000000 4.004017 0.017081 -6.054921 160
555 dense 8192 8192 1.000000 3.858489 0.016368 -3.168857 187
556 dense 8192 8192 1.000000 3.667649 0.063029 -2.285979 587
557 dense 8192 1024 8.000000 3.736707 0.022439 -5.221240 117
558 dense 29568 8192 3.609375 3.964508 0.015837 -1.196625 450
559 dense 29568 8192 3.609375 5.647464 0.021508 -2.641032 531
560 dense 29568 8192 3.609375 5.558989 0.015329 -2.281419 595