Qwen2.5-32B-Instruct


Find this model in the Qwen2.5 model summary


Qwen2.5-32B-Instruct Model Set Plots


Qwen2.5 Compared to Base Model Plots



Qwen2.5-32B-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 5120 5120 1.0 2.709885 0.020472 -3.835406 223
2 dense 27648 5120 5.4 3.606900 0.019187 -3.623911 324
3 dense 27648 5120 5.4 3.615404 0.024795 -2.836012 225
4 dense 27648 5120 5.4 3.677434 0.028558 -2.935092 227
5 dense 5120 1024 5.0 3.537941 0.033156 -7.611076 73
6 dense 5120 5120 1.0 2.727389 0.029834 -4.446820 168
7 dense 5120 1024 5.0 2.580847 0.023581 -4.912199 224
8 dense 27648 5120 5.4 2.658585 0.042035 -1.193044 391
9 dense 5120 5120 1.0 1.653038 0.038062 -3.119952 346 over-trained
10 dense 5120 1024 5.0 2.376466 0.039156 -4.613495 33
11 dense 27648 5120 5.4 2.479336 0.028967 -2.688001 222
12 dense 27648 5120 5.4 2.265406 0.022597 -2.571658 236
13 dense 5120 1024 5.0 1.610115 0.032426 -3.496406 208 over-trained
14 dense 5120 5120 1.0 2.164042 0.024616 -2.162439 82
15 dense 27648 5120 5.4 3.216457 0.034672 6.328363 90
16 dense 5120 1024 5.0 1.600253 0.027611 -3.281041 407 over-trained
17 dense 27648 5120 5.4 2.900447 0.029855 -2.418792 654
18 dense 5120 1024 5.0 2.509734 0.024295 -4.686645 79
19 dense 5120 5120 1.0 2.390893 0.048807 -3.902685 47
20 dense 27648 5120 5.4 2.832379 0.033574 8.607668 192
21 dense 5120 5120 1.0 2.401697 0.014907 -2.740983 125
22 dense 27648 5120 5.4 2.688134 0.017580 -1.946717 221
23 dense 27648 5120 5.4 3.160907 0.026188 -2.697859 708
24 dense 27648 5120 5.4 2.971455 0.024842 -1.924656 215
25 dense 5120 1024 5.0 2.000682 0.041587 -4.269874 202
26 dense 5120 5120 1.0 2.631533 0.019611 -3.310968 105
27 dense 5120 5120 1.0 2.136637 0.047882 -3.350711 282
28 dense 5120 1024 5.0 2.578039 0.017612 -5.005184 120
29 dense 5120 5120 1.0 2.856721 0.015373 -3.754691 114
30 dense 5120 5120 1.0 3.308624 0.040602 -5.074505 27
31 dense 5120 1024 5.0 2.834541 0.025370 -5.678894 114
32 dense 5120 1024 5.0 2.063685 0.034607 -4.050846 174
33 dense 27648 5120 5.4 3.512475 0.019548 -2.901136 629
34 dense 27648 5120 5.4 2.757134 0.026433 -1.869543 308
35 dense 27648 5120 5.4 2.666231 0.028823 -1.984704 323
36 dense 27648 5120 5.4 3.627273 0.013730 -3.450385 618
37 dense 27648 5120 5.4 2.849296 0.013114 -2.059650 559
38 dense 27648 5120 5.4 2.719615 0.023084 -2.179532 476
39 dense 5120 1024 5.0 2.421397 0.022107 -4.661115 166
40 dense 5120 5120 1.0 2.757265 0.008294 -3.922048 197
41 dense 5120 5120 1.0 2.338002 0.019046 -3.060673 370
42 dense 5120 1024 5.0 2.766306 0.022092 -4.904097 167
43 dense 27648 5120 5.4 4.367421 0.036440 8.259259 511
44 dense 5120 1024 5.0 2.356124 0.018071 -4.885019 176
45 dense 5120 5120 1.0 2.646113 0.015832 -3.979361 171
46 dense 5120 5120 1.0 2.304110 0.020689 -3.041125 341
47 dense 5120 1024 5.0 2.797909 0.020285 -5.386395 118
48 dense 27648 5120 5.4 3.567456 0.015601 -3.576926 701
49 dense 27648 5120 5.4 2.956098 0.010537 9.242445 877
50 dense 5120 5120 1.0 2.355302 0.018236 -3.165501 409
51 dense 27648 5120 5.4 3.067980 0.007459 -2.702699 220
52 dense 27648 5120 5.4 3.573522 0.005638 -3.806160 396
53 dense 5120 5120 1.0 2.625998 0.012243 -3.961396 249
54 dense 5120 1024 5.0 2.441835 0.019317 -4.170630 170
55 dense 27648 5120 5.4 3.408475 0.012109 -2.769446 677
56 dense 5120 1024 5.0 2.856771 0.014692 -5.545235 112
57 dense 5120 1024 5.0 2.408349 0.015651 -4.639905 187
58 dense 27648 5120 5.4 3.120606 0.010092 -2.714071 489
59 dense 27648 5120 5.4 3.453180 0.017247 -2.968935 774
60 dense 27648 5120 5.4 3.483353 0.008251 -3.774088 413
61 dense 5120 5120 1.0 2.314475 0.015122 -3.170793 474
62 dense 5120 1024 5.0 2.805738 0.019102 -5.492232 153
63 dense 5120 5120 1.0 2.644004 0.015035 -3.846926 193
64 dense 27648 5120 5.4 3.594630 0.010603 -4.644772 411
65 dense 5120 5120 1.0 2.896106 0.016247 -4.706822 152
66 dense 27648 5120 5.4 3.098063 0.012802 -2.289152 682
67 dense 5120 1024 5.0 2.449021 0.016823 -5.260009 196
68 dense 27648 5120 5.4 3.238383 0.017406 -2.318814 802
69 dense 5120 5120 1.0 2.361409 0.016773 -3.287676 455
70 dense 5120 1024 5.0 3.139642 0.015599 -6.579938 114
71 dense 5120 1024 5.0 2.665693 0.024594 -5.446752 245
72 dense 5120 5120 1.0 3.081241 0.014952 -4.964253 133
73 dense 5120 5120 1.0 2.544453 0.015852 -3.571079 436
74 dense 27648 5120 5.4 3.114248 0.030671 8.945696 1641
75 dense 5120 1024 5.0 3.085133 0.015833 -6.082795 131
76 dense 27648 5120 5.4 8.710219 0.035167 16.981571 176 under-trained
77 dense 27648 5120 5.4 3.685010 0.008380 -5.254683 282
78 dense 5120 5120 1.0 3.097587 0.024087 -5.067402 98
79 dense 5120 5120 1.0 2.343855 0.017264 -3.415341 443
80 dense 5120 1024 5.0 3.353015 0.019705 -7.164024 68
81 dense 27648 5120 5.4 3.710138 0.006503 -5.243679 352
82 dense 27648 5120 5.4 3.077904 0.007512 -2.483099 671
83 dense 27648 5120 5.4 3.008938 0.005326 -2.502663 524
84 dense 5120 1024 5.0 2.517811 0.023158 -4.959880 165
85 dense 27648 5120 5.4 3.811675 0.009473 -5.449971 374
86 dense 27648 5120 5.4 3.171163 0.006416 -2.440400 544
87 dense 27648 5120 5.4 3.125804 0.006291 -2.501252 451
88 dense 5120 1024 5.0 2.584264 0.020842 -5.583155 147
89 dense 5120 5120 1.0 3.095571 0.022298 -5.202564 119
90 dense 5120 5120 1.0 2.474023 0.022532 -3.626372 302
91 dense 5120 1024 5.0 3.375786 0.017904 -7.171033 92
92 dense 27648 5120 5.4 3.641848 0.009473 -4.987780 453
93 dense 27648 5120 5.4 3.209922 0.009103 -2.444821 645
94 dense 27648 5120 5.4 3.102409 0.007608 -2.479008 502
95 dense 5120 1024 5.0 2.608218 0.022213 -5.615495 151
96 dense 5120 5120 1.0 3.062334 0.026851 -5.204038 140
97 dense 5120 5120 1.0 2.468640 0.019323 -3.655433 321
98 dense 5120 1024 5.0 3.547773 0.019170 -7.704861 82
99 dense 27648 5120 5.4 9.050164 0.017748 16.685739 180 under-trained
100 dense 5120 1024 5.0 2.661224 0.026573 -5.850288 196
101 dense 5120 5120 1.0 3.183134 0.027874 -5.680512 120
102 dense 5120 5120 1.0 2.509899 0.018789 -3.748410 390
103 dense 5120 1024 5.0 3.400137 0.018209 -7.118459 86
104 dense 27648 5120 5.4 3.617394 0.007974 -4.873910 441
105 dense 27648 5120 5.4 3.833841 0.011428 11.249030 848
106 dense 5120 1024 5.0 3.662929 0.018742 -7.993858 82
107 dense 5120 5120 1.0 3.217069 0.033056 -5.766053 142
108 dense 5120 5120 1.0 2.483197 0.016720 -3.715326 341
109 dense 27648 5120 5.4 3.072750 0.007897 -2.441898 302
110 dense 27648 5120 5.4 3.149292 0.009164 -2.320749 651
111 dense 27648 5120 5.4 3.605581 0.009514 -4.653764 486
112 dense 5120 1024 5.0 2.568362 0.021158 -5.492651 157
113 dense 5120 1024 5.0 2.429654 0.023802 -5.179040 199
114 dense 5120 1024 5.0 3.368927 0.023187 -7.053983 79
115 dense 5120 5120 1.0 2.427220 0.019469 -3.605230 304
116 dense 5120 5120 1.0 3.054764 0.028671 -4.995390 142
117 dense 27648 5120 5.4 3.098152 0.007124 -2.160701 581
118 dense 27648 5120 5.4 3.042341 0.006941 -2.244665 245
119 dense 27648 5120 5.4 3.537500 0.009625 -4.619394 499
120 dense 27648 5120 5.4 3.537860 0.007182 -4.532356 455
121 dense 5120 5120 1.0 2.711657 0.036921 -4.726068 303
122 dense 5120 1024 5.0 2.510607 0.025758 -5.495391 196
123 dense 5120 1024 5.0 3.385586 0.021701 -7.148262 73
124 dense 5120 5120 1.0 2.501590 0.020068 -3.641907 292
125 dense 27648 5120 5.4 3.015078 0.007259 -2.204687 285
126 dense 27648 5120 5.4 3.048890 0.005767 -2.137967 539
127 dense 5120 1024 5.0 2.571880 0.016896 -5.325307 156
128 dense 27648 5120 5.4 6.191279 0.048836 12.139514 366 under-trained
129 dense 27648 5120 5.4 3.427215 0.006059 -4.358868 439
130 dense 5120 1024 5.0 3.147023 0.030673 -6.262389 77
131 dense 5120 5120 1.0 2.442935 0.018672 -3.515603 311
132 dense 27648 5120 5.4 3.854396 0.011433 10.995909 720
133 dense 5120 5120 1.0 2.843858 0.028828 -4.354456 143
134 dense 27648 5120 5.4 2.917923 0.008402 -1.813386 361
135 dense 27648 5120 5.4 3.376831 0.006022 -4.242132 421
136 dense 27648 5120 5.4 2.968437 0.007615 -1.699498 585
137 dense 5120 1024 5.0 2.460843 0.018615 -4.940541 161
138 dense 5120 5120 1.0 2.808079 0.021712 -4.271130 124
139 dense 5120 5120 1.0 2.398282 0.017249 -3.351524 347
140 dense 5120 1024 5.0 2.829690 0.017501 -5.398176 109
141 dense 27648 5120 5.4 3.310454 0.005829 -4.107512 403
142 dense 27648 5120 5.4 2.877199 0.007160 -1.633539 589
143 dense 27648 5120 5.4 2.846356 0.007074 -1.715918 308
144 dense 5120 1024 5.0 2.514066 0.019810 -5.440261 201
145 dense 5120 1024 5.0 3.306123 0.028164 -6.643428 44
146 dense 5120 5120 1.0 2.917770 0.028326 -4.807132 136
147 dense 5120 5120 1.0 2.444738 0.021115 -3.361201 276
148 dense 27648 5120 5.4 2.813145 0.005635 -1.525410 566
149 dense 5120 5120 1.0 2.621596 0.030371 -3.935294 182
150 dense 27648 5120 5.4 2.769527 0.007158 -1.587919 361
151 dense 5120 1024 5.0 2.441079 0.022301 -4.921981 153
152 dense 27648 5120 5.4 3.250576 0.006299 -3.801090 393
153 dense 5120 5120 1.0 2.436277 0.025795 -3.349807 256
154 dense 5120 1024 5.0 2.936509 0.017690 -5.641341 87
155 dense 5120 5120 1.0 2.710027 0.029105 -4.073608 220
156 dense 5120 5120 1.0 2.412347 0.027029 -3.285260 283
157 dense 5120 1024 5.0 3.011611 0.019055 -5.772829 68
158 dense 27648 5120 5.4 3.324131 0.006048 -3.933828 396
159 dense 27648 5120 5.4 5.447724 0.051723 10.490754 354
160 dense 5120 1024 5.0 2.345494 0.028276 -4.559157 247
161 dense 27648 5120 5.4 3.684804 0.019245 10.435310 635
162 dense 27648 5120 5.4 2.789826 0.006594 -1.620463 433
163 dense 5120 5120 1.0 2.682153 0.033349 -4.173440 239
164 dense 5120 1024 5.0 3.068630 0.022111 -6.118813 78
165 dense 27648 5120 5.4 3.353236 0.006506 -3.875892 352
166 dense 27648 5120 5.4 2.833780 0.008233 -1.501439 718
167 dense 5120 1024 5.0 2.406403 0.024298 -5.180157 176
168 dense 5120 5120 1.0 2.404679 0.023538 -2.982157 280
169 dense 5120 5120 1.0 2.415064 0.022999 -3.196192 362
170 dense 27648 5120 5.4 2.834613 0.007988 -1.623120 673
171 dense 5120 1024 5.0 2.520176 0.022514 -5.390460 174
172 dense 27648 5120 5.4 2.834717 0.006240 -1.747809 401
173 dense 27648 5120 5.4 3.572221 0.009366 -4.623193 277
174 dense 5120 1024 5.0 3.194453 0.021362 -6.480451 96
175 dense 5120 5120 1.0 2.784282 0.033657 -4.483150 198
176 dense 5120 1024 5.0 3.045525 0.023555 -6.054419 98
177 dense 27648 5120 5.4 3.526632 0.006711 -4.434439 324
178 dense 5120 1024 5.0 2.576070 0.022557 -5.326836 186
179 dense 5120 5120 1.0 2.964015 0.039808 -4.764931 134
180 dense 27648 5120 5.4 2.814689 0.008249 -1.679749 343
181 dense 5120 5120 1.0 2.475945 0.024502 -3.257163 354
182 dense 27648 5120 5.4 2.810198 0.006349 -1.566906 599
183 dense 5120 5120 1.0 2.441896 0.020070 -3.307408 320
184 dense 5120 1024 5.0 2.921357 0.020634 -5.777613 134
185 dense 5120 5120 1.0 3.019324 0.033835 -4.806730 76
186 dense 5120 1024 5.0 2.494541 0.015907 -4.913893 179
187 dense 27648 5120 5.4 5.930083 0.035124 11.642756 149
188 dense 27648 5120 5.4 3.946741 0.027331 10.884938 492
189 dense 27648 5120 5.4 3.580675 0.014093 -4.733341 183
190 dense 5120 5120 1.0 2.414181 0.018262 -3.091042 323
191 dense 5120 5120 1.0 3.326174 0.035572 -5.020631 42
192 dense 5120 1024 5.0 3.198750 0.019116 -6.512454 80
193 dense 27648 5120 5.4 2.775280 0.005594 -1.424910 528
194 dense 27648 5120 5.4 2.776700 0.005654 -1.568303 339
195 dense 27648 5120 5.4 3.540270 0.010919 -4.572412 216
196 dense 5120 1024 5.0 2.468607 0.021573 -5.073682 173
197 dense 5120 5120 1.0 2.329062 0.020668 -2.926592 364
198 dense 27648 5120 5.4 2.778408 0.006709 -1.612158 473
199 dense 5120 1024 5.0 2.972747 0.015535 -5.638557 97
200 dense 27648 5120 5.4 2.780057 0.008741 -1.425929 720
201 dense 5120 5120 1.0 3.074118 0.025422 -4.550443 69
202 dense 5120 1024 5.0 2.368277 0.021081 -4.518243 181
203 dense 27648 5120 5.4 3.501710 0.015590 -4.434366 201
204 dense 27648 5120 5.4 2.772259 0.006465 -1.718625 467
205 dense 5120 5120 1.0 3.534294 0.036178 -5.883543 45
206 dense 5120 5120 1.0 2.420326 0.018571 -3.117746 361
207 dense 27648 5120 5.4 3.576351 0.015725 -4.679588 262
208 dense 5120 1024 5.0 2.529225 0.024372 -5.344060 188
209 dense 5120 1024 5.0 3.133949 0.017535 -6.387408 119
210 dense 27648 5120 5.4 2.756229 0.007019 -1.526275 743
211 dense 5120 1024 5.0 2.575505 0.027075 -5.605813 127
212 dense 5120 5120 1.0 2.441861 0.027064 -3.173412 350
213 dense 27648 5120 5.4 3.702478 0.013523 -4.769863 234
214 dense 5120 1024 5.0 3.438627 0.019966 -7.343318 113
215 dense 27648 5120 5.4 3.978371 0.022625 11.050323 428
216 dense 27648 5120 5.4 5.633057 0.048894 11.288775 301
217 dense 5120 5120 1.0 3.716923 0.038306 -6.229103 34
218 dense 5120 5120 1.0 3.615371 0.024641 -5.961100 57
219 dense 27648 5120 5.4 2.811103 0.006046 -1.779104 512
220 dense 27648 5120 5.4 3.671011 0.009201 -4.632209 271
221 dense 5120 1024 5.0 3.361274 0.016428 -7.082668 86
222 dense 5120 5120 1.0 2.493148 0.020477 -3.332954 297
223 dense 5120 1024 5.0 2.542622 0.020965 -5.253936 159
224 dense 27648 5120 5.4 2.788847 0.007375 -1.541165 774
225 dense 5120 5120 1.0 2.419631 0.019860 -3.343002 365
226 dense 5120 1024 5.0 3.365545 0.015520 -7.221766 100
227 dense 27648 5120 5.4 2.864297 0.009902 -1.632760 803
228 dense 27648 5120 5.4 2.884276 0.008727 -1.942207 368
229 dense 5120 1024 5.0 2.422369 0.023584 -5.042507 213
230 dense 27648 5120 5.4 3.647579 0.008236 -4.632398 301
231 dense 5120 5120 1.0 3.517949 0.024724 -5.794346 57
232 dense 5120 1024 5.0 2.546158 0.018662 -5.193647 178
233 dense 27648 5120 5.4 2.872550 0.009894 -1.941315 419
234 dense 5120 5120 1.0 2.734655 0.041600 -4.582490 264
235 dense 27648 5120 5.4 3.700286 0.007830 -4.865997 253
236 dense 5120 5120 1.0 2.462502 0.017906 -3.187629 321
237 dense 27648 5120 5.4 2.837381 0.007592 -1.654603 791
238 dense 5120 1024 5.0 3.341808 0.020796 -6.985421 105
239 dense 5120 1024 5.0 2.543281 0.017128 -5.287575 178
240 dense 5120 5120 1.0 3.283925 0.035314 -5.075692 60
241 dense 27648 5120 5.4 6.171230 0.028154 12.197038 295 under-trained
242 dense 5120 5120 1.0 2.432350 0.021882 -3.217916 293
243 dense 27648 5120 5.4 3.606714 0.009967 -4.351264 217
244 dense 5120 1024 5.0 3.326178 0.023879 -6.858572 83
245 dense 27648 5120 5.4 3.938824 0.017683 11.128617 593
246 dense 27648 5120 5.4 3.532032 0.009269 -4.160285 230
247 dense 5120 5120 1.0 2.414764 0.016952 -3.206956 333
248 dense 5120 1024 5.0 3.130235 0.021418 -6.332049 97
249 dense 27648 5120 5.4 2.802303 0.008576 -1.451054 846
250 dense 5120 1024 5.0 2.455979 0.017800 -4.981753 185
251 dense 27648 5120 5.4 2.817206 0.008217 -1.731886 448
252 dense 5120 5120 1.0 3.140082 0.032083 -4.984929 78
253 dense 5120 5120 1.0 3.455029 0.035983 -5.489060 48
254 dense 5120 5120 1.0 2.398821 0.019769 -3.189454 349
255 dense 5120 1024 5.0 2.448934 0.015428 -5.096672 211
256 dense 5120 1024 5.0 3.510558 0.020353 -7.430871 77
257 dense 27648 5120 5.4 2.785491 0.006426 -1.679627 440
258 dense 27648 5120 5.4 2.740400 0.008554 -1.385661 858
259 dense 27648 5120 5.4 3.455727 0.013662 -4.215694 221
260 dense 27648 5120 5.4 2.715041 0.006478 -1.571972 327
261 dense 5120 5120 1.0 3.229598 0.039884 -5.125427 52
262 dense 5120 1024 5.0 3.168386 0.020508 -6.479542 80
263 dense 27648 5120 5.4 3.342531 0.014053 -3.900856 207
264 dense 5120 1024 5.0 2.513759 0.021358 -5.227684 150
265 dense 27648 5120 5.4 2.680832 0.007194 -1.289879 866
266 dense 5120 5120 1.0 2.444546 0.026583 -3.135828 294
267 dense 5120 1024 5.0 3.292276 0.017771 -6.947066 95
268 dense 27648 5120 5.4 3.919232 0.010163 10.592912 677
269 dense 27648 5120 5.4 5.182218 0.020494 11.427381 442
270 dense 5120 1024 5.0 2.503929 0.025423 -5.297858 153
271 dense 5120 5120 1.0 2.398740 0.027872 -3.019473 320
272 dense 27648 5120 5.4 3.373313 0.012902 -3.912931 222
273 dense 5120 5120 1.0 3.246090 0.036958 -5.206035 84
274 dense 27648 5120 5.4 2.743485 0.006360 -1.440564 728
275 dense 5120 1024 5.0 2.534592 0.021093 -4.917106 161
276 dense 5120 5120 1.0 2.386410 0.028871 -2.868838 325
277 dense 5120 1024 5.0 3.231160 0.019559 -6.611509 120
278 dense 27648 5120 5.4 3.484802 0.012446 -3.917445 175
279 dense 27648 5120 5.4 2.807580 0.008380 -1.801905 360
280 dense 5120 5120 1.0 3.489044 0.029797 -4.853688 41
281 dense 27648 5120 5.4 3.815718 0.015399 -4.883736 127
282 dense 27648 5120 5.4 2.795950 0.005766 -1.639588 516
283 dense 27648 5120 5.4 2.894714 0.010988 -2.007883 268
284 dense 5120 1024 5.0 2.550292 0.028274 -5.508885 201
285 dense 5120 1024 5.0 3.750098 0.021571 -8.446458 62
286 dense 5120 5120 1.0 2.466559 0.030983 -3.177489 298
287 dense 5120 5120 1.0 2.563222 0.066872 -4.262862 359
288 dense 27648 5120 5.4 2.875668 0.009217 -1.901943 245
289 dense 27648 5120 5.4 2.756632 0.005521 -1.552789 425
290 dense 5120 1024 5.0 3.702252 0.026497 -8.030720 59
291 dense 27648 5120 5.4 3.736674 0.015761 -4.568474 114
292 dense 5120 5120 1.0 2.223170 0.072134 -3.616868 679
293 dense 5120 1024 5.0 2.643277 0.020071 -5.638093 159
294 dense 5120 5120 1.0 2.496900 0.029764 -3.110182 259
295 dense 5120 1024 5.0 2.646388 0.021586 -5.465136 144
296 dense 5120 5120 1.0 1.895059 0.068466 -2.751887 1209 over-trained
297 dense 5120 5120 1.0 2.528162 0.028822 -3.364657 212
298 dense 27648 5120 5.4 4.073099 0.008495 10.859401 546
299 dense 5120 1024 5.0 3.194834 0.017190 -6.649017 117
300 dense 27648 5120 5.4 5.333155 0.020177 10.573644 316
301 dense 27648 5120 5.4 3.616059 0.021095 -4.443471 113
302 dense 27648 5120 5.4 2.663551 0.006465 -1.481951 571
303 dense 5120 5120 1.0 2.424389 0.024597 -3.132665 329
304 dense 5120 1024 5.0 3.293917 0.022364 -7.071872 104
305 dense 5120 5120 1.0 1.782522 0.072533 -2.823706 1708 over-trained
306 dense 27648 5120 5.4 2.739631 0.009048 -1.798960 331
307 dense 27648 5120 5.4 3.487394 0.017506 -4.062975 126
308 dense 5120 1024 5.0 2.569868 0.025975 -5.357999 170
309 dense 5120 1024 5.0 2.499863 0.026123 -4.710948 148
310 dense 5120 5120 1.0 1.868515 0.073939 -2.370148 1316 over-trained
311 dense 5120 5120 1.0 2.346988 0.029271 -2.708446 311
312 dense 5120 1024 5.0 3.230212 0.015102 -6.900922 104
313 dense 27648 5120 5.4 3.513670 0.019644 -3.985155 125
314 dense 27648 5120 5.4 2.652858 0.008198 -1.361573 697
315 dense 27648 5120 5.4 2.722539 0.011427 -1.553844 408
316 dense 5120 1024 5.0 3.270122 0.018132 -6.918826 98
317 dense 27648 5120 5.4 3.611704 0.025647 -4.457476 128
318 dense 27648 5120 5.4 2.674945 0.007493 -1.540288 486
319 dense 5120 1024 5.0 2.566035 0.019595 -5.324929 170
320 dense 27648 5120 5.4 2.766154 0.011504 -1.774561 340
321 dense 5120 5120 1.0 3.453643 0.025481 -5.248990 72
322 dense 5120 5120 1.0 2.387066 0.027055 -2.995903 290
323 dense 27648 5120 5.4 4.035669 0.029807 -5.431044 86
324 dense 5120 1024 5.0 2.751564 0.026182 -5.906757 107
325 dense 27648 5120 5.4 5.318583 0.026092 10.958761 409
326 dense 5120 5120 1.0 2.465041 0.032270 -3.110092 267
327 dense 5120 5120 1.0 2.235037 0.075869 -3.900125 659
328 dense 27648 5120 5.4 4.178789 0.013155 11.095453 556
329 dense 5120 1024 5.0 3.680575 0.027034 -8.418889 99
330 dense 27648 5120 5.4 3.310278 0.057550 -4.501009 535
331 dense 27648 5120 5.4 2.889904 0.011050 -2.200260 299
332 dense 5120 5120 1.0 1.855030 0.079853 -3.172543 1521 over-trained
333 dense 5120 1024 5.0 3.781925 0.024681 -8.496251 48
334 dense 5120 1024 5.0 2.790833 0.028950 -6.006728 106
335 dense 27648 5120 5.4 2.769003 0.008410 -1.770459 354
336 dense 5120 5120 1.0 2.514392 0.029351 -3.488748 274
337 dense 27648 5120 5.4 2.828646 0.007076 -1.903505 334
338 dense 27648 5120 5.4 3.168862 0.056128 -4.352835 668
339 dense 5120 1024 5.0 2.718802 0.024596 -5.696249 140
340 dense 5120 5120 1.0 2.507746 0.024313 -3.340457 299
341 dense 5120 1024 5.0 3.596087 0.017943 -7.930522 89
342 dense 5120 5120 1.0 3.811689 0.020857 -5.647882 69
343 dense 27648 5120 5.4 2.957275 0.012164 -2.330991 280
344 dense 27648 5120 5.4 3.040566 0.010673 -2.498053 274
345 dense 27648 5120 5.4 2.914052 0.008220 -2.043085 316
346 dense 5120 1024 5.0 3.883455 0.024276 -8.814755 55
347 dense 27648 5120 5.4 3.399918 0.059372 -4.593500 596
348 dense 5120 5120 1.0 1.958512 0.081818 -3.435708 1443 over-trained
349 dense 5120 1024 5.0 2.706320 0.027357 -5.783219 203
350 dense 5120 5120 1.0 2.611051 0.028441 -3.618173 225
351 dense 27648 5120 5.4 4.520909 0.006947 12.406185 562
352 dense 5120 1024 5.0 2.791105 0.021585 -5.783955 151
353 dense 27648 5120 5.4 7.508827 0.025089 15.356831 159 under-trained
354 dense 27648 5120 5.4 4.417170 0.028234 -5.843730 78
355 dense 5120 5120 1.0 2.570792 0.034293 -3.530847 270
356 dense 5120 1024 5.0 3.912890 0.023843 -8.797535 53
357 dense 5120 5120 1.0 3.964296 0.025962 -6.565913 42
358 dense 27648 5120 5.4 3.176981 0.012792 -2.828065 298
359 dense 5120 5120 1.0 3.376300 0.042841 -5.564814 144
360 dense 5120 1024 5.0 2.695316 0.021024 -5.487701 172
361 dense 5120 5120 1.0 2.601250 0.020606 -3.715753 243
362 dense 27648 5120 5.4 4.158320 0.017323 -5.440439 126
363 dense 27648 5120 5.4 3.035346 0.009131 -2.275121 322
364 dense 5120 1024 5.0 3.864475 0.024028 -8.851167 75
365 dense 27648 5120 5.4 2.993944 0.008870 -2.165232 472
366 dense 5120 5120 1.0 2.502661 0.021618 -3.454431 282
367 dense 5120 1024 5.0 3.572608 0.027843 -7.726149 72
368 dense 5120 5120 1.0 3.214901 0.029263 -4.662053 130
369 dense 5120 1024 5.0 2.636498 0.019332 -5.389265 164
370 dense 27648 5120 5.4 4.079400 0.018634 -5.152826 166
371 dense 27648 5120 5.4 3.123964 0.016556 -2.714469 367
372 dense 5120 5120 1.0 3.533733 0.017642 -4.714091 99
373 dense 27648 5120 5.4 3.021801 0.006560 -2.249078 542
374 dense 5120 5120 1.0 2.487276 0.023962 -3.332954 274
375 dense 27648 5120 5.4 3.136775 0.014684 -2.739184 417
376 dense 5120 1024 5.0 3.291730 0.015552 -6.783657 110
377 dense 27648 5120 5.4 4.102092 0.017415 -5.050030 164
378 dense 5120 1024 5.0 2.596179 0.022061 -5.220756 166
379 dense 27648 5120 5.4 4.357811 0.013339 12.152600 791
380 dense 5120 5120 1.0 3.391903 0.022614 -4.809075 109
381 dense 5120 5120 1.0 2.567843 0.027987 -3.342447 305
382 dense 5120 1024 5.0 3.312417 0.025386 -6.920131 94
383 dense 27648 5120 5.4 4.123767 0.016879 -4.990734 161
384 dense 27648 5120 5.4 7.456811 0.034393 15.092796 250 under-trained
385 dense 5120 1024 5.0 2.790608 0.017404 -5.899896 181
386 dense 27648 5120 5.4 4.061109 0.013169 -4.806114 246
387 dense 27648 5120 5.4 3.126281 0.013868 -2.662314 490
388 dense 5120 5120 1.0 3.566673 0.028577 -5.382564 138
389 dense 5120 1024 5.0 3.493093 0.016791 -7.276295 105
390 dense 5120 1024 5.0 2.622733 0.019525 -5.265959 202
391 dense 27648 5120 5.4 3.030287 0.010804 -2.272891 638
392 dense 5120 5120 1.0 2.490586 0.018621 -3.340999 305
393 dense 5120 5120 1.0 3.313462 0.029755 -4.525080 172
394 dense 27648 5120 5.4 3.026761 0.010503 -2.289915 585
395 dense 27648 5120 5.4 3.136234 0.012826 -2.718036 450
396 dense 5120 5120 1.0 2.464906 0.023708 -3.165570 320
397 dense 5120 1024 5.0 2.587928 0.019422 -4.789167 218
398 dense 27648 5120 5.4 4.111948 0.013399 -4.767780 233
399 dense 5120 1024 5.0 3.099033 0.014232 -6.050179 148
400 dense 5120 5120 1.0 2.774343 0.019572 -3.048636 276
401 dense 5120 5120 1.0 2.336680 0.020132 -3.003723 408
402 dense 27648 5120 5.4 3.128289 0.009129 -2.663101 441
403 dense 27648 5120 5.4 3.015625 0.009363 -2.269587 582
404 dense 27648 5120 5.4 4.029599 0.015349 -4.505930 300
405 dense 5120 1024 5.0 2.497981 0.018665 -4.795317 231
406 dense 5120 1024 5.0 2.930241 0.021355 -5.504731 90
407 dense 5120 5120 1.0 2.409238 0.019915 -2.960204 360
408 dense 5120 5120 1.0 2.871466 0.031487 -3.411563 178
409 dense 27648 5120 5.4 4.674723 0.012715 12.949352 609
410 dense 5120 1024 5.0 2.578759 0.022199 -4.684148 207
411 dense 5120 1024 5.0 2.722804 0.010636 -4.915472 189
412 dense 27648 5120 5.4 9.003249 0.041932 19.078966 303 under-trained
413 dense 27648 5120 5.4 3.938815 0.011252 -4.280013 360
414 dense 27648 5120 5.4 3.802359 0.006314 -3.922397 432
415 dense 27648 5120 5.4 3.019239 0.011304 -2.324445 515
416 dense 27648 5120 5.4 2.886571 0.012086 -1.992990 668
417 dense 5120 1024 5.0 2.614829 0.021138 -5.266028 211
418 dense 5120 1024 5.0 3.120341 0.014104 -5.731834 132
419 dense 5120 5120 1.0 2.510178 0.023791 -3.084242 247
420 dense 5120 5120 1.0 3.342970 0.040215 -3.320638 139
421 dense 27648 5120 5.4 3.659617 0.008149 -3.491920 498
422 dense 5120 5120 1.0 2.981062 0.037307 -2.378325 279
423 dense 5120 5120 1.0 2.460654 0.022853 -2.958164 260
424 dense 5120 1024 5.0 3.043603 0.016131 -4.973654 165
425 dense 27648 5120 5.4 2.985106 0.012474 -2.102393 430
426 dense 27648 5120 5.4 2.827004 0.009413 -1.826723 574
427 dense 5120 1024 5.0 2.590093 0.017097 -5.235842 192
428 dense 5120 1024 5.0 2.687638 0.012542 -3.810816 195
429 dense 27648 5120 5.4 3.583456 0.008955 -2.816742 512
430 dense 5120 5120 1.0 2.697533 0.029924 -1.520583 251
431 dense 5120 1024 5.0 2.484281 0.017664 -4.350511 200
432 dense 5120 5120 1.0 2.331928 0.019639 -2.549463 338
433 dense 27648 5120 5.4 2.942069 0.012000 -1.494840 519
434 dense 27648 5120 5.4 2.794035 0.007494 -1.246544 576
435 dense 5120 5120 1.0 3.189871 0.035233 -1.943553 141
436 dense 5120 5120 1.0 2.502440 0.020879 -2.765992 240
437 dense 27648 5120 5.4 5.293105 0.038543 15.391023 853
438 dense 27648 5120 5.4 3.538705 0.020509 10.356287 114
439 dense 5120 1024 5.0 2.894354 0.029036 -4.070587 237
440 dense 5120 1024 5.0 2.539179 0.018458 -4.770707 210
441 dense 27648 5120 5.4 3.552495 0.023442 -2.340327 629
442 dense 27648 5120 5.4 3.183730 0.025266 -1.890742 714
443 dense 27648 5120 5.4 2.981510 0.023189 -1.278140 343
444 dense 5120 5120 1.0 2.290131 0.035955 -1.742007 418
445 dense 5120 1024 5.0 2.459440 0.026552 -3.245545 218
446 dense 5120 1024 5.0 2.324899 0.014592 -3.833394 189
447 dense 27648 5120 5.4 2.833992 0.014037 -0.947976 304
448 dense 5120 5120 1.0 2.444021 0.016065 -2.108884 149