Llama-3.1-70B


Find this model in the Llama model summary

Llama-3.1-70B Model Set Plots

Llama-3.1-70B Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 28672 8192 3.5 3.095252 0.014777 6.915071 408
2 dense 28672 8192 3.5 2.101083 0.020595 12.525099 2315
3 dense 28672 8192 3.5 2.101598 0.028922 12.521066 2333
4 dense 8192 1024 8.0 1.313218 0.018356 6.720873 503 over-trained
5 dense 8192 8192 1.0 2.399866 0.025383 3.904321 837
6 dense 8192 8192 1.0 1.484716 0.015076 8.282944 156 over-trained
7 dense 8192 1024 8.0 1.486253 0.010986 8.212374 754 over-trained
8 dense 28672 8192 3.5 3.013666 0.037130 8.921994 769
9 dense 28672 8192 3.5 4.171960 0.011393 7.651088 407
10 dense 8192 1024 8.0 1.565117 0.060086 5.939120 62 over-trained
11 dense 8192 1024 8.0 2.047533 0.068974 6.512559 87
12 dense 8192 8192 1.0 3.740747 0.014693 6.347203 161
13 dense 28672 8192 3.5 2.350067 0.014487 7.451720 1663
14 dense 8192 8192 1.0 2.055043 0.037296 7.482608 139
15 dense 8192 8192 1.0 1.483131 0.048576 4.379086 1317 over-trained
16 dense 8192 1024 8.0 4.173644 0.073221 11.788630 208
17 dense 8192 8192 1.0 3.470890 0.015519 5.527792 278
18 dense 28672 8192 3.5 2.538322 0.011559 9.349363 1410
19 dense 28672 8192 3.5 3.151554 0.047917 11.647354 906
20 dense 28672 8192 3.5 4.312139 0.008146 7.582202 616
21 dense 8192 1024 8.0 1.331296 0.060207 3.393426 687 over-trained
22 dense 28672 8192 3.5 3.801924 0.013719 7.171006 724
23 dense 28672 8192 3.5 3.021035 0.016423 11.599758 1051
24 dense 28672 8192 3.5 3.608028 0.050448 13.781781 979
25 dense 8192 1024 8.0 2.417908 0.055480 8.505322 107
26 dense 8192 8192 1.0 3.624302 0.020857 7.032971 243
27 dense 8192 8192 1.0 2.450021 0.040528 9.726412 142
28 dense 8192 1024 8.0 3.927700 0.086732 13.875277 279
29 dense 28672 8192 3.5 3.343499 0.017843 12.352804 1128
30 dense 28672 8192 3.5 4.341870 0.033664 15.970020 746
31 dense 8192 1024 8.0 7.576448 0.055416 5.269628 50 under-trained
32 dense 28672 8192 3.5 2.970892 0.055152 5.442892 1400
33 dense 8192 8192 1.0 2.867365 0.028571 4.830603 404
34 dense 8192 1024 8.0 1.567800 0.112944 3.543834 524 over-trained
35 dense 8192 8192 1.0 1.737498 0.065507 4.362792 1409 over-trained
36 dense 28672 8192 3.5 3.674502 0.051460 6.281839 846
37 dense 28672 8192 3.5 3.021709 0.024866 14.875487 1670
38 dense 28672 8192 3.5 3.609613 0.039902 17.752577 1333
39 dense 8192 1024 8.0 3.030269 0.028801 7.764836 92
40 dense 8192 8192 1.0 3.782541 0.044798 5.250284 161
41 dense 8192 8192 1.0 2.083566 0.057068 5.065404 580
42 dense 8192 1024 8.0 4.404878 0.067388 10.299459 171
43 dense 8192 1024 8.0 4.683657 0.062150 2.955489 163
44 dense 8192 8192 1.0 3.278973 0.033477 4.764137 357
45 dense 8192 1024 8.0 4.495674 0.028104 9.534760 46
46 dense 8192 8192 1.0 2.765629 0.047665 6.638823 283
47 dense 28672 8192 3.5 3.158517 0.004664 7.815000 970
48 dense 28672 8192 3.5 3.885643 0.018043 6.660087 480
49 dense 28672 8192 3.5 4.010555 0.029851 9.741902 918
50 dense 8192 8192 1.0 3.168828 0.035140 4.757261 228
51 dense 28672 8192 3.5 3.229756 0.007340 7.081097 782
52 dense 28672 8192 3.5 3.365124 0.034165 6.279154 933
53 dense 28672 8192 3.5 4.682025 0.014471 9.222320 369
54 dense 8192 8192 1.0 1.812721 0.062625 4.244593 1822 over-trained
55 dense 8192 1024 8.0 4.223578 0.045568 8.617273 38
56 dense 8192 1024 8.0 3.611433 0.099536 2.647643 199
57 dense 8192 8192 1.0 1.991222 0.065807 5.157672 975 over-trained
58 dense 28672 8192 3.5 3.126461 0.033501 5.553041 1312
59 dense 28672 8192 3.5 3.196533 0.011106 11.445811 841
60 dense 28672 8192 3.5 4.043771 0.024703 14.418608 781
61 dense 8192 1024 8.0 3.166062 0.035391 7.464609 74
62 dense 8192 8192 1.0 2.984291 0.033598 4.772602 312
63 dense 8192 1024 8.0 6.623069 0.060295 4.062231 65 under-trained
64 dense 8192 8192 1.0 2.718005 0.039879 7.065016 110
65 dense 8192 1024 8.0 7.324773 0.056664 4.516623 56 under-trained
66 dense 8192 1024 8.0 2.689156 0.041597 6.374689 80
67 dense 8192 8192 1.0 3.337610 0.037692 5.081177 204
68 dense 28672 8192 3.5 4.091166 0.030500 19.809990 491
69 dense 28672 8192 3.5 3.320004 0.017157 16.140623 460
70 dense 28672 8192 3.5 4.921420 0.021940 8.417758 142
71 dense 8192 8192 1.0 2.004297 0.058924 4.739465 1288
72 dense 8192 8192 1.0 3.326540 0.020580 4.727683 244
73 dense 8192 1024 8.0 2.641660 0.100034 5.328265 211
74 dense 8192 1024 8.0 5.639930 0.055652 3.118406 121
75 dense 28672 8192 3.5 3.090969 0.012319 6.821615 1059
76 dense 28672 8192 3.5 6.175212 0.017816 10.407124 98 under-trained
77 dense 28672 8192 3.5 4.288176 0.041435 8.852417 560
78 dense 28672 8192 3.5 2.686490 0.036045 4.765530 1583
79 dense 28672 8192 3.5 3.318243 0.019965 10.749061 800
80 dense 28672 8192 3.5 4.782192 0.042627 15.293433 576
81 dense 8192 1024 8.0 3.562360 0.053227 8.020733 28
82 dense 8192 8192 1.0 3.733347 0.023446 4.635373 492
83 dense 8192 8192 1.0 2.947376 0.020448 7.538872 141
84 dense 8192 1024 8.0 8.461487 0.047929 8.038222 91 under-trained
85 dense 8192 1024 8.0 5.291483 0.077140 3.212912 93
86 dense 28672 8192 3.5 2.701054 0.046131 4.788418 1601
87 dense 8192 8192 1.0 2.947117 0.027634 7.562959 152
88 dense 28672 8192 3.5 3.533638 0.026552 7.259579 567
89 dense 8192 1024 8.0 5.151899 0.060570 11.274172 54
90 dense 28672 8192 3.5 4.860995 0.044959 8.477422 379
91 dense 8192 8192 1.0 2.917795 0.040223 4.311374 414
92 dense 28672 8192 3.5 2.739010 0.058485 4.901659 1736
93 dense 28672 8192 3.5 3.762176 0.038626 7.888279 282
94 dense 28672 8192 3.5 5.263897 0.036621 9.530938 135
95 dense 8192 1024 8.0 2.026714 0.090332 4.334283 300
96 dense 8192 8192 1.0 2.933258 0.051870 4.044959 637
97 dense 8192 8192 1.0 2.541399 0.040454 6.487205 294
98 dense 8192 1024 8.0 5.927345 0.080936 2.411327 157
99 dense 8192 8192 1.0 3.143564 0.028253 4.291030 277
100 dense 8192 1024 8.0 4.317172 0.086391 1.791195 279
101 dense 8192 8192 1.0 2.011409 0.055823 4.933524 1233
102 dense 8192 1024 8.0 5.834236 0.028145 11.610699 40
103 dense 28672 8192 3.5 4.247024 0.034408 9.108951 142
104 dense 28672 8192 3.5 2.716121 0.040223 5.415334 1519
105 dense 28672 8192 3.5 5.475731 0.039317 9.574803 135
106 dense 28672 8192 3.5 3.640797 0.029897 8.060094 366
107 dense 8192 1024 8.0 1.934225 0.085809 3.874736 364 over-trained
108 dense 8192 8192 1.0 2.814082 0.062686 3.981980 780
109 dense 8192 8192 1.0 2.206008 0.049228 5.395425 635
110 dense 8192 1024 8.0 4.835402 0.063956 3.026984 100
111 dense 28672 8192 3.5 3.004883 0.043164 5.632411 1053
112 dense 28672 8192 3.5 4.545311 0.057001 7.748230 480
113 dense 8192 8192 1.0 3.029421 0.050773 7.513227 107
114 dense 8192 1024 8.0 6.987979 0.096448 3.154227 90 under-trained
115 dense 8192 8192 1.0 3.201971 0.047554 4.620698 268
116 dense 8192 1024 8.0 3.888157 0.073244 7.931734 63
117 dense 28672 8192 3.5 4.731402 0.033636 8.124773 332
118 dense 28672 8192 3.5 3.884804 0.023578 8.530628 261
119 dense 28672 8192 3.5 3.063307 0.043902 5.559069 1082
120 dense 28672 8192 3.5 3.109121 0.035627 5.648648 1224
121 dense 28672 8192 3.5 3.777272 0.023624 8.459849 383
122 dense 28672 8192 3.5 4.610315 0.036066 7.878116 505
123 dense 8192 1024 8.0 2.234810 0.090830 4.466506 307
124 dense 8192 8192 1.0 3.575214 0.019867 4.564943 353
125 dense 8192 8192 1.0 2.599039 0.043739 6.255382 353
126 dense 8192 1024 8.0 4.810542 0.077615 1.307246 356
127 dense 28672 8192 3.5 3.281746 0.012049 5.928281 1478
128 dense 8192 1024 8.0 12.755912 0.057620 3.615038 46 under-trained
129 dense 28672 8192 3.5 3.840588 0.012371 9.375143 280
130 dense 8192 8192 1.0 3.932609 0.040914 4.936120 212
131 dense 8192 1024 8.0 2.809235 0.105408 5.567189 188
132 dense 8192 8192 1.0 2.211162 0.043483 5.155782 792
133 dense 28672 8192 3.5 5.691789 0.028223 9.105711 232
134 dense 8192 8192 1.0 2.197928 0.052294 5.343441 944
135 dense 8192 1024 8.0 3.606705 0.090019 1.551686 438
136 dense 8192 1024 8.0 3.802898 0.092828 7.623655 82
137 dense 8192 8192 1.0 3.480529 0.077552 4.226487 580
138 dense 28672 8192 3.5 5.159225 0.023570 8.695437 309
139 dense 28672 8192 3.5 3.437238 0.005682 8.828914 592
140 dense 28672 8192 3.5 4.339620 0.012714 7.250146 1115
141 dense 28672 8192 3.5 4.131474 0.009149 6.739053 893
142 dense 28672 8192 3.5 3.958421 0.010615 9.629065 441
143 dense 28672 8192 3.5 5.917422 0.017838 10.200204 270
144 dense 8192 1024 8.0 2.782728 0.102854 5.839752 197
145 dense 8192 8192 1.0 4.088307 0.017229 5.004630 389
146 dense 8192 8192 1.0 2.599363 0.021674 6.322833 635
147 dense 8192 1024 8.0 3.234971 0.122176 1.562462 558
148 dense 28672 8192 3.5 6.557425 0.013425 10.783443 214 under-trained
149 dense 28672 8192 3.5 4.148474 0.005531 10.272119 336
150 dense 28672 8192 3.5 5.391640 0.026285 8.805796 114
151 dense 8192 8192 1.0 3.789171 0.012539 4.602412 538
152 dense 8192 8192 1.0 2.798762 0.027970 6.529284 317
153 dense 8192 1024 8.0 3.473541 0.077810 6.869584 162
154 dense 8192 1024 8.0 5.175984 0.099944 1.972900 240
155 dense 8192 8192 1.0 2.721159 0.012046 6.707782 695
156 dense 8192 8192 1.0 6.154553 0.028481 7.768379 113 under-trained
157 dense 8192 1024 8.0 3.052401 0.070821 6.160089 145
158 dense 8192 1024 8.0 4.366344 0.111384 1.660482 333
159 dense 28672 8192 3.5 4.413928 0.014183 11.165337 261
160 dense 28672 8192 3.5 4.156542 0.048179 6.708380 1043
161 dense 28672 8192 3.5 8.418059 0.026037 13.388991 131 under-trained
162 dense 28672 8192 3.5 5.997367 0.019580 9.512161 144
163 dense 28672 8192 3.5 4.516119 0.017194 11.421926 245
164 dense 28672 8192 3.5 7.294794 0.062314 11.910525 328 under-trained
165 dense 8192 1024 8.0 3.232972 0.095967 6.539000 132
166 dense 8192 8192 1.0 5.564820 0.031015 7.545944 123
167 dense 8192 8192 1.0 2.704561 0.013952 6.569064 600
168 dense 8192 1024 8.0 12.529298 0.116795 4.083640 80 under-trained
169 dense 8192 8192 1.0 2.409604 0.020892 6.468638 641
170 dense 8192 1024 8.0 3.410383 0.131820 1.341371 476
171 dense 8192 8192 1.0 3.793921 0.013297 5.657228 579
172 dense 8192 1024 8.0 2.165544 0.041729 5.072348 193
173 dense 28672 8192 3.5 8.886563 0.023450 14.923743 123 under-trained
174 dense 28672 8192 3.5 4.685893 0.014587 11.258644 340
175 dense 28672 8192 3.5 3.942006 0.049674 6.637093 648
176 dense 8192 8192 1.0 2.771541 0.012116 6.989337 672
177 dense 8192 8192 1.0 5.187064 0.010756 7.574865 234
178 dense 8192 1024 8.0 2.980251 0.083507 6.324106 113
179 dense 8192 1024 8.0 18.382372 0.124765 7.151504 46 under-trained
180 dense 28672 8192 3.5 4.807274 0.012413 11.579387 329
181 dense 28672 8192 3.5 3.064905 0.036428 5.179165 1408
182 dense 28672 8192 3.5 9.055362 0.013489 14.295947 135 under-trained
183 dense 28672 8192 3.5 4.436291 0.004308 10.658190 540
184 dense 28672 8192 3.5 7.951243 0.014098 12.157958 162 under-trained
185 dense 8192 1024 8.0 2.418397 0.075910 5.054729 280
186 dense 8192 8192 1.0 4.166446 0.014694 6.234900 337
187 dense 8192 8192 1.0 3.023078 0.018726 7.527923 255
188 dense 8192 1024 8.0 16.963084 0.053073 7.722067 33 under-trained
189 dense 28672 8192 3.5 2.973250 0.011783 5.334557 1415
190 dense 8192 8192 1.0 2.545780 0.036171 6.150556 562
191 dense 8192 1024 8.0 8.554871 0.026612 3.120734 59 under-trained
192 dense 8192 8192 1.0 3.536517 0.041867 5.350787 373
193 dense 28672 8192 3.5 3.483515 0.040417 6.386432 1197
194 dense 28672 8192 3.5 4.798378 0.012747 7.926156 706
195 dense 28672 8192 3.5 3.754568 0.012259 9.108099 1138
196 dense 8192 1024 8.0 2.321466 0.084182 4.816491 275
197 dense 28672 8192 3.5 3.459204 0.036142 6.428270 1111
198 dense 28672 8192 3.5 3.748467 0.008006 9.112498 1076
199 dense 28672 8192 3.5 4.704331 0.009921 8.038499 749
200 dense 8192 1024 8.0 2.739506 0.069829 5.563456 234
201 dense 8192 8192 1.0 3.336588 0.012417 5.346736 628
202 dense 8192 8192 1.0 2.609638 0.025415 6.239717 656
203 dense 8192 1024 8.0 10.170345 0.117612 5.705205 94 under-trained
204 dense 8192 1024 8.0 8.030073 0.039651 5.830380 73 under-trained
205 dense 28672 8192 3.5 4.945727 0.015079 8.041387 621
206 dense 28672 8192 3.5 3.413667 0.021774 6.229496 771
207 dense 8192 8192 1.0 2.817724 0.017456 6.793033 399
208 dense 8192 1024 8.0 2.842513 0.084567 5.794964 244
209 dense 8192 8192 1.0 3.588422 0.013161 5.817386 413
210 dense 28672 8192 3.5 3.865833 0.007009 9.575775 970
211 dense 28672 8192 3.5 3.326892 0.014135 6.364142 1084
212 dense 28672 8192 3.5 3.882081 0.004344 9.461353 855
213 dense 28672 8192 3.5 4.827839 0.017850 7.351818 658
214 dense 8192 1024 8.0 2.672061 0.080750 5.672222 204
215 dense 8192 8192 1.0 4.224782 0.030501 6.194596 144
216 dense 8192 8192 1.0 2.654891 0.045759 6.546962 490
217 dense 8192 1024 8.0 13.025319 0.035623 5.589959 34 under-trained
218 dense 8192 1024 8.0 10.402369 0.047023 3.084001 50 under-trained
219 dense 8192 8192 1.0 2.544428 0.036276 5.930162 553
220 dense 8192 8192 1.0 3.195559 0.013057 4.841611 404
221 dense 28672 8192 3.5 3.400759 0.017252 6.183112 1215
222 dense 28672 8192 3.5 4.445977 0.017033 7.220886 802
223 dense 28672 8192 3.5 3.652821 0.009164 8.991824 1170
224 dense 8192 1024 8.0 2.433793 0.090899 4.722656 330
225 dense 28672 8192 3.5 3.689186 0.004706 8.838504 859
226 dense 28672 8192 3.5 4.438520 0.017664 7.750622 755
227 dense 28672 8192 3.5 3.439876 0.015652 6.351616 1016
228 dense 8192 1024 8.0 3.898117 0.050966 8.352320 32
229 dense 8192 8192 1.0 2.610764 0.034278 6.629959 328
230 dense 8192 8192 1.0 4.747560 0.028234 7.752545 79
231 dense 8192 1024 8.0 8.195749 0.101517 4.552217 122 under-trained
232 dense 28672 8192 3.5 3.529721 0.007097 6.677831 1078
233 dense 28672 8192 3.5 3.645846 0.010296 18.934174 1159
234 dense 28672 8192 3.5 4.371754 0.011967 22.611208 881
235 dense 8192 1024 8.0 2.887057 0.098445 5.739291 311
236 dense 8192 8192 1.0 3.258988 0.017752 5.233665 358
237 dense 8192 8192 1.0 2.969460 0.020457 6.972186 379
238 dense 8192 1024 8.0 5.206267 0.075939 1.752923 189
239 dense 8192 8192 1.0 3.568983 0.017187 5.999614 297
240 dense 8192 1024 8.0 10.183202 0.036034 3.938206 75 under-trained
241 dense 8192 8192 1.0 2.734150 0.036333 6.623581 303
242 dense 28672 8192 3.5 4.615622 0.010988 7.476458 679
243 dense 28672 8192 3.5 3.653992 0.009793 9.536823 1136
244 dense 28672 8192 3.5 4.227319 0.004417 7.845885 778
245 dense 8192 1024 8.0 3.241651 0.081510 6.728947 172
246 dense 8192 1024 8.0 2.331799 0.090836 4.804109 277
247 dense 8192 8192 1.0 2.569954 0.030417 6.118267 391
248 dense 8192 1024 8.0 7.678658 0.039323 4.715895 67 under-trained
249 dense 28672 8192 3.5 4.353286 0.019351 7.378597 206
250 dense 28672 8192 3.5 3.673468 0.007799 9.402163 1048
251 dense 28672 8192 3.5 4.897539 0.024715 8.302330 618
252 dense 8192 8192 1.0 2.830096 0.024714 4.933905 1037
253 dense 8192 1024 8.0 3.179412 0.109745 1.224377 522
254 dense 8192 8192 1.0 2.499503 0.024538 6.280414 338
255 dense 8192 8192 1.0 5.292839 0.015747 7.746719 217
256 dense 28672 8192 3.5 4.902227 0.020947 8.997458 592
257 dense 28672 8192 3.5 3.689311 0.009458 8.985716 1142
258 dense 28672 8192 3.5 4.598232 0.015533 7.800671 137
259 dense 8192 1024 8.0 2.227602 0.044353 4.880602 274
260 dense 28672 8192 3.5 4.810932 0.020528 7.803256 100
261 dense 28672 8192 3.5 4.014986 0.006401 9.703982 804
262 dense 28672 8192 3.5 5.697288 0.040269 9.653261 483
263 dense 8192 1024 8.0 2.389284 0.049133 5.228301 322
264 dense 8192 8192 1.0 5.962680 0.049767 9.039651 242
265 dense 8192 8192 1.0 2.610138 0.023956 6.425565 372
266 dense 8192 1024 8.0 5.373002 0.109087 0.858762 307
267 dense 8192 8192 1.0 3.439391 0.044786 4.477644 942
268 dense 8192 1024 8.0 2.543255 0.098627 5.543668 298
269 dense 8192 8192 1.0 2.386379 0.036898 5.915993 1117
270 dense 28672 8192 3.5 4.051420 0.005787 9.973438 792
271 dense 28672 8192 3.5 6.975461 0.030227 11.309280 670 under-trained
272 dense 28672 8192 3.5 6.093634 0.049566 9.095797 528 under-trained
273 dense 8192 1024 8.0 12.119383 0.106388 3.029318 101 under-trained
274 dense 8192 8192 1.0 4.078700 0.036490 7.215070 785
275 dense 8192 8192 1.0 2.513421 0.031023 6.147352 895
276 dense 8192 1024 8.0 2.326872 0.082521 5.021902 277
277 dense 8192 1024 8.0 10.234338 0.061919 4.578699 74 under-trained
278 dense 28672 8192 3.5 4.064800 0.009289 9.773628 786
279 dense 28672 8192 3.5 8.390703 0.038737 12.865774 541 under-trained
280 dense 28672 8192 3.5 6.139010 0.056193 9.987543 509 under-trained
281 dense 28672 8192 3.5 4.157184 0.006314 9.697570 831
282 dense 28672 8192 3.5 7.439990 0.025090 12.690013 151 under-trained
283 dense 8192 1024 8.0 2.881899 0.084194 6.266342 194
284 dense 8192 8192 1.0 3.878703 0.016590 5.355389 674
285 dense 8192 8192 1.0 2.557304 0.017941 6.536845 900
286 dense 8192 1024 8.0 6.054113 0.026377 3.256799 151 under-trained
287 dense 28672 8192 3.5 7.675574 0.035158 11.400088 607 under-trained
288 dense 8192 8192 1.0 2.587791 0.016025 6.355847 892
289 dense 8192 8192 1.0 7.768363 0.057513 8.691525 244 under-trained
290 dense 8192 1024 8.0 2.290449 0.079101 5.013243 330
291 dense 8192 1024 8.0 7.446356 0.129531 1.731865 201 under-trained
292 dense 28672 8192 3.5 4.523675 0.011347 10.427693 624
293 dense 28672 8192 3.5 7.750127 0.041839 12.084518 635 under-trained
294 dense 28672 8192 3.5 6.705767 0.075736 10.516161 617 under-trained
295 dense 8192 8192 1.0 2.611279 0.020757 6.696696 708
296 dense 8192 8192 1.0 8.064154 0.018796 8.830455 174 under-trained
297 dense 8192 1024 8.0 3.080461 0.033704 7.047178 77
298 dense 8192 1024 8.0 6.614521 0.116265 2.329653 214 under-trained
299 dense 28672 8192 3.5 5.549573 0.021773 12.822712 167
300 dense 28672 8192 3.5 8.322379 0.041433 12.974935 538 under-trained
301 dense 28672 8192 3.5 6.451486 0.088406 9.116529 801 under-trained
302 dense 28672 8192 3.5 5.193095 0.016660 11.754199 195
303 dense 8192 1024 8.0 3.297763 0.039428 7.338404 57
304 dense 8192 8192 1.0 5.922697 0.026277 7.727476 397
305 dense 8192 8192 1.0 3.566736 0.018025 8.838104 85
306 dense 8192 1024 8.0 8.977634 0.075743 5.181340 104 under-trained
307 dense 28672 8192 3.5 9.559857 0.032348 13.262033 370 under-trained
308 dense 28672 8192 3.5 7.870205 0.091077 11.469736 554 under-trained
309 dense 8192 8192 1.0 2.740242 0.020355 6.469640 726
310 dense 8192 1024 8.0 6.704790 0.042148 4.029810 64 under-trained
311 dense 8192 8192 1.0 4.116056 0.015541 5.544238 342
312 dense 8192 1024 8.0 2.932187 0.067552 5.914845 204
313 dense 28672 8192 3.5 8.554705 0.033504 13.491561 304 under-trained
314 dense 28672 8192 3.5 4.578038 0.009596 10.325653 758
315 dense 28672 8192 3.5 8.936615 0.031972 13.079698 445 under-trained
316 dense 28672 8192 3.5 9.494299 0.026320 13.568495 356 under-trained
317 dense 28672 8192 3.5 5.201832 0.008982 11.799368 434
318 dense 28672 8192 3.5 10.727671 0.044800 16.112603 216 under-trained
319 dense 8192 1024 8.0 3.015020 0.035908 6.782151 109
320 dense 8192 8192 1.0 4.832309 0.009045 5.680346 484
321 dense 8192 8192 1.0 2.638571 0.021494 6.578040 605
322 dense 8192 1024 8.0 9.620711 0.043188 4.418569 99 under-trained
323 dense 28672 8192 3.5 5.902477 0.018827 13.551694 325
324 dense 28672 8192 3.5 9.129587 0.012182 12.163474 279 under-trained
325 dense 8192 1024 8.0 3.492873 0.123527 1.747490 476
326 dense 28672 8192 3.5 14.559521 0.043865 20.178374 132 under-trained
327 dense 8192 8192 1.0 17.749438 0.087072 16.955017 150 under-trained
328 dense 8192 1024 8.0 2.182920 0.035003 5.678500 71
329 dense 8192 8192 1.0 2.050750 0.032578 5.347182 766
330 dense 8192 8192 1.0 2.658781 0.023532 6.541444 866
331 dense 8192 8192 1.0 5.803014 0.012767 7.065341 363
332 dense 8192 1024 8.0 3.595564 0.058337 7.987196 66
333 dense 8192 1024 8.0 5.059159 0.018957 3.894583 176
334 dense 28672 8192 3.5 5.743783 0.016449 13.013227 364
335 dense 28672 8192 3.5 8.896080 0.011196 12.143514 227 under-trained
336 dense 28672 8192 3.5 13.518095 0.039850 19.328534 167 under-trained
337 dense 28672 8192 3.5 8.480637 0.015038 12.105192 327 under-trained
338 dense 28672 8192 3.5 4.717834 0.016041 10.475582 99
339 dense 28672 8192 3.5 10.198534 0.043080 15.576273 314 under-trained
340 dense 8192 1024 8.0 3.179493 0.025555 7.207166 88
341 dense 8192 8192 1.0 4.818338 0.015405 5.759116 552
342 dense 8192 8192 1.0 2.741353 0.017708 6.736177 738
343 dense 8192 1024 8.0 4.519550 0.056421 2.396870 251
344 dense 28672 8192 3.5 12.464070 0.046710 18.013024 232 under-trained
345 dense 8192 8192 1.0 4.572154 0.030516 5.216069 720
346 dense 28672 8192 3.5 5.741056 0.022009 12.773694 547
347 dense 28672 8192 3.5 7.853880 0.008922 11.241591 302 under-trained
348 dense 8192 1024 8.0 8.245890 0.035301 3.915704 94 under-trained
349 dense 8192 8192 1.0 2.639133 0.024417 6.488376 901
350 dense 8192 1024 8.0 3.350021 0.049026 7.380596 83
351 dense 28672 8192 3.5 7.259719 0.012591 10.665196 358 under-trained
352 dense 28672 8192 3.5 6.232658 0.026158 14.072821 471 under-trained
353 dense 28672 8192 3.5 17.110797 0.041576 22.618433 128 under-trained
354 dense 8192 1024 8.0 2.893239 0.033832 6.834158 51
355 dense 8192 8192 1.0 8.168797 0.017095 7.553460 236 under-trained
356 dense 8192 8192 1.0 2.468130 0.025443 6.146496 793
357 dense 8192 1024 8.0 14.200877 0.116450 6.564533 72 under-trained
358 dense 8192 8192 1.0 2.740707 0.018895 6.724082 753
359 dense 8192 8192 1.0 4.469293 0.034278 5.352484 107
360 dense 8192 1024 8.0 3.306420 0.030963 7.440251 55
361 dense 8192 1024 8.0 5.434633 0.030670 2.965743 179
362 dense 28672 8192 3.5 5.861407 0.021491 12.900195 575
363 dense 28672 8192 3.5 7.462978 0.011996 10.712797 331 under-trained
364 dense 28672 8192 3.5 15.358025 0.043654 20.864115 156 under-trained
365 dense 8192 8192 1.0 2.517385 0.027075 5.825767 1070
366 dense 8192 8192 1.0 4.479557 0.036372 5.633825 273
367 dense 8192 1024 8.0 2.522783 0.108258 5.019932 232
368 dense 8192 1024 8.0 8.154617 0.022645 4.515060 57 under-trained
369 dense 28672 8192 3.5 4.550653 0.020429 9.957048 71
370 dense 28672 8192 3.5 8.274363 0.014868 11.156993 272 under-trained
371 dense 28672 8192 3.5 10.684976 0.048641 15.904916 338 under-trained
372 dense 28672 8192 3.5 7.541138 0.014098 10.408879 307 under-trained
373 dense 28672 8192 3.5 6.019288 0.025716 13.382268 575 under-trained
374 dense 28672 8192 3.5 13.214001 0.050132 18.593808 234 under-trained
375 dense 8192 1024 8.0 4.057307 0.030950 8.911204 44
376 dense 8192 8192 1.0 7.215231 0.012864 7.255806 231 under-trained
377 dense 8192 8192 1.0 2.673159 0.023157 6.366512 941
378 dense 8192 1024 8.0 7.829076 0.060292 3.250486 104 under-trained
379 dense 8192 1024 8.0 14.004991 0.123465 4.753745 92 under-trained
380 dense 28672 8192 3.5 6.880886 0.013912 9.856004 301 under-trained
381 dense 8192 8192 1.0 2.373931 0.026069 5.821358 755
382 dense 8192 8192 1.0 6.105411 0.051666 6.478846 566 under-trained
383 dense 8192 1024 8.0 3.112670 0.039489 7.247702 39
384 dense 28672 8192 3.5 17.321154 0.042948 22.532484 146 under-trained
385 dense 28672 8192 3.5 6.976391 0.031112 15.316508 433 under-trained
386 dense 28672 8192 3.5 7.047988 0.012874 10.270803 253 under-trained
387 dense 28672 8192 3.5 6.550191 0.027480 14.409585 494 under-trained
388 dense 28672 8192 3.5 15.866000 0.048569 20.873555 182 under-trained
389 dense 8192 1024 8.0 3.159175 0.040182 7.275775 53
390 dense 8192 8192 1.0 3.883691 0.019080 7.649104 278
391 dense 8192 8192 1.0 2.461644 0.023980 6.195611 766
392 dense 8192 1024 8.0 8.649342 0.046204 7.548692 102 under-trained
393 dense 8192 8192 1.0 2.466561 0.016890 5.692056 1251
394 dense 8192 8192 1.0 4.438024 0.032750 5.615805 109
395 dense 8192 1024 8.0 2.494438 0.058143 4.774295 211
396 dense 8192 1024 8.0 3.377181 0.056599 1.937098 421
397 dense 28672 8192 3.5 5.591967 0.025957 12.443735 730
398 dense 28672 8192 3.5 7.752919 0.021554 11.268492 283 under-trained
399 dense 28672 8192 3.5 11.884071 0.047566 16.735529 298 under-trained
400 dense 28672 8192 3.5 7.626449 0.050738 10.731103 307 under-trained
401 dense 8192 1024 8.0 4.326955 0.054677 3.201179 317
402 dense 8192 8192 1.0 2.708908 0.018945 6.424692 855
403 dense 28672 8192 3.5 14.702225 0.049212 19.714837 217 under-trained
404 dense 8192 1024 8.0 2.575221 0.076268 5.523766 183
405 dense 28672 8192 3.5 6.293497 0.029369 13.949895 564 under-trained
406 dense 8192 8192 1.0 5.748147 0.031088 8.256506 428
407 dense 28672 8192 3.5 6.055701 0.057371 8.679784 565 under-trained
408 dense 28672 8192 3.5 7.339287 0.033535 16.069653 435 under-trained
409 dense 28672 8192 3.5 19.110692 0.053797 23.916848 140 under-trained
410 dense 8192 1024 8.0 2.555501 0.027033 5.895335 175
411 dense 8192 8192 1.0 3.187129 0.045835 5.171893 23
412 dense 8192 8192 1.0 2.420743 0.025571 5.895385 948
413 dense 8192 1024 8.0 4.933362 0.059323 3.544686 261
414 dense 8192 8192 1.0 5.432949 0.047752 8.079038 651
415 dense 8192 1024 8.0 4.968308 0.056779 3.902307 23
416 dense 8192 1024 8.0 2.748729 0.040518 6.541694 91
417 dense 8192 8192 1.0 2.524835 0.017398 6.208497 780
418 dense 28672 8192 3.5 6.633105 0.027790 15.143594 509 under-trained
419 dense 28672 8192 3.5 6.174302 0.054529 8.275652 456 under-trained
420 dense 28672 8192 3.5 17.631363 0.051457 23.230793 168 under-trained
421 dense 8192 1024 8.0 2.723385 0.073488 5.371040 220
422 dense 8192 8192 1.0 4.697209 0.027239 6.885168 593
423 dense 8192 8192 1.0 2.580174 0.016461 6.115986 1204
424 dense 8192 1024 8.0 3.237624 0.053763 3.264380 481
425 dense 28672 8192 3.5 6.641204 0.064537 8.776944 481 under-trained
426 dense 28672 8192 3.5 5.725830 0.025817 13.168055 707
427 dense 28672 8192 3.5 12.679919 0.052935 19.093278 292 under-trained
428 dense 8192 8192 1.0 2.629102 0.024331 6.383299 980
429 dense 8192 8192 1.0 10.692788 0.084144 10.001116 222 under-trained
430 dense 8192 1024 8.0 2.949319 0.040564 6.823795 59
431 dense 8192 1024 8.0 3.722678 0.055141 2.409524 420
432 dense 28672 8192 3.5 6.323001 0.031701 14.685707 598 under-trained
433 dense 28672 8192 3.5 5.489766 0.053589 7.406981 616
434 dense 28672 8192 3.5 15.680940 0.057728 21.322318 204 under-trained
435 dense 8192 8192 1.0 2.307631 0.022009 5.772038 623
436 dense 8192 8192 1.0 7.664317 0.087223 9.869997 515 under-trained
437 dense 8192 1024 8.0 2.032344 0.040044 5.344749 74
438 dense 8192 1024 8.0 6.594052 0.130995 3.874918 278 under-trained
439 dense 28672 8192 3.5 7.432859 0.032872 17.205676 454 under-trained
440 dense 28672 8192 3.5 4.719611 0.047113 6.765267 730
441 dense 28672 8192 3.5 20.507494 0.054920 25.957087 146 under-trained
442 dense 8192 1024 8.0 2.827935 0.026679 6.860067 94
443 dense 8192 8192 1.0 2.713819 0.022551 6.776995 507
444 dense 8192 1024 8.0 6.788402 0.078547 5.230043 183 under-trained
445 dense 28672 8192 3.5 4.700705 0.041533 7.155977 601
446 dense 28672 8192 3.5 6.831216 0.028878 16.301099 479 under-trained
447 dense 28672 8192 3.5 17.712567 0.062641 23.932434 200 under-trained
448 dense 8192 8192 1.0 4.499688 0.029745 5.606184 88
449 dense 8192 8192 1.0 2.552636 0.020513 6.033438 1182
450 dense 8192 1024 8.0 3.177196 0.050194 2.169071 527
451 dense 8192 8192 1.0 6.074483 0.023849 7.229672 240 under-trained
452 dense 8192 1024 8.0 2.639917 0.072167 5.538389 192
453 dense 28672 8192 3.5 14.270949 0.057550 20.995976 278 under-trained
454 dense 28672 8192 3.5 5.941442 0.019793 14.507968 568
455 dense 28672 8192 3.5 4.517755 0.054398 6.534710 1086
456 dense 28672 8192 3.5 4.329021 0.043958 5.943988 968
457 dense 28672 8192 3.5 6.113418 0.022740 15.151443 551 under-trained
458 dense 28672 8192 3.5 16.224579 0.060417 23.091659 238 under-trained
459 dense 8192 1024 8.0 2.715612 0.043117 6.794076 26
460 dense 8192 8192 1.0 2.279580 0.076961 4.319788 18
461 dense 8192 8192 1.0 2.604212 0.015590 6.563472 571
462 dense 8192 1024 8.0 8.305017 0.084066 6.382592 145 under-trained
463 dense 8192 8192 1.0 2.685755 0.013383 6.859823 674
464 dense 8192 8192 1.0 4.430334 0.017408 6.659010 193
465 dense 8192 1024 8.0 2.959462 0.038103 7.142638 57
466 dense 8192 1024 8.0 9.873583 0.038343 8.005779 59 under-trained
467 dense 28672 8192 3.5 7.229230 0.030926 17.099991 479 under-trained
468 dense 28672 8192 3.5 3.871286 0.030407 5.621657 1133
469 dense 28672 8192 3.5 19.073791 0.061936 25.494289 186 under-trained
470 dense 8192 8192 1.0 2.757128 0.016886 6.878999 1001
471 dense 8192 8192 1.0 4.644757 0.023655 5.600660 547
472 dense 8192 1024 8.0 3.626209 0.023013 8.102627 57
473 dense 8192 1024 8.0 10.052213 0.054134 5.833783 48 under-trained
474 dense 28672 8192 3.5 6.841529 0.023545 16.071979 479 under-trained
475 dense 28672 8192 3.5 3.768384 0.024156 5.547604 1178
476 dense 28672 8192 3.5 17.447536 0.060675 23.959370 218 under-trained
477 dense 28672 8192 3.5 6.134118 0.027916 14.993804 567 under-trained
478 dense 28672 8192 3.5 13.602444 0.059765 21.162157 327 under-trained
479 dense 8192 1024 8.0 2.655874 0.058272 5.592661 218
480 dense 8192 8192 1.0 6.464006 0.027777 7.497524 105 under-trained
481 dense 8192 8192 1.0 2.660846 0.017935 6.456888 1089
482 dense 8192 1024 8.0 3.123942 0.049327 2.232126 513
483 dense 28672 8192 3.5 3.891285 0.019435 5.790211 1243
484 dense 8192 8192 1.0 3.522464 0.011835 5.064037 830
485 dense 8192 1024 8.0 5.528257 0.033692 3.679626 186
486 dense 8192 1024 8.0 3.254809 0.033688 7.600841 61
487 dense 8192 8192 1.0 2.787468 0.011706 7.142319 832
488 dense 28672 8192 3.5 6.266611 0.028625 15.238849 586 under-trained
489 dense 28672 8192 3.5 3.732657 0.017532 5.885743 1352
490 dense 28672 8192 3.5 14.825829 0.063078 22.055577 289 under-trained
491 dense 28672 8192 3.5 3.563729 0.018185 5.697614 1486
492 dense 28672 8192 3.5 6.955001 0.020749 15.741886 496 under-trained
493 dense 28672 8192 3.5 14.556343 0.065097 20.718369 297 under-trained
494 dense 8192 1024 8.0 2.970864 0.034841 6.562082 187
495 dense 8192 8192 1.0 3.539682 0.016081 5.995902 612
496 dense 8192 8192 1.0 2.789724 0.016553 7.182649 775
497 dense 8192 1024 8.0 7.127680 0.023367 6.364786 131 under-trained
498 dense 28672 8192 3.5 3.825814 0.018383 6.061341 1235
499 dense 8192 1024 8.0 5.145255 0.098240 3.258004 328
500 dense 8192 8192 1.0 2.509045 0.024800 6.349333 1087
501 dense 28672 8192 3.5 12.633273 0.055950 19.929146 356 under-trained
502 dense 8192 1024 8.0 2.788507 0.064367 5.829941 212
503 dense 28672 8192 3.5 6.705543 0.029493 15.702672 565 under-trained
504 dense 8192 8192 1.0 4.470108 0.035737 6.739419 274
505 dense 8192 8192 1.0 2.415090 0.042945 6.062345 1355
506 dense 8192 8192 1.0 3.299729 0.016472 6.296666 460
507 dense 8192 1024 8.0 4.434320 0.033761 9.280049 39
508 dense 8192 1024 8.0 5.362522 0.050258 5.836246 135
509 dense 28672 8192 3.5 5.819190 0.027153 14.052181 625
510 dense 28672 8192 3.5 4.472432 0.014486 7.097246 852
511 dense 28672 8192 3.5 10.140068 0.047627 17.288179 455 under-trained
512 dense 28672 8192 3.5 4.592406 0.016810 7.003275 824
513 dense 28672 8192 3.5 5.849601 0.032125 14.342870 705
514 dense 28672 8192 3.5 4.424211 0.053223 7.666089 23
515 dense 8192 1024 8.0 1.930101 0.094984 4.062220 533 over-trained
516 dense 8192 8192 1.0 3.507472 0.019449 6.927541 260
517 dense 8192 8192 1.0 2.373431 0.014733 6.198206 1172
518 dense 8192 1024 8.0 2.214572 0.061557 2.031782 550
519 dense 28672 8192 3.5 4.399803 0.019136 6.920169 999
520 dense 28672 8192 3.5 8.413513 0.054082 15.378133 649 under-trained
521 dense 8192 1024 8.0 10.608433 0.081127 12.212839 121 under-trained
522 dense 28672 8192 3.5 5.597130 0.029884 13.658394 774
523 dense 8192 8192 1.0 3.416613 0.015240 6.291947 172
524 dense 8192 1024 8.0 2.524207 0.043337 5.308371 308
525 dense 8192 8192 1.0 2.590914 0.029955 6.558795 569
526 dense 8192 8192 1.0 2.526456 0.020584 6.278823 435
527 dense 8192 8192 1.0 3.379889 0.046383 5.517262 30
528 dense 8192 1024 8.0 2.385092 0.026447 4.829891 312
529 dense 8192 1024 8.0 12.661888 0.056401 8.585546 129 under-trained
530 dense 28672 8192 3.5 4.787719 0.028206 12.084706 908
531 dense 28672 8192 3.5 6.710972 0.021409 10.260047 448 under-trained
532 dense 28672 8192 3.5 4.398490 0.032929 8.449294 41
533 dense 28672 8192 3.5 5.960748 0.015397 9.184759 560
534 dense 28672 8192 3.5 4.968773 0.040412 14.169829 1076
535 dense 28672 8192 3.5 5.832979 0.045012 14.173499 1005
536 dense 8192 1024 8.0 2.469186 0.075751 5.206536 287
537 dense 8192 8192 1.0 3.097779 0.022330 5.960722 492
538 dense 8192 8192 1.0 2.416431 0.030599 6.392605 582
539 dense 8192 1024 8.0 4.084132 0.015609 4.627558 282
540 dense 8192 8192 1.0 5.343194 0.011909 8.488359 184
541 dense 28672 8192 3.5 3.749809 0.025713 8.197226 37
542 dense 28672 8192 3.5 4.384001 0.030241 11.230441 1174
543 dense 8192 8192 1.0 2.325572 0.011658 6.065593 1072
544 dense 8192 1024 8.0 3.077333 0.067888 2.835742 473
545 dense 8192 1024 8.0 2.686151 0.073414 5.576983 200
546 dense 28672 8192 3.5 5.602802 0.021757 8.946504 747
547 dense 8192 1024 8.0 3.841147 0.059421 3.099514 461
548 dense 8192 8192 1.0 3.813921 0.020606 6.098239 155
549 dense 8192 1024 8.0 3.722649 0.052673 8.180987 35
550 dense 8192 8192 1.0 2.372571 0.015653 6.367139 1048
551 dense 28672 8192 3.5 2.945139 0.017366 7.921387 78
552 dense 28672 8192 3.5 5.936113 0.027234 10.775428 718
553 dense 28672 8192 3.5 4.172102 0.027647 10.031321 1438
554 dense 8192 8192 1.0 2.351596 0.013274 6.702113 681
555 dense 28672 8192 3.5 4.113648 0.013948 7.962863 1039
556 dense 28672 8192 3.5 3.345635 0.027388 10.793211 1843
557 dense 28672 8192 3.5 3.416920 0.016150 10.170600 1653
558 dense 8192 1024 8.0 2.488552 0.026162 6.405850 120
559 dense 8192 8192 1.0 3.437579 0.032580 5.684958 74
560 dense 8192 1024 8.0 22.663271 0.100190 16.314732 69 under-trained