falcon2-11B


Find this model in the Falcon2 model summary

falcon2-11B Model Set Plots

falcon2-11B Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 16384 4096 4.0 6.514919 0.049051 11.382380 261 under-trained
2 dense 16384 4096 4.0 3.413714 0.056158 10.456118 507
3 dense 4096 4096 1.0 2.471829 0.028877 4.758757 137
4 dense 6144 4096 1.5 1.622502 0.027530 5.632758 1157 over-trained
5 dense 16384 4096 4.0 5.019262 0.029911 10.430128 436
6 dense 16384 4096 4.0 2.982394 0.033381 10.055173 201
7 dense 4096 4096 1.0 3.384061 0.019400 5.988287 119
8 dense 6144 4096 1.5 3.397196 0.026949 9.388837 105
9 dense 4096 4096 1.0 3.601806 0.024013 5.326012 131
10 dense 6144 4096 1.5 2.973224 0.019352 6.938695 159
11 dense 16384 4096 4.0 3.422279 0.037906 6.631236 71
12 dense 16384 4096 4.0 2.578421 0.022385 8.234014 395
13 dense 6144 4096 1.5 3.234460 0.029575 6.875676 158
14 dense 4096 4096 1.0 3.183423 0.040888 4.368057 311
15 dense 16384 4096 4.0 2.809654 0.015657 9.194297 972
16 dense 16384 4096 4.0 5.332673 0.034723 12.169919 560
17 dense 6144 4096 1.5 2.538900 0.036639 5.703998 628
18 dense 16384 4096 4.0 4.752431 0.010357 8.892293 380
19 dense 4096 4096 1.0 4.034161 0.021664 5.579538 199
20 dense 16384 4096 4.0 3.345854 0.022665 10.673883 898
21 dense 6144 4096 1.5 3.456362 0.020689 7.725477 96
22 dense 4096 4096 1.0 3.451795 0.041479 4.843042 299
23 dense 16384 4096 4.0 4.090095 0.013450 12.867270 576
24 dense 16384 4096 4.0 4.201745 0.006236 7.984105 401
25 dense 4096 4096 1.0 3.906065 0.045638 5.144331 229
26 dense 16384 4096 4.0 4.370325 0.020048 13.813868 595
27 dense 16384 4096 4.0 5.265953 0.019150 8.772149 183
28 dense 6144 4096 1.5 3.791371 0.014441 8.291507 119
29 dense 6144 4096 1.5 4.356170 0.023685 9.547256 63
30 dense 4096 4096 1.0 3.702165 0.041635 5.245144 241
31 dense 16384 4096 4.0 4.186100 0.024456 13.144990 728
32 dense 16384 4096 4.0 4.218762 0.016803 7.003101 414
33 dense 6144 4096 1.5 3.378033 0.026791 7.611611 127
34 dense 4096 4096 1.0 4.095804 0.041390 5.566727 236
35 dense 16384 4096 4.0 4.487643 0.032533 13.949842 707
36 dense 16384 4096 4.0 5.109290 0.014379 8.133785 420
37 dense 6144 4096 1.5 3.692805 0.019316 8.454928 101
38 dense 4096 4096 1.0 3.305090 0.069757 4.966770 358
39 dense 16384 4096 4.0 4.718444 0.013179 8.426639 360
40 dense 16384 4096 4.0 3.942863 0.017402 12.514103 715
41 dense 4096 4096 1.0 4.034668 0.031500 5.776432 172
42 dense 6144 4096 1.5 3.369285 0.024215 7.746280 130
43 dense 16384 4096 4.0 4.681924 0.020951 8.291386 356
44 dense 16384 4096 4.0 3.444386 0.023807 10.898604 82
45 dense 6144 4096 1.5 3.759945 0.019242 8.588084 106
46 dense 4096 4096 1.0 4.326075 0.052036 5.380104 220
47 dense 16384 4096 4.0 4.246095 0.028018 13.451468 766
48 dense 16384 4096 4.0 5.178406 0.015871 8.493202 286
49 dense 16384 4096 4.0 5.439118 0.023989 8.789551 253
50 dense 4096 4096 1.0 3.157606 0.071720 4.436340 440
51 dense 16384 4096 4.0 4.328392 0.011824 13.709503 531
52 dense 6144 4096 1.5 3.758188 0.023894 8.727780 57
53 dense 6144 4096 1.5 3.938392 0.018111 9.130191 97
54 dense 16384 4096 4.0 5.177289 0.025005 8.454177 319
55 dense 16384 4096 4.0 4.283808 0.019838 13.610538 624
56 dense 4096 4096 1.0 5.317314 0.057363 6.548090 130
57 dense 6144 4096 1.5 3.855367 0.019075 8.958072 70
58 dense 4096 4096 1.0 4.243398 0.063907 6.157357 204
59 dense 16384 4096 4.0 4.741998 0.027752 7.558738 303
60 dense 16384 4096 4.0 4.409417 0.017457 13.880679 560
61 dense 16384 4096 4.0 5.622710 0.022257 9.128546 106
62 dense 16384 4096 4.0 4.675394 0.019744 14.663562 517
63 dense 4096 4096 1.0 3.516748 0.062748 5.776877 366
64 dense 6144 4096 1.5 3.779712 0.019054 8.770257 153
65 dense 16384 4096 4.0 4.087517 0.032652 6.674342 405
66 dense 16384 4096 4.0 4.216574 0.013290 13.094309 550
67 dense 4096 4096 1.0 4.830464 0.037433 7.904999 50
68 dense 6144 4096 1.5 2.991597 0.043795 7.070796 287
69 dense 6144 4096 1.5 3.099919 0.028358 7.369223 251
70 dense 4096 4096 1.0 4.038723 0.049818 5.532011 198
71 dense 16384 4096 4.0 4.922002 0.030493 8.209860 182
72 dense 16384 4096 4.0 4.388293 0.015645 13.488728 510
73 dense 16384 4096 4.0 4.393783 0.008816 7.216516 352
74 dense 16384 4096 4.0 4.022782 0.011977 12.302477 135
75 dense 4096 4096 1.0 4.782703 0.046206 6.868985 140
76 dense 6144 4096 1.5 3.399191 0.025766 7.963085 116
77 dense 16384 4096 4.0 4.428158 0.021948 6.633022 358
78 dense 16384 4096 4.0 4.247489 0.007589 13.058540 385
79 dense 4096 4096 1.0 4.094606 0.063558 5.755325 131
80 dense 6144 4096 1.5 2.842225 0.059329 6.642381 304
81 dense 4096 4096 1.0 5.106190 0.071879 6.996525 92
82 dense 16384 4096 4.0 5.274401 0.013576 7.669035 304
83 dense 16384 4096 4.0 4.477025 0.014379 13.878414 496
84 dense 6144 4096 1.5 3.994216 0.026949 9.217569 60
85 dense 6144 4096 1.5 2.910646 0.048833 6.831624 370
86 dense 4096 4096 1.0 4.180221 0.049331 6.454993 206
87 dense 16384 4096 4.0 3.958057 0.008127 12.341469 340
88 dense 16384 4096 4.0 4.687310 0.013357 7.312020 318
89 dense 16384 4096 4.0 4.653969 0.018224 7.154949 382
90 dense 16384 4096 4.0 4.300855 0.007822 13.375692 300
91 dense 4096 4096 1.0 3.968499 0.039249 5.427405 209
92 dense 6144 4096 1.5 3.419992 0.019431 7.986853 195
93 dense 16384 4096 4.0 5.178183 0.009519 7.861576 304
94 dense 16384 4096 4.0 4.466449 0.013793 13.912695 536
95 dense 4096 4096 1.0 3.288821 0.078211 4.230857 503
96 dense 6144 4096 1.5 3.604163 0.024794 8.348791 140
97 dense 4096 4096 1.0 3.777835 0.037410 5.759610 206
98 dense 6144 4096 1.5 3.220928 0.029585 7.518440 260
99 dense 16384 4096 4.0 4.579504 0.010271 6.743404 415
100 dense 16384 4096 4.0 4.400679 0.006663 13.619640 441
101 dense 16384 4096 4.0 4.718409 0.009234 6.859414 413
102 dense 16384 4096 4.0 4.467049 0.009799 13.692217 459
103 dense 4096 4096 1.0 3.356015 0.027546 5.173380 311
104 dense 6144 4096 1.5 3.237417 0.034503 7.650816 147
105 dense 16384 4096 4.0 4.384772 0.015004 13.320421 540
106 dense 4096 4096 1.0 3.364389 0.037348 4.877625 338
107 dense 6144 4096 1.5 4.030735 0.027387 9.477116 40
108 dense 16384 4096 4.0 5.399339 0.011831 8.026067 349
109 dense 6144 4096 1.5 2.678133 0.046561 6.473532 336
110 dense 16384 4096 4.0 5.026305 0.017268 7.974251 492
111 dense 16384 4096 4.0 4.316938 0.018082 13.314152 479
112 dense 4096 4096 1.0 6.166201 0.035929 8.315848 105 under-trained
113 dense 4096 4096 1.0 4.561188 0.043955 5.991628 205
114 dense 6144 4096 1.5 3.146366 0.047281 7.455479 360
115 dense 16384 4096 4.0 9.699481 0.018637 14.218402 62 under-trained
116 dense 16384 4096 4.0 3.560325 0.008867 11.210713 344
117 dense 4096 4096 1.0 7.079649 0.030086 9.579838 145 under-trained
118 dense 6144 4096 1.5 4.172481 0.021083 9.852242 138
119 dense 16384 4096 4.0 8.089376 0.021122 12.147345 136 under-trained
120 dense 16384 4096 4.0 4.236342 0.014269 13.415601 420
121 dense 16384 4096 4.0 7.691492 0.025110 11.262816 98 under-trained
122 dense 16384 4096 4.0 4.225783 0.014594 13.228177 475
123 dense 4096 4096 1.0 7.274479 0.054560 9.029781 79 under-trained
124 dense 6144 4096 1.5 3.819266 0.021181 8.809827 178
125 dense 16384 4096 4.0 6.423424 0.016033 9.426727 177 under-trained
126 dense 16384 4096 4.0 4.528077 0.017087 14.150203 436
127 dense 4096 4096 1.0 4.696413 0.045801 6.017266 183
128 dense 6144 4096 1.5 4.028754 0.019321 9.406785 63
129 dense 16384 4096 4.0 5.773721 0.010984 8.397207 291
130 dense 16384 4096 4.0 4.541414 0.016232 14.232116 477
131 dense 4096 4096 1.0 7.406250 0.025663 10.567532 89 under-trained
132 dense 6144 4096 1.5 4.219748 0.013335 9.987635 184
133 dense 6144 4096 1.5 3.537184 0.013060 8.397276 273
134 dense 4096 4096 1.0 6.721357 0.071074 8.158106 137 under-trained
135 dense 16384 4096 4.0 6.981020 0.010422 9.955885 167 under-trained
136 dense 16384 4096 4.0 4.342135 0.009946 13.451037 366
137 dense 16384 4096 4.0 6.055975 0.014576 8.356046 288 under-trained
138 dense 16384 4096 4.0 4.387101 0.012571 13.628579 504
139 dense 4096 4096 1.0 7.475229 0.032292 9.407433 88 under-trained
140 dense 6144 4096 1.5 3.733860 0.013339 8.792339 211
141 dense 6144 4096 1.5 4.463129 0.023248 10.499724 232
142 dense 16384 4096 4.0 6.252650 0.014808 9.290507 296 under-trained
143 dense 16384 4096 4.0 4.466198 0.010885 13.916330 507
144 dense 4096 4096 1.0 8.628405 0.032536 11.223454 76 under-trained
145 dense 4096 4096 1.0 6.619114 0.018850 8.843430 95 under-trained
146 dense 6144 4096 1.5 4.925530 0.029559 11.518889 202
147 dense 16384 4096 4.0 6.860535 0.016947 10.277153 261 under-trained
148 dense 16384 4096 4.0 4.508975 0.009903 13.987022 493
149 dense 6144 4096 1.5 3.181212 0.030868 7.446840 415
150 dense 4096 4096 1.0 5.876389 0.048662 7.502374 88
151 dense 16384 4096 4.0 6.076423 0.020591 9.226087 334 under-trained
152 dense 16384 4096 4.0 4.468919 0.011055 13.728020 442
153 dense 16384 4096 4.0 6.632792 0.018888 10.113035 262 under-trained
154 dense 16384 4096 4.0 4.463369 0.009351 13.697559 438
155 dense 4096 4096 1.0 5.780383 0.029985 7.621166 135
156 dense 6144 4096 1.5 3.265610 0.033927 7.646421 333
157 dense 16384 4096 4.0 6.169618 0.019963 9.789433 300 under-trained
158 dense 16384 4096 4.0 4.626582 0.009467 14.289124 450
159 dense 4096 4096 1.0 5.864445 0.016551 9.681071 140
160 dense 6144 4096 1.5 4.271146 0.012281 10.071723 198
161 dense 16384 4096 4.0 6.021875 0.023749 9.846169 353 under-trained
162 dense 6144 4096 1.5 3.224661 0.039867 7.631708 296
163 dense 4096 4096 1.0 3.926845 0.039498 5.412177 245
164 dense 16384 4096 4.0 4.447073 0.011656 13.601784 463
165 dense 16384 4096 4.0 6.092225 0.022241 10.158456 334 under-trained
166 dense 16384 4096 4.0 4.536505 0.013726 13.875819 411
167 dense 4096 4096 1.0 3.555698 0.040315 5.216571 493
168 dense 6144 4096 1.5 3.439341 0.040078 7.898326 210
169 dense 16384 4096 4.0 5.699669 0.019807 9.486007 375
170 dense 16384 4096 4.0 4.455463 0.018886 13.541121 487
171 dense 4096 4096 1.0 5.917654 0.025415 7.799267 126
172 dense 6144 4096 1.5 2.631475 0.042190 6.244407 629
173 dense 16384 4096 4.0 5.871900 0.021793 9.402199 365
174 dense 16384 4096 4.0 4.501459 0.020601 13.682229 408
175 dense 4096 4096 1.0 7.304436 0.022727 9.416050 106 under-trained
176 dense 6144 4096 1.5 3.351900 0.015806 7.955167 282
177 dense 6144 4096 1.5 3.876614 0.010252 9.090336 250
178 dense 4096 4096 1.0 6.090479 0.019310 8.902476 124 under-trained
179 dense 16384 4096 4.0 6.162783 0.019545 9.508544 324 under-trained
180 dense 16384 4096 4.0 4.314952 0.023977 13.047275 464
181 dense 16384 4096 4.0 6.308975 0.016574 9.516054 258 under-trained
182 dense 16384 4096 4.0 4.429354 0.017612 13.261453 279
183 dense 4096 4096 1.0 5.440574 0.024971 7.451138 145
184 dense 6144 4096 1.5 3.985657 0.014622 9.415194 82
185 dense 16384 4096 4.0 8.310478 0.015983 12.611737 153 under-trained
186 dense 16384 4096 4.0 4.188254 0.009894 12.737809 489
187 dense 4096 4096 1.0 6.051239 0.030948 8.284924 68 under-trained
188 dense 6144 4096 1.5 3.212504 0.018677 7.721437 378
189 dense 16384 4096 4.0 7.425273 0.018062 11.226728 174 under-trained
190 dense 16384 4096 4.0 4.172113 0.011204 12.587979 452
191 dense 4096 4096 1.0 6.369493 0.020326 9.090299 137 under-trained
192 dense 6144 4096 1.5 2.913021 0.018577 7.000018 444
193 dense 6144 4096 1.5 3.267688 0.016573 7.771934 361
194 dense 4096 4096 1.0 5.372352 0.052849 8.010466 257
195 dense 16384 4096 4.0 4.269336 0.013188 12.905282 417
196 dense 16384 4096 4.0 7.011486 0.026120 10.906260 198 under-trained
197 dense 16384 4096 4.0 6.175479 0.016257 9.535671 279 under-trained
198 dense 16384 4096 4.0 4.326351 0.013116 12.936327 370
199 dense 4096 4096 1.0 6.023110 0.034552 8.797779 178 under-trained
200 dense 6144 4096 1.5 2.574273 0.016807 6.198574 562
201 dense 16384 4096 4.0 5.914624 0.017418 8.960863 290
202 dense 16384 4096 4.0 4.303255 0.014988 12.905168 382
203 dense 4096 4096 1.0 5.103944 0.027652 7.200067 190
204 dense 6144 4096 1.5 2.787723 0.017028 6.729002 463
205 dense 16384 4096 4.0 6.819548 0.021545 11.064137 206 under-trained
206 dense 16384 4096 4.0 4.416494 0.016190 13.192366 395
207 dense 4096 4096 1.0 5.882233 0.026534 9.974601 177
208 dense 6144 4096 1.5 4.212408 0.012993 9.822304 235
209 dense 6144 4096 1.5 2.926643 0.017548 6.994499 440
210 dense 4096 4096 1.0 4.869141 0.019762 7.800097 207
211 dense 16384 4096 4.0 6.478430 0.020898 10.336074 192 under-trained
212 dense 16384 4096 4.0 4.413988 0.017876 12.943553 407
213 dense 16384 4096 4.0 6.415339 0.013873 10.991720 188 under-trained
214 dense 16384 4096 4.0 4.589804 0.012212 13.590916 411
215 dense 4096 4096 1.0 4.969519 0.034064 8.972268 238
216 dense 6144 4096 1.5 3.625229 0.016096 8.877409 340
217 dense 16384 4096 4.0 4.638950 0.013692 13.560004 425
218 dense 4096 4096 1.0 6.950031 0.037171 10.671388 160 under-trained
219 dense 6144 4096 1.5 2.962477 0.024712 6.822764 531
220 dense 16384 4096 4.0 6.033366 0.012240 11.124889 265 under-trained
221 dense 6144 4096 1.5 3.188857 0.020255 7.463656 268
222 dense 16384 4096 4.0 5.816346 0.022233 11.677181 336
223 dense 16384 4096 4.0 4.555010 0.019536 13.200148 529
224 dense 4096 4096 1.0 5.316385 0.027165 9.576268 122
225 dense 6144 4096 1.5 2.863287 0.012138 6.623313 518
226 dense 4096 4096 1.0 6.475386 0.044231 10.241857 202 under-trained
227 dense 16384 4096 4.0 3.728436 0.025059 10.890359 76
228 dense 16384 4096 4.0 6.400812 0.019568 13.170901 254 under-trained
229 dense 16384 4096 4.0 5.726266 0.027458 11.756994 364
230 dense 16384 4096 4.0 3.352753 0.019988 10.013860 77
231 dense 4096 4096 1.0 3.482967 0.024732 7.923998 91
232 dense 6144 4096 1.5 3.087106 0.009095 7.602071 262
233 dense 6144 4096 1.5 3.359476 0.017348 7.936330 191
234 dense 16384 4096 4.0 5.312537 0.042237 14.646707 439
235 dense 16384 4096 4.0 3.172349 0.018216 9.537114 90
236 dense 4096 4096 1.0 3.485566 0.026554 7.597801 77
237 dense 16384 4096 4.0 2.798923 0.017093 8.567305 95
238 dense 4096 4096 1.0 4.595899 0.040800 8.683902 220
239 dense 16384 4096 4.0 4.025803 0.027548 11.673205 414
240 dense 6144 4096 1.5 2.748319 0.011759 6.870542 533