Qwen2-7B-Instruct


Find this model in the Qwen2.0 model summary

Qwen2-7B-Instruct Model Set Plots

Qwen2.0 Compared to Base Model Plots

Qwen2-7B-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 18944 3584 5.285714 3.827833 0.021596 -1.649583 53
2 dense 18944 3584 5.285714 7.529381 0.014817 -5.557845 98 under-trained
3 dense 18944 3584 5.285714 6.119183 0.027498 -2.292381 174 under-trained
4 dense 3584 512 7.000000 3.540174 0.026670 -3.760467 88
5 dense 3584 3584 1.000000 6.295397 0.026300 -9.835923 68 under-trained
6 dense 3584 3584 1.000000 3.313656 0.028296 -0.294163 162
7 dense 3584 512 7.000000 5.020715 0.037784 -12.177107 51
8 dense 18944 3584 5.285714 6.137520 0.063093 -4.839822 407 under-trained
9 dense 18944 3584 5.285714 4.948454 0.018173 -4.064508 128
10 dense 18944 3584 5.285714 4.768833 0.017697 -3.216544 155
11 dense 3584 512 7.000000 2.318790 0.067058 -3.523559 102
12 dense 3584 3584 1.000000 4.912853 0.030254 -6.605871 72
13 dense 3584 3584 1.000000 3.214351 0.085850 -2.389971 142
14 dense 3584 512 7.000000 7.068408 0.049649 -15.011750 26 under-trained
15 dense 18944 3584 5.285714 5.210764 0.067226 -3.032364 640
16 dense 18944 3584 5.285714 4.068943 0.073537 -3.683073 490
17 dense 18944 3584 5.285714 4.723505 0.026438 -3.494888 224
18 dense 3584 512 7.000000 4.232403 0.037645 -6.573964 69
19 dense 3584 3584 1.000000 5.481066 0.031543 -7.420700 131
20 dense 3584 3584 1.000000 4.933385 0.068776 -5.572019 145
21 dense 3584 512 7.000000 7.320793 0.043502 -15.913585 42 under-trained
22 dense 18944 3584 5.285714 14.728418 0.027805 -17.480191 106 under-trained
23 dense 18944 3584 5.285714 5.205904 0.078339 -5.084552 443
24 dense 18944 3584 5.285714 6.815533 0.082516 -7.345657 280 under-trained
25 dense 3584 512 7.000000 4.095406 0.077686 -6.751180 113
26 dense 3584 3584 1.000000 6.808569 0.035929 -11.207788 58 under-trained
27 dense 3584 3584 1.000000 6.227434 0.042722 -6.761675 65 under-trained
28 dense 3584 512 7.000000 6.929568 0.104956 -15.958196 90 under-trained
29 dense 18944 3584 5.285714 15.812011 0.021720 -19.613133 72 under-trained
30 dense 18944 3584 5.285714 7.180244 0.071941 -7.164007 270 under-trained
31 dense 18944 3584 5.285714 7.611634 0.077836 -8.750038 282 under-trained
32 dense 3584 512 7.000000 3.659986 0.099166 -6.142033 148
33 dense 3584 3584 1.000000 3.748502 0.046328 -5.277765 310
34 dense 3584 3584 1.000000 5.424208 0.095513 -5.698919 168
35 dense 3584 512 7.000000 4.731302 0.087271 -9.502363 116
36 dense 18944 3584 5.285714 16.119888 0.036616 -20.145035 45 under-trained
37 dense 18944 3584 5.285714 12.146417 0.024501 -12.442339 47 under-trained
38 dense 18944 3584 5.285714 10.972742 0.022984 -12.702739 75 under-trained
39 dense 3584 512 7.000000 5.737048 0.041710 -10.166241 47
40 dense 3584 3584 1.000000 8.393849 0.029824 -12.656610 52 under-trained
41 dense 3584 3584 1.000000 6.269133 0.035296 -7.773024 66 under-trained
42 dense 3584 512 7.000000 6.720820 0.108852 -13.538193 105 under-trained
43 dense 3584 512 7.000000 4.976421 0.097533 -8.809428 88
44 dense 3584 3584 1.000000 6.699461 0.089491 -10.787180 152 under-trained
45 dense 3584 3584 1.000000 7.148721 0.028486 -8.826292 52 under-trained
46 dense 3584 512 7.000000 8.268489 0.106270 -18.724206 74 under-trained
47 dense 18944 3584 5.285714 13.742627 0.043801 -14.913547 118 under-trained
48 dense 18944 3584 5.285714 12.444162 0.053029 -14.078010 188 under-trained
49 dense 18944 3584 5.285714 11.790302 0.056039 -13.006703 183 under-trained
50 dense 18944 3584 5.285714 11.065810 0.060333 -11.492291 215 under-trained
51 dense 18944 3584 5.285714 13.622782 0.063404 -15.121974 172 under-trained
52 dense 18944 3584 5.285714 11.980701 0.059607 -12.403306 193 under-trained
53 dense 3584 3584 1.000000 10.714022 0.024058 -18.471086 41 under-trained
54 dense 3584 512 7.000000 5.673294 0.101268 -10.626236 97
55 dense 3584 512 7.000000 9.884776 0.125870 -22.990711 74 under-trained
56 dense 3584 3584 1.000000 6.821773 0.104996 -9.197187 163 under-trained
57 dense 3584 512 7.000000 6.542466 0.114912 -11.906496 85 under-trained
58 dense 18944 3584 5.285714 15.162407 0.052921 -16.677595 134 under-trained
59 dense 18944 3584 5.285714 12.864953 0.060901 -13.215888 179 under-trained
60 dense 18944 3584 5.285714 11.847615 0.063163 -12.317928 201 under-trained
61 dense 3584 3584 1.000000 10.683674 0.080650 -15.377659 62 under-trained
62 dense 3584 3584 1.000000 6.991108 0.091704 -12.082390 135 under-trained
63 dense 3584 512 7.000000 11.821033 0.101732 -27.480685 39 under-trained
64 dense 3584 512 7.000000 11.081873 0.120760 -26.126272 55 under-trained
65 dense 3584 512 7.000000 6.358925 0.104219 -12.135334 79 under-trained
66 dense 18944 3584 5.285714 12.615194 0.041025 -14.833560 136 under-trained
67 dense 3584 3584 1.000000 9.612863 0.050552 -13.427615 60 under-trained
68 dense 3584 3584 1.000000 9.836068 0.029775 -16.824128 53 under-trained
69 dense 18944 3584 5.285714 13.028131 0.055859 -12.443383 137 under-trained
70 dense 18944 3584 5.285714 18.333931 0.053290 -23.472221 97 under-trained
71 dense 18944 3584 5.285714 12.357096 0.066348 -12.544129 198 under-trained
72 dense 18944 3584 5.285714 17.551183 0.064192 -20.476723 114 under-trained
73 dense 3584 3584 1.000000 9.434544 0.027365 -13.085609 44 under-trained
74 dense 3584 3584 1.000000 11.540441 0.026935 -20.410739 46 under-trained
75 dense 3584 512 7.000000 6.539457 0.108576 -12.133055 81 under-trained
76 dense 3584 512 7.000000 11.799986 0.131128 -27.305950 66 under-trained
77 dense 18944 3584 5.285714 11.166136 0.065057 -11.868974 227 under-trained
78 dense 18944 3584 5.285714 12.155687 0.060516 -13.259029 191 under-trained
79 dense 18944 3584 5.285714 17.335530 0.067922 -20.315805 125 under-trained
80 dense 18944 3584 5.285714 12.313799 0.060853 -12.723888 195 under-trained
81 dense 3584 512 7.000000 8.455042 0.121449 -19.899653 80 under-trained
82 dense 3584 3584 1.000000 9.593295 0.107805 -14.430189 100 under-trained
83 dense 3584 3584 1.000000 11.861369 0.097739 -21.602520 68 under-trained
84 dense 3584 512 7.000000 8.743703 0.121388 -15.941639 70 under-trained
85 dense 3584 512 7.000000 6.916814 0.100664 -12.732316 75 under-trained
86 dense 18944 3584 5.285714 12.914739 0.062422 -14.230437 171 under-trained
87 dense 18944 3584 5.285714 13.020852 0.062161 -13.267091 180 under-trained
88 dense 18944 3584 5.285714 18.281113 0.058587 -21.452184 108 under-trained
89 dense 3584 3584 1.000000 7.717398 0.109881 -13.935495 183 under-trained
90 dense 3584 3584 1.000000 10.182172 0.102114 -14.958543 79 under-trained
91 dense 3584 512 7.000000 11.586884 0.103197 -27.629189 45 under-trained
92 dense 3584 3584 1.000000 7.431664 0.112673 -10.842198 170 under-trained
93 dense 18944 3584 5.285714 18.678098 0.055609 -22.649973 97 under-trained
94 dense 3584 512 7.000000 9.247485 0.118765 -17.283464 58 under-trained
95 dense 18944 3584 5.285714 12.547385 0.063995 -13.686094 185 under-trained
96 dense 18944 3584 5.285714 14.143445 0.059057 -14.126494 147 under-trained
97 dense 3584 512 7.000000 7.508673 0.132566 -18.615411 107 under-trained
98 dense 3584 3584 1.000000 12.488197 0.111937 -23.776919 94 under-trained
99 dense 3584 512 7.000000 6.365526 0.030621 -11.570635 51 under-trained
100 dense 18944 3584 5.285714 13.320604 0.065216 -13.144311 171 under-trained
101 dense 3584 512 7.000000 4.154870 0.128597 -9.661329 188
102 dense 3584 3584 1.000000 8.451028 0.048282 -13.959369 68 under-trained
103 dense 3584 3584 1.000000 8.926719 0.034506 -12.131262 45 under-trained
104 dense 18944 3584 5.285714 18.901946 0.057147 -23.027471 97 under-trained
105 dense 18944 3584 5.285714 13.151524 0.063882 -14.205637 165 under-trained
106 dense 18944 3584 5.285714 20.608792 0.055108 -25.000069 79 under-trained
107 dense 18944 3584 5.285714 12.715760 0.062011 -12.611401 177 under-trained
108 dense 18944 3584 5.285714 12.292234 0.062639 -13.122373 193 under-trained
109 dense 3584 512 7.000000 7.695781 0.050273 -13.884127 34 under-trained
110 dense 3584 3584 1.000000 7.722658 0.112893 -14.210201 165 under-trained
111 dense 3584 3584 1.000000 9.732768 0.046837 -14.392432 61 under-trained
112 dense 3584 512 7.000000 10.040745 0.120017 -23.489592 52 under-trained
113 dense 18944 3584 5.285714 22.459118 0.045674 -28.141030 61 under-trained
114 dense 18944 3584 5.285714 13.659342 0.056000 -13.499172 147 under-trained
115 dense 18944 3584 5.285714 13.538864 0.055477 -14.382934 148 under-trained
116 dense 3584 512 7.000000 7.254782 0.091014 -13.305176 70 under-trained
117 dense 3584 3584 1.000000 7.349138 0.108385 -13.748797 186 under-trained
118 dense 3584 3584 1.000000 12.715241 0.097253 -18.656359 53 under-trained
119 dense 3584 512 7.000000 12.173487 0.127129 -29.204449 51 under-trained
120 dense 18944 3584 5.285714 21.231521 0.056892 -26.043435 70 under-trained
121 dense 18944 3584 5.285714 13.451103 0.060685 -13.334828 166 under-trained
122 dense 18944 3584 5.285714 13.908286 0.052042 -15.013297 148 under-trained
123 dense 3584 512 7.000000 4.880519 0.117340 -9.113713 156
124 dense 3584 3584 1.000000 7.027506 0.107643 -12.558477 211 under-trained
125 dense 3584 3584 1.000000 16.043069 0.096371 -23.806076 37 under-trained
126 dense 3584 512 7.000000 7.323175 0.121083 -17.312221 98 under-trained
127 dense 18944 3584 5.285714 17.851528 0.055417 -21.615246 102 under-trained
128 dense 18944 3584 5.285714 14.018358 0.062762 -13.878337 154 under-trained
129 dense 18944 3584 5.285714 13.530109 0.057382 -14.458801 172 under-trained
130 dense 3584 512 7.000000 5.630697 0.122917 -10.579349 120
131 dense 3584 3584 1.000000 10.308327 0.037556 -18.766210 58 under-trained
132 dense 3584 3584 1.000000 6.911556 0.113659 -8.878568 199 under-trained
133 dense 3584 512 7.000000 19.057301 0.109712 -47.008498 25 under-trained
134 dense 18944 3584 5.285714 22.035376 0.050623 -28.220026 74 under-trained
135 dense 18944 3584 5.285714 12.483032 0.066093 -12.185186 192 under-trained
136 dense 18944 3584 5.285714 12.378841 0.059770 -13.157371 197 under-trained
137 dense 3584 512 7.000000 7.249346 0.098497 -13.884040 67 under-trained
138 dense 3584 3584 1.000000 8.859316 0.106109 -16.681267 153 under-trained
139 dense 3584 3584 1.000000 7.632846 0.110756 -10.227166 152 under-trained
140 dense 3584 512 7.000000 9.798673 0.114509 -24.065314 58 under-trained
141 dense 18944 3584 5.285714 30.690161 0.044588 -41.698238 34 under-trained
142 dense 18944 3584 5.285714 13.168553 0.060768 -13.490165 188 under-trained
143 dense 18944 3584 5.285714 13.800035 0.058481 -15.195377 160 under-trained
144 dense 3584 512 7.000000 6.409509 0.121979 -12.247907 117 under-trained
145 dense 3584 3584 1.000000 10.815504 0.113450 -20.458262 107 under-trained
146 dense 3584 3584 1.000000 14.559957 0.057524 -22.266609 39 under-trained
147 dense 3584 512 7.000000 11.186028 0.122902 -26.769223 53 under-trained
148 dense 18944 3584 5.285714 27.981096 0.053733 -38.446387 41 under-trained
149 dense 18944 3584 5.285714 14.729997 0.069261 -15.691164 158 under-trained
150 dense 18944 3584 5.285714 15.432477 0.060014 -17.899132 131 under-trained
151 dense 3584 512 7.000000 5.477638 0.129163 -10.859439 136
152 dense 3584 3584 1.000000 7.880951 0.113948 -14.448568 187 under-trained
153 dense 3584 3584 1.000000 9.759118 0.109610 -14.718905 116 under-trained
154 dense 3584 512 7.000000 7.525349 0.126287 -18.409309 111 under-trained
155 dense 18944 3584 5.285714 15.589823 0.058448 -16.890465 134 under-trained
156 dense 18944 3584 5.285714 16.656009 0.054838 -19.654883 115 under-trained
157 dense 3584 512 7.000000 8.938670 0.097263 -17.515122 48 under-trained
158 dense 3584 3584 1.000000 22.899302 0.105690 -40.651131 31 under-trained
159 dense 3584 3584 1.000000 8.692759 0.109846 -12.938342 117 under-trained
160 dense 3584 512 7.000000 6.243006 0.134704 -14.485508 138 under-trained
161 dense 18944 3584 5.285714 20.830159 0.109022 -28.000389 136 under-trained
162 dense 18944 3584 5.285714 23.047336 0.052408 -30.329991 73 under-trained
163 dense 18944 3584 5.285714 14.629632 0.055561 -15.916012 145 under-trained
164 dense 18944 3584 5.285714 15.710477 0.051560 -18.612850 128 under-trained
165 dense 3584 512 7.000000 9.813685 0.123080 -19.333817 50 under-trained
166 dense 3584 3584 1.000000 14.564275 0.112578 -26.096037 73 under-trained
167 dense 3584 3584 1.000000 13.726786 0.100900 -20.629542 56 under-trained
168 dense 3584 512 7.000000 13.649112 0.107985 -31.201261 42 under-trained
169 dense 18944 3584 5.285714 15.442561 0.114961 -20.151862 218 under-trained
170 dense 18944 3584 5.285714 13.587030 0.058682 -15.242363 176 under-trained
171 dense 18944 3584 5.285714 15.984964 0.050763 -19.354485 123 under-trained
172 dense 3584 512 7.000000 9.604614 0.066685 -19.286736 28 under-trained
173 dense 3584 3584 1.000000 10.138807 0.105952 -16.037192 115 under-trained
174 dense 3584 3584 1.000000 10.719982 0.043036 -15.702776 48 under-trained
175 dense 3584 512 7.000000 11.472322 0.090444 -25.370565 42 under-trained
176 dense 18944 3584 5.285714 15.251909 0.111143 -18.928824 214 under-trained
177 dense 18944 3584 5.285714 12.386270 0.054368 -12.925284 197 under-trained
178 dense 18944 3584 5.285714 14.191131 0.051860 -16.445468 150 under-trained
179 dense 3584 512 7.000000 10.193086 0.050854 -19.416980 24 under-trained
180 dense 3584 3584 1.000000 14.575573 0.043541 -24.770084 50 under-trained
181 dense 3584 3584 1.000000 12.007345 0.088182 -17.878362 61 under-trained
182 dense 3584 512 7.000000 7.312087 0.123143 -15.067178 90 under-trained
183 dense 18944 3584 5.285714 13.216330 0.062604 -14.835393 160 under-trained
184 dense 18944 3584 5.285714 11.433945 0.061742 -11.066475 238 under-trained
185 dense 18944 3584 5.285714 13.329421 0.055414 -14.488934 172 under-trained
186 dense 3584 512 7.000000 5.828372 0.102330 -11.083249 91
187 dense 3584 3584 1.000000 9.211109 0.051324 -14.037846 101 under-trained
188 dense 3584 3584 1.000000 9.573045 0.094273 -13.393699 74 under-trained
189 dense 3584 512 7.000000 6.647694 0.125760 -13.124128 103 under-trained
190 dense 18944 3584 5.285714 8.331520 0.058047 -8.020058 268 under-trained
191 dense 18944 3584 5.285714 11.598058 0.065253 -11.563672 224 under-trained
192 dense 18944 3584 5.285714 11.946096 0.058148 -13.095404 183 under-trained
193 dense 3584 512 7.000000 5.171386 0.118525 -9.445717 114
194 dense 3584 3584 1.000000 9.183825 0.038216 -13.950984 61 under-trained
195 dense 3584 3584 1.000000 5.501722 0.042008 -5.977774 130
196 dense 3584 512 7.000000 8.386957 0.042567 -16.028389 32 under-trained