Qwen2.5-0.5B-Instruct


Find this model in the Qwen2.5-small model summary

Qwen2.5-0.5B-Instruct Model Set Plots

Qwen2.5-small Compared to Base Model Plots

Qwen2.5-0.5B-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 4864 896 5.428571 6.796745 0.078478 -6.422834 146 under-trained
2 dense 4864 896 5.428571 8.316737 0.034049 -10.357131 70 under-trained
3 dense 4864 896 5.428571 8.853733 0.046482 -13.624902 77 under-trained
4 dense 896 128 7.000000 1.517866 0.095835 -0.678882 80 over-trained
5 dense 896 896 1.000000 2.278895 0.054089 -3.214078 178
6 dense 896 896 1.000000 2.026583 0.030949 1.170068 46
7 dense 896 128 7.000000 2.390231 0.050512 -4.874272 58
8 dense 4864 896 5.428571 8.436567 0.093251 -11.622591 119 under-trained
9 dense 4864 896 5.428571 13.968728 0.112844 -21.803785 63 under-trained
10 dense 4864 896 5.428571 12.317036 0.124970 -21.138026 87 under-trained
11 dense 896 128 7.000000 3.758939 0.057685 -7.129252 27
12 dense 896 896 1.000000 5.499931 0.045913 -9.131922 55
13 dense 896 896 1.000000 3.605790 0.035022 -2.358173 87
14 dense 896 128 7.000000 4.867235 0.049082 -13.852550 26
15 dense 896 896 1.000000 7.463426 0.045636 -15.031191 34 under-trained
16 dense 4864 896 5.428571 9.174856 0.125862 -16.235339 135 under-trained
17 dense 896 896 1.000000 5.324761 0.124291 -7.619276 91
18 dense 896 128 7.000000 5.928357 0.057553 -12.080519 14
19 dense 4864 896 5.428571 17.990498 0.120369 -27.892761 48 under-trained
20 dense 4864 896 5.428571 12.730782 0.127014 -19.560987 81 under-trained
21 dense 896 128 7.000000 4.141989 0.146188 -10.824969 64
22 dense 896 896 1.000000 4.628873 0.032714 -6.807687 51
23 dense 4864 896 5.428571 14.231436 0.126026 -24.278822 72 under-trained
24 dense 896 896 1.000000 5.795670 0.114330 -12.168166 84
25 dense 896 128 7.000000 6.084989 0.060952 -13.396551 16 under-trained
26 dense 896 128 7.000000 4.143126 0.115240 -11.713774 57
27 dense 4864 896 5.428571 13.525137 0.122785 -21.047561 71 under-trained
28 dense 4864 896 5.428571 13.876587 0.125140 -23.665439 71 under-trained
29 dense 4864 896 5.428571 15.160811 0.119741 -22.237111 55 under-trained
30 dense 4864 896 5.428571 13.952509 0.112783 -22.970321 67 under-trained
31 dense 896 128 7.000000 5.256219 0.109425 -11.769231 28
32 dense 4864 896 5.428571 8.569976 0.128322 -13.863878 139 under-trained
33 dense 896 896 1.000000 4.099738 0.122064 -6.500038 125
34 dense 896 896 1.000000 7.048787 0.114590 -14.794884 53 under-trained
35 dense 896 128 7.000000 6.925805 0.138149 -19.816902 33 under-trained
36 dense 4864 896 5.428571 11.480030 0.128519 -19.375238 90 under-trained
37 dense 4864 896 5.428571 8.178580 0.119545 -13.569624 141 under-trained
38 dense 4864 896 5.428571 15.906301 0.095362 -22.036520 44 under-trained
39 dense 896 896 1.000000 7.036708 0.116930 -14.170529 54 under-trained
40 dense 896 128 7.000000 4.027207 0.131893 -9.336471 52
41 dense 896 128 7.000000 2.982682 0.156023 -8.427896 100
42 dense 896 896 1.000000 5.328060 0.121002 -8.479472 85
43 dense 4864 896 5.428571 15.250774 0.110842 -22.246926 57 under-trained
44 dense 4864 896 5.428571 22.284393 0.112657 -37.051797 37 under-trained
45 dense 896 128 7.000000 6.040139 0.132554 -13.776601 32 under-trained
46 dense 4864 896 5.428571 13.553654 0.118340 -21.856142 70 under-trained
47 dense 896 896 1.000000 6.987323 0.079717 -11.659409 32 under-trained
48 dense 896 896 1.000000 5.933998 0.099147 -12.428595 74
49 dense 896 128 7.000000 5.883831 0.141319 -15.870875 38
50 dense 896 896 1.000000 10.497154 0.107094 -23.624780 38 under-trained
51 dense 4864 896 5.428571 17.316267 0.109272 -27.793870 40 under-trained
52 dense 4864 896 5.428571 8.746994 0.120539 -12.720863 123 under-trained
53 dense 4864 896 5.428571 16.383636 0.063451 -26.046924 38 under-trained
54 dense 896 128 7.000000 4.619440 0.125661 -10.603045 43
55 dense 896 128 7.000000 3.736973 0.142307 -10.567390 72
56 dense 896 896 1.000000 5.758271 0.120266 -9.858747 73
57 dense 896 896 1.000000 4.263914 0.049953 -4.705403 75
58 dense 896 896 1.000000 6.503825 0.126500 -13.767809 74 under-trained
59 dense 896 128 7.000000 4.675507 0.070593 -9.514311 21
60 dense 4864 896 5.428571 7.205014 0.090412 -10.869181 110 under-trained
61 dense 4864 896 5.428571 4.893721 0.103890 -6.595804 220
62 dense 4864 896 5.428571 13.744268 0.120381 -21.774416 70 under-trained
63 dense 896 128 7.000000 4.070689 0.137954 -11.993508 62
64 dense 4864 896 5.428571 16.905307 0.071374 -25.092699 32 under-trained
65 dense 896 128 7.000000 4.649035 0.138426 -12.762854 52
66 dense 896 896 1.000000 3.748636 0.030642 -4.878690 68
67 dense 896 896 1.000000 3.112469 0.064355 -5.892548 142
68 dense 896 128 7.000000 3.328691 0.140789 -7.269070 58
69 dense 4864 896 5.428571 4.770617 0.095207 -7.041350 216
70 dense 4864 896 5.428571 4.159408 0.095707 -5.513785 273
71 dense 4864 896 5.428571 13.334280 0.123483 -19.797393 67 under-trained
72 dense 4864 896 5.428571 4.014544 0.089871 -5.164000 278
73 dense 4864 896 5.428571 4.405522 0.086526 -6.314324 242
74 dense 896 128 7.000000 4.995542 0.054818 -10.647225 26
75 dense 896 896 1.000000 5.043939 0.078702 -11.030999 66
76 dense 896 896 1.000000 4.774552 0.116577 -7.949736 80
77 dense 896 128 7.000000 3.554780 0.149162 -9.869027 74
78 dense 4864 896 5.428571 10.527661 0.060360 -15.009948 59 under-trained
79 dense 4864 896 5.428571 4.252179 0.081813 -5.664890 239
80 dense 4864 896 5.428571 4.397980 0.085622 -6.302206 237
81 dense 896 128 7.000000 3.494081 0.124822 -6.864912 45
82 dense 896 896 1.000000 1.991110 0.044552 -2.564996 284 over-trained
83 dense 896 896 1.000000 2.776342 0.045961 -3.005566 111
84 dense 896 128 7.000000 6.337409 0.108001 -16.861401 26 under-trained
85 dense 4864 896 5.428571 15.940175 0.116922 -24.056329 51 under-trained
86 dense 4864 896 5.428571 4.704182 0.092916 -6.128113 193
87 dense 4864 896 5.428571 4.732166 0.090507 -6.723654 219
88 dense 896 128 7.000000 4.703176 0.122326 -9.779464 32
89 dense 896 896 1.000000 4.681276 0.108688 -9.821942 99
90 dense 896 896 1.000000 5.348728 0.086452 -8.766297 56
91 dense 896 128 7.000000 4.763588 0.124007 -13.285397 43
92 dense 4864 896 5.428571 9.648480 0.121589 -14.869907 113 under-trained
93 dense 4864 896 5.428571 4.959857 0.091704 -6.735108 190
94 dense 4864 896 5.428571 6.116606 0.091354 -8.828412 130 under-trained
95 dense 896 128 7.000000 4.442438 0.052099 -8.690130 18
96 dense 896 896 1.000000 7.228789 0.057914 -15.389104 41 under-trained
97 dense 896 896 1.000000 4.751183 0.041896 -6.714040 41
98 dense 896 128 7.000000 3.976080 0.147326 -11.149317 57
99 dense 4864 896 5.428571 16.789417 0.126958 -26.266165 56 under-trained
100 dense 4864 896 5.428571 10.966986 0.117615 -14.530600 67 under-trained
101 dense 4864 896 5.428571 7.890956 0.122957 -11.575099 126 under-trained
102 dense 896 128 7.000000 4.089455 0.057016 -8.604156 23
103 dense 896 896 1.000000 4.063564 0.126469 -9.742553 149
104 dense 896 896 1.000000 3.651090 0.114489 -5.280280 136
105 dense 896 128 7.000000 3.819968 0.133043 -11.057980 73
106 dense 896 128 7.000000 3.512591 0.143528 -9.307302 65
107 dense 896 896 1.000000 4.750183 0.042829 -8.787033 65
108 dense 896 896 1.000000 5.842904 0.059945 -9.502087 31
109 dense 4864 896 5.428571 8.332588 0.112812 -12.332355 105 under-trained
110 dense 4864 896 5.428571 7.632361 0.110774 -10.455610 109 under-trained
111 dense 4864 896 5.428571 15.229441 0.113365 -23.988148 53 under-trained
112 dense 896 128 7.000000 4.777900 0.119076 -10.349861 34
113 dense 896 128 7.000000 3.830776 0.055042 -7.429132 22
114 dense 896 128 7.000000 7.508182 0.140259 -21.018639 26 under-trained
115 dense 896 896 1.000000 3.252692 0.051419 -4.489591 80
116 dense 896 896 1.000000 5.424869 0.111328 -10.570277 71
117 dense 4864 896 5.428571 15.748722 0.099606 -21.737209 41 under-trained
118 dense 4864 896 5.428571 8.175791 0.116508 -12.184532 122 under-trained
119 dense 4864 896 5.428571 6.507064 0.127308 -10.518767 194 under-trained
120 dense 4864 896 5.428571 7.261394 0.125168 -11.479688 170 under-trained
121 dense 896 896 1.000000 4.676467 0.126947 -6.013720 104
122 dense 4864 896 5.428571 9.667512 0.027838 -13.412925 53 under-trained
123 dense 896 128 7.000000 5.389544 0.065868 -11.496761 24
124 dense 896 896 1.000000 9.003658 0.118130 -18.378351 43 under-trained
125 dense 896 128 7.000000 5.030359 0.139349 -13.959944 51
126 dense 4864 896 5.428571 8.266755 0.027437 -10.580772 68 under-trained
127 dense 4864 896 5.428571 9.652396 0.123365 -15.304679 114 under-trained
128 dense 4864 896 5.428571 9.081788 0.040326 -12.560520 53 under-trained
129 dense 896 128 7.000000 6.319227 0.148281 -16.938471 37 under-trained
130 dense 896 128 7.000000 6.181004 0.138639 -14.411620 30 under-trained
131 dense 896 896 1.000000 3.974285 0.127526 -8.172765 158
132 dense 4864 896 5.428571 7.613635 0.029647 -9.939777 72 under-trained
133 dense 896 896 1.000000 5.934841 0.126967 -9.878657 77
134 dense 4864 896 5.428571 13.653499 0.050987 -20.076928 32 under-trained
135 dense 4864 896 5.428571 12.202735 0.119717 -18.565598 74 under-trained
136 dense 4864 896 5.428571 12.079121 0.127417 -20.005503 81 under-trained
137 dense 896 128 7.000000 3.370591 0.140444 -7.586391 62
138 dense 896 896 1.000000 9.340216 0.113969 -18.792646 44 under-trained
139 dense 896 896 1.000000 8.629328 0.114849 -14.200137 37 under-trained
140 dense 896 128 7.000000 5.096226 0.144998 -13.612413 52
141 dense 4864 896 5.428571 10.672546 0.029227 -14.977332 42 under-trained
142 dense 4864 896 5.428571 8.848785 0.115656 -12.704385 116 under-trained
143 dense 896 128 7.000000 4.189168 0.133208 -8.944850 38
144 dense 4864 896 5.428571 9.794930 0.122175 -16.460265 105 under-trained
145 dense 896 896 1.000000 5.339765 0.055483 -7.875163 39
146 dense 896 128 7.000000 4.036845 0.129426 -10.240644 50
147 dense 896 896 1.000000 6.176339 0.121968 -12.628653 83 under-trained
148 dense 4864 896 5.428571 7.072069 0.029277 -9.079815 83 under-trained
149 dense 4864 896 5.428571 7.091165 0.123241 -11.302136 171 under-trained
150 dense 896 896 1.000000 7.177379 0.080770 -12.330570 34 under-trained
151 dense 896 128 7.000000 5.426312 0.087072 -11.208065 17
152 dense 4864 896 5.428571 7.811014 0.034848 -10.296763 80 under-trained
153 dense 896 128 7.000000 4.881081 0.143873 -11.515850 44
154 dense 896 896 1.000000 3.667389 0.105508 -5.429983 110
155 dense 896 128 7.000000 3.710427 0.077902 -7.313113 32
156 dense 4864 896 5.428571 12.694372 0.048181 -19.203661 27 under-trained
157 dense 896 896 1.000000 5.281452 0.082414 -7.366407 32
158 dense 896 896 1.000000 4.452298 0.127083 -8.254509 127
159 dense 4864 896 5.428571 7.957367 0.042233 -10.477434 82 under-trained
160 dense 4864 896 5.428571 9.537416 0.049759 -12.593315 63 under-trained
161 dense 896 128 7.000000 5.625792 0.138816 -12.796147 40
162 dense 896 128 7.000000 3.974621 0.119519 -8.211341 43
163 dense 4864 896 5.428571 9.865053 0.074795 -12.171816 66 under-trained
164 dense 4864 896 5.428571 5.276874 0.073253 -6.014796 183
165 dense 896 896 1.000000 4.206936 0.104870 -5.682458 67
166 dense 896 896 1.000000 5.359288 0.033217 -9.707489 58
167 dense 896 128 7.000000 5.824821 0.139401 -13.003427 28
168 dense 4864 896 5.428571 9.848768 0.072226 -12.696973 65 under-trained