Genome = [0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1]
Genotype = [[[0], [0, 0], [1, 1, 0], [1]], [[1], [1, 0], [0, 1, 0], [0]], [[0], [1, 1], [1, 1, 0], [1]]]
param size = 0.10588MB
total params = 27757
flops = 0.0261M
valid_acc = 99.16

==================================================
Model Configuration
==================================================
search_space = macro
model_config_id = mlp_small
task_type = regression
input_dim = 3
output_dim = 1
C (channels) = 32
layers = 4
epochs = 50

==================================================
Training Progress
==================================================
Epoch   1 | Train Loss: 0.082674 | Val Loss: 0.036164 | LR: 0.000999
Epoch   2 | Train Loss: 0.035290 | Val Loss: 0.019353 | LR: 0.000996
Epoch   3 | Train Loss: 0.021358 | Val Loss: 0.018009 | LR: 0.000991
Epoch   4 | Train Loss: 0.017339 | Val Loss: 0.008294 | LR: 0.000984
Epoch   5 | Train Loss: 0.016128 | Val Loss: 0.009754 | LR: 0.000976
Epoch   6 | Train Loss: 0.015686 | Val Loss: 0.012013 | LR: 0.000965
Epoch   7 | Train Loss: 0.015722 | Val Loss: 0.009579 | LR: 0.000952
Epoch   8 | Train Loss: 0.016085 | Val Loss: 0.008274 | LR: 0.000938
Epoch   9 | Train Loss: 0.014890 | Val Loss: 0.010605 | LR: 0.000922
Epoch  10 | Train Loss: 0.014898 | Val Loss: 0.009085 | LR: 0.000905
Epoch  11 | Train Loss: 0.014743 | Val Loss: 0.008370 | LR: 0.000885
Epoch  12 | Train Loss: 0.015202 | Val Loss: 0.007775 | LR: 0.000864
Epoch  13 | Train Loss: 0.014528 | Val Loss: 0.008235 | LR: 0.000842
Epoch  14 | Train Loss: 0.014216 | Val Loss: 0.007528 | LR: 0.000819
Epoch  15 | Train Loss: 0.015074 | Val Loss: 0.007337 | LR: 0.000794
Epoch  16 | Train Loss: 0.014840 | Val Loss: 0.008246 | LR: 0.000768
Epoch  17 | Train Loss: 0.014982 | Val Loss: 0.011269 | LR: 0.000741
Epoch  18 | Train Loss: 0.013968 | Val Loss: 0.008495 | LR: 0.000713
Epoch  19 | Train Loss: 0.013597 | Val Loss: 0.010853 | LR: 0.000684
Epoch  20 | Train Loss: 0.013688 | Val Loss: 0.007931 | LR: 0.000655
Epoch  21 | Train Loss: 0.013989 | Val Loss: 0.009810 | LR: 0.000624
Epoch  22 | Train Loss: 0.014603 | Val Loss: 0.006922 | LR: 0.000594
Epoch  23 | Train Loss: 0.015405 | Val Loss: 0.010368 | LR: 0.000563
Epoch  24 | Train Loss: 0.014116 | Val Loss: 0.008999 | LR: 0.000531
Epoch  25 | Train Loss: 0.013842 | Val Loss: 0.008340 | LR: 0.000500
Epoch  26 | Train Loss: 0.015155 | Val Loss: 0.006748 | LR: 0.000469
Epoch  27 | Train Loss: 0.013220 | Val Loss: 0.007383 | LR: 0.000437
Epoch  28 | Train Loss: 0.013236 | Val Loss: 0.008074 | LR: 0.000406
Epoch  29 | Train Loss: 0.013444 | Val Loss: 0.007674 | LR: 0.000376
Epoch  30 | Train Loss: 0.014427 | Val Loss: 0.008850 | LR: 0.000345
Epoch  31 | Train Loss: 0.013666 | Val Loss: 0.006967 | LR: 0.000316
Epoch  32 | Train Loss: 0.013901 | Val Loss: 0.006843 | LR: 0.000287
Epoch  33 | Train Loss: 0.013397 | Val Loss: 0.007228 | LR: 0.000259
Epoch  34 | Train Loss: 0.013845 | Val Loss: 0.008183 | LR: 0.000232
Epoch  35 | Train Loss: 0.013147 | Val Loss: 0.007418 | LR: 0.000206
Epoch  36 | Train Loss: 0.013167 | Val Loss: 0.007263 | LR: 0.000181
Epoch  37 | Train Loss: 0.013309 | Val Loss: 0.007778 | LR: 0.000158
Epoch  38 | Train Loss: 0.013428 | Val Loss: 0.007475 | LR: 0.000136
Epoch  39 | Train Loss: 0.013484 | Val Loss: 0.006602 | LR: 0.000115
Epoch  40 | Train Loss: 0.013563 | Val Loss: 0.007013 | LR: 0.000095
Epoch  41 | Train Loss: 0.013169 | Val Loss: 0.008179 | LR: 0.000078
Epoch  42 | Train Loss: 0.013218 | Val Loss: 0.006401 | LR: 0.000062
Epoch  43 | Train Loss: 0.013636 | Val Loss: 0.007902 | LR: 0.000048
Epoch  44 | Train Loss: 0.013350 | Val Loss: 0.006911 | LR: 0.000035
Epoch  45 | Train Loss: 0.013630 | Val Loss: 0.008610 | LR: 0.000024
Epoch  46 | Train Loss: 0.013274 | Val Loss: 0.007902 | LR: 0.000016
Epoch  47 | Train Loss: 0.013172 | Val Loss: 0.008500 | LR: 0.000009
Epoch  48 | Train Loss: 0.013492 | Val Loss: 0.007689 | LR: 0.000004
Epoch  49 | Train Loss: 0.013113 | Val Loss: 0.008232 | LR: 0.000001
Epoch  50 | Train Loss: 0.013687 | Val Loss: 0.007389 | LR: 0.000000

Final val_loss = 0.006401
