Update config.json
Browse files- config.json +139 -21
config.json
CHANGED
|
@@ -4,65 +4,183 @@
|
|
| 4 |
"framework": "pytorch",
|
| 5 |
"version": "1.0",
|
| 6 |
"trained_epoch": 10,
|
| 7 |
-
"training_date": "2025-10-28T03:
|
| 8 |
"num_blocks": 9,
|
| 9 |
"total_parameters": 884327310,
|
| 10 |
"num_timestep_bins": 100,
|
| 11 |
"num_patterns_per_bin": 10,
|
| 12 |
-
"
|
| 13 |
"down_0": {
|
| 14 |
"input_dim": 320,
|
| 15 |
-
"scale_dim": 128
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
},
|
| 17 |
"down_1": {
|
| 18 |
"input_dim": 640,
|
| 19 |
-
"scale_dim": 192
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
},
|
| 21 |
"down_2": {
|
| 22 |
"input_dim": 1280,
|
| 23 |
-
"scale_dim": 256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
},
|
| 25 |
"down_3": {
|
| 26 |
"input_dim": 1280,
|
| 27 |
-
"scale_dim": 256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
},
|
| 29 |
"mid": {
|
| 30 |
"input_dim": 1280,
|
| 31 |
"scale_dim": 256,
|
| 32 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
"up_0": {
|
| 35 |
"input_dim": 1280,
|
| 36 |
-
"scale_dim": 256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
},
|
| 38 |
"up_1": {
|
| 39 |
"input_dim": 1280,
|
| 40 |
-
"scale_dim": 256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
},
|
| 42 |
"up_2": {
|
| 43 |
"input_dim": 640,
|
| 44 |
-
"scale_dim": 192
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
},
|
| 46 |
"up_3": {
|
| 47 |
"input_dim": 320,
|
| 48 |
-
"scale_dim": 128
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
}
|
| 50 |
},
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
|
|
|
|
|
|
| 59 |
},
|
| 60 |
"loss_config": {
|
| 61 |
"feature_similarity_weight": 0.4,
|
| 62 |
"rose_weight": 0.25,
|
| 63 |
"ce_weight": 0.15,
|
| 64 |
-
"cayley_weight": 0.1,
|
| 65 |
"pattern_diversity_weight": 0.05,
|
| 66 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
}
|
| 68 |
}
|
|
|
|
| 4 |
"framework": "pytorch",
|
| 5 |
"version": "1.0",
|
| 6 |
"trained_epoch": 10,
|
| 7 |
+
"training_date": "2025-10-28T03:34:06.000667",
|
| 8 |
"num_blocks": 9,
|
| 9 |
"total_parameters": 884327310,
|
| 10 |
"num_timestep_bins": 100,
|
| 11 |
"num_patterns_per_bin": 10,
|
| 12 |
+
"block_configs": {
|
| 13 |
"down_0": {
|
| 14 |
"input_dim": 320,
|
| 15 |
+
"scale_dim": 128,
|
| 16 |
+
"use_belly": true,
|
| 17 |
+
"belly_expand": 2.0,
|
| 18 |
+
"num_experts": 3,
|
| 19 |
+
"num_gate_heads": 3,
|
| 20 |
+
"projective_head": "auto"
|
| 21 |
},
|
| 22 |
"down_1": {
|
| 23 |
"input_dim": 640,
|
| 24 |
+
"scale_dim": 192,
|
| 25 |
+
"use_belly": true,
|
| 26 |
+
"belly_expand": 2.0,
|
| 27 |
+
"num_experts": 3,
|
| 28 |
+
"num_gate_heads": 3,
|
| 29 |
+
"projective_head": "auto"
|
| 30 |
},
|
| 31 |
"down_2": {
|
| 32 |
"input_dim": 1280,
|
| 33 |
+
"scale_dim": 256,
|
| 34 |
+
"use_belly": true,
|
| 35 |
+
"belly_expand": 2.0,
|
| 36 |
+
"num_experts": 3,
|
| 37 |
+
"num_gate_heads": 3,
|
| 38 |
+
"projective_head": "auto"
|
| 39 |
},
|
| 40 |
"down_3": {
|
| 41 |
"input_dim": 1280,
|
| 42 |
+
"scale_dim": 256,
|
| 43 |
+
"use_belly": true,
|
| 44 |
+
"belly_expand": 2.0,
|
| 45 |
+
"num_experts": 3,
|
| 46 |
+
"num_gate_heads": 3,
|
| 47 |
+
"projective_head": "auto"
|
| 48 |
},
|
| 49 |
"mid": {
|
| 50 |
"input_dim": 1280,
|
| 51 |
"scale_dim": 256,
|
| 52 |
+
"use_belly": true,
|
| 53 |
+
"belly_expand": 1.5,
|
| 54 |
+
"num_experts": 4,
|
| 55 |
+
"num_gate_heads": 4,
|
| 56 |
+
"projective_head": "custom"
|
| 57 |
},
|
| 58 |
"up_0": {
|
| 59 |
"input_dim": 1280,
|
| 60 |
+
"scale_dim": 256,
|
| 61 |
+
"use_belly": true,
|
| 62 |
+
"belly_expand": 2.0,
|
| 63 |
+
"num_experts": 3,
|
| 64 |
+
"num_gate_heads": 3,
|
| 65 |
+
"projective_head": "auto"
|
| 66 |
},
|
| 67 |
"up_1": {
|
| 68 |
"input_dim": 1280,
|
| 69 |
+
"scale_dim": 256,
|
| 70 |
+
"use_belly": true,
|
| 71 |
+
"belly_expand": 2.0,
|
| 72 |
+
"num_experts": 3,
|
| 73 |
+
"num_gate_heads": 3,
|
| 74 |
+
"projective_head": "auto"
|
| 75 |
},
|
| 76 |
"up_2": {
|
| 77 |
"input_dim": 640,
|
| 78 |
+
"scale_dim": 192,
|
| 79 |
+
"use_belly": true,
|
| 80 |
+
"belly_expand": 2.0,
|
| 81 |
+
"num_experts": 3,
|
| 82 |
+
"num_gate_heads": 3,
|
| 83 |
+
"projective_head": "auto"
|
| 84 |
},
|
| 85 |
"up_3": {
|
| 86 |
"input_dim": 320,
|
| 87 |
+
"scale_dim": 128,
|
| 88 |
+
"use_belly": true,
|
| 89 |
+
"belly_expand": 1.5,
|
| 90 |
+
"num_experts": 3,
|
| 91 |
+
"num_gate_heads": 3,
|
| 92 |
+
"projective_head": "auto"
|
| 93 |
}
|
| 94 |
},
|
| 95 |
+
"block_weights": {
|
| 96 |
+
"down_0": 0.8,
|
| 97 |
+
"down_1": 1.0,
|
| 98 |
+
"down_2": 1.2,
|
| 99 |
+
"down_3": 1.3,
|
| 100 |
+
"mid": 1.5,
|
| 101 |
+
"up_0": 1.3,
|
| 102 |
+
"up_1": 1.2,
|
| 103 |
+
"up_2": 1.0,
|
| 104 |
+
"up_3": 0.8
|
| 105 |
},
|
| 106 |
"loss_config": {
|
| 107 |
"feature_similarity_weight": 0.4,
|
| 108 |
"rose_weight": 0.25,
|
| 109 |
"ce_weight": 0.15,
|
|
|
|
| 110 |
"pattern_diversity_weight": 0.05,
|
| 111 |
+
"cayley_weight": 0.1,
|
| 112 |
+
"cantor_coherence_weight": 0.05,
|
| 113 |
+
"use_soft_assignment": true,
|
| 114 |
+
"temperature": 0.1,
|
| 115 |
+
"cayley_volume_floor": 0.0001,
|
| 116 |
+
"cayley_chaos_scale": 1.0,
|
| 117 |
+
"cayley_edge_weight": 0.5,
|
| 118 |
+
"cayley_gram_weight": 0.1
|
| 119 |
+
},
|
| 120 |
+
"training": {
|
| 121 |
+
"base_model": "runwayml/stable-diffusion-v1-5",
|
| 122 |
+
"sd_blocks_used": [
|
| 123 |
+
"down_0",
|
| 124 |
+
"down_1",
|
| 125 |
+
"down_2",
|
| 126 |
+
"down_3",
|
| 127 |
+
"mid",
|
| 128 |
+
"up_0",
|
| 129 |
+
"up_1",
|
| 130 |
+
"up_2",
|
| 131 |
+
"up_3"
|
| 132 |
+
],
|
| 133 |
+
"dataset": {
|
| 134 |
+
"type": "SymbolicPromptDataset",
|
| 135 |
+
"num_samples": 10000,
|
| 136 |
+
"complexity_distribution": {
|
| 137 |
+
"1": 0.05,
|
| 138 |
+
"2": 0.15,
|
| 139 |
+
"3": 0.4,
|
| 140 |
+
"4": 0.25,
|
| 141 |
+
"5": 0.15
|
| 142 |
+
},
|
| 143 |
+
"seed": 42
|
| 144 |
+
},
|
| 145 |
+
"batch_size": 16,
|
| 146 |
+
"num_epochs": 10,
|
| 147 |
+
"optimizer": {
|
| 148 |
+
"type": "AdamW",
|
| 149 |
+
"learning_rate": 0.001,
|
| 150 |
+
"weight_decay": 0.001
|
| 151 |
+
},
|
| 152 |
+
"pool_mode": "mean",
|
| 153 |
+
"checkpoint_interval": 2,
|
| 154 |
+
"num_workers": 2,
|
| 155 |
+
"pin_memory": true
|
| 156 |
+
},
|
| 157 |
+
"feature_extraction": {
|
| 158 |
+
"method": "SD1.5 UNet Hooks",
|
| 159 |
+
"spatial_features": true,
|
| 160 |
+
"pooling": "mean",
|
| 161 |
+
"dtype": "float32"
|
| 162 |
+
},
|
| 163 |
+
"capabilities": {
|
| 164 |
+
"timestep_classification": true,
|
| 165 |
+
"pattern_classification": true,
|
| 166 |
+
"joint_classification": true,
|
| 167 |
+
"num_classes": 1000,
|
| 168 |
+
"geometric_constraints": true,
|
| 169 |
+
"multi_expert_routing": true
|
| 170 |
+
},
|
| 171 |
+
"companions": {
|
| 172 |
+
"type": "GeoDavidCompanion",
|
| 173 |
+
"timestep_head": "ProjectiveHead",
|
| 174 |
+
"pattern_head": "ProjectiveHead",
|
| 175 |
+
"geometric_features": [
|
| 176 |
+
"cayley_menger_volume",
|
| 177 |
+
"edge_lengths",
|
| 178 |
+
"gram_matrix"
|
| 179 |
+
],
|
| 180 |
+
"loss_functions": [
|
| 181 |
+
"rose",
|
| 182 |
+
"cayley",
|
| 183 |
+
"cantor"
|
| 184 |
+
]
|
| 185 |
}
|
| 186 |
}
|