Update beatrix-cifar100 - Epoch 0 - Acc: 0.1074

README.md

@@ -12,14 +12,14 @@ license: mit
 # ViT-Beatrix: Fractal PE + Geometric Simplex Vision Transformer
 
 This model integrates Devil's Staircase positional encoding with geometric simplex features
-for vision tasks. Trained on CIFAR-10.
+for vision tasks. Trained on CIFAR-100.
 
 ## Model Details
 
 - **Architecture**: Vision Transformer with fractal positional encoding
 - **Dataset**: CIFAR-100 (100 classes)
-- **Embedding Dimension**: 256
-- **Depth**: 12 layers
+- **Embedding Dimension**: 512
+- **Depth**: 4 layers
 - **Patch Size**: 4x4
 - **PE Levels**: 12
 - **Simplex Dimension**: 5-simplex
@@ -28,7 +28,7 @@ for vision tasks. Trained on CIFAR-10.
 
 - **Dataset**: CIFAR-100
 - **Epochs**: 0
-- **Best Accuracy**: 0.0892
+- **Best Accuracy**: 0.1074
 - **Batch Size**: 512
 - **Learning Rate**: 0.001
 
@@ -49,15 +49,15 @@ from huggingface_hub import hf_hub_download
 # Download weights from Hub
 weights_path = hf_hub_download(
     repo_id="AbstractPhil/vit-beatrix",
-    filename="weights/beatrix-cifar100/20251007_181653/model.safetensors"
+    filename="weights/beatrix-cifar100/20251007_181852/model.safetensors"
 )
 
 # Load model
 model = SimplifiedGeometricClassifier(
-    num_classes=100,  # CIFAR-100
+    num_classes=100,
     img_size=32,
-    embed_dim=256,
-    depth=12
+    embed_dim=512,
+    depth=4
 )
 
 # Load weights

weights/beatrix-cifar100/20251007_181852/config.json

@@ -0,0 +1,43 @@
+{
+  "num_classes": 100,
+  "img_size": 32,
+  "patch_size": 4,
+  "embed_dim": 512,
+  "k_simplex": 5,
+  "depth": 4,
+  "num_heads": 8,
+  "mlp_ratio": 4.0,
+  "dropout": 0.0,
+  "pe_levels": 12,
+  "pe_features_per_level": 2,
+  "pe_smooth_tau": 0.25,
+  "simplex_feature_weight": 0.2,
+  "batch_size": 512,
+  "num_epochs": 50,
+  "learning_rate": 0.001,
+  "weight_decay": 0.005,
+  "warmup_epochs": 10,
+  "task_loss_weight": 1.0,
+  "flow_loss_weight": 0.5,
+  "coherence_loss_weight": 0.3,
+  "multiscale_loss_weight": 0.2,
+  "volume_reg_weight": 0.1,
+  "use_augmentation": true,
+  "mixup_alpha": 0.2,
+  "cutmix_alpha": 1.0,
+  "device": "cuda",
+  "num_workers": 2,
+  "pin_memory": true,
+  "save_dir": "./checkpoints",
+  "save_every": 10,
+  "use_safetensors": true,
+  "timestamp_dirs": true,
+  "push_to_hub": true,
+  "hub_model_id": "AbstractPhil/vit-beatrix",
+  "hub_model_name": "beatrix-cifar100",
+  "hub_upload_best_only": true,
+  "use_tensorboard": true,
+  "log_dir": "./logs",
+  "log_every": 50,
+  "train_baseline": false
+}

weights/beatrix-cifar100/20251007_181852/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac2aa619f8043deb184307abb828d7f50d90e9b0723f008a074e26e72c5cbea
+size 50831604