Epoch 200: 67.76%

README.md

@@ -5,7 +5,7 @@ tags:
 - cifar100
 - geometric-learning
 - fractal-encoding
-- in-training
+- trained
 - no-attention
 - no-cross-entropy
 datasets:
@@ -25,7 +25,7 @@ model-index:
       type: cifar100
     metrics:
     - type: accuracy
-      value: 67.43
+      value: 68.37
       name: Test Accuracy
       verified: false
 ---
@@ -34,9 +34,9 @@ model-index:
 
 **Geometric Basin Classification for CIFAR-100**
 
-🚧 **Training in Progress** 🚧
+🎉 **Training Complete** 🎉
 
-Current Status: Epoch 150/200
+Final Status: Epoch 200/200
 
 ---
 
@@ -44,25 +44,25 @@ Current Status: Epoch 150/200
 
 | Metric | Value |
 |--------|-------|
-| **Best Test Accuracy** | **67.43%** |
+| **Best Test Accuracy** | **68.37%** |
 | **Best Epoch** | 195 |
-| **Current Train Accuracy** | 73.96% |
-| **Current Test Accuracy** | 66.19% |
-| **Current α (Cantor param)** | 0.4444 |
+| **Current Train Accuracy** | 73.83% |
+| **Current Test Accuracy** | 67.76% |
+| **Current α (Cantor param)** | 0.4439 |
 | **Total Parameters** | 46,338,737 |
-| **Training Time** | 0:41:17 |
+| **Training Time** | 0:55:26 |
 
 ### All Training Runs
 
 | Timestamp | Status | Best Epoch | Test Acc | Train Acc | α |
 |-----------|--------|------------|----------|-----------|---|
-| `20251010_025042` | 🔄 | 195 | **67.43%** | 73.96% | 0.4444 |
+| `20251010_025042` | ✅ | 195 | **68.37%** | 73.83% | 0.4439 |
 
 ### Comparison to State-of-the-Art
 
 | Model | Accuracy | Status |
 |-------|----------|--------|
-| **geo-beatrix (this model)** | **67.43%** | 🔄 Training |
+| **geo-beatrix (this model)** | **68.37%** | ✅ Complete |
 | vit-beatrix-dualstream | 66.0% | Vision Transformer + Cross-Entropy |
 | CLIP ViT-L/14 (zero-shot) | ~63-65% | 400M image-text pairs |
 | CLIP ViT-B/32 (zero-shot) | ~63.5% | Vision Transformer |
@@ -189,23 +189,24 @@ epoch_checkpoint = hf_hub_download(
 
 ### Best Checkpoint
 - Epoch: 195
-- Train Acc: 73.96%
-- Test Acc: 67.43%
-- Alpha: 0.4444
-- Loss: 0.0000
+- Train Acc: 71.12%
+- Test Acc: 68.37%
+- Alpha: 0.4439
+- Loss: 0.5276
 
 ### Latest 5 Epochs
 
-- **Epoch 146**: Train 69.94%, Test 0.00%, α=0.4428, Loss=0.5624
-- **Epoch 147**: Train 74.67%, Test 0.00%, α=0.4433, Loss=0.5763
-- **Epoch 148**: Train 71.69%, Test 0.00%, α=0.4430, Loss=0.5626
-- **Epoch 149**: Train 75.45%, Test 0.00%, α=0.4426, Loss=0.5743
-- **Epoch 150**: Train 73.96%, Test 66.19%, α=0.4444, Loss=0.5696
+- **Epoch 196**: Train 67.31%, Test 0.00%, α=0.4439, Loss=0.5133
+- **Epoch 197**: Train 70.67%, Test 0.00%, α=0.4439, Loss=0.5191
+- **Epoch 198**: Train 73.48%, Test 0.00%, α=0.4439, Loss=0.5260
+- **Epoch 199**: Train 66.64%, Test 0.00%, α=0.4439, Loss=0.5095
+- **Epoch 200**: Train 73.83%, Test 67.76%, α=0.4439, Loss=0.5309
 
 ### Training Milestones
 - 🎯 **50% Accuracy** reached at epoch 35
 - 🎯 **60% Accuracy** reached at epoch 65
 - 🏆 **Beat vit-beatrix (66.0%)** at epoch 130
+- 🚀 **67% Accuracy** reached at epoch 165
 - 📊 **α ≥ 0.40** reached at epoch 10
 - 📊 **α ≥ 0.44** (near triadic equilibrium) at epoch 105