Epoch 200: 54.90%

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: 55.56
+      value: 56.12
       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
 
 ---
 
@@ -44,19 +44,19 @@ Current Status: Epoch 150/200
 
 | Metric | Value |
 |--------|-------|
-| **Best Test Accuracy** | **55.56%** |
-| **Best Epoch** | 145 |
-| **Current Train Accuracy** | 71.29% |
-| **Current Test Accuracy** | 55.35% |
-| **Current α (Cantor param)** | 0.4498 |
+| **Best Test Accuracy** | **56.12%** |
+| **Best Epoch** | 160 |
+| **Current Train Accuracy** | 67.82% |
+| **Current Test Accuracy** | 54.90% |
+| **Current α (Cantor param)** | 0.4481 |
 | **Total Parameters** | 17,738,741 |
-| **Training Time** | 0:20:26 |
+| **Training Time** | 0:27:21 |
 
 ### All Training Runs
 
 | Timestamp | Status | Best Epoch | Test Acc | Train Acc | α |
 |-----------|--------|------------|----------|-----------|---|
-| `20251010_203717` | 🔄 | 145 | **55.56%** | 71.29% | 0.4498 |
+| `20251010_203717` | ✅ | 160 | **56.12%** | 67.82% | 0.4481 |
 | `20251010_200842` | ✅ | 180 | **53.61%** | 67.53% | 0.4442 |
 | `20251010_185133` | ✅ | 200 | **52.97%** | 69.87% | 0.4452 |
 
@@ -64,10 +64,10 @@ Current Status: Epoch 150/200
 
 | Model | Accuracy | Status |
 |-------|----------|--------|
-| **geo-beatrix (this model)** | **55.56%** | 🔄 Training |
+| **geo-beatrix (this model)** | **56.12%** | ✅ Complete |
 | geo-beatrix      | 69.0% | Geometric Basin CONV architecture - 50m Params |
 
-🎯 **Current target**: Beat geo-beatrix (69.0%) - Currently -13.44%
+🎯 **Current target**: Beat geo-beatrix (69.0%) - Currently -12.88%
 
 ---
 
@@ -206,19 +206,19 @@ epoch_checkpoint = hf_hub_download(
 ## Training History
 
 ### Best Checkpoint
-- Epoch: 145
-- Train Acc: 67.56%
-- Test Acc: 55.56%
-- Alpha: 0.4482
-- Loss: 0.7221
+- Epoch: 160
+- Train Acc: 75.82%
+- Test Acc: 56.12%
+- Alpha: 0.4504
+- Loss: 0.7204
 
 ### Latest 5 Epochs
 
-- **Epoch 146**: Train 70.54%, Test 0.00%, α=0.4474, Loss=0.7299
-- **Epoch 147**: Train 72.85%, Test 0.00%, α=0.4495, Loss=0.7320
-- **Epoch 148**: Train 71.40%, Test 0.00%, α=0.4492, Loss=0.7273
-- **Epoch 149**: Train 73.56%, Test 0.00%, α=0.4492, Loss=0.7268
-- **Epoch 150**: Train 71.29%, Test 55.35%, α=0.4498, Loss=0.7280
+- **Epoch 196**: Train 72.92%, Test 0.00%, α=0.4481, Loss=0.6446
+- **Epoch 197**: Train 68.70%, Test 0.00%, α=0.4481, Loss=0.6144
+- **Epoch 198**: Train 70.45%, Test 0.00%, α=0.4481, Loss=0.6430
+- **Epoch 199**: Train 71.07%, Test 0.00%, α=0.4481, Loss=0.6430
+- **Epoch 200**: Train 67.82%, Test 54.90%, α=0.4481, Loss=0.6142
 
 ### Training Milestones
 - 🎯 **50% Accuracy** reached at epoch 50