Epoch 50: 36.42%

README.md

@@ -5,7 +5,7 @@ tags:
 - cifar100
 - geometric-learning
 - fractal-encoding
-- trained
+- in-training
 - no-attention
 - no-cross-entropy
 datasets:
@@ -34,9 +34,9 @@ model-index:
 
 **Geometric Basin Classification for CIFAR-100**
 
-🎉 **Training Complete** 🎉
+🚧 **Training in Progress** 🚧
 
-Final Status: Epoch 200/200
+Current Status: Epoch 50/200
 
 ---
 
@@ -46,11 +46,11 @@ Final Status: Epoch 200/200
 |--------|-------|
 | **Best Test Accuracy** | **56.12%** |
 | **Best Epoch** | 160 |
-| **Current Train Accuracy** | 65.10% |
-| **Current Test Accuracy** | 52.69% |
-| **Current α (Cantor param)** | 0.4326 |
+| **Current Train Accuracy** | 39.53% |
+| **Current Test Accuracy** | 36.42% |
+| **Current α (Cantor param)** | 0.4102 |
 | **Total Parameters** | 28,561,101 |
-| **Training Time** | 0:27:29 |
+| **Training Time** | 0:06:40 |
 
 ### All Training Runs
 
@@ -67,6 +67,7 @@ Final Status: Epoch 200/200
 | `20251011_025919` | ✅ | 160 | **56.12%** | 57.80% | 0.4994 |
 | `20251011_032343` | ✅ | 160 | **56.12%** | 53.80% | 0.4377 |
 | `20251011_034748` | ✅ | 160 | **56.12%** | 65.10% | 0.4326 |
+| `20251011_041716` | 🔄 | 160 | **56.12%** | 39.53% | 0.4102 |
 | `20251010_200842` | ✅ | 180 | **53.61%** | 67.53% | 0.4442 |
 | `20251010_185133` | ✅ | 200 | **52.97%** | 69.87% | 0.4452 |
 
@@ -74,7 +75,7 @@ Final Status: Epoch 200/200
 
 | Model | Accuracy | Status |
 |-------|----------|--------|
-| **geo-beatrix (this model)** | **56.12%** | ✅ Complete |
+| **geo-beatrix (this model)** | **56.12%** | 🔄 Training |
 | geo-beatrix (50M params) | 69.0% | Geometric Basin CONV architecture |
 
 🎯 **Current target**: Beat geo-beatrix (69.0%) - Currently -12.88%
@@ -127,7 +128,7 @@ Final Status: Epoch 200/200
     ],
     "spatial_ratio": 0.1,
     "curriculum_start": 0.0,
-    "curriculum_end": 0.5,
+    "curriculum_end": 0.75,
     "fractal_steps": [
       1,
       3
@@ -142,7 +143,7 @@ Final Status: Epoch 200/200
   "loss_function": "Geometric Basin Compatibility",
   "cross_entropy": false,
   "attention_mechanisms": false,
-  "timestamp": "20251011_034748"
+  "timestamp": "20251011_041716"
 }
 ```
 
@@ -156,7 +157,7 @@ Final Status: Epoch 200/200
 ├── best_model_info.json     (which epoch/run this came from)
 ├── runs_history.json        (all training runs and their results)
 ├── README.md
-├── weights/geo-beatrix-resnet34-step20-feats1000/20251011_034748/
+├── weights/geo-beatrix-resnet34-step20-feats1000/20251011_041716/
 │   ├── model.pt                 (best from this training run)
 │   ├── model.safetensors        (best from this training run)
 │   ├── config.json
@@ -166,7 +167,7 @@ Final Status: Epoch 200/200
 │       ├── checkpoint_epoch_100.safetensors
 │       └── checkpoint_epoch_150.safetensors
 │       (snapshots every 10 epochs)
-└── runs/geo-beatrix-resnet34-step20-feats1000/20251011_034748/
+└── runs/geo-beatrix-resnet34-step20-feats1000/20251011_041716/
     ├── events.out.tfevents.*    (TensorBoard logs)
     └── metrics.csv              (training metrics)
 ```
@@ -202,13 +203,13 @@ with open(info_path) as f:
 # Or download from specific training run
 model_path = hf_hub_download(
     repo_id="AbstractPhil/geo-beatrix-resnet",
-    filename="weights/geo-beatrix-resnet34-step20-feats1000/20251011_034748/model.safetensors"
+    filename="weights/geo-beatrix-resnet34-step20-feats1000/20251011_041716/model.safetensors"
 )
 
 # Download specific epoch checkpoint
 epoch_checkpoint = hf_hub_download(
     repo_id="AbstractPhil/geo-beatrix-resnet",
-    filename="weights/geo-beatrix-resnet34-step20-feats1000/20251011_034748/checkpoints/checkpoint_epoch_100.safetensors"
+    filename="weights/geo-beatrix-resnet34-step20-feats1000/20251011_041716/checkpoints/checkpoint_epoch_100.safetensors"
 )
 ```
 
@@ -218,21 +219,20 @@ epoch_checkpoint = hf_hub_download(
 
 ### Best Checkpoint
 - Epoch: 160
-- Train Acc: 64.67%
-- Test Acc: 52.16%
-- Alpha: 0.4345
-- Loss: 0.8826
+- Train Acc: 39.53%
+- Test Acc: 56.12%
+- Alpha: 0.4102
+- Loss: 0.0000
 
 ### Latest 5 Epochs
 
-- **Epoch 196**: Train 66.24%, Test 0.00%, α=0.4326, Loss=0.8374
-- **Epoch 197**: Train 65.13%, Test 0.00%, α=0.4326, Loss=0.7934
-- **Epoch 198**: Train 65.10%, Test 0.00%, α=0.4326, Loss=0.7766
-- **Epoch 199**: Train 65.58%, Test 0.00%, α=0.4326, Loss=0.8093
-- **Epoch 200**: Train 65.10%, Test 52.69%, α=0.4326, Loss=0.7978
+- **Epoch 46**: Train 38.41%, Test 0.00%, α=0.4076, Loss=1.7733
+- **Epoch 47**: Train 38.46%, Test 0.00%, α=0.4071, Loss=1.6722
+- **Epoch 48**: Train 39.58%, Test 0.00%, α=0.4094, Loss=1.7336
+- **Epoch 49**: Train 38.96%, Test 0.00%, α=0.4089, Loss=1.6738
+- **Epoch 50**: Train 39.53%, Test 36.42%, α=0.4102, Loss=1.6315
 
 ### Training Milestones
-- 🎯 **50% Accuracy** reached at epoch 115
 - 📊 **α ≥ 0.40** reached at epoch 17
 
 ---