Epoch 50: 17.03%

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
 
 ---
 
@@ -46,17 +46,18 @@ Final Status: Epoch 200/200
 |--------|-------|
 | **Best Test Accuracy** | **56.12%** |
 | **Best Epoch** | 160 |
-| **Current Train Accuracy** | 67.82% |
-| **Current Test Accuracy** | 54.90% |
-| **Current α (Cantor param)** | 0.4481 |
+| **Current Train Accuracy** | 16.21% |
+| **Current Test Accuracy** | 17.03% |
+| **Current α (Cantor param)** | 0.3879 |
 | **Total Parameters** | 17,738,741 |
-| **Training Time** | 0:27:21 |
+| **Training Time** | 0:06:31 |
 
 ### All Training Runs
 
 | Timestamp | Status | Best Epoch | Test Acc | Train Acc | α |
 |-----------|--------|------------|----------|-----------|---|
 | `20251010_203717` | ✅ | 160 | **56.12%** | 67.82% | 0.4481 |
+| `20251010_211210` | 🔄 | 160 | **56.12%** | 16.21% | 0.3879 |
 | `20251010_200842` | ✅ | 180 | **53.61%** | 67.53% | 0.4442 |
 | `20251010_185133` | ✅ | 200 | **52.97%** | 69.87% | 0.4452 |
 
@@ -64,7 +65,7 @@ Final Status: Epoch 200/200
 
 | Model | Accuracy | Status |
 |-------|----------|--------|
-| **geo-beatrix (this model)** | **56.12%** | ✅ Complete |
+| **geo-beatrix (this model)** | **56.12%** | 🔄 Training |
 | geo-beatrix      | 69.0% | Geometric Basin CONV architecture - 50m Params |
 
 🎯 **Current target**: Beat geo-beatrix (69.0%) - Currently -12.88%
@@ -101,6 +102,7 @@ Final Status: Epoch 200/200
   "pe_features_per_level": 1000,
   "dropout": 0.1,
   "pretrained_resnet": true,
+  "frozen_resnet": true,
   "a100_optimizations": {
     "mixed_precision": true,
     "torch_compile": false,
@@ -131,7 +133,7 @@ Final Status: Epoch 200/200
   "loss_function": "Geometric Basin Compatibility",
   "cross_entropy": false,
   "attention_mechanisms": false,
-  "timestamp": "20251010_203717"
+  "timestamp": "20251010_211210"
 }
 ```
 
@@ -145,7 +147,7 @@ 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-resnet18-imagenetpretrain-step18-feats1000/20251010_203717/
+├── weights/geo-beatrix-resnet18-imagenetpretrain-step18-feats1000/20251010_211210/
 │   ├── model.pt                 (best from this training run)
 │   ├── model.safetensors        (best from this training run)
 │   ├── config.json
@@ -155,7 +157,7 @@ Final Status: Epoch 200/200
 │       ├── checkpoint_epoch_100.safetensors
 │       └── checkpoint_epoch_150.safetensors
 │       (snapshots every 10 epochs)
-└── runs/geo-beatrix-resnet18-imagenetpretrain-step18-feats1000/20251010_203717/
+└── runs/geo-beatrix-resnet18-imagenetpretrain-step18-feats1000/20251010_211210/
     ├── events.out.tfevents.*    (TensorBoard logs)
     └── metrics.csv              (training metrics)
 ```
@@ -191,13 +193,13 @@ 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-resnet18-imagenetpretrain-step18-feats1000/20251010_203717/model.safetensors"
+    filename="weights/geo-beatrix-resnet18-imagenetpretrain-step18-feats1000/20251010_211210/model.safetensors"
 )
 
 # Download specific epoch checkpoint
 epoch_checkpoint = hf_hub_download(
     repo_id="AbstractPhil/geo-beatrix-resnet",
-    filename="weights/geo-beatrix-resnet18-imagenetpretrain-step18-feats1000/20251010_203717/checkpoints/checkpoint_epoch_100.safetensors"
+    filename="weights/geo-beatrix-resnet18-imagenetpretrain-step18-feats1000/20251010_211210/checkpoints/checkpoint_epoch_100.safetensors"
 )
 ```
 
@@ -207,23 +209,22 @@ epoch_checkpoint = hf_hub_download(
 
 ### Best Checkpoint
 - Epoch: 160
-- Train Acc: 75.82%
+- Train Acc: 16.21%
 - Test Acc: 56.12%
-- Alpha: 0.4504
-- Loss: 0.7204
+- Alpha: 0.3879
+- Loss: 0.0000
 
 ### Latest 5 Epochs
 
-- **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
+- **Epoch 46**: Train 16.06%, Test 0.00%, α=0.3940, Loss=2.2744
+- **Epoch 47**: Train 16.18%, Test 0.00%, α=0.3953, Loss=2.3605
+- **Epoch 48**: Train 16.25%, Test 0.00%, α=0.3902, Loss=2.2532
+- **Epoch 49**: Train 16.27%, Test 0.00%, α=0.3907, Loss=2.2053
+- **Epoch 50**: Train 16.21%, Test 17.03%, α=0.3879, Loss=2.2668
 
 ### Training Milestones
-- 🎯 **50% Accuracy** reached at epoch 50
-- 📊 **α ≥ 0.40** reached at epoch 9
-- 📊 **α ≥ 0.44** (near triadic equilibrium) at epoch 52
+
+- 🔄 Training in early stages...
 
 ---