Epoch 50: 44.88%

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** | 52.13% |
-| **Current Test Accuracy** | 33.92% |
-| **Current α (Cantor param)** | 0.4997 |
+| **Current Train Accuracy** | 48.67% |
+| **Current Test Accuracy** | 44.88% |
+| **Current α (Cantor param)** | 0.4290 |
 | **Total Parameters** | 21,846,001 |
-| **Training Time** | 0:11:41 |
+| **Training Time** | 0:06:27 |
 
 ### All Training Runs
 
@@ -60,6 +60,7 @@ Final Status: Epoch 200/200
 | `20251010_211210` | 🔄 | 160 | **56.12%** | 16.21% | 0.3879 |
 | `20251010_213807` | ✅ | 160 | **56.12%** | 64.44% | 0.4419 |
 | `20251010_230300` | ✅ | 160 | **56.12%** | 52.13% | 0.4997 |
+| `20251010_234239` | 🔄 | 160 | **56.12%** | 48.67% | 0.4290 |
 | `20251010_200842` | ✅ | 180 | **53.61%** | 67.53% | 0.4442 |
 | `20251010_185133` | ✅ | 200 | **52.97%** | 69.87% | 0.4452 |
 
@@ -67,7 +68,7 @@ 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%
@@ -97,7 +98,7 @@ Final Status: Epoch 200/200
   "num_classes": 100,
   "batch_size": 1024,
   "num_epochs": 200,
-  "base_learning_rate": 0.01,
+  "base_learning_rate": 0.001,
   "weight_decay": 0.0,
   "warmup_epochs": 10,
   "pe_levels": 12,
@@ -135,7 +136,7 @@ Final Status: Epoch 200/200
   "loss_function": "Geometric Basin Compatibility",
   "cross_entropy": false,
   "attention_mechanisms": false,
-  "timestamp": "20251010_230300"
+  "timestamp": "20251010_234239"
 }
 ```
 
@@ -149,7 +150,7 @@ 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-step12-feats100/20251010_230300/
+├── weights/geo-beatrix-resnet34-step12-feats100/20251010_234239/
 │   ├── model.pt                 (best from this training run)
 │   ├── model.safetensors        (best from this training run)
 │   ├── config.json
@@ -159,7 +160,7 @@ Final Status: Epoch 200/200
 │       ├── checkpoint_epoch_100.safetensors
 │       └── checkpoint_epoch_150.safetensors
 │       (snapshots every 10 epochs)
-└── runs/geo-beatrix-resnet34-step12-feats100/20251010_230300/
+└── runs/geo-beatrix-resnet34-step12-feats100/20251010_234239/
     ├── events.out.tfevents.*    (TensorBoard logs)
     └── metrics.csv              (training metrics)
 ```
@@ -195,13 +196,13 @@ 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-step12-feats100/20251010_230300/model.safetensors"
+    filename="weights/geo-beatrix-resnet34-step12-feats100/20251010_234239/model.safetensors"
 )
 
 # Download specific epoch checkpoint
 epoch_checkpoint = hf_hub_download(
     repo_id="AbstractPhil/geo-beatrix-resnet",
-    filename="weights/geo-beatrix-resnet34-step12-feats100/20251010_230300/checkpoints/checkpoint_epoch_100.safetensors"
+    filename="weights/geo-beatrix-resnet34-step12-feats100/20251010_234239/checkpoints/checkpoint_epoch_100.safetensors"
 )
 ```
 
@@ -211,23 +212,21 @@ epoch_checkpoint = hf_hub_download(
 
 ### Best Checkpoint
 - Epoch: 160
-- Train Acc: 51.05%
-- Test Acc: 33.51%
-- Alpha: 0.4990
-- Loss: 0.6207
+- Train Acc: 48.67%
+- Test Acc: 56.12%
+- Alpha: 0.4290
+- Loss: 0.0000
 
 ### Latest 5 Epochs
 
-- **Epoch 196**: Train 48.17%, Test 31.52%, α=0.4995, Loss=0.5705
-- **Epoch 197**: Train 55.84%, Test 0.00%, α=0.4996, Loss=0.6154
-- **Epoch 198**: Train 46.81%, Test 31.33%, α=0.4997, Loss=0.5750
-- **Epoch 199**: Train 48.07%, Test 0.00%, α=0.4997, Loss=0.5928
-- **Epoch 200**: Train 52.13%, Test 33.92%, α=0.4997, Loss=0.5905
+- **Epoch 46**: Train 44.09%, Test 44.26%, α=0.4215, Loss=1.1601
+- **Epoch 47**: Train 47.62%, Test 0.00%, α=0.4243, Loss=1.4618
+- **Epoch 48**: Train 42.52%, Test 44.36%, α=0.4247, Loss=1.1314
+- **Epoch 49**: Train 45.33%, Test 0.00%, α=0.4260, Loss=1.2854
+- **Epoch 50**: Train 48.67%, Test 44.88%, α=0.4290, Loss=1.4133
 
 ### Training Milestones
-- 📊 **α ≥ 0.40** reached at epoch 6
-- 📊 **α ≥ 0.44** (near triadic equilibrium) at epoch 8
-- ⚛️  **α = 0.50** (TRIADIC EQUILIBRIUM!) at epoch 21
+- 📊 **α ≥ 0.40** reached at epoch 36
 
 ---