Reconcile SHD accuracy and drop SOTA column

README.md

@@ -31,7 +31,7 @@ model-index:
             value: 84.5
           - name: Float Accuracy (N1)
             type: accuracy
-            value: 90.6
+            value: 85.9
           - name: Quantised Accuracy (N3, int16)
             type: accuracy
             value: 90.8
@@ -52,11 +52,11 @@ Spiking Neural Network trained on the Spiking Heidelberg Digits (SHD) dataset us
 
 ## Results
 
-| Generation | Architecture | Float Accuracy | Params | vs SOTA |
-|------------|-------------|----------------|--------|---------|
-| **N3** | 700→1536→20 (rec, adLIF) | **91.0%** | 3.47M | Matches Loihi 2 (90.9%) |
-| N2 | 700→512→20 (rec, adLIF) | 84.5% | 759K | — |
-| N1 | 700→1024→20 (rec, LIF) | 90.6% | 1.79M | Basic LIF baseline |
+| Generation | Architecture | Float Accuracy | Params |
+|------------|-------------|----------------|--------|
+| **N3** | 700→1536→20 (rec, adLIF) | **91.0%** | 3.47M |
+| N2 | 700→512→20 (rec, adLIF) | 84.5% | 759K |
+| N1 | 700→1024→20 (rec, LIF) | 85.9% | 1.79M |
 
 ## Reproduce
 
@@ -65,13 +65,13 @@ git clone https://github.com/catalyst-neuromorphic/catalyst-benchmarks.git
 cd catalyst-benchmarks
 pip install -e .
 
-# N3 (91.0%)
+# N3
 python shd/train.py --neuron adlif --hidden 1536 --epochs 200 --device cuda:0 --amp
 
-# N2 (84.5%)
+# N2
 python shd/train.py --neuron adlif --hidden 512 --epochs 200 --device cuda:0
 
-# N1 (90.6%)
+# N1
 python shd/train.py --neuron lif --hidden 1024 --epochs 200 --device cuda:0
 ```