Upload README.md

README.md

@@ -8,11 +8,11 @@ pinned: false
 ---
 
 
-# Random Baseline Model for Climate Disinformation Classification
+# Logistic regression Model for Climate Disinformation Classification
 
 ## Model Description
 
-This is a random baseline model for the Frugal AI Challenge 2024, specifically for the text classification task of identifying climate disinformation. The model serves as a performance floor, randomly assigning labels to text inputs without any learning.
+This is a Logistic regression baseline model for the Frugal AI Challenge 2024, specifically for the text classification task of identifying climate disinformation. The model serves as a performance floor.
 
 ### Intended Use
 
@@ -40,7 +40,7 @@ The model uses the QuotaClimat/frugalaichallenge-text-train dataset:
 ## Performance
 
 ### Metrics
-- **Accuracy**: ~12.5% (random chance with 8 classes)
+- **Accuracy**: ~63.5% 
 - **Environmental Impact**:
   - Emissions tracked in gCO2eq
   - Energy consumption tracked in Wh
@@ -57,10 +57,10 @@ Environmental impact is tracked using CodeCarbon, measuring:
 This tracking helps establish a baseline for the environmental impact of model deployment and inference.
 
 ## Limitations
-- Makes completely random predictions
+- Makes Logistic regression predictions
 - No learning or pattern recognition
-- No consideration of input text
-- Serves only as a baseline reference
+- Input text vectorized
+- Serves only as a LR baseline reference
 - Not suitable for any real-world applications
 
 ## Ethical Considerations