Update README.md

README.md

@@ -84,11 +84,10 @@ Each article was annotated for media framing according to Entman's theory.
 
 #### Testing Data
 
-A hold-out test set consisting of 600 news articles from the same sources as training.
+A hold-out test set consisting of 3000 news articles from the same sources as training.
 
 #### Factors
 
-- Media source
 - Framing category
 
 #### Metrics
@@ -98,12 +97,12 @@ A hold-out test set consisting of 600 news articles from the same sources as tra
 
 ### Results
 
-- Accuracy: 84.2%
-- Macro F1: 0.83
+- Accuracy: 0.2400
+- Macro F1: 0.6386
 
 ## Environmental Impact
 
-- **Hardware Type:** NVIDIA Tesla T4 (Google Colab Pro)
+- **Hardware Type:** Google Colab
 - **Hours used:** ~2 hours
 - **Cloud Provider:** Google Cloud
 - **Compute Region:** US
@@ -117,7 +116,7 @@ This model uses BERT (base, uncased) architecture with a classification head to
 
 ### Compute Infrastructure
 
-- **Hardware:** Google Colab Pro GPU (Tesla T4)
+- **Hardware:** Google Colab
 - **Software:** Python 3.10, PyTorch 2.1.2, Transformers 4.40.1
 
 ## Citation