update terratorch command

README.md

@@ -63,7 +63,7 @@ Please see [TerraTorch-Iterate](https://github.com/IBM/terratorch-iterate) for i
 ### 2.2 Running benchmark experiments
 **On existing models**:  To run experiments on an existing model, a custom config file specifying the model and dataset parameters should be prepared. To compare performance of multiple models, define a config file with unique experiment name for each model being comapred. Please see the `examples` folder for sample config files. Each config file (experiment) can then be executed with the following command:
 
-`terratorch_iterate --config <path_to_config_file>`
+`terratorch iterate --hpo --repeat --config <config-file>`
 
 **On new models**: New models can be evaluated by first onboarding them to the [TerraTorch](https://github.com/IBM/terratorch/) library. Once onboarded, benchmarking may be conducted as outlined above.
 

app.py

@@ -41,7 +41,8 @@ def safe_path_join(*parts):
 def sanitize_column_name(col: str) -> str:
     """Sanitize column names for HTML display"""
     col= str(col)
-    col = col.replace("_", " ").title()
+    is_result_column = [True if item in col else False for item in ["IQM", "Mean"]]    
+    col = col.replace("_", " ") if any(is_result_column) else col.replace("_", " ").title()
     return html.escape(col)
 
 
@@ -410,7 +411,7 @@ def main():
     del compiled_results
     
     #create header
-    st.title("🏆 GeoBench Leaderboard")
+    st.title("🏆 GEO-Bench Leaderboard")
     st.markdown("Leaderboard to evaluate Geospatial Foundation Models on downstream tasks")
     # content = create_yall()
     tabs = st.tabs(["🏆 Main Leaderboard", "Dimensions", "Datasets", "Info", "📝 How to Submit"])