update readme with w&b guide

README.md

@@ -140,13 +140,19 @@ res = module._compute(payload, max_iou=0.5, recognition_thresholds=[0.3, 0.5, 0.
 module.wandb(res,log_plots=True, debug=True)
 ```
 
+- If `log_plots` is `True`, the W&B logging function generates four bar plots:  
+  - **Recognition metrics**  
+  - **Recognized metrics**  
+  - **Evaluation metrics** (F1, precision, recall)  
+  - **Confusion metrics** (false negatives, false positives, true positives)
+   
+- If `debug` is `True`, the function logs the global metrics plus the per-sequence evaluation metrics in descending order of F1 score under the **Logs** section of the run page.
 
+- If both `log_plots` and `debug` are `False`, the function logs the metrics to the **Summary**.  
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65ca2aafdc38a2858aa43f1e/RYEsFwt6K-jP0mp7_RIZv.png)
 
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/65ca2aafdc38a2858aa43f1e/zVbKzrURGYV858rpnOt_Q.png)
-
 ## Citations
 
 ```bibtex {"id":"01HPS3ASFJXVQR88985GKHAQRE"}