Add example compute function

README.md

@@ -115,7 +115,18 @@ TBA
 
 *Give code examples of the metric being used. Try to include examples that clear up any potential ambiguity left from the metric description above. If possible, provide a range of examples that show both typical and atypical results, as well as examples where a variety of input parameters are passed.*
 
-TBA
+```python
+def compute_metrics(p: EvalPrediction):
+    preds = p.predictions[0] if isinstance(p.predictions, tuple) else p.predictions
+    preds = np.argmax(preds, axis=1)
+    # Use labels instead of ids for hierarchical ISCO-08 classification
+    preds = [model.config.id2label[p] for p in preds]
+    refs = [model.config.id2label[r] for r in p.label_ids]
+    result = metric.compute(predictions=preds, references=refs)
+    return result
+```
+
+More TBA
 
 ## Limitations and Bias