Update readme for how to use

README.md

@@ -23,6 +23,7 @@ pinned: false
 *Give general statement of how to use the metric*
 
 *Provide simplest possible example for using the metric*
+
 ```python
 import evaluate
 
@@ -37,6 +38,7 @@ valid_labels = [
     "/推薦/其他",
     ""
 ]
+
 predictions = [
     ["/開箱/xxx", "/教學/yyy", "/表達/zzz"],
     ["/分享/外部資訊/aaa", "/教學/yyy", "/表達/zzz", "/分享/個人資訊/bbb"]
@@ -45,11 +47,16 @@ references = [
     ["/開箱/xxx", "/教學/yyy", "/表達/zzz"],
     ["/推薦/產品/bbb", "/教學/yyy", "/表達/zzz"]
 ]
+
 metric = evaluate.load("DarrenChensformer/action_generation")
 result = metric.compute(predictions=predictions, references=references, valid_labels=valid_labels, detailed_scores=True)
 print(result)
 ```
 
+```
+{'class': {'precision': 0.7143, 'recall': 0.8333, 'f1': 0.7692}, 'phrase': {'precision': 0.8571, 'recall': 1.0, 'f1': 0.9231}, 'weighted_sum': {'precision': 0.7429, 'recall': 0.8666, 'f1': 0.8}}
+```
+
 ### Inputs
 *List all input arguments in the format below*
 - **input_field** *(type): Definition of input, with explanation if necessary. State any default value(s).*