model update

README.md

@@ -14,7 +14,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9297619047619048
+      value: 0.8450793650793651
   - task:
       name: Analogy Questions (SAT full)
       type: multiple-choice-qa
@@ -91,10 +91,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.9199939731806539
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.9158483158560947
   - task:
       name: Lexical Relation Classification (CogALexV)
       type: classification
@@ -105,10 +105,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.8457746478873239
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.6760195209742395
   - task:
       name: Lexical Relation Classification (EVALution)
       type: classification
@@ -119,10 +119,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.6684723726977249
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.65910797043685
   - task:
       name: Lexical Relation Classification (K&H+N)
       type: classification
@@ -133,10 +133,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.959379564582319
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.8779321856206035
   - task:
       name: Lexical Relation Classification (ROOT09)
       type: classification
@@ -147,10 +147,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.9031651519899718
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.9015700872047177
 
 ---
 # relbert/roberta-large-semeval2012-average-no-mask-prompt-e-nce
@@ -167,13 +167,13 @@ It achieves the following results on the relation understanding tasks:
     - Accuracy on U4: 0.6203703703703703
     - Accuracy on Google: 0.886
 - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-no-mask-prompt-e-nce/raw/main/classification.json)):
-    - Micro F1 score on BLESS: None
-    - Micro F1 score on CogALexV: None
-    - Micro F1 score on EVALution: None
-    - Micro F1 score on K&H+N: None
-    - Micro F1 score on ROOT09: None
+    - Micro F1 score on BLESS: 0.9199939731806539
+    - Micro F1 score on CogALexV: 0.8457746478873239
+    - Micro F1 score on EVALution: 0.6684723726977249
+    - Micro F1 score on K&H+N: 0.959379564582319
+    - Micro F1 score on ROOT09: 0.9031651519899718
 - Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-no-mask-prompt-e-nce/raw/main/relation_mapping.json)):
-    - Accuracy on Relation Mapping: 0.9297619047619048 
+    - Accuracy on Relation Mapping: 0.8450793650793651 
 
 
 ### Usage