Add evaluation results on the default config of multi_nli

README.md

@@ -121,6 +121,59 @@ model-index:
       type: loss
       value: 1.0105403661727905
       verified: true
+  - task:
+      type: natural-language-inference
+      name: Natural Language Inference
+    dataset:
+      name: multi_nli
+      type: multi_nli
+      config: default
+      split: validation_mismatched
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.902766476810415
+      verified: true
+    - name: Precision Macro
+      type: precision
+      value: 0.9023816542652491
+      verified: true
+    - name: Precision Micro
+      type: precision
+      value: 0.902766476810415
+      verified: true
+    - name: Precision Weighted
+      type: precision
+      value: 0.9034597464719761
+      verified: true
+    - name: Recall Macro
+      type: recall
+      value: 0.9024304801555488
+      verified: true
+    - name: Recall Micro
+      type: recall
+      value: 0.902766476810415
+      verified: true
+    - name: Recall Weighted
+      type: recall
+      value: 0.902766476810415
+      verified: true
+    - name: F1 Macro
+      type: f1
+      value: 0.9023086094638595
+      verified: true
+    - name: F1 Micro
+      type: f1
+      value: 0.902766476810415
+      verified: true
+    - name: F1 Weighted
+      type: f1
+      value: 0.9030161011457231
+      verified: true
+    - name: loss
+      type: loss
+      value: 0.3283354640007019
+      verified: true
 ---
 # DeBERTa-v3-base-mnli-fever-anli
 ## Model description