Add evaluation results on the plain_text config and dev_r1 split of anli

README.md

@@ -174,6 +174,59 @@ model-index:
       type: loss
       value: 0.3283354640007019
       verified: true
+  - task:
+      type: natural-language-inference
+      name: Natural Language Inference
+    dataset:
+      name: anli
+      type: anli
+      config: plain_text
+      split: dev_r1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.737
+      verified: true
+    - name: Precision Macro
+      type: precision
+      value: 0.737681071614645
+      verified: true
+    - name: Precision Micro
+      type: precision
+      value: 0.737
+      verified: true
+    - name: Precision Weighted
+      type: precision
+      value: 0.7376755842752241
+      verified: true
+    - name: Recall Macro
+      type: recall
+      value: 0.7369675064285843
+      verified: true
+    - name: Recall Micro
+      type: recall
+      value: 0.737
+      verified: true
+    - name: Recall Weighted
+      type: recall
+      value: 0.737
+      verified: true
+    - name: F1 Macro
+      type: f1
+      value: 0.7366853496239583
+      verified: true
+    - name: F1 Micro
+      type: f1
+      value: 0.737
+      verified: true
+    - name: F1 Weighted
+      type: f1
+      value: 0.7366990292378379
+      verified: true
+    - name: loss
+      type: loss
+      value: 0.9349392056465149
+      verified: true
 ---
 # DeBERTa-v3-base-mnli-fever-anli
 ## Model description