Add evaluation results on the sst2 config and validation split of glue

README.md

@@ -6,56 +6,83 @@ datasets:
 - glue
 metrics:
 - accuracy
+name: autoevaluate/binary-classification
+results:
+- task:
+    type: text-classification
+    name: Text Classification
+  dataset:
+    name: glue
+    type: glue
+    config: sst2
+    split: validation
+  metrics:
+  - type: accuracy
+    value: 0.8967889908256881
+    name: Accuracy
+    verified: true
+    verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWY0OWI1MDEwOGU0OGU1MDkwN2RhZDIxYWUzNjc0ZTdhYzBlZjZlODY4NjdhYTAzZWQ5YjM5OGE2ZmIzMWQzOSIsInZlcnNpb24iOjF9.hcAWhrsrj1jbkjutDTvsIbfTMW3LCQ5ASMdPRme84tnPETSxMvyD3Jdap24XySAEdglhI-8e7Bzxhriur7CQAQ
+  - type: precision
+    value: 0.8898678414096917
+    name: Precision
+    verified: true
+    verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTZkNTY0N2IyODEwN2Q2YjY5NDk5NTlmNTBhMTIyOGYyNzUzZmE1NjEwNmEzODhkZmZhZmU3OGZmNTdiMDk4OCIsInZlcnNpb24iOjF9.1rIs3ZnUAUjXnd6rAihsUDDtmG8uBNPDdV429_-8RoBijGm9EZoWTg3-naCFAVJC3IMfSrdTKt1PHChcd5aiAw
+  - type: recall
+    value: 0.9099099099099099
+    name: Recall
+    verified: true
+    verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWFlNmEwNDVkY2JlNDgxOTYwZThhZDc4NTMwOGQ1ZDc5YjM4OTllMTRiMDk3ZTJlZGExNjg0NWYwN2VkZWYyOCIsInZlcnNpb24iOjF9.4L8Wzz4m7InEScIVH7Xv2M0Dvf9ej7K_xzpfV67ckE7Bho4snFQ9NrDihpxloErMuqNgYa16X8b3yRcDtNI-Cw
+  - type: auc
+    value: 0.9672186789593331
+    name: AUC
+    verified: true
+    verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGExZWU4MjgwZWU2OTgxYjJkODZmZjE0Y2M3MWZjNWNiNzk4YjhkYjZhZWQ4NjE1MjQzZmIxMDc3MGM4ZGY1MSIsInZlcnNpb24iOjF9.p0sDV5eJ0-yETPadJ7abgS-FdmzFsRs4jpAk8oRtAP2y5IhauTBbN9ki7-6aZFvAL2_FBTXE2tkktrqkwdDhBw
+  - type: f1
+    value: 0.8997772828507795
+    name: F1
+    verified: true
+    verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2ZlMzlmYjI0NjMzNDM5MGY0YzBhMWY3YjNkMGI4MTgzNDBjYzcxMzhiZWIxOWI3MjJiYzkwOTc3YmY1ZGViZCIsInZlcnNpb24iOjF9.ZlLSiUiws0lzlnYzntz8xLcNigC80b9ABzZy53hpxJss1aS-o_Kjv-UZvQCD6Wy9cDNwpuTjCvX8Ouqq9kyBBA
 model-index:
 - name: autoevaluate-binary-classification
   results:
   - task:
-      name: Text Classification
       type: text-classification
+      name: Text Classification
     dataset:
       name: glue
       type: glue
       args: sst2
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.8967889908256881
-  - task:
-      type: text-classification
-      name: Text Classification
-    dataset:
-      name: glue
-      type: glue
-      config: sst2
-      split: validation
-    metrics:
-    - name: Accuracy
-      type: accuracy
+      name: Accuracy
+    - type: accuracy
       value: 0.8967889908256881
+      name: Accuracy
       verified: true
-    - name: Precision
-      type: precision
+    - type: precision
       value: 0.8898678414096917
+      name: Precision
       verified: true
-    - name: Recall
-      type: recall
+    - type: recall
       value: 0.9099099099099099
+      name: Recall
       verified: true
-    - name: AUC
-      type: auc
+    - type: auc
       value: 0.967247621453229
+      name: AUC
       verified: true
-    - name: F1
-      type: f1
+    - type: f1
       value: 0.8997772828507795
+      name: F1
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 0.30091655254364014
+      name: loss
       verified: true
-    - name: matthews_correlation
-      type: matthews_correlation
+    - type: matthews_correlation
       value: 0.793630584795814
+      name: matthews_correlation
       verified: true
 ---