Add evaluation results on the autoevaluate--conll2003-sample config and test split of autoevaluate/conll2003-sample

README.md

@@ -14,50 +14,91 @@ model-index:
 - name: entity-extraction
   results:
   - task:
-      name: Token Classification
       type: token-classification
+      name: Token Classification
     dataset:
       name: conll2003
       type: conll2003
       args: conll2003
     metrics:
-    - name: Precision
-      type: precision
+    - type: precision
       value: 0.8862817854414493
-    - name: Recall
-      type: recall
+      name: Precision
+    - type: recall
       value: 0.9084908826490659
-    - name: F1
-      type: f1
+      name: Recall
+    - type: f1
       value: 0.8972489227709645
-    - name: Accuracy
-      type: accuracy
+      name: F1
+    - type: accuracy
       value: 0.9774889986814304
+      name: Accuracy
+    - type: accuracy
+      value: 0.9703231821006837
+      name: Accuracy
+      verified: true
+    - type: precision
+      value: 0.9758137392136365
+      name: Precision
+      verified: true
+    - type: recall
+      value: 0.9764192759122017
+      name: Recall
+      verified: true
+    - type: f1
+      value: 0.9761164136513085
+      name: F1 Score
+      verified: true
+    - type: accuracy
+      value: 0.9703231821006837
+      name: Accuracy
+      verified: true
+    - type: precision
+      value: 0.9758137392136365
+      name: Precision
+      verified: true
+    - type: recall
+      value: 0.9764192759122017
+      name: Recall
+      verified: true
+    - type: f1
+      value: 0.9761164136513085
+      name: F1 Score
+      verified: true
   - task:
       type: token-classification
-      name: entity_extraction
+      name: Token Classification
     dataset:
-      type: conll2003
-      name: conll2003
-      config: conll2003
+      name: autoevaluate/conll2003-sample
+      type: autoevaluate/conll2003-sample
+      config: autoevaluate--conll2003-sample
       split: test
     metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.9703231821006837
+    - type: accuracy
+      value: 0.9680247550283652
+      name: Accuracy
       verified: true
-    - name: Precision
-      type: precision
-      value: 0.9758137392136365
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTgzYzIwNTcyNzgxN2JiNGU0Y2RhMmY2YzRhMzUyNGY5NGE2MDA0NTVmYTFjYzdjMWQ2M2UxOTY4YmJkNWI2OCIsInZlcnNpb24iOjF9.TXZVtZoAvkUw_iXjmVwAdPtzhimwv33pA0BqxbKLGP3QSpJAsFbAbDwh2kUaKH4mTtgmcGgmtsywIgV5_ZEFAA
+    - type: precision
+      value: 0.9708377518557795
+      name: Precision
       verified: true
-    - name: Recall
-      type: recall
-      value: 0.9764192759122017
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWJkYzQ0MzhmNGE4Y2UyMmIzNThmMTdlZjMzODdlOWMzMTg1NTEwNWQ3NDMyNTYxODZiMzZhYTQ5NDU2ZGZlMSIsInZlcnNpb24iOjF9.rFvd0bxUagfktMsv-Q0NJr2WN2MuZ74dR0Opq9_MqjXnhi1wPxRcfbjw2RYUKnRM9PVVkBrb3WyTGYljcJYMCA
+    - type: recall
+      value: 0.9754928076718167
+      name: Recall
       verified: true
-    - name: F1 Score
-      type: f1
-      value: 0.9761164136513085
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjkzMGExNzU3NWY4Y2E0ODgyZTU5MzY1NTYxMDU3M2E3N2RkMmEwNzRmNWRmZDA1N2Y3MDQ5OGE3ZWQ3ZDA0NyIsInZlcnNpb24iOjF9.yAlh4o8i2o4GG6TES8-IoYlvqCh8NS09OeQ8yILRiRo8Uk9u6CdaZAklstD60jyMlanP7c_IP-SQsqokJ41tCg
+    - type: f1
+      value: 0.9731597129949509
+      name: F1
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmFiNDdjODdjNGJhYjNiZGUwNzc2OTQ0NDhhMjk5ZTFlMjM4NTE5MTViYTBlYzI2ZTE4MzQ5MmE3MTBiZWU0ZiIsInZlcnNpb24iOjF9.amNItmETm5mBYgwTYkYEO7L7mlO6xxPJhHfy8X8LidtLir8euAUxoj4gLro9-NETDGaZOLLvvjx7SRyODMwrAg
+    - type: loss
+      value: 0.1187286302447319
+      name: loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWFlYThiZGFhYzI4ZjZiNDUyMmQ3ZDVhMGIzZDJhNmU3ZjEwNTU1NTE2YjA3ZjM2NGNlNTA1MmYwNWY4NTdjMiIsInZlcnNpb24iOjF9.qBgBdwqISdVvRHyJQ-8JgqeGGG6J1wrNEcoJiqUgZ8OQIn8FKi6I0xmdBukkoYMapegWqwIGjNVNF4WAsjoyAg
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You