Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator

README.md

@@ -1,10 +1,10 @@
 ---
 language: en
-inference: false
+license: other
 tags:
 - text-generation
 - opt
-license: other
+inference: false
 commercial: false
 model-index:
 - name: inverse-scaling/opt-30b_eval
@@ -18,14 +18,16 @@ model-index:
       config: inverse-scaling--NeQA
       split: train
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.55
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2YyNWE2MzFmNGY3Y2Q0ZmM3NDI5YWY5MjdiNWRiMjRmYmE4ZDM4YzMzZWQyNDQ0ZGVlYjlkMWIyMThlZWZmNiIsInZlcnNpb24iOjF9.l1k3x_AcXaglNXFsuOFpoRPsKHP6GITNiqLGsCEwToId9I3eBks4JEzcqWzWFXir76oH0lAF1GnjmnAG1_2kDQ
+    - type: loss
       value: 0.7019585407276948
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjQ0ZDRhMWJjZjNlYjNhZDI5MmMzYzFiM2U2ZGZhY2VhOTdkNjAwNzkxMTY5NDdhMjE0ZjE1MDUyZDM3YTYyMiIsInZlcnNpb24iOjF9.ASg3Rqp-BSAU1cc-r63u2p_fwS-DJZtkskAyot-o3cPhNHeRMF4DOAE0UoQc7PnOSiqpUjUfkn2YOlCAqhrrBw
   - task:
       type: zero-shot-classification
       name: Zero-Shot Text Classification
@@ -35,14 +37,16 @@ model-index:
       config: inverse-scaling--quote-repetition
       split: train
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.79
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjVkNmVhZWY2ZDg4MTNhNjA5M2IwZTlmZDc3ZDk0ODE3NmQyYTU0YTMyNWE2NmQzODk2ZDY0ODE4YzQxMWEwYSIsInZlcnNpb24iOjF9.T4pGsrDqa0B5wJmhCQiB_M1x54ydxVZ0kqA91Ntf-K76f7TTg16TTO9fEwLR8aZKbT3a47wN1a8As2l3bT0hDg
+    - type: loss
       value: 0.41041071306856103
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjkwOGFiMTdlNTI2ODY3YTc5MjZmZDc0YWI2NDIwYTc5ODgwNmY0NjkxYjgwYzljMjJmNGYyNmI1MzcwN2EzYiIsInZlcnNpb24iOjF9.hqCd9YFWQChfatU7KJAMPnIV7qFvxxmUVnnI6JrB5k8a-CnEfjc3x5Ypcehk2RdbeH0U4I9RWPPafRKhVzZcDg
   - task:
       type: zero-shot-classification
       name: Zero-Shot Text Classification
@@ -52,14 +56,16 @@ model-index:
       config: inverse-scaling--redefine-math
       split: train
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.6588888888888889
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWJiYjNhMmI2Y2M2OGRhZjFjNTMwMTE3NmQ2NmJhODkyY2M3Yzk3YjcyZjUzNzE0MmE4MmIxZTU0N2NkN2Q2YSIsInZlcnNpb24iOjF9.CWcWlNJrbdh-4PLSep9B_E9Z3RaTFkuHKWx3C7tPy9bUjuOJeq8v0rg48SqSd4U2V0EfUxiyvkx_W2dR92m6DQ
+    - type: loss
       value: 0.645329966363497
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDhmMGVlYTY2YjQxODBkNmE3N2UwZDI3NGVkNGM3MzU1NzNkOWM0Zjg5M2Y1ZGJiMTU3NWQyZGEzNWNkMmUzMyIsInZlcnNpb24iOjF9.1hUXv7-fI1_VLWGEMooX6uyOJD_NywB-AqbvW1vfCouK4HCMGgGLZr6XAEi1JjWW6jM0BcR41kLBH09Yh5v5Dw
   - task:
       type: zero-shot-classification
       name: Zero-Shot Text Classification
@@ -69,14 +75,16 @@ model-index:
       config: inverse-scaling--hindsight-neglect-10shot
       split: train
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.35555555555555557
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjExZTczY2Q5Y2QxMWE1YWU4MTUwN2MyNzQ4MGFmNmFiNzMxYTUzMWQzNDMzMDhiNjEyZGI4YWUzNzZkM2VlZSIsInZlcnNpb24iOjF9.y7hWqH23GPDyo9jQw3oHyqo2uDaFTLj8rRsjwce515i9uESj-8QIk84bDRV2QD2meclpk6SPe3iQCSokFrWoBw
+    - type: loss
       value: 0.7992834513149564
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWRlY2EzZDQ2ODJhN2JhOGY1MDI5MDUxYzBlMjg5Mzc1YzFkNDg3YTdmMzVkZmIxMDExNjMzNDQzNDAwOTFkOSIsInZlcnNpb24iOjF9.aZzEsysk1bytA5xuWthZpjchXhnQnDbd1AFBqW-7dBAjYAk7rngcu8aD8bbFnlO5QDuYc3wcBbwG00hxrqPZCw
   - task:
       type: zero-shot-classification
       name: Zero-Shot Text Classification
@@ -86,14 +94,16 @@ model-index:
       config: mathemakitten--winobias_antistereotype_test_v5
       split: test
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.3713592233009709
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDRkMmM4ZGFjYjU2MDYxODlmMzE5NWNmMDhmMjhjMmZmYjA2YThkY2FhYTQ1Mjk0ZmQyZThlMmI3MWUwN2MyOSIsInZlcnNpb24iOjF9.lRwyFiJdt0FoZo_qYqmtr2MRzQmbt1PN4R3cLEjOunKnR0NYJWcJV66qMRK5iwGFJvs88_4hnRVTp9g1JP7uAQ
+    - type: loss
       value: 1.3576936555171002
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzczNzUwYTRmM2U3MWQzOTBhMjRkOTFiNGU0ZWVmOTg0MTE1ZmM1ZDkyNDY5OTI3MjA2MjEwOTQ1NTg3ZjNmMCIsInZlcnNpb24iOjF9.hVx0oXYBfVBOdFyjYzE1eRDc_hmmqcQqoO6cZIsSdV1QztQkD2EWzduXSLsDQKk1UHV2G-zCamu4ivstLSanCA
 ---
 
 # OPT : Open Pre-trained Transformer Language Models