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-2.7b_eval
@@ -18,14 +18,16 @@ model-index:
       config: inverse-scaling--NeQA
       split: train
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.5266666666666666
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmIwMTQ3ZjkzYWM2ZDQzNzgwMWZiZTQzZTY1MjcwNTM4YWI5NDg5N2EyNzJmMjI1MjdiOTk4ZDJlMzI1MDhhMCIsInZlcnNpb24iOjF9.nLyuA5mmpTqttnYFM4jLwpfYG87evd1SVnzlA149qagPUVkrHEgNAEV3MDYzBKm7aDWMB-SYxHYZab7gbzbFAA
+    - type: loss
       value: 0.7040334887305896
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2M4ZmI0NjQxMTE3MGI0NTQ3NjY3NzExNWZjNWIzZTdkNjA3NTVlNjQ5ODllMmNhZWQwMTEzYTI2ZTU5ZWRiMSIsInZlcnNpb24iOjF9.7YOIf1gfgzqMEnp5rScnVap6Ne607-FNWWkux9ohHb2jai3qKH73TBx0KjnUh2a-rx5CLyiDWKu2Zq2CIxrvDw
   - 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: 0.9433333333333334
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjJlYjU4NzY1YjU2ZmZjYjA4YmU3MGFmYWVkZmZjZWY2NzE3ODU2Y2RlNjdkZDNmYTc2MDhiNzA2MzQ5ZDVhYSIsInZlcnNpb24iOjF9.5n5u4QxFudSeAMIWzXBabBwzQJXxXomlL4k3UZWghrMwg2yR_ZMQ-T1XPvj4QX7znzn2OEceL4XhcyGV_lslAg
+    - type: loss
       value: 0.08805314021493173
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWNkOTFjYmU1OGM3YjEyMzhkNDI5OGE2ZjgxMWJhOTc3YjgxNDYxMWE4NjFkNWVmYjIwMmRlZDI5YTBkYjAwOCIsInZlcnNpb24iOjF9.7wQKzALinVldcU7gbodn4nxBiC1uISsf8yRaqIDB9BAbIRP4sdE_2H3PGTXAd-I7srGO_Ru8fnUhY5yZt1lmBg
   - 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: 0.72
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmE4YWE1MzQ1YTgyMjhmMzljNzlhOGJhZjk3ZGU1YzBmYzk2NjljNDEyYWZkYmI1NzM5Y2MyNDkwNDc2MjdkMSIsInZlcnNpb24iOjF9.kx2jS5AMDdD9tiNA_11-1oztP8B41AUeY5HiqsgbUIGUpZbA-FL4FCd9c6f2MUb7WbsGKUax4-gLUDm-XKl6Cw
+    - type: loss
       value: 0.6120818952802155
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTQyMGE1ODcxNDVkMThkZjZhMzQzNTQwZmY1ZTg0YjVkMmIwNDc0NWQzM2JmZTc0YWQzYWNiNWU4M2RlZDY5ZiIsInZlcnNpb24iOjF9.n5b4tXIiRrT9bS3n1aJ5W-RLmRZ5Ro0uQ0-G7spzDGf1w0zP5H05ZlNN3gnEGdApKlmqsIhfwGZqMU_XoVCzCg
   - 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: 0.44761904761904764
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTUzZTkyMDQ5OTI5ZjkxM2FmMWE5Mzg1NTFmNjg3MTRhMWZlYWNlZDZhMTkxOTZiNjc0Yjc5MTg2NTJiZGNjNyIsInZlcnNpb24iOjF9.AspGLsz8cCCmVIilO-nKuYmNcHr83f3NjnY_e5_vSaKUw22VyMixSGOowbLfROl3Lh2Rfibh3PHnhTyprQnqDA
+    - type: loss
       value: 0.8747565217197888
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTZjYWJhNTMzZjFlYzVjMjdhZjQyNDJkYzgyZmRjYTgzZjlmMjRhMTljZGU5N2E0ODBhOGI1NzdjZDM2NWEzYSIsInZlcnNpb24iOjF9.N7zwfGpX8v6CRvhyUlJ_znKVJyo238fDcL5CQkDWAWBWRtfxCoPXE_Xk69G7UBvrbQLPpPTuTPVUMVh7GGi-Dw
   - task:
       type: zero-shot-classification
       name: Zero-Shot Text Classification
@@ -86,14 +94,16 @@ model-index:
       config: mathemakitten--winobias_antistereotype_test_cot_v1
       split: test
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.39805825242718446
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGUyODYzYjg5MzI1MDEyZTk2OGY3ZTdlYThlZDE5YzVmMzNlMjI1N2JlYmM3NmMxM2VlMzM4ODFlNjJkZDdkOSIsInZlcnNpb24iOjF9.2iaV9PkSnUUYldLb6krXbCPXOkPqibzVWyqkBzp4OKtcJW5z9y_Es8W81vBaAdXxGoojKYKdpraovzf7SQAdDQ
+    - type: loss
       value: 1.3472958901782706
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDZmOWY1ODdkMzJmMmM2MzM3OGM4MzU4MmE3MmQyM2Q4MjQ2MzNjM2E3ZTcyNDQyNzVhMzVmZmMwYWY5OTE0YiIsInZlcnNpb24iOjF9.xIVeCNxXTgjJLu6EtlcXzuA4J3HNEyFEvoDovF1hH_-sUwZqMMApVl-JC63lnxCs1BxeW2XHNl3CkNHEVii2CQ
   - task:
       type: zero-shot-classification
       name: Zero-Shot Text Classification
@@ -103,14 +113,16 @@ model-index:
       config: mathemakitten--winobias_antistereotype_test_cot_v3
       split: test
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.38106796116504854
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODhmMjYzMzg3MGE1ZDg4ZWZiM2Q4NmE1N2YwODZiNzBiNjRhODE4NjIwZjI3Y2ZlMjY4NWU1OTFhMDUxMDA0NCIsInZlcnNpb24iOjF9.97nWVkITOK8236d9JNEUQ3M3xsL0cSlHbPvnUU0Va0kkgCMnqI62kJF0_1JMb36tD9n243RnWp6rrpfSi2IUCA
+    - type: loss
       value: 1.2352868161494008
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGZlY2NkYWJkMmE4MWNjZDFjZWRlZWY3OTIzMzc4MTU0ZThhMmQ0ZTAyYTEyMjZmNWNhODMzY2Q4YmNlZjRlYyIsInZlcnNpb24iOjF9.fPAkjMH3VU2AAE-EVKhEZTNM47LrFUCF-EqGE2C8NyY0yU3o0IE9xBnF3kn9F-McsnTnHB9fIuVk8B6OL_OEDg
   - task:
       type: zero-shot-classification
       name: Zero-Shot Text Classification
@@ -120,14 +132,16 @@ model-index:
       config: mathemakitten--winobias_antistereotype_test_v5
       split: test
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.4029126213592233
+      name: Accuracy
       verified: true
-    - name: Loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2RmNTY3YzYxZDljZmFmOGQzMWIxODBmNTNlNDAxOTE4NjJmNzZmZjY1NGE1YjRjMzlhMGRiOWExYzQ3Y2ViOSIsInZlcnNpb24iOjF9.8mFB5qYQUOkDXoNR0u-a9AbNDb-w2jnBH0seY_01pp_magRKFif9tBiTfV5qHFoO0wSHnoRBANa-psn6mv_vCw
+    - type: loss
       value: 1.3491194838988576
+      name: Loss
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODA2MGFmYmEwMDc4YzY3MjI3OWE2ZjA4MDUxMzFlYWM0NGMxOTVjZTIzZGFkNTA5MWVmZGI1MmZiMjc5MWViYiIsInZlcnNpb24iOjF9.X78VtBUzeKI931pe1JdcUAaE7CwKPcaur4TjnAAIJp7DBxyC8QSS2r2LpgvO4p6Q-HnSBXGpK23MCCkDPeQIAA
 ---
 
 # OPT : Open Pre-trained Transformer Language Models