Commit
·
21354d3
1
Parent(s):
08fb8b8
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#2)
Browse files- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (6acb7d5699211887d765cc149f5ddd2805a7cbea)
Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -12,16 +12,16 @@ model-index:
|
|
| 12 |
- name: bert-base-uncased-rte
|
| 13 |
results:
|
| 14 |
- task:
|
| 15 |
-
name: Text Classification
|
| 16 |
type: text-classification
|
|
|
|
| 17 |
dataset:
|
| 18 |
name: GLUE RTE
|
| 19 |
type: glue
|
| 20 |
args: rte
|
| 21 |
metrics:
|
| 22 |
-
-
|
| 23 |
-
type: accuracy
|
| 24 |
value: 0.6895306859205776
|
|
|
|
| 25 |
- task:
|
| 26 |
type: natural-language-inference
|
| 27 |
name: Natural Language Inference
|
|
@@ -31,30 +31,36 @@ model-index:
|
|
| 31 |
config: rte
|
| 32 |
split: validation
|
| 33 |
metrics:
|
| 34 |
-
-
|
| 35 |
-
type: accuracy
|
| 36 |
value: 0.6823104693140795
|
|
|
|
| 37 |
verified: true
|
| 38 |
-
|
| 39 |
-
|
| 40 |
value: 0.7047619047619048
|
|
|
|
| 41 |
verified: true
|
| 42 |
-
|
| 43 |
-
|
| 44 |
value: 0.5648854961832062
|
|
|
|
| 45 |
verified: true
|
| 46 |
-
|
| 47 |
-
|
| 48 |
value: 0.7394646031580048
|
|
|
|
| 49 |
verified: true
|
| 50 |
-
|
| 51 |
-
|
| 52 |
value: 0.6271186440677967
|
|
|
|
| 53 |
verified: true
|
| 54 |
-
|
| 55 |
-
|
| 56 |
value: 0.7001310586929321
|
|
|
|
| 57 |
verified: true
|
|
|
|
| 58 |
---
|
| 59 |
|
| 60 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 12 |
- name: bert-base-uncased-rte
|
| 13 |
results:
|
| 14 |
- task:
|
|
|
|
| 15 |
type: text-classification
|
| 16 |
+
name: Text Classification
|
| 17 |
dataset:
|
| 18 |
name: GLUE RTE
|
| 19 |
type: glue
|
| 20 |
args: rte
|
| 21 |
metrics:
|
| 22 |
+
- type: accuracy
|
|
|
|
| 23 |
value: 0.6895306859205776
|
| 24 |
+
name: Accuracy
|
| 25 |
- task:
|
| 26 |
type: natural-language-inference
|
| 27 |
name: Natural Language Inference
|
|
|
|
| 31 |
config: rte
|
| 32 |
split: validation
|
| 33 |
metrics:
|
| 34 |
+
- type: accuracy
|
|
|
|
| 35 |
value: 0.6823104693140795
|
| 36 |
+
name: Accuracy
|
| 37 |
verified: true
|
| 38 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTc4OTUzYmQ0NWRkMjdmYjI3ZDhmNWU5MTQ1YTM4ZTQzOWM5MTJjYzlmMjM3ZTE2Y2ZhMGJlNTI0OTJhYjNmMCIsInZlcnNpb24iOjF9.siPkmQhZKOZ1k_SyS1xIMavpK_CQ8tHTm39McCIEjiF7G1x62lbuKfrZsLoKoPf9XpNJqXoaXIRPCpHBKlfwCA
|
| 39 |
+
- type: precision
|
| 40 |
value: 0.7047619047619048
|
| 41 |
+
name: Precision
|
| 42 |
verified: true
|
| 43 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzdmMjk0ZjRkNzM4ZWE1ZGUyOWUxZTFjNmEyNTRmNjZmMDUxOTJlZmUxNjUzMWFhZTYzZTM1ZGNkMDg1YTMzYyIsInZlcnNpb24iOjF9.Cm2kMSTsWVPU9mBv8xAyvo7msTHdG3SECIYZ4kQ5RpN4NV3WE1k0EqmcGzAedwYNfSEg1qXL-qWDKOeoXDAnCw
|
| 44 |
+
- type: recall
|
| 45 |
value: 0.5648854961832062
|
| 46 |
+
name: Recall
|
| 47 |
verified: true
|
| 48 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjc1NTMzYWI5OGRjODdhYmJjZDQ3ODdiMWE3ODYzZjNhZDg1MGIyNjA1YzQwNzcwYTQzNjJkNGVjNmNjMWJmNSIsInZlcnNpb24iOjF9.MwRAu1AKhCt__2vBjhvEqU0gvXaJ5EMOOotKmwGXsuF3eGJEEDDuiWBgu9y291aqndTTwWvuH9CNQjGKLCoNCw
|
| 49 |
+
- type: auc
|
| 50 |
value: 0.7394646031580048
|
| 51 |
+
name: AUC
|
| 52 |
verified: true
|
| 53 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGQwMWVhZjlhNjhhZDRhNGYwNWUyOTZjMTgwMDQ5ZWM3MDcxNDc5OGJiNDE5NTNhOTU0MDMwYTdkYjcxNzFiZiIsInZlcnNpb24iOjF9.ZLyE_ZDWyVAr_GL_3lSqBmuIip7C13oj5kT1lI9JQOidt-IXsRHYUmJt_f7HWUNU1-FBD5lzHYcstF6WQ0VrAw
|
| 54 |
+
- type: f1
|
| 55 |
value: 0.6271186440677967
|
| 56 |
+
name: F1
|
| 57 |
verified: true
|
| 58 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmU0YjI4Y2MyMzU5ZTYzMmE0YzhjOTgwM2UwYTNhZDFmZWE3NTdhODMzYmU1ZWUxYTc2Yjk3Nzg3MjAyOThiOSIsInZlcnNpb24iOjF9.GJhnKNSHN5Sv9W3gl8fgPAAbM5EtMlhOHoOFcj_O65FLtcTi_ANpyv7gi41fPbMjS2TG4fgdVHQ_UZg7M6W2Cw
|
| 59 |
+
- type: loss
|
| 60 |
value: 0.7001310586929321
|
| 61 |
+
name: loss
|
| 62 |
verified: true
|
| 63 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjMwMTY5OGVkMzVhMzdjMmY1YmIzYTViOTRlNzcxMTI4NWNiOTQ5ZjMwMjRlODE4ZWUwMGVhZjhiMmIzM2ViOSIsInZlcnNpb24iOjF9.IsJhfeeqnVZFn10sOkCW7vAzfw1WQMwR8b99B3-hct_lrI1xodt5ySGltDvx2Q8ufD6hzfQ7YaDeHytDmeeFBw
|
| 64 |
---
|
| 65 |
|
| 66 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|