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

#10
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +30 -25
README.md CHANGED
@@ -1,4 +1,3 @@
1
-
2
  ---
3
  language: en
4
  license: mit
@@ -23,24 +22,24 @@ model-index:
23
  name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization'
24
  type: samsum
25
  metrics:
26
- - name: Validation ROGUE-1
27
- type: rogue-1
28
  value: 42.621
29
- - name: Validation ROGUE-2
30
- type: rogue-2
31
  value: 21.9825
32
- - name: Validation ROGUE-L
33
- type: rogue-l
34
  value: 33.034
35
- - name: Test ROGUE-1
36
- type: rogue-1
37
  value: 41.3174
38
- - name: Test ROGUE-2
39
- type: rogue-2
40
  value: 20.8716
41
- - name: Test ROGUE-L
42
- type: rogue-l
43
  value: 32.1337
 
44
  - task:
45
  type: summarization
46
  name: Summarization
@@ -50,30 +49,36 @@ model-index:
50
  config: samsum
51
  split: test
52
  metrics:
53
- - name: ROUGE-1
54
- type: rouge
55
  value: 41.3282
 
56
  verified: true
57
- - name: ROUGE-2
58
- type: rouge
59
  value: 20.8755
 
60
  verified: true
61
- - name: ROUGE-L
62
- type: rouge
63
  value: 32.1353
 
64
  verified: true
65
- - name: ROUGE-LSUM
66
- type: rouge
67
  value: 38.401
 
68
  verified: true
69
- - name: loss
70
- type: loss
71
  value: 1.4297215938568115
 
72
  verified: true
73
- - name: gen_len
74
- type: gen_len
75
  value: 60.0757
 
76
  verified: true
 
77
  ---
78
 
79
  ## `bart-large-cnn-samsum`
 
1
  ---
2
  language: en
3
  license: mit
22
  name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization'
23
  type: samsum
24
  metrics:
25
+ - type: rogue-1
 
26
  value: 42.621
27
+ name: Validation ROGUE-1
28
+ - type: rogue-2
29
  value: 21.9825
30
+ name: Validation ROGUE-2
31
+ - type: rogue-l
32
  value: 33.034
33
+ name: Validation ROGUE-L
34
+ - type: rogue-1
35
  value: 41.3174
36
+ name: Test ROGUE-1
37
+ - type: rogue-2
38
  value: 20.8716
39
+ name: Test ROGUE-2
40
+ - type: rogue-l
41
  value: 32.1337
42
+ name: Test ROGUE-L
43
  - task:
44
  type: summarization
45
  name: Summarization
49
  config: samsum
50
  split: test
51
  metrics:
52
+ - type: rouge
 
53
  value: 41.3282
54
+ name: ROUGE-1
55
  verified: true
56
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTYzNzZkZDUzOWQzNGYxYTJhNGE4YWYyZjA0NzMyOWUzMDNhMmVhYzY1YTM0ZTJhYjliNGE4MDZhMjhhYjRkYSIsInZlcnNpb24iOjF9.OOM6l3v5rJCndmUIJV-2SDh2NjbPo5IgQOSL-Ju1Gwbi1voL5amsDEDOelaqlUBE3n55KkUsMLZhyn66yWxZBQ
57
+ - type: rouge
58
  value: 20.8755
59
+ name: ROUGE-2
60
  verified: true
61
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWZiODFiYWQzY2NmOTc5YjA3NTI0YzQ1MzQ0ODk2NjgyMmVlMjA5MjZiNTJkMGRmZGEzN2M3MDNkMjkxMDVhYSIsInZlcnNpb24iOjF9.b8cPk2-IL24La3Vd0hhtii4tRXujh5urAwy6IVeTWHwYfXaURyC2CcQOWtlOx5bdO5KACeaJFrFBCGgjk-VGCQ
62
+ - type: rouge
63
  value: 32.1353
64
+ name: ROUGE-L
65
  verified: true
66
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWNmYzdiYWQ2ZWRkYzRiMGMxNWUwODgwZTdkY2NjZTc1NWE5NTFiMzU0OTU1N2JjN2ExYWQ2NGZkNjk5OTc4YSIsInZlcnNpb24iOjF9.Fzv4p-TEVicljiCqsBJHK1GsnE_AwGqamVmxTPI0WBNSIhZEhliRGmIL_z1pDq6WOzv3GN2YUGvhowU7GxnyAQ
67
+ - type: rouge
68
  value: 38.401
69
+ name: ROUGE-LSUM
70
  verified: true
71
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGI4MWY0NWMxMmQ0ODQ5MDhiNDczMDAzYzJkODBiMzgzYWNkMWM2YTZkZDJmNWJiOGQ3MmNjMGViN2UzYWI2ZSIsInZlcnNpb24iOjF9.7lw3h5k5lJ7tYFLZGUtLyDabFYd00l6ByhmvkW4fykocBy9Blyin4tdw4Xps4DW-pmrdMLgidHxBWz5MrSx1Bw
72
+ - type: loss
73
  value: 1.4297215938568115
74
+ name: loss
75
  verified: true
76
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzI0ZWNhNDM5YTViZDMyZGJjMDA1ZWFjYzNhOTdlOTFiNzhhMDBjNmM2MjA3ZmRkZjJjMjEyMGY3MzcwOTI2NyIsInZlcnNpb24iOjF9.oNaZsAtUDqGAqoZWJavlcW7PKx1AWsnkbhaQxadpOKk_u7ywJJabvTtzyx_DwEgZslgDETCf4MM-JKitZKjiDA
77
+ - type: gen_len
78
  value: 60.0757
79
+ name: gen_len
80
  verified: true
81
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTgwYWYwMDRkNTJkMDM5N2I2MWNmYzQ3OWM1NDJmODUyZGViMGE4ZTdkNmIwYWM2N2VjZDNmN2RiMDE4YTYyYiIsInZlcnNpb24iOjF9.PbXTcNYX_SW-BuRQEcqyc21M7uKrOMbffQSAK6k2GLzTVRrzZxsDC57ktKL68zRY8fSiRGsnknOwv-nAR6YBCQ
82
  ---
83
 
84
  ## `bart-large-cnn-samsum`