pszemraj autoevaluator HF staff commited on
Commit
8d5900d
1 Parent(s): 8a9f9df

Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#3)

Browse files

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (29c3c2e2c141393d7d2fb5d02982280946480fbc)


Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +39 -27
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
 
 
 
2
  tags:
3
  - summarization
4
  - summary
5
  - booksum
6
  - long-document
7
  - long-form
8
- license:
9
- - apache-2.0
10
- - bsd-3-clause
11
  datasets:
12
  - kmfoda/booksum
13
  metrics:
@@ -25,30 +25,36 @@ model-index:
25
  config: samsum
26
  split: test
27
  metrics:
28
- - name: ROUGE-1
29
- type: rouge
30
  value: 23.5177
 
31
  verified: true
32
- - name: ROUGE-2
33
- type: rouge
34
  value: 4.668
 
35
  verified: true
36
- - name: ROUGE-L
37
- type: rouge
38
  value: 16.6091
 
39
  verified: true
40
- - name: ROUGE-LSUM
41
- type: rouge
42
  value: 20.3174
 
43
  verified: true
44
- - name: loss
45
- type: loss
46
  value: 3.2174887657165527
 
47
  verified: true
48
- - name: gen_len
49
- type: gen_len
50
  value: 57.1966
 
51
  verified: true
 
52
  - task:
53
  type: summarization
54
  name: Summarization
@@ -58,30 +64,36 @@ model-index:
58
  config: kmfoda--booksum
59
  split: test
60
  metrics:
61
- - name: ROUGE-1
62
- type: rouge
63
  value: 35.9884
 
64
  verified: true
65
- - name: ROUGE-2
66
- type: rouge
67
  value: 6.0596
 
68
  verified: true
69
- - name: ROUGE-L
70
- type: rouge
71
  value: 16.1419
 
72
  verified: true
73
- - name: ROUGE-LSUM
74
- type: rouge
75
  value: 32.9992
 
76
  verified: true
77
- - name: loss
78
- type: loss
79
  value: 2.9468588829040527
 
80
  verified: true
81
- - name: gen_len
82
- type: gen_len
83
  value: 298.2593
 
84
  verified: true
 
85
  ---
86
 
87
 
 
1
  ---
2
+ license:
3
+ - apache-2.0
4
+ - bsd-3-clause
5
  tags:
6
  - summarization
7
  - summary
8
  - booksum
9
  - long-document
10
  - long-form
 
 
 
11
  datasets:
12
  - kmfoda/booksum
13
  metrics:
 
25
  config: samsum
26
  split: test
27
  metrics:
28
+ - type: rouge
 
29
  value: 23.5177
30
+ name: ROUGE-1
31
  verified: true
32
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjMxNGRmYjc0ZjNmZWY3YjFjNDEzYjRhYTAyNWNkOGQ3ODMzM2EwMzk0NTVkMzQ5MGMyYjYxMTkzYWQyMjZiMyIsInZlcnNpb24iOjF9.-PPUZc4Jr6EjNcQ-u9n814SfeviFEaddbFco5d1wbJNoECN_HqciNphSjXh7w99I_rQ6rPIXu8DA93u7aFj9CA
33
+ - type: rouge
34
  value: 4.668
35
+ name: ROUGE-2
36
  verified: true
37
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWMwYWI1NTg0ZTUwNGIwZjlhYWU2MzQwN2I0NzA1M2MyOTA5YjQ4MTEyYzU2MjRmZTA0NzNiYWM2ZDU0ZThhYyIsInZlcnNpb24iOjF9.CQfgJ3Lha9XR2-IudjfFuaUh_uphWPdYk6TMQOLriWM78_X-paqEIBZDh1Q-WbWoUf-CAyf6UvqXqELRDb3hBQ
38
+ - type: rouge
39
  value: 16.6091
40
+ name: ROUGE-L
41
  verified: true
42
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzhkODRjM2FiYTFhN2E5MWFiNzk3MjgzMGI0NmY0ODNkYjAxZWNmYmFmYmY0NDBmNjRmOTBkMGVhMGYzMmRkMCIsInZlcnNpb24iOjF9.Y66qsqvvGeAoiMCr1xa9enBMfcXt6a6I2i5s7VAJ3aoh3DtM2RlaMm4nuXG4uzWHedWW1NDivBWMZtycYed9DA
43
+ - type: rouge
44
  value: 20.3174
45
+ name: ROUGE-LSUM
46
  verified: true
47
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWJjODE5NDdlMjM2YjNkOWU3NDJiMWFlZGU2YTRkNzliMTg5MGNkNDQ3YWU3MTBmY2E5ZTUxMzEyMDc0ZTU5YiIsInZlcnNpb24iOjF9.Kc1accwOycbNU1F7AT8LV8jC3NpYKMmOsZmdLeDdIi5BqgMJcQSP8oNt3L-hGbscLb-D7iIvQBFtmmiGqpnGDQ
48
+ - type: loss
49
  value: 3.2174887657165527
50
+ name: loss
51
  verified: true
52
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTQ0MzQxYTQ1M2NiODcwNTBjOTRiMGEzZDE0NDFlZWJlNmNlOWI1M2M1N2Q2ZTVkNWFiMzQxNDhjODQxNDFkYSIsInZlcnNpb24iOjF9.Vat1Thj2t_1of477BCINeYoTeNZX1NIPG13qVskJ44ivKLJgMr4BCp0luYNEi2skNTv3kYK2orqBdDfxPZlfDw
53
+ - type: gen_len
54
  value: 57.1966
55
+ name: gen_len
56
  verified: true
57
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2I3MmZkMDY1YmM5N2VmMGE5OWQ0NDg5OWM0OWViMzU1ZTM1NjBmYWRmN2I2YmM5YTVkNGVlZGViNWEwOGYwMyIsInZlcnNpb24iOjF9.4c6j-ll2veK_PuCcXvRK8-8cPFdedKsqGHQsEhGpwj48uwI3PMqj9mF4HYvSGq5H3rVM_dvyPEEs9RhjCvSHBw
58
  - task:
59
  type: summarization
60
  name: Summarization
 
64
  config: kmfoda--booksum
65
  split: test
66
  metrics:
67
+ - type: rouge
 
68
  value: 35.9884
69
+ name: ROUGE-1
70
  verified: true
71
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWMzODFmZGYwZmNjY2FkZTJmZWYyMjI1NDdlZDI3OTdmY2MzNzU0M2FhYmMxNTdkOGRiNzIwMTEyMTMwMTgyMSIsInZlcnNpb24iOjF9.pbT1OOzVOjnUp4q6lcpUPunDYTQqOiwQeRLRV69699SoMI3ay4bfd_hbWZUvXOuivoJ5JiDd9KBhEqYUninNCA
72
+ - type: rouge
73
  value: 6.0596
74
+ name: ROUGE-2
75
  verified: true
76
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODNkNTE1NjU5ZmY3MmVmOGQxMjhhODRhZjIzMDRhMzJlYTY3YTkyNzM4YTAyMGI2YzRlMzljMDM5YzFjNzIyOCIsInZlcnNpb24iOjF9.NevkOank_Ou1u2ZfkEa3o4FF4DapvpFK_ucxLRm-xL-ZWGl9cLdLTOxVECrTn8Yasi_sWrjZUhGRWPkCKlJADQ
77
+ - type: rouge
78
  value: 16.1419
79
+ name: ROUGE-L
80
  verified: true
81
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzNkM2M4YjQxM2IwNzIzMjAyMjM3MThlMGQwMDgzMGI3NDU0NWVlOTFhMzBlOGQ3ZTQzOGNkNmE5ZGI5NTkzOCIsInZlcnNpb24iOjF9.8DYhyJAiKIK2aIkQSwMy4NEiBSC4v8_h_3feA-TFBdd-icGg5YvKMQR7_IOa1-9AHBe6PphVSFjl82-nDp6lDA
82
+ - type: rouge
83
  value: 32.9992
84
+ name: ROUGE-LSUM
85
  verified: true
86
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTEwMmViZmZjMzA3OWYxNWMxZjFhMDBmMDRjOGViYzdiYzllNzk0YWZmNTU0NWIwMmVmZjQzNjlkZTBmZTU0YyIsInZlcnNpb24iOjF9.KFwuSVaUXx958EWZctKpK1wawA0EH4yxBJdp3Zru4Sn97oSyP_s5m-jjZiLfP6kmSajd3849dna-Uw77s3sVBg
87
+ - type: loss
88
  value: 2.9468588829040527
89
+ name: loss
90
  verified: true
91
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzhmODMwMDM2ZDFmNTMzZmFjMmJjMGQ0MmQzMDcyMmFiNmFjMzBhY2RjMTI1MDhiMjI4NTEyYWFlYTNlMzE0ZSIsInZlcnNpb24iOjF9.PHX9VAAgiUGOR8Uxuam4otU65hIzW6hBapaf1KY8o1FDfaoHWAKbSnpjZ3nXKYYeVV6LyGRny_7RdRbbbM8LAA
92
+ - type: gen_len
93
  value: 298.2593
94
+ name: gen_len
95
  verified: true
96
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGYzMDAzNTQyMzgxM2RhNjY3MDIyNGEyMWZjYmYyYmJlNWM3MTFkYzRjMDhkMmZhNDZiN2FhYTY3MGI2NDcxNyIsInZlcnNpb24iOjF9.ax3H6LohHUodVGhSMUWMZZZ-bCTXHEaGpK4jXuOdZkGsewYrX8fO1oRA0uDjACM-eceKFfVnMveHoU9EdMaeCA
97
  ---
98
 
99