philschmid HF staff autoevaluator HF staff commited on
Commit
d8bbb00
1 Parent(s): a823ff6

Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#4)

Browse files

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (d55ba7ffa61409a61a529175cb6a2c9cb37b8219)


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

Files changed (1) hide show
  1. README.md +55 -38
README.md CHANGED
@@ -1,11 +1,10 @@
1
-
2
  ---
3
  language: en
 
4
  tags:
5
  - sagemaker
6
  - bart
7
  - summarization
8
- license: apache-2.0
9
  datasets:
10
  - samsum
11
  widget:
@@ -25,30 +24,36 @@ model-index:
25
  config: samsum
26
  split: test
27
  metrics:
28
- - name: ROUGE-1
29
- type: rouge
30
  value: 41.0895
 
31
  verified: true
32
- - name: ROUGE-2
33
- type: rouge
34
  value: 20.7459
 
35
  verified: true
36
- - name: ROUGE-L
37
- type: rouge
38
  value: 31.5952
 
39
  verified: true
40
- - name: ROUGE-LSUM
41
- type: rouge
42
  value: 38.3389
 
43
  verified: true
44
- - name: loss
45
- type: loss
46
  value: 1.4566329717636108
 
47
  verified: true
48
- - name: gen_len
49
- type: gen_len
50
  value: 59.6032
 
51
  verified: true
 
52
  - task:
53
  type: summarization
54
  name: Summarization
@@ -58,30 +63,36 @@ model-index:
58
  config: default
59
  split: test
60
  metrics:
61
- - name: ROUGE-1
62
- type: rouge
63
  value: 21.1644
 
64
  verified: true
65
- - name: ROUGE-2
66
- type: rouge
67
  value: 4.0659
 
68
  verified: true
69
- - name: ROUGE-L
70
- type: rouge
71
  value: 13.9414
 
72
  verified: true
73
- - name: ROUGE-LSUM
74
- type: rouge
75
  value: 17.0718
 
76
  verified: true
77
- - name: loss
78
- type: loss
79
  value: 3.002755880355835
 
80
  verified: true
81
- - name: gen_len
82
- type: gen_len
83
  value: 71.2969
 
84
  verified: true
 
85
  - task:
86
  type: summarization
87
  name: Summarization
@@ -91,30 +102,36 @@ model-index:
91
  config: 3.0.0
92
  split: test
93
  metrics:
94
- - name: ROUGE-1
95
- type: rouge
96
  value: 42.9764
 
97
  verified: true
98
- - name: ROUGE-2
99
- type: rouge
100
  value: 19.8711
 
101
  verified: true
102
- - name: ROUGE-L
103
- type: rouge
104
  value: 29.5196
 
105
  verified: true
106
- - name: ROUGE-LSUM
107
- type: rouge
108
  value: 39.959
 
109
  verified: true
110
- - name: loss
111
- type: loss
112
  value: 3.014679193496704
 
113
  verified: true
114
- - name: gen_len
115
- type: gen_len
116
  value: 81.956
 
117
  verified: true
 
118
  ---
119
 
120
  ## `distilbart-cnn-12-6-samsum`
 
1
  ---
2
  language: en
3
+ license: apache-2.0
4
  tags:
5
  - sagemaker
6
  - bart
7
  - summarization
 
8
  datasets:
9
  - samsum
10
  widget:
24
  config: samsum
25
  split: test
26
  metrics:
27
+ - type: rouge
 
28
  value: 41.0895
29
+ name: ROUGE-1
30
  verified: true
31
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTBlZmQzZDFmNzY5YTBjMTI3ZjRkNDk4NTI3YzQxOGY4MjlkMTU4ZGJkZWE4YjQ4ZDFhOTIxM2M1YWEyMDQ4MCIsInZlcnNpb24iOjF9.Nw7idRmEmjS-c91HthjVGw6YxttVA_tRB2QRkGwVSVABR3_BY84HvwLOZVstc6a9gUHopMj_W9SRfa_6xTWcBA
32
+ - type: rouge
33
  value: 20.7459
34
+ name: ROUGE-2
35
  verified: true
36
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjRhN2E4ZDNiNWNkY2RkNjMxMjhiYjcxYjc4OWM4NWQ5MDNjZDMwOGIwNWI2NWJiYzljMzc0NzY1ZDBmMTRmZCIsInZlcnNpb24iOjF9.nYxNimi33AW0T8T1JhqFUukxe4W4niXj4UzLRTuc40NeZveDTSpPS8QzR4rF1gK-r2irqIX5FrvG4dwQHrESBA
37
+ - type: rouge
38
  value: 31.5952
39
+ name: ROUGE-L
40
  verified: true
41
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjYzYTRjOTU1MDVhN2ZlOGE3YTIxMjk1NDBiY2E2ZWI1MDA5ZTJkOTQ4MzgxNThkOGU4OTUzODU0YWE1OTQ5MiIsInZlcnNpb24iOjF9.G2EtxIlJ86AcNx2bqw2nu1UbdczQ-anl1c02EopQyC81BEcEAbnY-liPvHXLjPVQvP97GGGjqTDLZYjYJ71hDQ
42
+ - type: rouge
43
  value: 38.3389
44
+ name: ROUGE-LSUM
45
  verified: true
46
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWExZmM2YWI1MDU0ZjE1YWY1NDNiY2E4YTkwZjA5MTE0YmM1NzI4YTc1YjI0MWFmZDlkYTBlZjVlMDk2ZGQxZSIsInZlcnNpb24iOjF9.jjBghJ66Gj_95AdDpWG2TR_MnuUtj8Fzc0M3KS9vqsM0iqtlu9khY8lXrFpMaIeDxVBYKltMMFdZWH8mVv2wCg
47
+ - type: loss
48
  value: 1.4566329717636108
49
+ name: loss
50
  verified: true
51
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDAyYjFmNzRlYzkyNmUxMWM5YWYxNjgwZGQ1ZDc1Njg0MzU1ZjM4MjI5MTJlODRiNDdiNGRjYTkzZGUxNGMyZiIsInZlcnNpb24iOjF9.2eH5b7DlPeVQ_zFGlvKyRvqrc7yyT8vcf3koJGKGysV00vCQew8sOmFEmDegiBka8gq3UL987Dd2yZCU3b64Cw
52
+ - type: gen_len
53
  value: 59.6032
54
+ name: gen_len
55
  verified: true
56
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTFkOTlmMjFlODIxZWExZmQyMTQyNDYyY2RmNjY3YmM1NDFlNTI3OTRhZjU0MDQxNGY2NGQ4ZWY2OWFmNDliMyIsInZlcnNpb24iOjF9.K9qwFg3Flnu2-1H-WI9adj7yoBuJ3zBBDyda5BxRpJ1D4L_alLpCweqrVGuynOPl9PAWPuHo7bAG1y2zZNmmDw
57
  - task:
58
  type: summarization
59
  name: Summarization
63
  config: default
64
  split: test
65
  metrics:
66
+ - type: rouge
 
67
  value: 21.1644
68
+ name: ROUGE-1
69
  verified: true
70
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzVjNWI1MWJmOTAzMDYxNjlkYzg4NjM3MzczMDJiYjNjYTg3NjYzNjQ3YTczYzg5MGU2NDcxOWQwZjdlODU4YSIsInZlcnNpb24iOjF9.CqB-ANpnx0GvwhsjeCzLB_RxaKqbnhc_980RG8fqDb2hNTk4LvDhqdDfkLFQMj8kvW4nQLLDSNUENQ7Uni9kCA
71
+ - type: rouge
72
  value: 4.0659
73
+ name: ROUGE-2
74
  verified: true
75
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjgzYTc5Y2VjZTliNmEwYTZjNTViODdjYTg2MGMyZTFkMjgyMjk0OGIzZjg1ODgzZDJmOTMwNmU4MzdlNTI2OCIsInZlcnNpb24iOjF9.1AfPtrpJ38Khz5vfRsN4Jwb3J_PdycddRH9DJtEccqmEz9BzDo-AO7Ts94sfVlYfSf3srplLHDcd_XFCwQtlBg
76
+ - type: rouge
77
  value: 13.9414
78
+ name: ROUGE-L
79
  verified: true
80
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODZlZTM2OTM5NzVlNDBjYjc2NDdhNmIxNDZhNGVjOTk4YzIzZmEwYzEwZmQ2ZmNmMjIzNzYwMzkxMjU1ODcxMCIsInZlcnNpb24iOjF9.vvp5PKmEp-Hyt46zgsvzjGOO8wrV0cDG68Z0VPqW2WfY5Sp3k3krEcKLATdQAQjfy96gKCCkQpBFefpjYWcmDA
81
+ - type: rouge
82
  value: 17.0718
83
+ name: ROUGE-LSUM
84
  verified: true
85
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWEyN2QyOWFhMjAzZTk4NjU5ODU5YjgxMjczNzc1MTM5OTY1OTVjZDMwZDhjODFlZTVmODNkYzFhOTc5NzZhYiIsInZlcnNpb24iOjF9.PwJT3EYTV3KifWaySiwSTxGyBWTB8bHMuaXG3AyRvWkY2xju1BSaBjPGCcfmlZs1yJwghOH7N4dBW5yJBEp5DA
86
+ - type: loss
87
  value: 3.002755880355835
88
+ name: loss
89
  verified: true
90
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGY0NjgzOGExZWZmNWI3ZTA1ZjRlYTU2OTZkYzk5NDdmOGVmNDdkNWU5YjViMWQyNGE2MTNkODhkZmQ1ZGE2OSIsInZlcnNpb24iOjF9.pWru9Nhl0aZThHz0qveOHmxTOCrZjHu9ySt5wI9MnGQ5ZEpxfufjpI196EMMn-KSSxAl-s7wHygtGC9_WtC1BQ
91
+ - type: gen_len
92
  value: 71.2969
93
+ name: gen_len
94
  verified: true
95
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q4ODZlZDY4YzE1MDEwNzJjNmNiYjI4NTU5NjRlNmY2NWNjYmUwNzcwZmY3NWVlZDA3NTMxY2Y2NWI1ODYwMCIsInZlcnNpb24iOjF9.0Y_lnTKQ5nmjnwAEju9T7xlLObWgwPLMOxlWDpjPBkDeW0bzHYqJcRADtFcvAhznJ3HktIV830QxjqkRYjZTDw
96
  - task:
97
  type: summarization
98
  name: Summarization
102
  config: 3.0.0
103
  split: test
104
  metrics:
105
+ - type: rouge
 
106
  value: 42.9764
107
+ name: ROUGE-1
108
  verified: true
109
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzQ0NzAyNDM5YWIyZmY5OTUwNWZjNzRkYTliYWI0YzdmZTg5ZGVhZjJlMDBiZjg2YmE0ZjkxNzU4YjRkYTJjNCIsInZlcnNpb24iOjF9.dymlXdITNpMZpOaYvif-LcxaSRWKh8_RxV6mdBpuvlThPPi3-TwKCW20Fowor8H5RPsC0M1cfvNNzINCyApKCA
110
+ - type: rouge
111
  value: 19.8711
112
+ name: ROUGE-2
113
  verified: true
114
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTY5ZTI0OTEzNzI1NDRjYWE5MDk2NzVhZDEyNGEzNzU3OTE0NmJmYzhkMTU0MTI2MDVlOTdlNGU0OGI2MTdlNSIsInZlcnNpb24iOjF9.7xN2u4HjPL78CkkihB9I0befTn04IQqimvNlSHpc888arBm_qCtTGl7q7389ArpWUKEdkhvZ94BgB-Z_cXsqCg
115
+ - type: rouge
116
  value: 29.5196
117
+ name: ROUGE-L
118
  verified: true
119
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGY3YzRiYjljZWJhNGJiMTdhNDY5OTk0ODJhYWMxOGMwYjY4ZTBlNmQ0YTUxMzQ3YmZiNzg0ZDJiNTg4MzdiYyIsInZlcnNpb24iOjF9.Yj0ZaJelYcMJ-8SIon9x7GxRityWR3p0vcLNctTfcg6eCClalTQKBclCVgpDCO8WQyVxSz8EyCDb2qedRgF9CQ
120
+ - type: rouge
121
  value: 39.959
122
+ name: ROUGE-LSUM
123
  verified: true
124
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmI2MTE3NjQ2M2MwYjJmN2JmMTEwN2JkMDVhMWRiMDBiM2FlMzM5NjAxYWM1N2Q2MTA5MGRhZmI5ZDNjNzMwYSIsInZlcnNpb24iOjF9.A-2Ch4-M691OBAp4KmsYut10K3sF0fjw5ztutK_LTtn68Ne0x8w-u-7pEyjTuWJrJx4Q3Yb1eW3yeHPTnFI0DA
125
+ - type: loss
126
  value: 3.014679193496704
127
+ name: loss
128
  verified: true
129
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmNiNWZlOGZmOWZhNWZjNTg1ODIzMzY2ZGYxNzBiOWIxMWRiZTQ5MzM5NjRlYTQwMzRjOGI3YzNmZDhmYjQ3MCIsInZlcnNpb24iOjF9.BZkiJxZG0RdFzNgxgcS8U6_zPT1t7rvs-603cnC1tjMMYF3Lbae7rExRb-fVHN_ofZV_w5vl4uRLQ3OxZUY5Ag
130
+ - type: gen_len
131
  value: 81.956
132
+ name: gen_len
133
  verified: true
134
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTdhNGYxYWRlNTU0MzAxMWU1NzNmMTBjMmY3NzkzODAyYTMzZWYyZmNiMTViMzNmYTE0ZmFmNDdhMzQwMmJkNyIsInZlcnNpb24iOjF9.8lm84JtbCh-diuNQ01oXK6P8vV9CPyA8y-7D9o_OHb9Vk3pNEFM1jMSZVdEG9wFuMpWL3ARbXLadEPQB5HN8AQ
135
  ---
136
 
137
  ## `distilbart-cnn-12-6-samsum`