autoevaluator HF staff commited on
Commit
fc78337
1 Parent(s): 3156501

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

Browse files

Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋! We've added a new `verifyToken` field to your evaluation results to verify that they are produced by the model evaluator. Accept this PR to ensure that your results remain listed as **verified** on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards).

Files changed (1) hide show
  1. README.md +58 -40
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: 24.5482
 
31
  verified: true
32
- - name: ROUGE-2
33
- type: rouge
34
  value: 4.811
 
35
  verified: true
36
- - name: ROUGE-L
37
- type: rouge
38
  value: 17.2505
 
39
  verified: true
40
- - name: ROUGE-LSUM
41
- type: rouge
42
  value: 20.906
 
43
  verified: true
44
- - name: loss
45
- type: loss
46
  value: 3.3002164363861084
 
47
  verified: true
48
- - name: gen_len
49
- type: gen_len
50
- value: 52.0
 
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: 35.3305
 
64
  verified: true
65
- - name: ROUGE-2
66
- type: rouge
67
  value: 5.8001
 
68
  verified: true
69
- - name: ROUGE-L
70
- type: rouge
71
  value: 16.0557
 
72
  verified: true
73
- - name: ROUGE-LSUM
74
- type: rouge
75
  value: 32.3409
 
76
  verified: true
77
- - name: loss
78
- type: loss
79
  value: 3.0063540935516357
 
80
  verified: true
81
- - name: gen_len
82
- type: gen_len
83
  value: 268.4032
 
84
  verified: true
 
85
  - task:
86
  type: summarization
87
  name: Summarization
@@ -91,30 +103,36 @@ model-index:
91
  config: plain_text
92
  split: test
93
  metrics:
94
- - name: ROUGE-1
95
- type: rouge
96
  value: 37.0412
 
97
  verified: true
98
- - name: ROUGE-2
99
- type: rouge
100
  value: 8.519
 
101
  verified: true
102
- - name: ROUGE-L
103
- type: rouge
104
  value: 17.8685
 
105
  verified: true
106
- - name: ROUGE-LSUM
107
- type: rouge
108
  value: 33.5036
 
109
  verified: true
110
- - name: loss
111
- type: loss
112
  value: 3.628979444503784
 
113
  verified: true
114
- - name: gen_len
115
- type: gen_len
116
  value: 219.3885
 
117
  verified: true
 
118
  ---
119
 
120
  # long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP15
 
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: 24.5482
30
+ name: ROUGE-1
31
  verified: true
32
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2U3MGNlNzI0MGNiYWQ2NGRhYzg5M2Y3NjhjYTdhZmVlYWNmM2Y0YTFhN2I2ZmI5NDVkY2I2M2MxMjM5ZDIwOSIsInZlcnNpb24iOjF9.tHnV8ofGr9jbx0fHm3cDL6p8nqXZITS1H6XLjW-iWaNFuQJ7Qfs7E0uYNf2haQP6Mu5K5eWWGdg54KtMi1N9DA
33
+ - type: rouge
34
  value: 4.811
35
+ name: ROUGE-2
36
  verified: true
37
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzE1ODYzOGFhMDE4ZGU1OTM0OTM5NDBkNjEwODQzY2I1NzRhYTc0NDJjZmM5YzI4ZGZmZGNkZjljYmNlYTQ1YyIsInZlcnNpb24iOjF9.n7tOZFKEePwSEqM7a0Y-fBiEEi3jZL7QwP0MCQNun5yKsd2OIkTlruuauV3h8yHN5yKxg33CUfpzS2B44kGjBg
38
+ - type: rouge
39
  value: 17.2505
40
+ name: ROUGE-L
41
  verified: true
42
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjM3YTYwNjAyYzY5MmZjMzI1MmYwNzI2OWNmMzJiNzk3MTY5Y2E4ZmM1OTIyYjQ1NTkxMjI1ZGMwYmRiYzg5NiIsInZlcnNpb24iOjF9.1VQIehrugMj213RavmSAf1qsKTG3Jmj6DAJGi3KOeOYrJpKeLBQ6ftQZ_wSje8UiyR9uekne1wTd256sr61DBQ
43
+ - type: rouge
44
  value: 20.906
45
+ name: ROUGE-LSUM
46
  verified: true
47
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDdhNjJlOTY3ZjgxOGMzYjkzOGI2NGJlZDY0MDk0NmE5ZDcyMzIyNTA1M2ZhNmMyOTFlODJjZWJkY2ZjMTQ3NCIsInZlcnNpb24iOjF9.SLAdCUY_9PFb7BrvvpN2ABDU9uvy7EIMEHKtnlpH94nZbv2G2sj74tWLcIQstuTkmXmLTk6_HvdZTEaoUc-5CA
48
+ - type: loss
49
  value: 3.3002164363861084
50
+ name: loss
51
  verified: true
52
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDFkM2UyOWQ5YzM2ZDIwZGRmNTY2YTRlMzUzY2QxZDhkNGFmODljNjIxNWQxZjFhM2E2YjM4ZWRjZDUzNWQxNyIsInZlcnNpb24iOjF9.HUYhxEAGbZS8J76Zt9k5KNFt6dx_vdoqf34k5ht3X0BTB4u2WiYwVS9O0ka2ExCynIODo9OMWLcMG2CW-xnjBA
53
+ - type: gen_len
54
+ value: 52
55
+ name: gen_len
56
  verified: true
57
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTkxMWQ0ZWVlNWUxNjYwNTU3MTQzYjRhZGI1YjQ1ODYxOGRlNTU0ZjlkOGZiN2UzM2I5MjU3Y2QxODU3MTJmZCIsInZlcnNpb24iOjF9.9iDB-q3h2qYZIRHLKryZIjYYUeN_4_9hr5miRgmJl8TYB1Prf69NNziW7QPOkMXMOM-5-xvRVKmx-JqZQSkcDg
58
  - task:
59
  type: summarization
60
  name: Summarization
 
64
  config: kmfoda--booksum
65
  split: test
66
  metrics:
67
+ - type: rouge
 
68
  value: 35.3305
69
+ name: ROUGE-1
70
  verified: true
71
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q0NWU1Mjc0ZTYxOGM5NjI3NTlmODYwMmU4ODE3Y2VjYjdmNTRhOWI2MDdlM2U3OTk5N2Q3YTcyYTViYzIwMiIsInZlcnNpb24iOjF9.ScFds-4QZgG0Wro-w0qnoaQSoXXMpWOTEE4zYrvA9k2lew965geaqeBVAt7QQxwchuB9q26hSGYCEqLMdX3EBw
72
+ - type: rouge
73
  value: 5.8001
74
+ name: ROUGE-2
75
  verified: true
76
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjFiNjU2ZjI1YmE2NDViZjUwMjI1ZWFiNDkyMjExZjJjMjBmN2I5ZmYyYjE0MGEzNzk3ZGE4YTMzNzA0M2NjNSIsInZlcnNpb24iOjF9.H4r1JTjEC3ABkgVIi8i3TRxQ1gMsYoQR8qCBbJVkdWJQwECzWGZRw6QIaWz0kZv73nQ890kf90JE6FKeD2MpAg
77
+ - type: rouge
78
  value: 16.0557
79
+ name: ROUGE-L
80
  verified: true
81
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjBjNTBiYmM3OWM3ZjFkN2FjZTBiMGJkMTg4MTYxYzRjNWUzNWE2YWVjOWJiMzRkZTMxMGFkYThlYmZiN2UwNSIsInZlcnNpb24iOjF9.mLij-24wue3udXSS5H3kBniefh7NDTmNf3bxacq7UinFkbTtqx9OvS6Ywun4LfJj_Ufn9-uTMR2VbaoIIQKkBA
82
+ - type: rouge
83
  value: 32.3409
84
+ name: ROUGE-LSUM
85
  verified: true
86
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjg3ODliOTAzYzg4Y2NhNzI4M2I4OGM1ZGQwMWE5ZjBiZGQyNTNhMDQxZDllMzgxOGM0NWZjZTJjMzFkZGVkZSIsInZlcnNpb24iOjF9.LpNcyf7HNaL_xwb4zqrBgOPoTBWFaBN0AgSbzsgfsQ7J12CIi7s0UoBhxg_c8UYwNuqFOZouYIq78r1PM81RCA
87
+ - type: loss
88
  value: 3.0063540935516357
89
+ name: loss
90
  verified: true
91
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTJmMGM2Y2U0MDU0OTFlMzJlNTNlZjViYTAyYjE4YTVkOWJhMmQxZjc3MjM4ZGNkNTNmOTViNDYwZjg0MWI0YyIsInZlcnNpb24iOjF9.VLKkHEjp4Iq1r3-CXSABBzgPJFx1sbjRt5KbbKe_AEuKuJtXI6rRWPuBjudOLB-CHBvutDzVS9wR60pGaQ5jCg
92
+ - type: gen_len
93
  value: 268.4032
94
+ name: gen_len
95
  verified: true
96
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjJmYjZhOGFkMGNkZjEzOTA0Y2RjNWU3Yjc2ZGI5NWU1MTNjZjY5NzFiZjI0YjBhZjUxMDFlMjBmZTYxMWE0ZCIsInZlcnNpb24iOjF9.vnImpJVQBidfhKVOzEYuA2okKgbTvB0bkc4GNmvkTlxXdZlsqg1KuevQa587lmy0LQOZk1_pYWz0aVJ4VQQQAA
97
  - task:
98
  type: summarization
99
  name: Summarization
 
103
  config: plain_text
104
  split: test
105
  metrics:
106
+ - type: rouge
 
107
  value: 37.0412
108
+ name: ROUGE-1
109
  verified: true
110
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTQ0NzdhYjdlNDNhYjJmNzQwM2E1OWQ3ZTQxMTZiY2IwNjJkMzE0YzNmMWZjZTI0NGI2NWYzNTU0ODM0OTVmMCIsInZlcnNpb24iOjF9.1Gf6zoMOLmf71bkW9RdiXJPDms-vfc0hu0jJehdb7XCjW-hPcmLxdk8ALwWi9knBmeHZ18GHHSJklgU_maFoAA
111
+ - type: rouge
112
  value: 8.519
113
+ name: ROUGE-2
114
  verified: true
115
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2M0MTE2YTE5NmE1NjhkMGM0ZjYxMzJiOTFjZGNmOTdlZWFhOTExZTAzOGUyOWE4Yjg4MTE3NDcwZTg5ZDk0MCIsInZlcnNpb24iOjF9.6EeSA2FzddyK5EfHhBViKNDXIZp9svVTpvSi4O_9YULWX6Gs4bZYcGRQATGLS6Pfvh1swky1ZXXR5GpX4tN-Ag
116
+ - type: rouge
117
  value: 17.8685
118
+ name: ROUGE-L
119
  verified: true
120
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTZmMWRhZmNmZDY5MzYzM2JhNDc5NzdiMWI3MmRlYWViZjA0NGQxZDJhNjIxZTY3ZTM2NTJjYjI0ODE5MGFlYiIsInZlcnNpb24iOjF9.Tz6vT3YFZO5Hd8BySoXmtcwDQMSvr4DLGvKYpTeH7L0iZOaIFr8XILCPbLV6ZxjglSgFwMzcwsjN1d032mEqBA
121
+ - type: rouge
122
  value: 33.5036
123
+ name: ROUGE-LSUM
124
  verified: true
125
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzgzNGQyMTIxYWUwMDlkMjQwZDE5ZDRmYzczODJkZTIxOGE5MTEyZDNjYzMzZWFhMGUyMjljNDQ5NGQ4ZGRkOCIsInZlcnNpb24iOjF9.oR8vSpgDjMskRmcImHV4E5dkXbP74BKNYXmfpkpO5zIHIJWNNyJvUSKurDDy5rhbhbkI98kF5GmOcLlfghyrDA
126
+ - type: loss
127
  value: 3.628979444503784
128
+ name: loss
129
  verified: true
130
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTNkY2E0Y2Q1YjA3Y2VhYTAyOGE1NmQyYWQ0YzM5NzczOTBkYThiYzNjMDljY2YzZGYzMGQ3NGQ5YzRhN2M5OCIsInZlcnNpb24iOjF9.kD1yDRyt6PR5wKBHvsU4l6stGmcsvPbkGB1dMgSfvMWV0LjjSc3MaXUS2ykNciLdnJK_aSqIjSUbUDyO0e4oDA
131
+ - type: gen_len
132
  value: 219.3885
133
+ name: gen_len
134
  verified: true
135
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI2MjIyZWViY2I0NTE0YWMxYTE3OTAyODdhOTNlZDZkOTIyMjQ1NzdkMmU5YTY5NmNjYTNkOGI0ODk4YzE2OSIsInZlcnNpb24iOjF9.sqlm-kWBzo-sJ4PaelnJWeQ1usF3nM5ZJP8igXE2GhWNhAQVsST3tlvcA8GwRtfbVCAy_x7Ex9iOuYqpccdbDA
136
  ---
137
 
138
  # long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP15