autoevaluator HF staff commited on
Commit
076544b
1 Parent(s): deb0f97

Add evaluation results on the samsum config and test split of samsum

Browse files

Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\
Your model has been evaluated on the samsum config and test split of the [samsum](https://huggingface.co/datasets/samsum) dataset by

@wuhou

, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-eval-samsum-samsum-bc6414-46260145184).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=samsum).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=samsum).

Files changed (1) hide show
  1. README.md +53 -14
README.md CHANGED
@@ -1,12 +1,12 @@
1
  ---
2
  language:
3
  - en
 
4
  tags:
5
  - summarization
6
- license: mit
7
- thumbnail: https://huggingface.co/front/thumbnails/facebook.png
8
  datasets:
9
  - cnn_dailymail
 
10
  model-index:
11
  - name: facebook/bart-large-cnn
12
  results:
@@ -19,30 +19,69 @@ model-index:
19
  config: 3.0.0
20
  split: train
21
  metrics:
22
- - name: ROUGE-1
23
- type: rouge
24
  value: 42.9486
 
25
  verified: true
26
- - name: ROUGE-2
27
- type: rouge
28
  value: 20.8149
 
29
  verified: true
30
- - name: ROUGE-L
31
- type: rouge
32
  value: 30.6186
 
33
  verified: true
34
- - name: ROUGE-LSUM
35
- type: rouge
36
  value: 40.0376
 
37
  verified: true
38
- - name: loss
39
- type: loss
40
  value: 2.529000997543335
 
41
  verified: true
42
- - name: gen_len
43
- type: gen_len
44
  value: 78.5866
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  verified: true
 
46
  ---
47
  # BART (large-sized model), fine-tuned on CNN Daily Mail
48
 
1
  ---
2
  language:
3
  - en
4
+ license: mit
5
  tags:
6
  - summarization
 
 
7
  datasets:
8
  - cnn_dailymail
9
+ thumbnail: https://huggingface.co/front/thumbnails/facebook.png
10
  model-index:
11
  - name: facebook/bart-large-cnn
12
  results:
19
  config: 3.0.0
20
  split: train
21
  metrics:
22
+ - type: rouge
 
23
  value: 42.9486
24
+ name: ROUGE-1
25
  verified: true
26
+ - type: rouge
 
27
  value: 20.8149
28
+ name: ROUGE-2
29
  verified: true
30
+ - type: rouge
 
31
  value: 30.6186
32
+ name: ROUGE-L
33
  verified: true
34
+ - type: rouge
 
35
  value: 40.0376
36
+ name: ROUGE-LSUM
37
  verified: true
38
+ - type: loss
 
39
  value: 2.529000997543335
40
+ name: loss
41
  verified: true
42
+ - type: gen_len
 
43
  value: 78.5866
44
+ name: gen_len
45
+ verified: true
46
+ - task:
47
+ type: summarization
48
+ name: Summarization
49
+ dataset:
50
+ name: samsum
51
+ type: samsum
52
+ config: samsum
53
+ split: test
54
+ metrics:
55
+ - type: rouge
56
+ value: 30.7334
57
+ name: ROUGE-1
58
+ verified: true
59
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTQwMGVjNmZlYTc0YzkxZjdlNGFkZTJiZDY5NzUxY2ExODYzYzkwNWEyNTdlY2RjNDc0NzhkMTg0NTc1OTI2MSIsInZlcnNpb24iOjF9.8zpDqNoH7SDhXRQHY5zFzxrUr8Nob6FWQubGq_nq33DKHd8Cs7TyNzCIM3vjLHEwJNmJuIcxmC97sDgu34F1Bw
60
+ - type: rouge
61
+ value: 10.2462
62
+ name: ROUGE-2
63
+ verified: true
64
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmQzMTdkM2IwZmZjMTdhYWVlNDAzZThiYjZjNzI2MTBjY2E0YTZiYTE1MTQyYWRiYTdkNWQxZDkyZDMwMjE3YiIsInZlcnNpb24iOjF9.371GLVgHGue_EF0gxKcKwFFnmyKD3R5CC7BW58Kj4Rya6HEdkKs0Sm9rb47jvHGRp0USA72-SHZzLRgttO_eBA
65
+ - type: rouge
66
+ value: 23.0923
67
+ name: ROUGE-L
68
+ verified: true
69
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWU4NjllNDM1YmZjODIxNDlmZGVkZmE2OTEwN2UwNGI2YjExMzM4Mzc1MTk2Zjk4NGVjMTBkMjE4YTk2NzA0OSIsInZlcnNpb24iOjF9.DI9gd21hx9FFOVXU9L0BGX02y2Arv-auknRqOmlMdQzJnBfvGbLDbKQygSuX1-39m6fKFPyUxcqZyHH_UHIVBQ
70
+ - type: rouge
71
+ value: 28.634
72
+ name: ROUGE-LSUM
73
+ verified: true
74
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzMzOTI4MTYyZmQyN2M3Nzc5NGQ5NjU0ZmJmNDFlYWJjOGExM2U5YmY2MzVkNDVkY2JjNTlkZDQ4YjNmNzMxMSIsInZlcnNpb24iOjF9.z0udm2LNnm6GCZ16PJX0hlQXFPkRVjSfsUjlMMuptCLjRrowS_gDerlt8gUwk6H_7Gj0tjmf5gcSUakmtfvqBg
75
+ - type: loss
76
+ value: 2.1912083625793457
77
+ name: loss
78
+ verified: true
79
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDU0MTNkMTcxYjI4MjAzZjdmYjIyMDRiZDQ1NzI2MjRjM2QyNzU0MTliOTA5MDE3ZmIyYmY2NzI0MjE0OWM1NyIsInZlcnNpb24iOjF9.Z7ezEIG_ovOGFCsCnMLg4Wcede5cBlZP0lRbks9w9ceuSCESp8Qdeksa8S7pHpGBCBbOwR1xFyMOOxZZAp9pDA
80
+ - type: gen_len
81
+ value: 66.6813
82
+ name: gen_len
83
  verified: true
84
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTRmMWYwMzgyZjVkZjk4YjZlNGZiODhhNTc0YjI5MmFmMWJhYWNlNTIyMDU2NTM0OTc5YTVmNWQ5MGYxZjBkMSIsInZlcnNpb24iOjF9.l95E7CZ_UaQ5Cke_7l6MNoqyRXah6fLZTC7e2FYRGPp8dst-Ke-fyB-o7TdKFV_2tXYtz2J5PWmunYf9Oe3QBA
85
  ---
86
  # BART (large-sized model), fine-tuned on CNN Daily Mail
87