Hugging Face's logo

datien228
/
distilbart-cnn-12-6-ftn-multi_news

Summarization
Transformers
PyTorch
bart
text2text-generation
Eval Results
Inference Endpoints
Model card Files Community
5
datien228 commited on
Commit
f61d207
•
1 Parent(s): a2462ea

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - summarization
5
  datasets:
6
  - multi_news
7
  metrics:
@@ -11,7 +11,7 @@ model-index:
11
  results:
12
  - task:
13
  name: Sequence-to-sequence Language Modeling
14
- type: summarization
15
  dataset:
16
  name: multi_news
17
  type: multi_news
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Rouge1
21
  type: rouge
22
- value: 39.9832
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,12 +29,12 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on the multi_news dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 4.0202
33
- - Rouge1: 39.9832
34
- - Rouge2: 13.0653
35
- - Rougel: 22.1761
36
- - Rougelsum: 34.5466
37
- - Gen Len: 132.41
38
 
39
  ## Model description
40
 
@@ -68,12 +68,12 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
70
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
71
- | 4.1427 | 0.89 | 400 | 4.0202 | 39.9832 | 13.0653 | 22.1761 | 34.5466 | 132.41 |
72
 
73
 
74
  ### Framework versions
75
 
76
- - Transformers 4.18.0
77
- - Pytorch 1.11.0
78
- - Datasets 2.1.0
79
  - Tokenizers 0.12.1
 
1
  ---
2
  license: apache-2.0
3
  tags:
4
+ - generated_from_trainer
5
  datasets:
6
  - multi_news
7
  metrics:
 
11
  results:
12
  - task:
13
  name: Sequence-to-sequence Language Modeling
14
+ type: text2text-generation
15
  dataset:
16
  name: multi_news
17
  type: multi_news
 
19
  metrics:
20
  - name: Rouge1
21
  type: rouge
22
+ value: 41.6136
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on the multi_news dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 3.8143
33
+ - Rouge1: 41.6136
34
+ - Rouge2: 14.7454
35
+ - Rougel: 23.3597
36
+ - Rougelsum: 36.1973
37
+ - Gen Len: 130.874
38
 
39
  ## Model description
40
 
 
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
70
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
71
+ | 3.8821 | 0.89 | 2000 | 3.8143 | 41.6136 | 14.7454 | 23.3597 | 36.1973 | 130.874 |
72
 
73
 
74
  ### Framework versions
75
 
76
+ - Transformers 4.20.1
77
+ - Pytorch 1.11.0+cu113
78
+ - Datasets 2.3.2
79
  - Tokenizers 0.12.1