Hugging Face's logo

cs608
/
multi-news-model

Summarization
Transformers
PyTorch
TensorBoard
bart
text2text-generation
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
cs608 commited on
Commit
66df073
•
1 Parent(s): c64663b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -15
README.md CHANGED
@@ -3,11 +3,26 @@ license: apache-2.0
3
  tags:
4
  - summarization
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - rouge
8
  model-index:
9
  - name: CS685-text-summarizer
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,13 +30,13 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # CS685-text-summarizer
17
 
18
- This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.6758
21
- - Rouge1: 50.1818
22
- - Rouge2: 25.0255
23
- - Rougel: 45.4346
24
- - Rougelsum: 45.4932
25
 
26
  ## Model description
27
 
@@ -41,24 +56,27 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 5.6e-05
44
- - train_batch_size: 10
45
- - eval_batch_size: 10
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 2
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
- | 2.0628 | 1.0 | 613 | 1.7464 | 48.9466 | 24.0276 | 44.5506 | 44.6348 |
56
- | 1.5004 | 2.0 | 1226 | 1.6758 | 50.1818 | 25.0255 | 45.4346 | 45.4932 |
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
- - Transformers 4.28.1
62
  - Pytorch 2.0.0+cu118
63
  - Datasets 2.12.0
64
  - Tokenizers 0.13.3
 
3
  tags:
4
  - summarization
5
  - generated_from_trainer
6
+ datasets:
7
+ - multi_news
8
  metrics:
9
  - rouge
10
  model-index:
11
  - name: CS685-text-summarizer
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: multi_news
18
+ type: multi_news
19
+ config: default
20
+ split: train[:20%]
21
+ args: default
22
+ metrics:
23
+ - name: Rouge1
24
+ type: rouge
25
+ value: 9.8777
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # CS685-text-summarizer
32
 
33
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the multi_news dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.4960
36
+ - Rouge1: 9.8777
37
+ - Rouge2: 3.6509
38
+ - Rougel: 7.597
39
+ - Rougelsum: 9.0495
40
 
41
  ## Model description
42
 
 
56
 
57
  The following hyperparameters were used during training:
58
  - learning_rate: 5.6e-05
59
+ - train_batch_size: 6
60
+ - eval_batch_size: 6
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
+ - num_epochs: 5
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
70
+ | 2.8402 | 1.0 | 1349 | 2.5256 | 9.7548 | 3.5429 | 7.5078 | 8.9174 |
71
+ | 2.5581 | 2.0 | 2698 | 2.5011 | 9.7256 | 3.6262 | 7.5644 | 8.8904 |
72
+ | 2.3908 | 3.0 | 4047 | 2.4948 | 9.7569 | 3.5976 | 7.5209 | 8.8919 |
73
+ | 2.2744 | 4.0 | 5396 | 2.4875 | 9.9116 | 3.7758 | 7.6823 | 9.0881 |
74
+ | 2.1908 | 5.0 | 6745 | 2.4960 | 9.8777 | 3.6509 | 7.597 | 9.0495 |
75
 
76
 
77
  ### Framework versions
78
 
79
+ - Transformers 4.29.1
80
  - Pytorch 2.0.0+cu118
81
  - Datasets 2.12.0
82
  - Tokenizers 0.13.3