Hugging Face's logo

Gabriel
/
bart-base-cnn-xsum-swe

Summarization
Transformers
PyTorch
TensorBoard
Swedish
bart
text2text-generation
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
Gabriel commited on
Commit
2783f9e
•
1 Parent(s): 4a77a48

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -12
README.md CHANGED
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [Gabriel/bart-base-cnn-swe](https://huggingface.co/Gabriel/bart-base-cnn-swe) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.1140
20
- - Rouge1: 30.7101
21
- - Rouge2: 11.9532
22
- - Rougel: 25.1864
23
- - Rougelsum: 25.2227
24
- - Gen Len: 19.7448
25
 
26
  ## Model description
27
 
@@ -40,7 +40,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 3.75e-05
44
  - train_batch_size: 16
45
  - eval_batch_size: 16
46
  - seed: 42
@@ -49,21 +49,22 @@ The following hyperparameters were used during training:
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 500
52
- - num_epochs: 3
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
59
- | 2.3087 | 1.0 | 6375 | 2.1997 | 29.7666 | 11.0222 | 24.2659 | 24.2915 | 19.7172 |
60
- | 2.0793 | 2.0 | 12750 | 2.1285 | 30.4447 | 11.7671 | 24.9238 | 24.9622 | 19.7051 |
61
- | 1.9186 | 3.0 | 19125 | 2.1140 | 30.7101 | 11.9532 | 25.1864 | 25.2227 | 19.7448 |
 
62
 
63
 
64
  ### Framework versions
65
 
66
- - Transformers 4.22.1
67
  - Pytorch 1.12.1+cu113
68
  - Datasets 2.5.1
69
  - Tokenizers 0.12.1
 
16
 
17
  This model is a fine-tuned version of [Gabriel/bart-base-cnn-swe](https://huggingface.co/Gabriel/bart-base-cnn-swe) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.1027
20
+ - Rouge1: 30.9467
21
+ - Rouge2: 12.2589
22
+ - Rougel: 25.4487
23
+ - Rougelsum: 25.4792
24
+ - Gen Len: 19.7379
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 4e-05
44
  - train_batch_size: 16
45
  - eval_batch_size: 16
46
  - seed: 42
 
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 500
52
+ - num_epochs: 4
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
59
+ | 2.3076 | 1.0 | 6375 | 2.1986 | 29.7041 | 10.9883 | 24.2149 | 24.2406 | 19.7193 |
60
+ | 2.0733 | 2.0 | 12750 | 2.1246 | 30.4521 | 11.8107 | 24.9519 | 24.9745 | 19.6592 |
61
+ | 1.8933 | 3.0 | 19125 | 2.0989 | 30.9407 | 12.2682 | 25.4135 | 25.4378 | 19.7195 |
62
+ | 1.777 | 4.0 | 25500 | 2.1027 | 30.9467 | 12.2589 | 25.4487 | 25.4792 | 19.7379 |
63
 
64
 
65
  ### Framework versions
66
 
67
+ - Transformers 4.22.2
68
  - Pytorch 1.12.1+cu113
69
  - Datasets 2.5.1
70
  - Tokenizers 0.12.1