Hugging Face's logo

emilstabil
/
DanSumT5-baseV_38821

Text2Text Generation
Transformers
PyTorch
mt5
Generated from Trainer
Inference Endpoints
Model card Files Community
1
emilstabil commited on
Commit
f04aa61
·
1 Parent(s): 28a4bcd

End of training

Browse files
Files changed (2) hide show
  1. README.md +34 -29
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -6,23 +6,23 @@ tags:
6
  metrics:
7
  - rouge
8
  model-index:
9
- - name: DanSumT5-base-finetuned-test_6887
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- # DanSumT5-base-finetuned-test_6887
17
 
18
  This model is a fine-tuned version of [Danish-summarisation/DanSumT5-base](https://huggingface.co/Danish-summarisation/DanSumT5-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.5277
21
- - Rouge1: 31.3188
22
- - Rouge2: 7.8236
23
- - Rougel: 17.8296
24
- - Rougelsum: 28.6162
25
- - Gen Len: 127.0
26
 
27
  ## Model description
28
 
@@ -42,34 +42,39 @@ More information needed
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 2e-05
45
- - train_batch_size: 3
46
- - eval_batch_size: 3
47
  - seed: 42
48
  - gradient_accumulation_steps: 4
49
- - total_train_batch_size: 12
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 15
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
57
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
58
- | No log | 0.99 | 66 | 2.7401 | 29.9221 | 6.3861 | 16.5877 | 27.0611 | 125.09 |
59
- | No log | 1.99 | 133 | 2.6815 | 30.6874 | 6.9413 | 16.9609 | 27.8851 | 125.98 |
60
- | No log | 3.0 | 200 | 2.6440 | 31.2045 | 7.4012 | 17.7421 | 28.3497 | 126.63 |
61
- | No log | 4.0 | 267 | 2.6199 | 31.3329 | 7.4574 | 17.8549 | 28.643 | 126.98 |
62
- | No log | 4.99 | 333 | 2.5984 | 31.5184 | 7.7763 | 17.9153 | 29.0627 | 127.0 |
63
- | No log | 5.99 | 400 | 2.5822 | 31.8839 | 7.9755 | 18.0572 | 29.2282 | 126.65 |
64
- | No log | 7.0 | 467 | 2.5677 | 31.5939 | 7.9515 | 17.865 | 29.2019 | 126.45 |
65
- | 2.8684 | 8.0 | 534 | 2.5587 | 31.4931 | 7.6042 | 17.6853 | 28.8366 | 126.79 |
66
- | 2.8684 | 8.99 | 600 | 2.5496 | 31.105 | 7.6714 | 17.5128 | 28.5242 | 126.78 |
67
- | 2.8684 | 9.99 | 667 | 2.5423 | 31.6087 | 8.0358 | 17.9956 | 28.9514 | 126.78 |
68
- | 2.8684 | 11.0 | 734 | 2.5364 | 31.411 | 7.9534 | 17.895 | 28.7595 | 127.0 |
69
- | 2.8684 | 12.0 | 801 | 2.5326 | 31.4648 | 7.9777 | 17.9589 | 28.8168 | 127.0 |
70
- | 2.8684 | 12.99 | 867 | 2.5296 | 31.374 | 7.8341 | 17.8341 | 28.8146 | 127.0 |
71
- | 2.8684 | 13.99 | 934 | 2.5278 | 31.2822 | 7.7789 | 17.7983 | 28.5903 | 127.0 |
72
- | 2.8684 | 14.83 | 990 | 2.5277 | 31.3188 | 7.8236 | 17.8296 | 28.6162 | 127.0 |
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
6
  metrics:
7
  - rouge
8
  model-index:
9
+ - name: DanSumT5-baseV_38821
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # DanSumT5-baseV_38821
17
 
18
  This model is a fine-tuned version of [Danish-summarisation/DanSumT5-base](https://huggingface.co/Danish-summarisation/DanSumT5-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.2026
21
+ - Rouge1: 34.9358
22
+ - Rouge2: 11.6813
23
+ - Rougel: 21.4935
24
+ - Rougelsum: 27.4979
25
+ - Gen Len: 126.3262
26
 
27
  ## Model description
28
 
 
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 2e-05
45
+ - train_batch_size: 2
46
+ - eval_batch_size: 2
47
  - seed: 42
48
  - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 8
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 20
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
57
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
58
+ | No log | 1.0 | 232 | 2.4684 | 33.3966 | 9.9982 | 19.6472 | 27.3865 | 126.8712 |
59
+ | No log | 2.0 | 465 | 2.3905 | 34.2228 | 10.5192 | 20.3584 | 27.4209 | 126.8712 |
60
+ | 2.8064 | 3.0 | 697 | 2.3486 | 34.5949 | 11.0682 | 20.8844 | 27.3403 | 126.6738 |
61
+ | 2.8064 | 4.0 | 930 | 2.3193 | 34.6865 | 11.0996 | 20.9574 | 27.337 | 126.2318 |
62
+ | 2.5767 | 5.0 | 1162 | 2.2963 | 34.3101 | 11.0183 | 20.8461 | 27.155 | 126.721 |
63
+ | 2.5767 | 6.0 | 1395 | 2.2774 | 34.9299 | 11.5927 | 21.3549 | 27.7805 | 126.4249 |
64
+ | 2.483 | 7.0 | 1627 | 2.2646 | 34.4741 | 11.1383 | 21.2722 | 27.3822 | 126.3004 |
65
+ | 2.483 | 8.0 | 1860 | 2.2521 | 34.9384 | 11.2651 | 21.3153 | 27.5792 | 126.9828 |
66
+ | 2.4134 | 9.0 | 2092 | 2.2410 | 34.9546 | 11.424 | 21.1427 | 27.6608 | 126.7854 |
67
+ | 2.4134 | 10.0 | 2325 | 2.2326 | 34.7566 | 11.5721 | 21.4418 | 27.5167 | 126.7425 |
68
+ | 2.3576 | 11.0 | 2557 | 2.2263 | 34.5968 | 11.623 | 21.2384 | 27.365 | 126.4506 |
69
+ | 2.3576 | 12.0 | 2790 | 2.2194 | 34.7363 | 11.5612 | 21.47 | 27.6572 | 126.5665 |
70
+ | 2.3288 | 13.0 | 3022 | 2.2142 | 34.971 | 11.7203 | 21.49 | 27.7418 | 126.5665 |
71
+ | 2.3288 | 14.0 | 3255 | 2.2114 | 34.761 | 11.6621 | 21.3963 | 27.568 | 126.6266 |
72
+ | 2.3288 | 15.0 | 3487 | 2.2064 | 34.9197 | 11.5475 | 21.4017 | 27.6388 | 126.3305 |
73
+ | 2.2951 | 16.0 | 3720 | 2.2067 | 34.8124 | 11.615 | 21.5177 | 27.605 | 126.3605 |
74
+ | 2.2951 | 17.0 | 3952 | 2.2042 | 34.7608 | 11.4738 | 21.3464 | 27.379 | 126.4034 |
75
+ | 2.2832 | 18.0 | 4185 | 2.2032 | 34.7593 | 11.6239 | 21.4029 | 27.4669 | 126.2489 |
76
+ | 2.2832 | 19.0 | 4417 | 2.2029 | 34.8386 | 11.5919 | 21.4719 | 27.5147 | 126.2318 |
77
+ | 2.2571 | 19.96 | 4640 | 2.2026 | 34.9358 | 11.6813 | 21.4935 | 27.4979 | 126.3262 |
78
 
79
 
80
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6966dfd32e10b7b7ff74248f30d567803eac7ea4a89b1c2835c6c6c3bf48cbeb
3
  size 2329703026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2e0948183a0d455972c242ee4d5c559a016ca4442cc1504ff32043d371c508
3
  size 2329703026