Hugging Face's logo

nandavikas16
/
bart-large-cnn-finetuned-scope-summarization

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Model card Files Metrics Community
nandavikas16 commited on
Commit
2bea5d9
·
verified ·
1 Parent(s): 233d337

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1466
21
- - Rouge1: 53.6452
22
- - Rouge2: 39.2506
23
- - Rougel: 44.3673
24
- - Rougelsum: 44.3521
25
 
26
  ## Model description
27
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
- | 0.5077 | 1.0 | 36 | 0.2435 | 43.0788 | 24.6647 | 32.4588 | 32.5662 |
56
- | 0.2391 | 2.0 | 72 | 0.2190 | 44.1416 | 26.995 | 33.4471 | 33.3775 |
57
- | 0.2086 | 3.0 | 108 | 0.2094 | 47.6567 | 31.6759 | 37.2761 | 37.2626 |
58
- | 0.1896 | 4.0 | 144 | 0.1986 | 49.8613 | 33.0333 | 38.6723 | 38.6662 |
59
- | 0.1868 | 5.0 | 180 | 0.1945 | 49.5133 | 33.8958 | 38.6023 | 38.6402 |
60
- | 0.1726 | 6.0 | 216 | 0.1745 | 52.5006 | 36.3466 | 41.5471 | 41.5067 |
61
- | 0.1656 | 7.0 | 252 | 0.1705 | 52.6514 | 38.6746 | 43.3252 | 43.3525 |
62
- | 0.1515 | 8.0 | 288 | 0.1580 | 53.659 | 37.2505 | 42.5857 | 42.6415 |
63
- | 0.1561 | 9.0 | 324 | 0.1492 | 54.5155 | 39.0607 | 44.2114 | 44.3034 |
64
- | 0.1363 | 10.0 | 360 | 0.1466 | 53.6452 | 39.2506 | 44.3673 | 44.3521 |
65
 
66
 
67
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0567
21
+ - Rouge1: 55.8275
22
+ - Rouge2: 45.1893
23
+ - Rougel: 50.0441
24
+ - Rougelsum: 50.1406
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
+ | 0.4872 | 1.0 | 31 | 0.1259 | 40.3668 | 25.4156 | 32.4952 | 32.5066 |
56
+ | 0.1349 | 2.0 | 62 | 0.1071 | 38.4137 | 23.9982 | 29.3169 | 29.3606 |
57
+ | 0.128 | 3.0 | 93 | 0.1000 | 45.61 | 29.904 | 36.2931 | 36.1606 |
58
+ | 0.1138 | 4.0 | 124 | 0.0993 | 47.4837 | 33.2177 | 40.1978 | 40.0854 |
59
+ | 0.1064 | 5.0 | 155 | 0.0832 | 48.4985 | 34.9247 | 42.5024 | 42.5047 |
60
+ | 0.0978 | 6.0 | 186 | 0.0792 | 50.4492 | 37.1342 | 42.4463 | 42.2735 |
61
+ | 0.0941 | 7.0 | 217 | 0.0726 | 53.0967 | 41.2303 | 45.9412 | 45.9511 |
62
+ | 0.0748 | 8.0 | 248 | 0.0653 | 54.9193 | 43.316 | 46.8554 | 46.7847 |
63
+ | 0.0791 | 9.0 | 279 | 0.0582 | 54.424 | 44.2063 | 47.1231 | 47.0471 |
64
+ | 0.0742 | 10.0 | 310 | 0.0567 | 55.8275 | 45.1893 | 50.0441 | 50.1406 |
65
 
66
 
67
  ### Framework versions