Hugging Face's logo

theojolliffe
/
bart-large-cnn-finetuned-roundup

Transformers
PyTorch
TensorBoard
bart
text2text-generation
Generated from Trainer
Model card Files
xet
 Metrics Community
1
theojolliffe commited on
Commit
3c00d12
·
1 Parent(s): b1e4213

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +79 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - rouge
7
+ model-index:
8
+ - name: bart-large-cnn-finetuned-roundup
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # bart-large-cnn-finetuned-roundup
16
+
17
+ This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8956
20
+ - Rouge1: 58.1914
21
+ - Rouge2: 45.822
22
+ - Rougel: 49.4407
23
+ - Rougelsum: 56.6379
24
+ - Gen Len: 142.0
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 1
45
+ - eval_batch_size: 1
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 16
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
56
+ | 1.2575 | 1.0 | 795 | 0.9154 | 53.8792 | 34.3203 | 35.8768 | 51.1789 | 142.0 |
57
+ | 0.7053 | 2.0 | 1590 | 0.7921 | 54.3918 | 35.3346 | 37.7539 | 51.6989 | 142.0 |
58
+ | 0.5379 | 3.0 | 2385 | 0.7566 | 52.1651 | 32.5699 | 36.3105 | 49.3327 | 141.5185 |
59
+ | 0.3496 | 4.0 | 3180 | 0.7584 | 54.3258 | 36.403 | 39.6938 | 52.0186 | 142.0 |
60
+ | 0.2688 | 5.0 | 3975 | 0.7343 | 55.9101 | 39.0709 | 42.4138 | 53.572 | 141.8333 |
61
+ | 0.1815 | 6.0 | 4770 | 0.7924 | 53.9272 | 36.8138 | 40.0614 | 51.7496 | 142.0 |
62
+ | 0.1388 | 7.0 | 5565 | 0.7674 | 55.0347 | 38.7978 | 42.0081 | 53.0297 | 142.0 |
63
+ | 0.1048 | 8.0 | 6360 | 0.7700 | 55.2993 | 39.4075 | 42.6837 | 53.5179 | 141.9815 |
64
+ | 0.0808 | 9.0 | 7155 | 0.7796 | 56.1508 | 40.0863 | 43.2178 | 53.7908 | 142.0 |
65
+ | 0.0719 | 10.0 | 7950 | 0.8057 | 56.2302 | 41.3004 | 44.7921 | 54.4304 | 142.0 |
66
+ | 0.0503 | 11.0 | 8745 | 0.8259 | 55.7603 | 41.0643 | 44.5518 | 54.2305 | 142.0 |
67
+ | 0.0362 | 12.0 | 9540 | 0.8604 | 55.8612 | 41.5984 | 44.444 | 54.2493 | 142.0 |
68
+ | 0.0307 | 13.0 | 10335 | 0.8516 | 57.7259 | 44.542 | 47.6724 | 56.0166 | 142.0 |
69
+ | 0.0241 | 14.0 | 11130 | 0.8826 | 56.7943 | 43.7139 | 47.2866 | 55.1824 | 142.0 |
70
+ | 0.0193 | 15.0 | 11925 | 0.8856 | 57.4135 | 44.3147 | 47.9136 | 55.8843 | 142.0 |
71
+ | 0.0154 | 16.0 | 12720 | 0.8956 | 58.1914 | 45.822 | 49.4407 | 56.6379 | 142.0 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.23.1
77
+ - Pytorch 1.12.1+cu113
78
+ - Datasets 2.6.1
79
+ - Tokenizers 0.13.1