0xhaz commited on
Commit
351ed70
1 Parent(s): 2886258

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - rouge
7
+ - meteor
8
+ model-index:
9
+ - name: distilbart-cnn-12-6-finetuned-1.3.2
10
+ results: []
11
+ datasets:
12
+ - ateneoscsl/BUOD_articlescraper
13
+ - cnn_dailymail
14
+ - xsum
15
+ language:
16
+ - tl
17
+ - en
18
+ ---
19
+
20
+ # 📋 BUOD: distilBART Transformer Model
21
+ [![Model:distilBART](https://img.shields.io/badge/model-distilBART-green)](https://huggingface.co/jamesesguerra/distilbart-cnn-12-6-finetuned-1.3.1)
22
+ Authors: [James Esguerra](https://huggingface.co/jamesesguerra), [Julia Avila](), [Hazielle Bugayong](https://huggingface.co/0xhaz)
23
+
24
+ This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on the KAMI-3000 dataset, for the task of Filipino Text Summarization.
25
+
26
+ It achieves the following results on the evaluation set:
27
+ - Loss: 1.8049
28
+ - Rouge1: 50.5143
29
+ - Rouge2: 23.2481
30
+ - Rougel: 34.135
31
+ - Rougelsum: 46.4261
32
+
33
+ ## 🔧 Finetuning/ Training procedure
34
+ #### Training hyperparameters
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 4
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 2
43
+
44
+ #### Training results
45
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
46
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
47
+ | 2.1377 | 1.0 | 586 | 1.8792 | 49.8737 | 22.7881 | 33.6698 | 45.8037 |
48
+ | 1.5731 | 2.0 | 1172 | 1.8049 | 50.5143 | 23.2481 | 34.135 | 46.4261 |
49
+
50
+
51
+ #### Framework versions
52
+ - Transformers 4.25.1
53
+ - Pytorch 1.12.1+cu113
54
+ - Datasets 2.7.1
55
+ - Tokenizers 0.13.2