Hugging Face's logo

thaomer
/
le-fine-tune-mbart-large-50

Summarization
Transformers
PyTorch
TensorBoard
mbart
text2text-generation
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
thaomer commited on
Commit
f52d1c9
•
1 Parent(s): 6442a2f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - summarization
5
+ - generated_from_trainer
6
+ datasets:
7
+ - ravkuk_summerize_dataset
8
+ metrics:
9
+ - rouge
10
+ model-index:
11
+ - name: le-fine-tune-mbart-large-50
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: ravkuk_summerize_dataset
18
+ type: ravkuk_summerize_dataset
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Rouge1
24
+ type: rouge
25
+ value: 0.2928
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # le-fine-tune-mbart-large-50
32
+
33
+ This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the ravkuk_summerize_dataset dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 2.7762
36
+ - Rouge1: 0.2928
37
+ - Rouge2: 0.1926
38
+ - Rougel: 0.2815
39
+ - Rougelsum: 0.2816
40
+ - Gen Len: 34.5028
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 5.6e-05
60
+ - train_batch_size: 8
61
+ - eval_batch_size: 8
62
+ - seed: 42
63
+ - gradient_accumulation_steps: 2
64
+ - total_train_batch_size: 16
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: linear
67
+ - num_epochs: 10
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
72
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
73
+ | 3.1169 | 1.0 | 197 | 2.3604 | 0.1878 | 0.0725 | 0.1737 | 0.1737 | 33.7784 |
74
+ | 1.8945 | 2.0 | 394 | 2.2522 | 0.1897 | 0.0765 | 0.1776 | 0.1776 | 34.2074 |
75
+ | 1.3083 | 3.0 | 591 | 2.2886 | 0.2001 | 0.0927 | 0.1895 | 0.1892 | 35.4432 |
76
+ | 0.8693 | 4.0 | 788 | 2.3727 | 0.2243 | 0.1123 | 0.2122 | 0.2117 | 31.4943 |
77
+ | 0.5507 | 5.0 | 985 | 2.5059 | 0.2577 | 0.1527 | 0.2463 | 0.2466 | 34.3693 |
78
+ | 0.3385 | 6.0 | 1182 | 2.6032 | 0.2703 | 0.1672 | 0.2593 | 0.2584 | 33.5994 |
79
+ | 0.2031 | 7.0 | 1379 | 2.6518 | 0.2912 | 0.1932 | 0.2812 | 0.281 | 34.1676 |
80
+ | 0.1272 | 8.0 | 1576 | 2.7040 | 0.2891 | 0.1895 | 0.2799 | 0.2796 | 34.6761 |
81
+ | 0.0842 | 9.0 | 1773 | 2.7515 | 0.2978 | 0.198 | 0.2888 | 0.2887 | 34.1932 |
82
+ | 0.0605 | 10.0 | 1970 | 2.7762 | 0.2928 | 0.1926 | 0.2815 | 0.2816 | 34.5028 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.26.1
88
+ - Pytorch 1.13.1+cu116
89
+ - Datasets 2.10.1
90
+ - Tokenizers 0.13.2