update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- summarization
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- wiki_lingua
|
7 |
+
model-index:
|
8 |
+
- name: mT5_multilingual_XLSum-finetuned-ar-wikilingua
|
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 |
+
# mT5_multilingual_XLSum-finetuned-ar-wikilingua
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [csebuetnlp/mT5_multilingual_XLSum](https://huggingface.co/csebuetnlp/mT5_multilingual_XLSum) on the wiki_lingua dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.6903
|
20 |
+
- Rouge-1: 24.47
|
21 |
+
- Rouge-2: 7.69
|
22 |
+
- Rouge-l: 20.04
|
23 |
+
- Gen Len: 39.64
|
24 |
+
- Bertscore: 72.63
|
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: 5e-05
|
44 |
+
- train_batch_size: 4
|
45 |
+
- eval_batch_size: 4
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 250
|
50 |
+
- num_epochs: 8
|
51 |
+
- label_smoothing_factor: 0.1
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len | Bertscore |
|
56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:-------:|:---------:|
|
57 |
+
| 4.4406 | 1.0 | 5111 | 3.9582 | 22.35 | 6.84 | 18.39 | 34.78 | 71.94 |
|
58 |
+
| 4.0158 | 2.0 | 10222 | 3.8316 | 22.87 | 7.24 | 18.92 | 34.7 | 71.99 |
|
59 |
+
| 3.8626 | 3.0 | 15333 | 3.7695 | 23.65 | 7.5 | 19.6 | 35.53 | 72.31 |
|
60 |
+
| 3.7626 | 4.0 | 20444 | 3.7313 | 24.01 | 7.59 | 19.68 | 38.16 | 72.41 |
|
61 |
+
| 3.6934 | 5.0 | 25555 | 3.7118 | 24.37 | 7.77 | 19.93 | 39.36 | 72.47 |
|
62 |
+
| 3.6421 | 6.0 | 30666 | 3.7016 | 24.48 | 7.8 | 20.07 | 38.58 | 72.58 |
|
63 |
+
| 3.6073 | 7.0 | 35777 | 3.6907 | 24.31 | 7.83 | 20.13 | 38.07 | 72.5 |
|
64 |
+
| 3.5843 | 8.0 | 40888 | 3.6903 | 24.55 | 7.88 | 20.2 | 38.33 | 72.6 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.18.0
|
70 |
+
- Pytorch 1.10.0+cu111
|
71 |
+
- Datasets 2.1.0
|
72 |
+
- Tokenizers 0.12.1
|