wicharnkeisei
commited on
Commit
•
f658868
1
Parent(s):
e68744b
Update README.md
Browse files
README.md
CHANGED
@@ -14,23 +14,17 @@ widget:
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
#
|
18 |
|
19 |
-
This model is a fine-tuned version of [deepset/xlm-roberta-base-squad2](https://huggingface.co/deepset/xlm-roberta-base-squad2) on
|
20 |
-
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.0899
|
22 |
-
|
23 |
-
## Model description
|
24 |
-
|
25 |
-
More information needed
|
26 |
|
27 |
## Intended uses & limitations
|
28 |
|
29 |
-
|
30 |
|
31 |
## Training and evaluation data
|
32 |
|
33 |
-
|
34 |
|
35 |
## Training procedure
|
36 |
|
@@ -47,13 +41,13 @@ The following hyperparameters were used during training:
|
|
47 |
- lr_scheduler_type: linear
|
48 |
- num_epochs: 2
|
49 |
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
|
58 |
### Framework versions
|
59 |
|
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
# thai-squad
|
18 |
|
19 |
+
This model is a fine-tuned version of [deepset/xlm-roberta-base-squad2](https://huggingface.co/deepset/xlm-roberta-base-squad2) on Thai dataset from [iApp Technology Co., Ltd.](https://github.com/iapp-technology/iapp-wiki-qa-dataset).
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## Intended uses & limitations
|
22 |
|
23 |
+
This model intends to use with Thai question and answering task
|
24 |
|
25 |
## Training and evaluation data
|
26 |
|
27 |
+
Trained and evaluated by [iApp Technology Co., Ltd.](https://github.com/iapp-technology/iapp-wiki-qa-dataset) dataset.
|
28 |
|
29 |
## Training procedure
|
30 |
|
|
|
41 |
- lr_scheduler_type: linear
|
42 |
- num_epochs: 2
|
43 |
|
44 |
+
## Performance
|
45 |
+
Evaluated on the SQuAD 1.0 test dataset
|
46 |
+
```
|
47 |
+
"exact": 62.51728907330567
|
48 |
+
"f1": 73.62388955749958
|
49 |
+
"total": 723
|
50 |
+
```
|
51 |
|
52 |
### Framework versions
|
53 |
|