Model save
Browse files- README.md +15 -30
- adapter-summarization/pytorch_adapter.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- id
|
4 |
license: apache-2.0
|
5 |
base_model: LazarusNLP/IndoNanoT5-base
|
6 |
tags:
|
@@ -11,20 +9,7 @@ metrics:
|
|
11 |
- rouge
|
12 |
model-index:
|
13 |
- name: liputan6-pt-pl5
|
14 |
-
results:
|
15 |
-
- task:
|
16 |
-
name: Summarization
|
17 |
-
type: summarization
|
18 |
-
dataset:
|
19 |
-
name: id_liputan6 canonical
|
20 |
-
type: id_liputan6
|
21 |
-
config: canonical
|
22 |
-
split: validation
|
23 |
-
args: canonical
|
24 |
-
metrics:
|
25 |
-
- name: Rouge1
|
26 |
-
type: rouge
|
27 |
-
value: 18.3412
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
# liputan6-pt-pl5
|
34 |
|
35 |
-
This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss:
|
38 |
-
- Rouge1:
|
39 |
-
- Rouge2:
|
40 |
-
- Rougel:
|
41 |
-
- Rougelsum:
|
42 |
-
- Gen Len:
|
43 |
|
44 |
## Model description
|
45 |
|
@@ -68,13 +53,13 @@ The following hyperparameters were used during training:
|
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2
|
72 |
-
|
73 |
-
| 4.
|
74 |
-
|
|
75 |
-
| 3.
|
76 |
-
| 3.
|
77 |
-
| 3.
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: LazarusNLP/IndoNanoT5-base
|
4 |
tags:
|
|
|
9 |
- rouge
|
10 |
model-index:
|
11 |
- name: liputan6-pt-pl5
|
12 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
17 |
|
18 |
# liputan6-pt-pl5
|
19 |
|
20 |
+
This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6 dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 2.7526
|
23 |
+
- Rouge1: 29.5518
|
24 |
+
- Rouge2: 13.5408
|
25 |
+
- Rougel: 24.834
|
26 |
+
- Rougelsum: 27.6096
|
27 |
+
- Gen Len: 51.956
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
58 |
+
| 4.309 | 1.0 | 63 | 3.4072 | 20.861 | 8.8494 | 18.3118 | 19.3333 | 41.853 |
|
59 |
+
| 3.6184 | 2.0 | 126 | 3.1460 | 25.8149 | 9.9065 | 21.2242 | 23.6534 | 51.44 |
|
60 |
+
| 3.3773 | 3.0 | 189 | 2.9716 | 27.0263 | 11.563 | 22.6018 | 25.0075 | 55.215 |
|
61 |
+
| 3.1793 | 4.0 | 252 | 2.8266 | 28.6871 | 12.9802 | 24.038 | 26.6558 | 52.119 |
|
62 |
+
| 3.0027 | 5.0 | 315 | 2.7526 | 29.5518 | 13.5408 | 24.834 | 27.6096 | 51.956 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter-summarization/pytorch_adapter.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 118368577
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebffda7654ef452fb721a627f56b0a0a902f5c4d0bfbd3f4df1d9a5aa9cc68b0
|
3 |
size 118368577
|