update model card README.md
Browse files
README.md
CHANGED
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [ku-nlp/bart-base-japanese](https://huggingface.co/ku-nlp/bart-base-japanese) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 2.
|
20 |
-
- Rouge1:
|
21 |
-
- Rouge2:
|
22 |
-
- Rougel:
|
23 |
-
- Rougelsum:
|
24 |
-
- Gen Len:
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -50,13 +50,13 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1
|
54 |
-
|
55 |
-
| 2.
|
56 |
-
|
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [ku-nlp/bart-base-japanese](https://huggingface.co/ku-nlp/bart-base-japanese) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.4647
|
20 |
+
- Rouge1: 9.203
|
21 |
+
- Rouge2: 1.326
|
22 |
+
- Rougel: 7.3269
|
23 |
+
- Rougelsum: 7.9726
|
24 |
+
- Gen Len: 25.78
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
55 |
+
| 2.1248 | 1.0 | 800 | 1.9659 | 4.6735 | 1.3973 | 3.3399 | 3.6754 | 13.69 |
|
56 |
+
| 0.9881 | 2.0 | 1600 | 2.0469 | 4.4604 | 0.6802 | 3.3883 | 3.5799 | 13.09 |
|
57 |
+
| 0.7473 | 3.0 | 2400 | 2.3957 | 7.1848 | 1.4395 | 5.7287 | 6.234 | 22.42 |
|
58 |
+
| 0.5128 | 4.0 | 3200 | 2.4013 | 9.7241 | 1.7342 | 7.7361 | 8.3869 | 24.21 |
|
59 |
+
| 0.4115 | 5.0 | 4000 | 2.4647 | 9.203 | 1.326 | 7.3269 | 7.9726 | 25.78 |
|
60 |
|
61 |
|
62 |
### Framework versions
|