Update README.md
Browse files
README.md
CHANGED
@@ -19,8 +19,12 @@ This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingf
|
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.3902
|
21 |
- Bleu: 35.1914
|
22 |
-
- Rouge
|
23 |
-
-
|
|
|
|
|
|
|
|
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -51,10 +55,10 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
55 |
-
|
56 |
-
| 1.1677 | 1.0 | 750 | 0.3902 | 35.1914 |
|
57 |
-
|
58 |
|
59 |
### Framework versions
|
60 |
|
|
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.3902
|
21 |
- Bleu: 35.1914
|
22 |
+
- Rouge
|
23 |
+
- Rouge1: 0.641952430267112
|
24 |
+
- Rouge2: 0.4572909036472911
|
25 |
+
- RougeL: 0.607001331434416
|
26 |
+
- RougeLsum: 0.6068905123656807
|
27 |
+
- Meteor: 0.5916610499445853
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
55 |
|
56 |
### Training results
|
57 |
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | RougeL | RougeLsum | Meteor |
|
59 |
+
|:-------------:|:-----:|:----:|:---------:|:-------:|:------:|:--------:|:------:|:---------:|:-----:|
|
60 |
+
| 1.1677 | 1.0 | 750 | 0.3902 | 35.1914 | 0.6419 | 0.4573 | 0.6070 | 0.6069 | 0.5917 |
|
61 |
+
* All values in the chart above are rounded to the nearest ten-thousandths.
|
62 |
|
63 |
### Framework versions
|
64 |
|