theojolliffe
commited on
Commit
•
2fa7b4c
1
Parent(s):
8d5682f
update model card README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
model-index:
|
5 |
- name: pegasus-model3
|
6 |
results: []
|
@@ -12,6 +14,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
# pegasus-model3
|
13 |
|
14 |
This model is a fine-tuned version of [theojolliffe/pegasus-cnn_dailymail-v4-e1-e4-feedback](https://huggingface.co/theojolliffe/pegasus-cnn_dailymail-v4-e1-e4-feedback) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
## Model description
|
17 |
|
@@ -41,9 +50,9 @@ The following hyperparameters were used during training:
|
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len
|
45 |
-
|
46 |
-
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- rouge
|
6 |
model-index:
|
7 |
- name: pegasus-model3
|
8 |
results: []
|
|
|
14 |
# pegasus-model3
|
15 |
|
16 |
This model is a fine-tuned version of [theojolliffe/pegasus-cnn_dailymail-v4-e1-e4-feedback](https://huggingface.co/theojolliffe/pegasus-cnn_dailymail-v4-e1-e4-feedback) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2808
|
19 |
+
- Rouge1: 70.5507
|
20 |
+
- Rouge2: 66.5776
|
21 |
+
- Rougel: 64.6438
|
22 |
+
- Rougelsum: 70.0264
|
23 |
+
- Gen Len: 123.7447
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
|
55 |
+
| 0.4839 | 1.0 | 748 | 0.2808 | 70.5507 | 66.5776 | 64.6438 | 70.0264 | 123.7447 |
|
56 |
|
57 |
|
58 |
### Framework versions
|