theojolliffe
commited on
Commit
•
b7e4706
1
Parent(s):
7f79833
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- rouge
|
6 |
+
model-index:
|
7 |
+
- name: pegasus-cnn_dailymail-v4-e1-e4-feedback
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# pegasus-cnn_dailymail-v4-e1-e4-feedback
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [theojolliffe/pegasus-cnn_dailymail-v4-e1](https://huggingface.co/theojolliffe/pegasus-cnn_dailymail-v4-e1) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 5.1815
|
19 |
+
- Rouge1: 59.7329
|
20 |
+
- Rouge2: 42.429
|
21 |
+
- Rougel: 53.5945
|
22 |
+
- Rougelsum: 52.9219
|
23 |
+
- Gen Len: 37.8636
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
+
- train_batch_size: 2
|
44 |
+
- eval_batch_size: 2
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 4
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
54 |
+
| No log | 1.0 | 90 | 5.5674 | 60.4652 | 43.8057 | 54.5759 | 52.5243 | 39.5 |
|
55 |
+
| No log | 2.0 | 180 | 5.3261 | 60.248 | 43.9953 | 54.9492 | 53.6372 | 38.6364 |
|
56 |
+
| No log | 3.0 | 270 | 5.2167 | 60.4887 | 43.6915 | 54.3825 | 53.5206 | 37.1364 |
|
57 |
+
| No log | 4.0 | 360 | 5.1815 | 59.7329 | 42.429 | 53.5945 | 52.9219 | 37.8636 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.12.3
|
63 |
+
- Pytorch 1.9.0
|
64 |
+
- Datasets 1.18.0
|
65 |
+
- Tokenizers 0.10.3
|