debbiesoon
commited on
Commit
•
f5f3d02
1
Parent(s):
d1497a4
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- multi_news
|
7 |
+
model-index:
|
8 |
+
- name: summarise_v5
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# summarise_v5
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the multi_news dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.3252
|
20 |
+
- Rouge2 Precision: 0.1458
|
21 |
+
- Rouge2 Recall: 0.1306
|
22 |
+
- Rouge2 Fmeasure: 0.1343
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 5e-05
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 16
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 1
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
56 |
+
| 2.6266 | 0.13 | 10 | 2.4604 | 0.1021 | 0.179 | 0.124 |
|
57 |
+
| 2.4818 | 0.27 | 20 | 2.4122 | 0.1402 | 0.1422 | 0.1345 |
|
58 |
+
| 2.3451 | 0.4 | 30 | 2.3846 | 0.1631 | 0.1177 | 0.1307 |
|
59 |
+
| 2.4462 | 0.53 | 40 | 2.3584 | 0.1671 | 0.1175 | 0.133 |
|
60 |
+
| 2.443 | 0.67 | 50 | 2.3395 | 0.1444 | 0.1359 | 0.1344 |
|
61 |
+
| 2.3822 | 0.8 | 60 | 2.3377 | 0.1517 | 0.1411 | 0.1395 |
|
62 |
+
| 2.4304 | 0.93 | 70 | 2.3252 | 0.1458 | 0.1306 | 0.1343 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.21.3
|
68 |
+
- Pytorch 1.12.1+cu113
|
69 |
+
- Datasets 2.6.2.dev0
|
70 |
+
- Tokenizers 0.12.1
|