Commit
•
a40504b
1
Parent(s):
97c48a3
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarisation
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: bert-small2bert-small-finetuned-cnn_daily_mail-summarization-finetuned-bbc-news
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# bert-small2bert-small-finetuned-cnn_daily_mail-summarization-finetuned-bbc-news
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [mrm8488/bert-small2bert-small-finetuned-cnn_daily_mail-summarization](https://huggingface.co/mrm8488/bert-small2bert-small-finetuned-cnn_daily_mail-summarization) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6835
|
| 21 |
+
- Rouge1: 58.9345
|
| 22 |
+
- Rouge2: 47.1037
|
| 23 |
+
- Rougel: 40.9839
|
| 24 |
+
- Rougelsum: 57.6981
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5.6e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 8
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 55 |
+
| 0.8246 | 1.0 | 223 | 0.7050 | 55.7882 | 42.9793 | 38.4511 | 54.3125 |
|
| 56 |
+
| 0.6414 | 2.0 | 446 | 0.6834 | 55.149 | 42.664 | 38.3864 | 53.7712 |
|
| 57 |
+
| 0.5603 | 3.0 | 669 | 0.6815 | 56.9756 | 44.8057 | 39.1377 | 55.5815 |
|
| 58 |
+
| 0.5079 | 4.0 | 892 | 0.6749 | 57.7397 | 45.6267 | 40.0509 | 56.3886 |
|
| 59 |
+
| 0.4622 | 5.0 | 1115 | 0.6781 | 58.07 | 45.9102 | 40.2704 | 56.7008 |
|
| 60 |
+
| 0.4263 | 6.0 | 1338 | 0.6798 | 58.1215 | 45.976 | 40.256 | 56.8203 |
|
| 61 |
+
| 0.399 | 7.0 | 1561 | 0.6798 | 58.5486 | 46.6901 | 40.8045 | 57.2947 |
|
| 62 |
+
| 0.3815 | 8.0 | 1784 | 0.6835 | 58.9345 | 47.1037 | 40.9839 | 57.6981 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.21.0
|
| 68 |
+
- Pytorch 1.12.0+cu113
|
| 69 |
+
- Datasets 2.4.0
|
| 70 |
+
- Tokenizers 0.12.1
|