|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: bart-base-finetuned-BBC |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bart-base-finetuned-BBC |
|
|
|
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2173 |
|
- Rouge1: 0.169 |
|
- Rouge2: 0.1419 |
|
- Rougel: 0.1624 |
|
- Rougelsum: 0.1651 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5.6e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 1.0798 | 1.0 | 7 | 0.4261 | 0.1312 | 0.0749 | 0.0947 | 0.0967 | |
|
| 0.4858 | 2.0 | 14 | 0.2775 | 0.1419 | 0.1037 | 0.1285 | 0.1288 | |
|
| 0.3719 | 3.0 | 21 | 0.2435 | 0.16 | 0.1307 | 0.151 | 0.1523 | |
|
| 0.298 | 4.0 | 28 | 0.2311 | 0.1619 | 0.1292 | 0.1527 | 0.1554 | |
|
| 0.2607 | 5.0 | 35 | 0.2318 | 0.1593 | 0.1259 | 0.1493 | 0.1526 | |
|
| 0.2276 | 6.0 | 42 | 0.2211 | 0.1566 | 0.1259 | 0.1479 | 0.151 | |
|
| 0.2173 | 7.0 | 49 | 0.2177 | 0.169 | 0.1419 | 0.1624 | 0.1651 | |
|
| 0.1801 | 8.0 | 56 | 0.2173 | 0.169 | 0.1419 | 0.1624 | 0.1651 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
