|
--- |
|
license: mit |
|
base_model: facebook/bart-large-cnn |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: Big-Bart-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. --> |
|
|
|
# Big-Bart-BBC |
|
|
|
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.1339 |
|
- Rouge1: 0.2638 |
|
- Rouge2: 0.1052 |
|
- Rougel: 0.2019 |
|
- Rougelsum: 0.202 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 3.001 | 1.0 | 1652 | 2.8616 | 0.2179 | 0.0571 | 0.1565 | 0.1564 | |
|
| 1.7636 | 2.0 | 3304 | 2.7371 | 0.2423 | 0.0772 | 0.1766 | 0.1767 | |
|
| 0.9422 | 3.0 | 4956 | 3.1619 | 0.2463 | 0.0842 | 0.1832 | 0.1832 | |
|
| 0.4259 | 4.0 | 6608 | 3.5730 | 0.2645 | 0.1009 | 0.2001 | 0.2002 | |
|
| 0.1637 | 5.0 | 8260 | 4.1339 | 0.2638 | 0.1052 | 0.2019 | 0.202 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
