|
--- |
|
license: apache-2.0 |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
datasets: |
|
- billsum |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: CS685-text-summarizer-2 |
|
results: |
|
- task: |
|
name: Sequence-to-sequence Language Modeling |
|
type: text2text-generation |
|
dataset: |
|
name: billsum |
|
type: billsum |
|
config: default |
|
split: train[:37%] |
|
args: default |
|
metrics: |
|
- name: Rouge1 |
|
type: rouge |
|
value: 17.4066 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# CS685-text-summarizer-2 |
|
|
|
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the billsum dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7516 |
|
- Rouge1: 17.4066 |
|
- Rouge2: 14.022 |
|
- Rougel: 16.9378 |
|
- Rougelsum: 17.0519 |
|
|
|
## 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: 6 |
|
- eval_batch_size: 6 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:| |
|
| 2.3529 | 1.0 | 1052 | 1.9277 | 17.1288 | 13.5932 | 16.6346 | 16.7728 | |
|
| 1.9686 | 2.0 | 2104 | 1.8297 | 17.2756 | 13.7685 | 16.7924 | 16.9242 | |
|
| 1.789 | 3.0 | 3156 | 1.7903 | 17.4219 | 14.0205 | 16.9082 | 17.0564 | |
|
| 1.6619 | 4.0 | 4208 | 1.7632 | 17.5055 | 14.1186 | 16.996 | 17.1265 | |
|
| 1.5819 | 5.0 | 5260 | 1.7516 | 17.4066 | 14.022 | 16.9378 | 17.0519 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
