metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- summarization
- generated_from_trainer
datasets:
- tldr_news
metrics:
- rouge
model-index:
- name: summary_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: tldr_news
type: tldr_news
config: all
split: test
args: all
metrics:
- name: Rouge1
type: rouge
value: 0.21590240799799404
summary_model
This model is a fine-tuned version of facebook/bart-large-cnn on the tldr_news dataset. It achieves the following results on the evaluation set:
- Loss: 2.9573
- Rouge1: 0.2159
- Rouge2: 0.0831
- Rougel: 0.1829
- Rougelsum: 0.1869
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.5871 | 1.0 | 63 | 2.7134 | 0.2176 | 0.0872 | 0.1881 | 0.1951 |
| 0.4422 | 2.0 | 126 | 2.9573 | 0.2159 | 0.0831 | 0.1829 | 0.1869 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0