metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- multi_news
metrics:
- rouge
pipeline_tag: summarization
base_model: slauw87/bart_summarisation
model-index:
- name: finetuned_multi_news_bart_text_summarisation
results:
- task:
type: textsummarization
name: Sequence-to-sequence Language Modeling
dataset:
name: multi_news
type: multi_news
config: default
split: test
args: default
metrics:
- type: rouge
value: 0.4038
name: Rouge1
finetuned_multi_news_bart_text_summarisation
This model is a fine-tuned version of slauw87/bart_summarisation on the multi_news dataset. It achieves the following results on the evaluation set:
- Loss: 2.8952
- Rouge1: 0.4038
- Rouge2: 0.1389
- Rougel: 0.2155
- Rougelsum: 0.2147
- Gen Len: 138.7667
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: 5e-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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 15 | 2.9651 | 0.3903 | 0.134 | 0.21 | 0.2098 | 137.6 |
| No log | 2.0 | 30 | 2.8952 | 0.4038 | 0.1389 | 0.2155 | 0.2147 | 138.7667 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3