metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
datasets:
- multi_news
metrics:
- rouge
model-index:
- name: bart-base-multi-news
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: multi_news
type: multi_news
config: train
split: validation
args: train
metrics:
- name: Rouge1
type: rouge
value: 27.57
bart-base-multi-news
This model is a fine-tuned version of facebook/bart-base on the multi_news dataset. It achieves the following results on the evaluation set:
- Loss: 2.9167
- Rouge1: 27.57
- Rouge2: 8.53
- Rougel: 15.17
- Rougelsum: 18.03
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 |
|---|---|---|---|---|---|---|---|
| 2.8539 | 1.0 | 1250 | 2.5026 | 27.57 | 8.53 | 15.17 | 18.03 |
| 2.3547 | 2.0 | 2500 | 2.5102 | 27.57 | 8.53 | 15.17 | 18.03 |
| 2.0079 | 3.0 | 3750 | 2.5593 | 27.57 | 8.53 | 15.17 | 18.03 |
| 1.7303 | 4.0 | 5000 | 2.6260 | 27.57 | 8.53 | 15.17 | 18.03 |
| 1.4993 | 5.0 | 6250 | 2.7184 | 27.57 | 8.53 | 15.17 | 18.03 |
| 1.3136 | 6.0 | 7500 | 2.8246 | 27.57 | 8.53 | 15.17 | 18.03 |
| 1.1718 | 7.0 | 8750 | 2.8684 | 27.57 | 8.53 | 15.17 | 18.03 |
| 1.0729 | 8.0 | 10000 | 2.9167 | 27.57 | 8.53 | 15.17 | 18.03 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3