metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-finetuned-sst2
results: []
datasets:
- samsum
language:
- en
pipeline_tag: summarization
bart-large-cnn-finetuned-sst2
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4287
- Rouge1: 0.4065
- Rouge2: 0.1979
- Rougel: 0.3084
- Rougelsum: 0.3750
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2977 | 1.0 | 920 | 0.3094 | 0.4036 | 0.2071 | 0.3097 | 0.3746 |
| 0.2253 | 2.0 | 1841 | 0.3163 | 0.4067 | 0.2109 | 0.3130 | 0.3769 |
| 0.159 | 3.0 | 2762 | 0.3258 | 0.4108 | 0.2101 | 0.3163 | 0.3796 |
| 0.1091 | 4.0 | 3683 | 0.3680 | 0.4060 | 0.2006 | 0.3069 | 0.3750 |
| 0.0723 | 5.0 | 4600 | 0.4287 | 0.4065 | 0.1979 | 0.3084 | 0.3750 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2