metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: billsum_model
results: []
billsum_model
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9651
- Rouge1: 0.1824
- Rouge2: 0.106
- Rougel: 0.1607
- Rougelsum: 0.1661
- Gen Len: 20.0
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: 2e-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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 124 | 2.0847 | 0.1748 | 0.1025 | 0.1561 | 0.1605 | 20.0 |
| No log | 2.0 | 248 | 2.0036 | 0.1842 | 0.108 | 0.1628 | 0.168 | 20.0 |
| No log | 3.0 | 372 | 1.9651 | 0.1824 | 0.106 | 0.1607 | 0.1661 | 20.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0