---
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: test_sum_abs_bart-base_wasa_stops
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# test_sum_abs_bart-base_wasa_stops

This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7765
- Rouge1: 0.4111
- Rouge2: 0.3012
- Rougel: 0.3719
- Rougelsum: 0.3724
- 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 0.9783        | 1.0   | 1764 | 0.8409          | 0.4112 | 0.3033 | 0.3713 | 0.3716    | 19.9932 |
| 0.8497        | 2.0   | 3528 | 0.8019          | 0.4063 | 0.2968 | 0.3665 | 0.3668    | 19.9974 |
| 0.7925        | 3.0   | 5292 | 0.7884          | 0.4143 | 0.3057 | 0.3757 | 0.3761    | 19.9986 |
| 0.7485        | 4.0   | 7056 | 0.7765          | 0.4111 | 0.3012 | 0.3719 | 0.3724    | 20.0    |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2