---
base_model: facebook/bart-base
library_name: peft
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: bart-base-summarization-medical_on_cnn-44
  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. -->

# bart-base-summarization-medical_on_cnn-44

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: 3.3974
- Rouge1: 0.2518
- Rouge2: 0.0939
- Rougel: 0.1991
- Rougelsum: 0.2234
- Gen Len: 18.193

## 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: 3e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 44
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 2.703         | 1.0   | 1250 | 3.3758          | 0.2513 | 0.0906 | 0.197  | 0.222     | 18.892  |
| 2.6143        | 2.0   | 2500 | 3.3837          | 0.2497 | 0.0914 | 0.1956 | 0.2202    | 18.433  |
| 2.5745        | 3.0   | 3750 | 3.3914          | 0.2487 | 0.0908 | 0.195  | 0.2188    | 18.475  |
| 2.5622        | 4.0   | 5000 | 3.3947          | 0.2481 | 0.0909 | 0.1957 | 0.2192    | 18.307  |
| 2.5308        | 5.0   | 6250 | 3.4010          | 0.2512 | 0.0935 | 0.1994 | 0.2232    | 18.139  |
| 2.5395        | 6.0   | 7500 | 3.3974          | 0.2518 | 0.0939 | 0.1991 | 0.2234    | 18.193  |


### Framework versions

- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1