---
library_name: transformers
license: apache-2.0
base_model: Heit39/bart-base_opus
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: bart-base_opus
  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_opus

This model is a fine-tuned version of [Heit39/bart-base_opus](https://huggingface.co/Heit39/bart-base_opus) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4335
- Bleu: 5.418
- Gen Len: 18.8368

## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
| 1.7055        | 1.0   | 6355  | 1.4818          | 5.1722 | 18.8348 |
| 1.5835        | 2.0   | 12710 | 1.4335          | 5.418  | 18.8368 |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3