---
library_name: transformers
license: apache-2.0
base_model: sshleifer/distilbart-xsum-12-6
tags:
- generated_from_trainer
model-index:
- name: bart-abs-2409-1947-lr-0.0003-bs-4-maxep-10
  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-abs-2409-1947-lr-0.0003-bs-4-maxep-10

This model is a fine-tuned version of [sshleifer/distilbart-xsum-12-6](https://huggingface.co/sshleifer/distilbart-xsum-12-6) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 7.1633
- Rouge/rouge1: 0.2439
- Rouge/rouge2: 0.0504
- Rouge/rougel: 0.2065
- Rouge/rougelsum: 0.2067
- Bertscore/bertscore-precision: 0.8544
- Bertscore/bertscore-recall: 0.8581
- Bertscore/bertscore-f1: 0.8562
- Meteor: 0.229
- Gen Len: 45.0

## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge/rouge1 | Rouge/rouge2 | Rouge/rougel | Rouge/rougelsum | Bertscore/bertscore-precision | Bertscore/bertscore-recall | Bertscore/bertscore-f1 | Meteor | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-----------------------------:|:--------------------------:|:----------------------:|:------:|:-------:|
| 3.3364        | 1.0   | 217  | 3.8952          | 0.2911       | 0.0832       | 0.2351       | 0.2361          | 0.8685                        | 0.8711                     | 0.8697                 | 0.2279 | 43.0    |
| 2.369         | 2.0   | 434  | 4.0594          | 0.2603       | 0.0584       | 0.2204       | 0.2202          | 0.871                         | 0.8545                     | 0.8626                 | 0.2129 | 35.0    |
| 1.4708        | 3.0   | 651  | 4.6061          | 0.2722       | 0.0714       | 0.2029       | 0.2031          | 0.8612                        | 0.8618                     | 0.8615                 | 0.2582 | 45.0    |
| 0.9251        | 4.0   | 868  | 5.2239          | 0.2333       | 0.0475       | 0.1761       | 0.1762          | 0.8431                        | 0.8562                     | 0.8495                 | 0.2342 | 58.8273 |
| 0.6367        | 5.0   | 1085 | 5.8193          | 0.2622       | 0.0744       | 0.2001       | 0.1997          | 0.8634                        | 0.8616                     | 0.8625                 | 0.1982 | 32.0    |
| 0.486         | 6.0   | 1302 | 6.2975          | 0.2591       | 0.0557       | 0.2009       | 0.2012          | 0.859                         | 0.8605                     | 0.8597                 | 0.2511 | 48.0091 |
| 0.3892        | 7.0   | 1519 | 6.5002          | 0.2582       | 0.0781       | 0.2156       | 0.2154          | 0.8771                        | 0.8626                     | 0.8697                 | 0.1855 | 29.0    |
| 0.3152        | 8.0   | 1736 | 6.7352          | 0.313        | 0.0882       | 0.2413       | 0.2416          | 0.8789                        | 0.8681                     | 0.8735                 | 0.2252 | 34.0    |
| 0.2751        | 9.0   | 1953 | 6.9970          | 0.2906       | 0.0847       | 0.2272       | 0.2274          | 0.8671                        | 0.8567                     | 0.8618                 | 0.1991 | 27.0    |
| 0.24          | 10.0  | 2170 | 7.1633          | 0.2439       | 0.0504       | 0.2065       | 0.2067          | 0.8544                        | 0.8581                     | 0.8562                 | 0.229  | 45.0    |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1