---
library_name: transformers
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-xsum-sentence-paraphrased-100-cnt-supervised-basic
  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-large-xsum-sentence-paraphrased-100-cnt-supervised-basic

This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1928
- Rouge1: 0.3485
- Rouge2: 0.137
- Rougel: 0.2802
- Rougelsum: 0.2801

## 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
| 2.7122        | 0.4   | 10   | 2.2588          | 0.1616 | 0.0208 | 0.1238 | 0.124     |
| 2.5247        | 0.8   | 20   | 1.9116          | 0.2843 | 0.1027 | 0.2274 | 0.2276    |
| 2.0552        | 1.2   | 30   | 1.8305          | 0.3346 | 0.1329 | 0.2676 | 0.2679    |
| 2.0861        | 1.6   | 40   | 1.8486          | 0.3255 | 0.128  | 0.2618 | 0.2618    |
| 1.6802        | 2.0   | 50   | 1.8226          | 0.3329 | 0.1331 | 0.2684 | 0.2683    |
| 1.4992        | 2.4   | 60   | 1.8888          | 0.3422 | 0.1361 | 0.2741 | 0.2744    |
| 1.5081        | 2.8   | 70   | 1.8947          | 0.348  | 0.14   | 0.2788 | 0.279     |
| 1.4839        | 3.2   | 80   | 1.8687          | 0.3498 | 0.1402 | 0.2809 | 0.2811    |
| 1.3555        | 3.6   | 90   | 1.8850          | 0.3519 | 0.1406 | 0.2821 | 0.2822    |
| 1.2862        | 4.0   | 100  | 1.9276          | 0.3539 | 0.144  | 0.2856 | 0.2856    |
| 1.4752        | 4.4   | 110  | 1.9748          | 0.3556 | 0.1442 | 0.2868 | 0.2868    |
| 1.032         | 4.8   | 120  | 1.9850          | 0.3551 | 0.1439 | 0.2865 | 0.2865    |
| 1.2276        | 5.2   | 130  | 2.0142          | 0.3533 | 0.1432 | 0.2858 | 0.2858    |
| 0.9779        | 5.6   | 140  | 2.0490          | 0.3531 | 0.1414 | 0.2851 | 0.285     |
| 1.1951        | 6.0   | 150  | 2.0365          | 0.3504 | 0.1391 | 0.2812 | 0.2812    |
| 0.8188        | 6.4   | 160  | 2.0638          | 0.3498 | 0.1399 | 0.281  | 0.2811    |
| 0.8834        | 6.8   | 170  | 2.1045          | 0.3509 | 0.1399 | 0.2829 | 0.2828    |
| 0.8476        | 7.2   | 180  | 2.1402          | 0.3522 | 0.1407 | 0.2833 | 0.2831    |
| 0.7733        | 7.6   | 190  | 2.1568          | 0.3515 | 0.1401 | 0.2829 | 0.283     |
| 0.8306        | 8.0   | 200  | 2.1479          | 0.3493 | 0.1375 | 0.2804 | 0.2802    |
| 0.8307        | 8.4   | 210  | 2.1540          | 0.3518 | 0.1387 | 0.2829 | 0.2828    |
| 0.619         | 8.8   | 220  | 2.1712          | 0.3498 | 0.1376 | 0.2813 | 0.2813    |
| 0.7299        | 9.2   | 230  | 2.1852          | 0.3492 | 0.1374 | 0.2806 | 0.2806    |
| 0.6445        | 9.6   | 240  | 2.1906          | 0.3491 | 0.1371 | 0.2804 | 0.2803    |
| 0.7616        | 10.0  | 250  | 2.1928          | 0.3485 | 0.137  | 0.2802 | 0.2801    |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1