| | --- |
| | library_name: transformers |
| | license: apache-2.0 |
| | base_model: sshleifer/distilbart-xsum-6-6 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: distilbart-summarization-base |
| | 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. --> |
| |
|
| | # distilbart-summarization-base |
| |
|
| | This model is a fine-tuned version of [sshleifer/distilbart-xsum-6-6](https://huggingface.co/sshleifer/distilbart-xsum-6-6) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 2.2566 |
| |
|
| | ## 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: 16 |
| | - eval_batch_size: 16 |
| | - seed: 42 |
| | - optimizer: Use OptimizerNames.ADAFACTOR and the args are: |
| | No additional optimizer arguments |
| | - lr_scheduler_type: linear |
| | - num_epochs: 2.0 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:------:|:----:|:---------------:| |
| | | 2.699 | 0.1882 | 500 | 2.5648 | |
| | | 2.5321 | 0.3764 | 1000 | 2.4413 | |
| | | 2.4701 | 0.5645 | 1500 | 2.3791 | |
| | | 2.4213 | 0.7527 | 2000 | 2.3353 | |
| | | 2.404 | 0.9409 | 2500 | 2.3089 | |
| | | 2.3352 | 1.1291 | 3000 | 2.2903 | |
| | | 2.2998 | 1.3173 | 3500 | 2.2765 | |
| | | 2.2999 | 1.5055 | 4000 | 2.2673 | |
| | | 2.2665 | 1.6936 | 4500 | 2.2611 | |
| | | 2.3412 | 1.8818 | 5000 | 2.2566 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.48.2 |
| | - Pytorch 2.5.1+cu124 |
| | - Datasets 3.2.0 |
| | - Tokenizers 0.21.0 |
| |
|
