|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: sshleifer/distilbart-xsum-6-6 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: distilbart-summarization-top-single |
|
|
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-top-single |
|
|
|
|
|
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: 2.2733 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 3.0316 | 0.1882 | 500 | 2.8583 | |
|
|
| 2.6153 | 0.3764 | 1000 | 2.5184 | |
|
|
| 2.5186 | 0.5645 | 1500 | 2.4173 | |
|
|
| 2.4484 | 0.7527 | 2000 | 2.3655 | |
|
|
| 2.4339 | 0.9409 | 2500 | 2.3337 | |
|
|
| 2.3517 | 1.1291 | 3000 | 2.3118 | |
|
|
| 2.32 | 1.3173 | 3500 | 2.2963 | |
|
|
| 2.3265 | 1.5055 | 4000 | 2.2847 | |
|
|
| 2.2928 | 1.6936 | 4500 | 2.2782 | |
|
|
| 2.3653 | 1.8818 | 5000 | 2.2733 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.2 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
