---
library_name: transformers
license: cc-by-4.0
base_model: paust/pko-t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: news_summary
  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. -->

# news_summary

This model is a fine-tuned version of [paust/pko-t5-small](https://huggingface.co/paust/pko-t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6527
- Rouge1: 70.6899
- Rouge2: 46.6513
- Rougel: 70.2192
- Rougelsum: 70.2198

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
| 0.9767        | 1.0   | 694  | 0.7406          | 68.7991 | 44.6095 | 68.2328 | 68.2022   |
| 0.7986        | 2.0   | 1388 | 0.6860          | 69.4903 | 45.5759 | 68.9732 | 68.9579   |
| 0.6901        | 3.0   | 2082 | 0.6652          | 70.2244 | 46.2359 | 69.7706 | 69.7221   |
| 0.6658        | 4.0   | 2776 | 0.6530          | 70.6414 | 46.4725 | 70.1    | 70.0898   |
| 0.6414        | 5.0   | 3470 | 0.6527          | 70.6899 | 46.6513 | 70.2192 | 70.2198   |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1