---
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-finetuned-xsum
  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. -->

# t5-small-finetuned-xsum

This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5786
- Rouge1: 17.6871
- Rouge2: 2.8149
- Rougel: 16.2108
- Rougelsum: 16.2872
- Gen Len: 19.0

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
| 3.6995        | 1.0   | 584  | 2.9255          | 15.8217 | 2.0723 | 14.7572 | 14.7712   | 19.0    |
| 3.1556        | 2.0   | 1168 | 2.7584          | 16.4802 | 2.3382 | 15.3252 | 15.3279   | 19.0    |
| 2.9966        | 3.0   | 1752 | 2.6738          | 16.8183 | 2.4782 | 15.5872 | 15.6212   | 19.0    |
| 2.9189        | 4.0   | 2336 | 2.6263          | 17.2365 | 2.6216 | 15.8703 | 15.9484   | 19.0    |
| 2.868         | 5.0   | 2920 | 2.5983          | 17.1636 | 2.6128 | 15.8154 | 15.8974   | 19.0    |
| 2.8187        | 6.0   | 3504 | 2.5832          | 17.6268 | 2.7895 | 16.1651 | 16.2396   | 19.0    |
| 2.8104        | 7.0   | 4088 | 2.5786          | 17.6871 | 2.8149 | 16.2108 | 16.2872   | 19.0    |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.0
- Tokenizers 0.15.1