---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-small-mlm-paraphrasing
  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-mlm-paraphrasing

This model is a fine-tuned version of [gayanin/t5-small-mlm-pubmed](https://huggingface.co/gayanin/t5-small-mlm-pubmed) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4243
- Rouge2 Precision: 0.8281
- Rouge2 Recall: 0.6508
- Rouge2 Fmeasure: 0.7125

## 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
| 0.6445        | 0.75  | 500  | 0.5049          | 0.821            | 0.6477        | 0.7078          |
| 0.5227        | 1.51  | 1000 | 0.4748          | 0.8243           | 0.6492        | 0.7099          |
| 0.5126        | 2.26  | 1500 | 0.4594          | 0.8254           | 0.6506        | 0.7111          |
| 0.4858        | 3.02  | 2000 | 0.4492          | 0.8266           | 0.651         | 0.712           |
| 0.4669        | 3.77  | 2500 | 0.4421          | 0.8268           | 0.6508        | 0.7118          |
| 0.4684        | 4.52  | 3000 | 0.4374          | 0.8272           | 0.6513        | 0.7124          |
| 0.463         | 5.28  | 3500 | 0.4342          | 0.8274           | 0.6508        | 0.712           |
| 0.4558        | 6.03  | 4000 | 0.4301          | 0.8278           | 0.6508        | 0.7123          |
| 0.4553        | 6.79  | 4500 | 0.4283          | 0.8279           | 0.6507        | 0.7122          |
| 0.443         | 7.54  | 5000 | 0.4259          | 0.8281           | 0.6511        | 0.7125          |
| 0.441         | 8.3   | 5500 | 0.4263          | 0.828            | 0.6503        | 0.7121          |
| 0.444         | 9.05  | 6000 | 0.4244          | 0.8281           | 0.6507        | 0.7125          |
| 0.4392        | 9.8   | 6500 | 0.4243          | 0.8281           | 0.6508        | 0.7125          |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6