---
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: MTSUSpring2025SoftwareEngineering
  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. -->

# MTSUSpring2025SoftwareEngineering

This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1089
- Rouge1: 0.3231
- Rouge2: 0.2685
- Rougel: 0.313
- Rougelsum: 0.313
- Gen Len: 19.8572

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 1.4692        | 1.0   | 14778 | 1.3005          | 0.3197 | 0.2609 | 0.3087 | 0.3087    | 19.8338 |
| 1.3442        | 2.0   | 29556 | 1.2153          | 0.321  | 0.2648 | 0.3108 | 0.3108    | 19.8476 |
| 1.2638        | 3.0   | 44334 | 1.1495          | 0.3214 | 0.2659 | 0.3112 | 0.3112    | 19.8867 |
| 1.2194        | 4.0   | 59112 | 1.1216          | 0.323  | 0.2682 | 0.3131 | 0.3131    | 19.8804 |
| 1.1679        | 5.0   | 73890 | 1.1089          | 0.3231 | 0.2685 | 0.313  | 0.313     | 19.8572 |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1