---
library_name: peft
license: apache-2.0
base_model: Salesforce/codet5-small
tags:
- base_model:adapter:Salesforce/codet5-small
- lora
- transformers
metrics:
- rouge
model-index:
- name: codet5-python-summarizer-v3
  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. -->

# codet5-python-summarizer-v3

This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0107
- Rouge1: 0.9856
- Rouge2: 0.9796
- Rougel: 0.9856
- Rougelsum: 0.9856

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
| 0.0298        | 1.0   | 1230 | 0.0146          | 0.9812 | 0.9741 | 0.9811 | 0.9812    |
| 0.0153        | 2.0   | 2460 | 0.0116          | 0.9855 | 0.9794 | 0.9855 | 0.9854    |
| 0.0236        | 3.0   | 3690 | 0.0107          | 0.9856 | 0.9796 | 0.9856 | 0.9856    |


### Framework versions

- PEFT 0.18.1
- Transformers 4.44.2
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.19.1