metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: codet5-small-Generate_Docstrings_for_Python
    results: []
datasets:
  - kejian/codesearchnet-python-raw
language:
  - en
pipeline_tag: text2text-generation

codet5-small-Generate_Docstrings_for_Python

This model is a fine-tuned version of Salesforce/codet5-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.4116
Rouge1: 0.3381
Rouge2: 0.1541
Rougel: 0.3045
Rougelsum: 0.3214
Gen Len: 15.8088

Model description

This model is trained to provide the docstring for functions.

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Generate%20Docstrings/Code_T5_Project.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Dataset Source: kejian/codesearchnet-python-raw (from HuggingFace Datasets; https://huggingface.co/datasets/kejian/codesearchnet-python-raw)

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.7447	1.0	7913	2.4116	0.3381	0.1541	0.3045	0.3214	15.8088

Framework versions

Transformers 4.27.3
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2