metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: codet5-base-Generate_Docstrings_for_Python-Condensed
    results: []
datasets:
  - calum/the-stack-smol-python-docstrings
language:
  - en
pipeline_tag: text2text-generation

codet5-base-Generate_Docstrings_for_Python-Condensed

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

Loss: 0.6199
Rouge1: 0.5017
Rouge2: 0.374
Rougel: 0.4866
Rougelsum: 0.4864
Gen Len: 13.8909

Model description

This model predicts the docstring (the output) for a function (the input).

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Generate%20Docstrings/Smol%20Dataset/Code_T5_Project-Base%20Checkpoint.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: calum/the-stack-smol-python-docstrings (from HuggingFace Datasets; https://huggingface.co/datasets/calum/the-stack-smol-python-docstrings)

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.8261	1.0	921	0.6435	0.4947	0.3661	0.4794	0.4791	13.7526
0.6234	2.0	1842	0.6199	0.5017	0.374	0.4866	0.4864	13.8909

Framework versions

Transformers 4.27.4
Pytorch 2.0.0
Datasets 2.11.0
Tokenizers 0.13.3