tags:
- summarization
widget:
- text: >-
new file mode 100644 index 000000000 . . 892fda21b Binary files / dev /
null and b / src / plugins / gateway / lib / joscar . jar differ
CodeTrans model for git commit message generation
Pretrained model on git commit using the t5 small model architecture. It was first released in this repository. This model is trained on tokenized git commit: it works best with tokenized git commit.
Model description
This CodeTrans model is based on the t5-small model. It has its own SentencePiece vocabulary model. It used transfer-learning pre-training on 7 unsupervised datasets in the software development domain. It is then fine-tuned on the git commit message generation task for the java commit changes.
Intended uses & limitations
The model could be used to generate the git commit message for the git commit changes or be fine-tuned on other relevant tasks. It can be used on unparsed and untokenized commit changes. However, if the change is tokenized, the performance should be better.
How to use
Here is how to use this model to generate git commit message using Transformers SummarizationPipeline:
from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline
pipeline = SummarizationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_small_commit_generation_transfer_learning_finetune"),
tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_small_commit_generation_transfer_learning_finetune", skip_special_tokens=True),
device=0
)
tokenized_code = "new file mode 100644 index 000000000 . . 892fda21b Binary files / dev / null and b / src / plugins / gateway / lib / joscar . jar differ"
pipeline([tokenized_code])
Run this example in colab notebook.
Training data
The supervised training tasks datasets can be downloaded on Link
Training procedure
Transfer-learning Pretraining
The model was trained on a single TPU Pod V3-8 for 500,000 steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
Fine-tuning
This model was then fine-tuned on a single TPU Pod V2-8 for 10,000 steps in total, using sequence length 512 (batch size 256), using only the dataset only containing commit changes.
Evaluation results
For the git commit message generation task, different models achieves the following results on different programming languages (in BLEU score):
Test results :
| Language / Model | Java |
|---|---|
| CodeTrans-ST-Small | 39.61 |
| CodeTrans-ST-Base | 38.67 |
| CodeTrans-TF-Small | 44.22 |
| CodeTrans-TF-Base | 44.17 |
| CodeTrans-TF-Large | 44.41 |
| CodeTrans-MT-Small | 36.17 |
| CodeTrans-MT-Base | 39.25 |
| CodeTrans-MT-Large | 41.18 |
| CodeTrans-MT-TF-Small | 43.96 |
| CodeTrans-MT-TF-Base | 44.19 |
| CodeTrans-MT-TF-Large | 44.34 |
| State of the art | 32.81 |
Created by Ahmed Elnaggar | LinkedIn and Wei Ding | LinkedIn