Jam_so
Jam_so is a GPT2-like model for research in fine-grained Java analysis. It is intended for fine-grained analysis of Java source code at the level of methods, statements, and variables, as a foundation for downstream tasks like code completion, comment generation, and automated bug repair.
Jam_so Training Details
We trained the jam_so model using the training procedures from Daniel Grittner's NanoGPT-LoRA
The dataset used to train our model is our own dataset so13m dataset, processed from 13 million StackOverflow posts picked from a Stack Exchange data dump for posts between January 2014 and December 2022.
We train the model on training set for 1 epoch, roughly 300,000 training iterations.
Our GitHub repo contains the code for re-training using the raw data.
| Hyperparameter | Description | Value |
|---|---|---|
| e | embedding dimensions | 1024 |
| L | number of layers | 24 |
| h | attention heads | 16 |
| c | block size / context length | 256 |
| b | batch size | 4 |
| a | accumulation steps | 32 |
| d | dropout | 0.20 |
| r | learning rate | 3e-5 |
| y | weight decay | 1e-1 |
We train our models using a single NVidia A5000 GPUs.
Jam Projects
Current projects using the jam_so pre-trained model can be found at our Github repository: