---
license: llama2
base_model: codellama/CodeLlama-7b-hf
tags:
- generated_from_trainer
model-index:
- name: CodeLlama-7b-hf-finetuned-py-to-cpp
  results: []
pipeline_tag: text-generation
library_name: transformers
---

<!-- 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. -->

# CodeLlama-7b-hf-finetuned-py-to-cpp

This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the [XLCoST](https://github.com/reddy-lab-code-research/XLCoST) (Python-C++) dataset, restricted to code snippets of <= 128 tokens long.
It achieves the following results on the evaluation set:
- Loss: 0.3878

Test set:
- BLEU: 65.06
- COMET: 89.13
- CodeBLEU: 78.52
  - N-gram match score: 66.81
  - Weighted n-gram match score: 82.49
  - Syntax match score: 75.77
  - Dataflow match score: 89.02


## 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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 0.99  | 67   | 0.8366          |
| No log        | 2.0   | 135  | 0.4170          |
| No log        | 2.98  | 201  | 0.3878          |


### Framework versions

- Transformers 4.33.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.13.3


```