Hugging Face's logo

hugo-albert
/
Code-Llama-3-8B-finetuned-py-to-cpp

Text Generation
Transformers
Generated from Trainer
conversational
Inference Endpoints
Model card Files Community
Code-Llama-3-8B-finetuned-py-to-cpp / README.md
hugo-albert's picture
hugo-albert
Update README.md
a6a7cdf verified
preview code
|
raw
history blame contribute delete
1.91 kB
metadata
license: llama3
base_model: ajibawa-2023/Code-Llama-3-8B
tags:
  - generated_from_trainer
model-index:
  - name: Code-Llama-3-8B-finetuned-py-to-cpp
    results: []
pipeline_tag: text-generation
library_name: transformers

Code-Llama-3-8B-finetuned-py-to-cpp

This model is a fine-tuned version of ajibawa-2023/Code-Llama-3-8B on the XLCoST (Python-C++) dataset, restricted to code snippets of <= 128 tokens long. It achieves the following results on the evaluation set:

  • Loss: 0.4550

Test set:

  • BLEU: 38.48
  • COMET: 79.28
  • CodeBLEU: 64.11
    • N-gram match score: 40.15
    • Weighted n-gram match score: 77.11
    • Syntax match score: 67.02
    • Dataflow match score: 72.13

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 87 0.5468
No log 2.0 175 0.4626
No log 2.98 261 0.4550

Framework versions

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