CodeLlama-7b-hf-finetuned-py-to-cpp
This model is a fine-tuned version of codellama/CodeLlama-7b-hf on the XLCoST (Python-C++) dataset, restricted to code snippets of <= 128 tokens long. It achieves the following results on the evaluation set:
- Loss: 0.3878
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
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for hugo-albert/CodeLlama-7b-hf-finetuned-py-to-cpp
Base model
codellama/CodeLlama-7b-hf