codellama-7b-openapi-completion-quick-fix
This model is a fine-tuned version of codellama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4698
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9033 | 0.1 | 100 | 0.4761 |
| 0.4185 | 0.2 | 200 | 0.4714 |
| 0.4128 | 0.3 | 300 | 0.4695 |
| 0.3661 | 0.4 | 400 | 0.4721 |
| 0.3184 | 0.5 | 500 | 0.4674 |
| 0.3352 | 0.6 | 600 | 0.4703 |
| 0.554 | 0.7 | 700 | 0.4770 |
| 0.3385 | 0.8 | 800 | 0.4704 |
| 0.2862 | 0.9 | 900 | 0.4690 |
| 0.385 | 1.0 | 1000 | 0.4698 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for BohdanPetryshyn/codellama-7b-openapi-completion-quick-fix
Base model
codellama/CodeLlama-7b-hf