STLlama-7b
This model is a fine-tuned version of meta-llama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3725
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2308 | 1.0 | 60 | 0.3055 |
| 0.138 | 2.0 | 120 | 0.2635 |
| 0.0865 | 3.0 | 180 | 0.2738 |
| 0.0498 | 4.0 | 240 | 0.2951 |
| 0.0286 | 5.0 | 300 | 0.3436 |
| 0.0183 | 6.0 | 360 | 0.3428 |
| 0.0137 | 7.0 | 420 | 0.3217 |
| 0.0107 | 8.0 | 480 | 0.3556 |
| 0.0097 | 9.0 | 540 | 0.3705 |
| 0.0095 | 10.0 | 600 | 0.3725 |
Framework versions
- PEFT 0.12.0
- Transformers 4.49.0
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 106
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for AdnanRiaz107/STLlama-7b
Base model
meta-llama/CodeLlama-7b-hf