STLlama-7b1
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: 0.4251
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: 2e-06
- 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 |
|---|---|---|---|
| 0.459 | 1.0 | 60 | 0.5063 |
| 0.4384 | 2.0 | 120 | 0.4862 |
| 0.4179 | 3.0 | 180 | 0.4668 |
| 0.4013 | 4.0 | 240 | 0.4518 |
| 0.3882 | 5.0 | 300 | 0.4405 |
| 0.3786 | 6.0 | 360 | 0.4331 |
| 0.3729 | 7.0 | 420 | 0.4285 |
| 0.3698 | 8.0 | 480 | 0.4262 |
| 0.3686 | 9.0 | 540 | 0.4253 |
| 0.3685 | 10.0 | 600 | 0.4251 |
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
- 13
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for AdnanRiaz107/STLlama-7b1
Base model
meta-llama/CodeLlama-7b-hf