Rafiq
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the Rafiq_finetune_train dataset. It achieves the following results on the evaluation set:
- Loss: 1.1838
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: 3
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 12
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2835 | 0.4976 | 500 | 1.2259 |
| 1.2339 | 0.9953 | 1000 | 1.1799 |
| 1.0201 | 1.4927 | 1500 | 1.1704 |
| 1.0261 | 1.9903 | 2000 | 1.1362 |
| 0.7328 | 2.4877 | 2500 | 1.1809 |
| 0.7868 | 2.9853 | 3000 | 1.1837 |
Framework versions
- PEFT 0.15.1
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.1
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for TKhattab/RAFIQ__V.2
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct