llama3.2_3B-urdu-qlora_2
This model is a fine-tuned version of meta-llama/Llama-3.2-3B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7366
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: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 48
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7853 | 1.0 | 625 | 1.7978 |
| 1.6817 | 2.0 | 1250 | 1.7543 |
| 1.638 | 3.0 | 1875 | 1.7414 |
| 1.6087 | 4.0 | 2500 | 1.7366 |
| 1.5899 | 5.0 | 3125 | 1.7366 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for SabahNawab/llama3.2_3B-urdu-qlora_2
Base model
meta-llama/Llama-3.2-3B