Mistral-7B-Instruct-v0.3-QLoRA-Legal
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5660
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3402 | 1.0 | 421 | 0.5741 |
| 0.2967 | 2.0 | 842 | 0.5674 |
| 0.2854 | 3.0 | 1263 | 0.5660 |
Framework versions
- PEFT 0.17.0
- Transformers 4.55.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4