sushilgpt-ft
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4781
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 OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2913 | 1.0 | 4 | 3.8195 |
| 3.5366 | 2.0 | 8 | 3.1608 |
| 2.9812 | 3.0 | 12 | 2.6754 |
| 2.5059 | 4.0 | 16 | 2.2791 |
| 2.1796 | 5.0 | 20 | 1.9582 |
| 1.7299 | 6.0 | 24 | 1.7228 |
| 1.5072 | 7.0 | 28 | 1.5915 |
| 1.4846 | 8.0 | 32 | 1.5249 |
| 1.4298 | 9.0 | 36 | 1.4902 |
| 1.3238 | 10.0 | 40 | 1.4781 |
Framework versions
- PEFT 0.17.1
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 1
Model tree for Prajapat/sushilgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2