shawgpt-ft-LoRA-rank-25
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1476
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|
| 8.5018 | 0.5714 | 1 | 4.2401 |
| 8.5156 | 1.5714 | 2 | 4.1397 |
| 8.0142 | 2.5714 | 3 | 3.9181 |
| 7.6452 | 3.5714 | 4 | 3.7279 |
| 7.2298 | 4.5714 | 5 | 3.5672 |
| 6.9677 | 5.5714 | 6 | 3.4304 |
| 6.7319 | 6.5714 | 7 | 3.3188 |
| 6.5321 | 7.5714 | 8 | 3.2340 |
| 6.3993 | 8.5714 | 9 | 3.1764 |
| 3.0991 | 9.5714 | 10 | 3.1476 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Jonasbukhave/shawgpt-ft-LoRA-rank-25
Base model
mistralai/Mistral-7B-Instruct-v0.2 Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ