shawgpt-ft
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: 1.7936
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 |
|---|---|---|---|
| 13.7741 | 1.0 | 4 | 3.7786 |
| 11.6644 | 2.0 | 8 | 3.1281 |
| 9.7172 | 3.0 | 12 | 2.6670 |
| 8.2995 | 4.0 | 16 | 2.3365 |
| 7.3375 | 5.0 | 20 | 2.1376 |
| 6.5111 | 6.0 | 24 | 1.9327 |
| 5.7964 | 7.0 | 28 | 1.8181 |
| 6.9656 | 7.6154 | 30 | 1.7936 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.6.0+cu118
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for gousigavs/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2 Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ